{"meta":{"query_hash":"151acead7183","filters":{"venue":"2022 IEEE International Conference on Big Data (Big Data)"},"cohort_total":41,"direct_labels_cover":0,"predictions_cover":41,"exported":41,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/151acead7183","api":"https://metacan.xera.ac/api/v1/cohort?venue=2022+IEEE+International+Conference+on+Big+Data+%28Big+Data%29"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4329335683524456,"score_gpt":0.41144588545225624,"score_spread":0.021487682900189375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226052253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012618975,0.00048902817,0.7868885,0.07368369,0.01640765,0.0032724133,0.111543305,0.0020134046,0.004440113],"genre_scores_gemma":[0.5046873,0.013782309,0.05478113,0.0034506116,0.0049525653,0.008360964,0.40710557,0.00030347335,0.002576056],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99168247,0.00045812043,0.0010368157,0.0039162035,0.0022752676,0.0006311298],"domain_scores_gemma":[0.97922486,0.0012269311,0.0008762106,0.018026091,0.0003604615,0.00028544382],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.0025041306,0.0007011896,0.0008315202,0.00068640814,0.0006055008,0.0012558368,0.08308052,0.0004295491,0.0007729074],"category_scores_gemma":[0.015071583,0.00070703786,0.000130428,0.00046289634,0.00019120004,0.0007545505,0.24447711,0.0027713715,0.00007193889],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029197984,0.0006743768,0.00008125772,0.00020299829,0.0032812129,0.00020945135,0.000039017945,0.00058212184,0.00025928827,0.03450948,0.43829972,0.52156913],"study_design_scores_gemma":[0.0004549671,0.00015393573,0.000019070963,0.00011115339,0.0001789297,0.000028566361,0.000014059761,0.7012509,0.00044785818,0.017361477,0.27933452,0.000644593],"about_ca_topic_score_codex":0.00048830465,"about_ca_topic_score_gemma":0.0013582573,"teacher_disagreement_score":0.73210734,"about_ca_system_score_codex":0.00029775553,"about_ca_system_score_gemma":0.0010233492,"threshold_uncertainty_score":0.99978095},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.46222809716017266,"score_gpt":0.41475548439871396,"score_spread":0.0474726127614587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317781640","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3060119,0.0027945973,0.10626929,0.1100787,0.33503443,0.0046383534,0.08207164,0.0016011926,0.051499907],"genre_scores_gemma":[0.9832289,0.001971796,0.0002174133,0.00025321534,0.004444456,0.000057441353,0.009040474,0.000021211126,0.0007650642],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939569,0.0006606187,0.0005108489,0.0018721547,0.0025422317,0.00045719894],"domain_scores_gemma":[0.99090546,0.00063055614,0.0002767557,0.0077604135,0.0002791932,0.00014763267],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.006323639,0.00022573787,0.00019109738,0.0003004352,0.0016269371,0.0011743519,0.014525625,0.00007633848,0.00006749957],"category_scores_gemma":[0.00084712415,0.00019816314,0.000023433608,0.00063755224,0.00018154818,0.001289463,0.02098801,0.001513417,0.000064595435],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023148398,0.00026637662,0.00048570277,0.000012865511,0.00009857707,0.00033036363,0.00026554105,0.000032317224,0.0005937731,0.019087872,0.19404455,0.7845506],"study_design_scores_gemma":[0.0003458173,0.00023153944,0.000653927,0.00007188039,0.000007645434,0.00019607012,0.00027023762,0.19529238,0.00035904918,0.0055744103,0.7967233,0.0002737304],"about_ca_topic_score_codex":0.0005850984,"about_ca_topic_score_gemma":0.0005129561,"teacher_disagreement_score":0.78427684,"about_ca_system_score_codex":0.00016257176,"about_ca_system_score_gemma":0.0003432218,"threshold_uncertainty_score":0.99986255},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.47588963696264636,"score_gpt":0.33149483326991913,"score_spread":0.14439480369272722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147159","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011812431,0.00007758827,0.94344246,0.0034676525,0.010862338,0.0005904366,0.039872933,0.0001685626,0.0003367842],"genre_scores_gemma":[0.9244427,0.000079479774,0.003836338,0.0029648682,0.0009843201,0.000174935,0.067065045,0.000037153113,0.00041512778],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99506956,0.00025002312,0.00055884133,0.0021442557,0.0014677978,0.0005094954],"domain_scores_gemma":[0.9922036,0.00042923735,0.0003895379,0.006479049,0.00032988438,0.00016869263],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0018886679,0.00036016226,0.00037703378,0.0002840101,0.0006006079,0.00061355793,0.018691063,0.000083629915,0.00008418977],"category_scores_gemma":[0.0003594149,0.00037741684,0.00008896274,0.00028123794,0.00005857875,0.0015590299,0.010589181,0.00068776525,0.000025526206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014555221,0.0010379828,0.00011766767,0.00004319388,0.0013515913,0.00039816007,0.00016932034,0.011707939,0.0070771533,0.3864312,0.23095518,0.3592551],"study_design_scores_gemma":[0.0013440397,0.00019876478,0.000019906727,0.00006866574,0.000049847255,0.000025243051,0.0002264229,0.967399,0.00012917591,0.0012500684,0.028857803,0.00043105477],"about_ca_topic_score_codex":0.00039263273,"about_ca_topic_score_gemma":0.00029697138,"teacher_disagreement_score":0.95569104,"about_ca_system_score_codex":0.00021716856,"about_ca_system_score_gemma":0.00044201093,"threshold_uncertainty_score":0.9998678},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3288503865665113,"score_gpt":0.4098341532725872,"score_spread":0.08098376670607593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147167","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012126277,0.00026905764,0.12713258,0.01623726,0.0069447425,0.003064519,0.77059865,0.00029499142,0.06333195],"genre_scores_gemma":[0.8494418,0.00021190512,0.0008106812,0.0005258239,0.0011682947,0.00031899795,0.14554664,0.000020753821,0.001955043],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99643147,0.0003956484,0.0005662617,0.001276815,0.0010422486,0.000287554],"domain_scores_gemma":[0.9942868,0.0003520852,0.00036362922,0.00454926,0.000308872,0.00013940697],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030007155,0.000170404,0.00024778393,0.00018319332,0.0010172039,0.00016083571,0.010610706,0.00006404257,0.011734592],"category_scores_gemma":[0.00040787866,0.00020160676,0.00004758112,0.00045407552,0.00033943157,0.0011586059,0.0022019264,0.00032336128,0.000034490313],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018470996,0.0011401417,0.00034927545,0.000046711117,0.00028992453,0.000004239989,0.0010941934,0.00016001271,0.0006651166,0.027435346,0.19663776,0.77199256],"study_design_scores_gemma":[0.00043239107,0.00009572615,0.0004440402,0.000013905262,0.00009179275,0.0000014838054,0.0064677144,0.1713104,0.00006359342,0.0034612422,0.81730115,0.00031653923],"about_ca_topic_score_codex":0.0082355635,"about_ca_topic_score_gemma":0.032866936,"teacher_disagreement_score":0.83731556,"about_ca_system_score_codex":0.000100449804,"about_ca_system_score_gemma":0.0015418665,"threshold_uncertainty_score":0.9983687},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.18264378705047773,"score_gpt":0.34405238847640135,"score_spread":0.16140860142592361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147168","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011360848,0.00007588638,0.9616096,0.0019493182,0.004439701,0.0010896735,0.018897837,0.00032219946,0.00025494475],"genre_scores_gemma":[0.79601574,0.00058448885,0.1493467,0.0007803363,0.003038225,0.001878039,0.04628352,0.0000919365,0.0019810442],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727875,0.00008763587,0.00042008664,0.0011759608,0.00072999764,0.00030755176],"domain_scores_gemma":[0.99610186,0.00026376976,0.00025977197,0.002971787,0.00029489404,0.000107907625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010482268,0.00021211874,0.0002258621,0.00021443839,0.0006165061,0.000385234,0.005228559,0.000065941094,0.00004778585],"category_scores_gemma":[0.00009616561,0.00021743684,0.000039854975,0.00040394146,0.00006690933,0.0009094949,0.0026282403,0.0002512415,0.00004241518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006390563,0.00198129,0.047985308,0.00081850035,0.00065297773,0.000028804567,0.0004288689,0.0036684964,0.037376348,0.0071643796,0.12579803,0.77345794],"study_design_scores_gemma":[0.0011043441,0.00016811029,0.002688063,0.00009044419,0.00004484898,0.00001724579,0.000076682954,0.8536895,0.0010630992,0.00064825336,0.13991217,0.00049724354],"about_ca_topic_score_codex":0.0003163077,"about_ca_topic_score_gemma":0.00005648427,"teacher_disagreement_score":0.850021,"about_ca_system_score_codex":0.00018877632,"about_ca_system_score_gemma":0.00041599412,"threshold_uncertainty_score":0.97160506},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.21032828965218048,"score_gpt":0.3246473363864822,"score_spread":0.11431904673430171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147483","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003097974,0.000009977057,0.9414078,0.0062627173,0.0037287306,0.00037179986,0.037258036,0.00015871362,0.010492417],"genre_scores_gemma":[0.5332628,0.00006379114,0.06993852,0.012126741,0.0013396335,0.00036224487,0.37746486,0.00006759883,0.005373806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948825,0.00023367653,0.0004965543,0.0020436472,0.0019056961,0.00043792583],"domain_scores_gemma":[0.99295884,0.00010760339,0.00024716175,0.00634312,0.00014037706,0.00020289555],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0014154958,0.0003269168,0.0003446902,0.001321944,0.0003466252,0.0010574168,0.021185935,0.00004510137,0.00029319056],"category_scores_gemma":[0.00010608916,0.00034173718,0.00010051252,0.0023416216,0.00006490536,0.0014052421,0.013042934,0.00045240554,0.00017830069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022469474,0.0020029785,0.0009651868,0.000035022862,0.0022376466,0.00011498693,0.00017883524,0.016623057,0.0000765644,0.12649281,0.4143861,0.43666214],"study_design_scores_gemma":[0.00048268354,0.00008182899,0.00037263715,0.0000080639775,0.00010749328,0.0000039525025,0.000081814054,0.9087697,0.000007672517,0.00047609856,0.08921655,0.00039145473],"about_ca_topic_score_codex":0.00029131744,"about_ca_topic_score_gemma":0.00036381066,"teacher_disagreement_score":0.8921467,"about_ca_system_score_codex":0.00018088298,"about_ca_system_score_gemma":0.00020398309,"threshold_uncertainty_score":0.99997956},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3210273366955822,"score_gpt":0.3386155405561522,"score_spread":0.017588203860569973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147587","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017977089,0.000077241064,0.9692883,0.0004839903,0.00259555,0.00047509337,0.00595841,0.00032548176,0.0028188794],"genre_scores_gemma":[0.78284115,0.00022005041,0.18569271,0.0006767326,0.0012735218,0.0001982605,0.028703185,0.00007180277,0.0003225667],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99457866,0.00043928224,0.00094446196,0.0017704908,0.0017569824,0.0005101204],"domain_scores_gemma":[0.99579805,0.00021047653,0.00077993097,0.0025933404,0.00045850326,0.000159685],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0021849584,0.00041393537,0.00047859247,0.0007383843,0.0006436945,0.0006165558,0.008187549,0.00012451972,0.00038981935],"category_scores_gemma":[0.00044954874,0.00046137,0.00009369228,0.0008790128,0.0001407304,0.0018494864,0.0063461554,0.0010970846,0.00003311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088542176,0.0005659429,0.00011499001,0.000039054863,0.0001829366,0.000031722302,0.0005101248,0.00051514676,0.038859714,0.0010006159,0.0021043292,0.95598686],"study_design_scores_gemma":[0.0010926047,0.00020651998,0.00006872723,0.00017087728,0.0000493118,0.00018254553,0.0007388224,0.9826981,0.0046986677,0.0009649312,0.008440451,0.00068842986],"about_ca_topic_score_codex":0.0003411322,"about_ca_topic_score_gemma":0.00010726845,"teacher_disagreement_score":0.982183,"about_ca_system_score_codex":0.00022422704,"about_ca_system_score_gemma":0.00031420184,"threshold_uncertainty_score":0.9997838},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5383621885771043,"score_gpt":0.3526381344140766,"score_spread":0.18572405416302767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147647","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04003178,0.000208154,0.82017624,0.00043189208,0.021773564,0.0006026444,0.08723974,0.0005130515,0.029022906],"genre_scores_gemma":[0.9674579,0.00006227559,0.0067838742,0.00024574212,0.0016165188,0.00007740056,0.02251542,0.000097602926,0.0011432706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978414,0.000036805242,0.00040832802,0.0007032328,0.0006116279,0.0003985861],"domain_scores_gemma":[0.9981785,0.00012505143,0.00012368978,0.0013948287,0.00008475692,0.00009318603],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000578081,0.00027557695,0.00022720023,0.00021397113,0.0003169326,0.00016815698,0.0030113093,0.0000605683,0.0003552554],"category_scores_gemma":[0.00012529887,0.0003104261,0.000050934417,0.00017365115,0.000036440633,0.0005457267,0.0013804537,0.00042200563,0.000014181713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013909584,0.00012561328,0.000121080455,0.000069227244,0.0003243291,0.00003612194,0.0003305797,0.75963384,0.0099571,0.008180215,0.04182647,0.17925633],"study_design_scores_gemma":[0.00043347327,0.000031443302,0.0000030269568,0.00005995285,0.000027579008,0.000028623013,0.00011272511,0.94431514,0.00025048852,0.0007650549,0.053644486,0.00032800107],"about_ca_topic_score_codex":0.00007464205,"about_ca_topic_score_gemma":0.00017383033,"teacher_disagreement_score":0.9274261,"about_ca_system_score_codex":0.00016968949,"about_ca_system_score_gemma":0.00013828042,"threshold_uncertainty_score":0.9999348},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.27058870296074505,"score_gpt":0.3671188911458947,"score_spread":0.09653018818514963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147653","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010384289,0.000069879265,0.9884655,0.0005926071,0.0051577636,0.00039485993,0.0036215112,0.00019862218,0.0004608419],"genre_scores_gemma":[0.44939741,0.00015184512,0.52914506,0.0008609174,0.0018224602,0.00009066663,0.018436637,0.00003317239,0.000061838844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963098,0.00032713558,0.00048672172,0.0012714495,0.0012384285,0.0003664536],"domain_scores_gemma":[0.99679095,0.00015498251,0.00041171417,0.0023130113,0.00022479327,0.0001045632],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00093628716,0.0002883886,0.00024766472,0.000336225,0.00062136014,0.00042786458,0.005876778,0.000065233166,0.000106667925],"category_scores_gemma":[0.00017951411,0.0003150704,0.00005858633,0.000793525,0.000096549156,0.0025907273,0.0037816288,0.0005144311,0.000017831882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040898446,0.00039879174,0.00015579535,0.000012130077,0.00024301567,0.00013957676,0.0007027267,0.05683004,0.004982248,0.05073051,0.010532274,0.8748639],"study_design_scores_gemma":[0.000622443,0.00016244367,0.00009858951,0.000028812585,0.000017966766,0.000030338759,0.00015693973,0.96914417,0.0004933913,0.015329182,0.013563824,0.00035191333],"about_ca_topic_score_codex":0.00019567089,"about_ca_topic_score_gemma":0.00014000559,"teacher_disagreement_score":0.9123141,"about_ca_system_score_codex":0.00021504294,"about_ca_system_score_gemma":0.00031466913,"threshold_uncertainty_score":0.99993014},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.5808910784080009,"score_gpt":0.3499821377569418,"score_spread":0.2309089406510591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2426676,0.00033657264,0.4804563,0.0011952829,0.0032101278,0.00035273327,0.26274967,0.00010813611,0.008923583],"genre_scores_gemma":[0.9484544,0.00009828261,0.0005296575,0.00014709841,0.00018823972,0.00004772185,0.04987683,0.000018898798,0.00063887355],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971802,0.000070121656,0.0009817684,0.0011807998,0.00034564984,0.00024142822],"domain_scores_gemma":[0.9968229,0.000045742414,0.00072782405,0.002211212,0.00010323075,0.00008909771],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010464686,0.00021749256,0.00054943655,0.001170319,0.00026119838,0.000114739814,0.0030815003,0.00007971544,0.0027406907],"category_scores_gemma":[0.00013892537,0.000259064,0.00016162614,0.0010731159,0.00004230458,0.0003936583,0.0012871432,0.00045721742,0.000039791066],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024892064,0.0020016646,0.22898878,0.000055739398,0.006536653,0.000025863481,0.00033116702,0.7233828,0.00024637784,0.019466635,0.0023766009,0.016338842],"study_design_scores_gemma":[0.00069563376,0.000020630143,0.0056389947,0.000008382227,0.00017897127,0.0000016961671,0.0003065174,0.9881675,0.000012459372,0.00010034805,0.0046063196,0.00026253625],"about_ca_topic_score_codex":0.00064875104,"about_ca_topic_score_gemma":0.00021937347,"teacher_disagreement_score":0.70578676,"about_ca_system_score_codex":0.00019508447,"about_ca_system_score_gemma":0.000090981026,"threshold_uncertainty_score":0.9999862},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5304000793599303,"score_gpt":0.36865175447630044,"score_spread":0.16174832488362983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147681","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008341111,0.00021160851,0.97489196,0.0008892864,0.004748727,0.00055426254,0.017624354,0.00005791936,0.00018778669],"genre_scores_gemma":[0.8159575,0.00019856128,0.16408154,0.0009568996,0.0010752317,0.0003626232,0.0169262,0.000044894772,0.00039657968],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967368,0.000057197558,0.0006089243,0.0012258644,0.0010334402,0.00033776098],"domain_scores_gemma":[0.9936808,0.001060703,0.0004698619,0.0044797775,0.00021719903,0.000091688744],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00223691,0.00023550494,0.00026495356,0.00012163881,0.00053369155,0.0004252514,0.013448981,0.000054793036,0.000025676563],"category_scores_gemma":[0.00088203244,0.00018787647,0.000018335324,0.00042658945,0.00008015796,0.0008957609,0.009114257,0.0003746318,0.000009023655],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020306058,0.00040046073,0.0010269968,0.000087492735,0.0004081832,0.00003417974,0.0004117929,0.0009185487,0.0013199425,0.041912355,0.08913579,0.8641412],"study_design_scores_gemma":[0.00080265634,0.00016721898,0.0006854865,0.00028731162,0.000028459046,0.000047625053,0.00029630162,0.6729468,0.00066180376,0.005519288,0.31812146,0.00043557675],"about_ca_topic_score_codex":0.00020965097,"about_ca_topic_score_gemma":0.000073438125,"teacher_disagreement_score":0.86370564,"about_ca_system_score_codex":0.00007946143,"about_ca_system_score_gemma":0.0006364522,"threshold_uncertainty_score":0.9988998},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.304841879149363,"score_gpt":0.3731440942115506,"score_spread":0.06830221506218759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147794","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074849236,0.00009302594,0.9647464,0.0053632827,0.01323283,0.00046658213,0.003843309,0.00054218614,0.0042274185],"genre_scores_gemma":[0.96540105,0.00024959352,0.007581398,0.0010374853,0.0009790782,0.00007939543,0.023824355,0.000034101584,0.0008135544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99531496,0.0004268783,0.0005414111,0.0017674369,0.0015284733,0.00042084788],"domain_scores_gemma":[0.9956364,0.00020366824,0.0004471705,0.0033984785,0.00017510031,0.00013920234],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008250314,0.0002987366,0.0002605509,0.00041044533,0.0005251564,0.0004362739,0.010495506,0.000060900704,0.00026606026],"category_scores_gemma":[0.0001821376,0.00032667114,0.000063434214,0.0007853389,0.0001135658,0.0023371566,0.007543416,0.0010755248,0.00006935865],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036164618,0.00044289415,0.0064173285,0.000014227135,0.00022122699,0.00045062858,0.00025775444,0.005960971,0.0045491974,0.057778582,0.06865,0.85489553],"study_design_scores_gemma":[0.0009909078,0.00044038423,0.0019088855,0.00004522875,0.000022025833,0.00017042401,0.00021668652,0.8289555,0.0006088278,0.025884785,0.1399221,0.0008342757],"about_ca_topic_score_codex":0.00025012527,"about_ca_topic_score_gemma":0.00017696581,"teacher_disagreement_score":0.95791614,"about_ca_system_score_codex":0.00010589236,"about_ca_system_score_gemma":0.00015094374,"threshold_uncertainty_score":0.9999185},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Public transport; Computer science; Transit (satellite); Transport engineering; Data science; Engineering","score_opus":0.2616339857047169,"score_gpt":0.3015119091661445,"score_spread":0.0398779234614276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147813","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05708959,0.0005162911,0.270536,0.0036382913,0.018366564,0.002599537,0.6277262,0.0020523109,0.017475242],"genre_scores_gemma":[0.9372232,0.0002110317,0.00009382267,0.00010680959,0.000052331667,0.000055313452,0.062197324,0.000014019376,0.0000461264],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99721545,0.00017754565,0.0007042271,0.0006910281,0.0010029417,0.00020879782],"domain_scores_gemma":[0.9954698,0.00012281685,0.00014082946,0.004133263,0.00006147486,0.000071818475],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0014277784,0.0001750187,0.000408987,0.0006249642,0.00005286673,0.0000731319,0.0066445637,0.000028757971,0.00060910016],"category_scores_gemma":[0.00018702743,0.0001918845,0.000029281828,0.00086162344,0.000032835575,0.00056712603,0.00178242,0.00032533568,0.000005477295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011366959,0.00088467676,0.0075659193,0.00407005,0.009586339,0.00017126568,0.0002847977,0.027845642,0.0011823621,0.009257176,0.8237459,0.11529217],"study_design_scores_gemma":[0.00023061094,0.000014167966,0.0021962216,0.000112606824,0.00024087228,0.0000022118177,0.00044116133,0.9811985,0.000021571595,0.000016190552,0.015330254,0.00019566897],"about_ca_topic_score_codex":0.11525185,"about_ca_topic_score_gemma":0.7952311,"teacher_disagreement_score":0.9533528,"about_ca_system_score_codex":0.00048744064,"about_ca_system_score_gemma":0.0004181443,"threshold_uncertainty_score":0.99872994},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.4654309621175568,"score_gpt":0.43339241516499916,"score_spread":0.032038546952557645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318147859","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022277432,0.000020836478,0.9558966,0.002665506,0.0023463643,0.0003727822,0.008451953,0.00012860143,0.007839932],"genre_scores_gemma":[0.95411336,0.00011605903,0.02909539,0.00042253538,0.00018283012,0.00007570186,0.015569495,0.000026316198,0.0003982989],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99515855,0.0006270029,0.00067574263,0.0012402647,0.0019394308,0.0003589812],"domain_scores_gemma":[0.9953462,0.00049020495,0.0006270287,0.0030950676,0.00032768532,0.00011381669],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001708834,0.00028009794,0.0003340147,0.00026638916,0.0004244745,0.00066162384,0.007555006,0.000035995206,0.0001943694],"category_scores_gemma":[0.0003773488,0.0002802954,0.000051515493,0.00046317893,0.00013281379,0.00318961,0.0056585497,0.000684987,0.000040114333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007710004,0.0034984115,0.0035575184,0.00022674244,0.0012789122,0.00047055702,0.0031475408,0.0026040738,0.095017314,0.102511734,0.015200988,0.7717152],"study_design_scores_gemma":[0.0047419877,0.0014116688,0.019734502,0.00025922048,0.0001337163,0.00008530421,0.0075519034,0.9013361,0.00573751,0.0029965825,0.05407296,0.0019385491],"about_ca_topic_score_codex":0.00051264145,"about_ca_topic_score_gemma":0.0004609226,"teacher_disagreement_score":0.93183595,"about_ca_system_score_codex":0.00018687441,"about_ca_system_score_gemma":0.0005191971,"threshold_uncertainty_score":0.9999649},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.7268565196499841,"score_gpt":0.47980048120678986,"score_spread":0.24705603844319424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318148079","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073853147,0.000046002388,0.6619424,0.016746527,0.005959207,0.0007169757,0.31317398,0.00013565039,0.0005407151],"genre_scores_gemma":[0.18555784,0.0002053567,0.032643326,0.001170495,0.0017209176,0.0001784737,0.777316,0.000039226907,0.0011683733],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912679,0.0007454842,0.00084484,0.003263452,0.0032707206,0.0006075887],"domain_scores_gemma":[0.9841397,0.0009281028,0.00045244038,0.0136492085,0.00063056935,0.00019999765],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007859824,0.00032043495,0.00030860584,0.0005789054,0.0010009978,0.0017405323,0.038418546,0.0000776883,0.0003180532],"category_scores_gemma":[0.0030133883,0.0003376369,0.000029936995,0.0007330783,0.00016596733,0.00485014,0.037829477,0.001138848,0.000122343],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021978295,0.000507305,0.00017613899,0.000023406306,0.00009250003,0.000028190583,0.00008689985,0.0007853724,0.00010570439,0.046860624,0.61179894,0.33931512],"study_design_scores_gemma":[0.0006289837,0.00012298074,0.001008608,0.000019019417,0.000011042762,0.00001190551,0.000058296064,0.50856847,0.0000055089877,0.0013711671,0.48797777,0.00021624756],"about_ca_topic_score_codex":0.0014059752,"about_ca_topic_score_gemma":0.0010920743,"teacher_disagreement_score":0.6292991,"about_ca_system_score_codex":0.00026452864,"about_ca_system_score_gemma":0.002472907,"threshold_uncertainty_score":0.99990755},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Data deduplication; Computer science; Data mining; Software versioning; Kernel (algebra); Database; Software; Operating system","score_opus":0.5054255254777182,"score_gpt":0.4297697773039301,"score_spread":0.07565574817378812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318148204","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24896824,0.00006396672,0.72909385,0.005338928,0.0026421214,0.0006339412,0.010835878,0.0005967025,0.0018263969],"genre_scores_gemma":[0.96884954,0.00017616013,0.012245461,0.00055204425,0.00026542763,0.00012134182,0.01771075,0.000016501006,0.00006279691],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995834,0.00015650516,0.00041901224,0.0015907701,0.0017003266,0.00029936503],"domain_scores_gemma":[0.99493235,0.00010995109,0.00024667042,0.0043664086,0.00023142423,0.00011318423],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0017016429,0.00022605431,0.00019270628,0.00033541836,0.00043928888,0.00033484265,0.00850097,0.00007319442,0.00006331935],"category_scores_gemma":[0.0005306479,0.00023752115,0.000016287426,0.00043120343,0.00014120068,0.0033156315,0.008200962,0.0006094473,0.000020772382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074305804,0.00027975783,0.002411202,0.000010400522,0.000055404715,0.0000110699875,0.00017126526,0.009577411,0.0008338721,0.022914516,0.009909265,0.9537515],"study_design_scores_gemma":[0.00039169603,0.00015345062,0.0012999998,0.000012834838,0.00002237058,0.00004157196,0.0001525655,0.98863214,0.000080946054,0.0040922537,0.0048703877,0.00024980376],"about_ca_topic_score_codex":0.00002880252,"about_ca_topic_score_gemma":0.00006522831,"teacher_disagreement_score":0.9790547,"about_ca_system_score_codex":0.00026415335,"about_ca_system_score_gemma":0.00044230168,"threshold_uncertainty_score":0.99982053},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.4726800557815008,"score_gpt":0.4217361885031067,"score_spread":0.05094386727839412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318148225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00084346975,0.00003000243,0.98492754,0.0010719359,0.00197954,0.0005302154,0.010168958,0.00017471326,0.00027361308],"genre_scores_gemma":[0.73868984,0.00009132178,0.2425025,0.0002646273,0.0004967786,0.00030357158,0.016857874,0.000048047157,0.0007454802],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946086,0.00022368779,0.0003755367,0.0022589408,0.0019873313,0.00054595136],"domain_scores_gemma":[0.9952162,0.00082471245,0.0001763452,0.0033562097,0.00030318796,0.00012336059],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.005531415,0.00023625001,0.0002271603,0.0009363489,0.0004663224,0.00050562865,0.021522962,0.000044544435,0.000043106724],"category_scores_gemma":[0.0034372082,0.00025873084,0.000020222142,0.001512878,0.00009423188,0.0031063843,0.016275901,0.0010179622,0.000015703035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055518735,0.00084905745,0.0019206302,0.00006556102,0.00018884192,0.00007926275,0.00086846267,0.19771515,0.019011945,0.056192126,0.026282676,0.6962711],"study_design_scores_gemma":[0.00052269164,0.00014941397,0.00021822244,0.000026796224,0.0000054906773,0.000028235003,0.00006513614,0.9884093,0.00033018313,0.00070082024,0.009274444,0.00026929224],"about_ca_topic_score_codex":0.0005706761,"about_ca_topic_score_gemma":0.0005372976,"teacher_disagreement_score":0.7906941,"about_ca_system_score_codex":0.00045322752,"about_ca_system_score_gemma":0.0017083242,"threshold_uncertainty_score":0.99998647},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.44725369165867457,"score_gpt":0.3922616421471449,"score_spread":0.054992049511529695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318148360","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041107252,0.00046341275,0.1022484,0.4614002,0.051014982,0.010653371,0.30047375,0.0014798351,0.031158777],"genre_scores_gemma":[0.8478464,0.00009672275,0.0024011445,0.023584425,0.001815149,0.00064074603,0.12138514,0.00009114327,0.002139157],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99591374,0.00009921122,0.00056647096,0.0015168325,0.0014496817,0.00045407185],"domain_scores_gemma":[0.9957911,0.0005103537,0.0002828419,0.00302429,0.00021698531,0.00017445868],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011718643,0.00034198546,0.00037096353,0.0004935606,0.0003795669,0.00012034336,0.0034789932,0.00006626761,0.00088520447],"category_scores_gemma":[0.0005578842,0.0003723426,0.00009135504,0.00035228994,0.000100491976,0.00034603255,0.0028484426,0.0005384409,0.00007107279],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018122889,0.0020820638,0.0014107606,0.0005348293,0.00060621544,0.00090367306,0.00006622465,0.0012744791,0.0022014014,0.0033315548,0.5246468,0.46112967],"study_design_scores_gemma":[0.0018411591,0.00027309643,0.0011338351,0.00026508665,0.0001626421,0.00005667863,0.00022094543,0.2828609,0.00034533686,0.00022963331,0.71226984,0.00034086013],"about_ca_topic_score_codex":0.00023257504,"about_ca_topic_score_gemma":0.00023557949,"teacher_disagreement_score":0.80673915,"about_ca_system_score_codex":0.00052710884,"about_ca_system_score_gemma":0.0005571554,"threshold_uncertainty_score":0.99987286},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.248189087809298,"score_gpt":0.3494119663719226,"score_spread":0.10122287856262463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318148398","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97455657,0.0013965801,0.000024801217,0.006058007,0.0006286052,0.0006499553,0.01660305,0.000007997057,0.00007443343],"genre_scores_gemma":[0.99394065,0.0005468069,0.00006690968,0.00021590648,0.00013096865,0.000080822916,0.004592783,0.000010423938,0.00041474568],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99868685,0.000084222105,0.00027021006,0.0005314934,0.00028769608,0.00013954318],"domain_scores_gemma":[0.99865764,0.0001441077,0.00014031994,0.0009438277,0.00008107361,0.000033044405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010641814,0.00012940433,0.00018104313,0.00009172887,0.00016332952,0.000040127787,0.0005658304,0.000035399433,0.00005320907],"category_scores_gemma":[0.00021042892,0.00009004824,0.000013162744,0.00014059206,0.00012685155,0.00021004319,0.0008689622,0.00032596194,3.2780858e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0068925233,0.0006747873,0.42754605,0.0007580493,0.00079449,0.00042518193,0.001818134,0.00007258656,0.014015694,0.0008486409,0.040847454,0.5053064],"study_design_scores_gemma":[0.008035734,0.0007050196,0.7154686,0.00065963384,0.0003474172,0.002535142,0.002432665,0.17343402,0.0017395823,0.00009364564,0.094001174,0.0005474105],"about_ca_topic_score_codex":0.0013229513,"about_ca_topic_score_gemma":0.09188995,"teacher_disagreement_score":0.504759,"about_ca_system_score_codex":0.000099045275,"about_ca_system_score_gemma":0.00017843717,"threshold_uncertainty_score":0.9246807},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.24122699971033065,"score_gpt":0.33973951328562285,"score_spread":0.0985125135752922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318185035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0088698575,0.000028819182,0.9440605,0.0005024527,0.013396121,0.0006043635,0.030008411,0.0013750652,0.001154404],"genre_scores_gemma":[0.94181746,0.000085708474,0.0017253107,0.00015411204,0.0005632547,0.00012775233,0.055337034,0.000049152142,0.00014021431],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982544,0.000057391284,0.0003611286,0.0006137669,0.00048064557,0.0002326631],"domain_scores_gemma":[0.99832445,0.00016462784,0.00012935889,0.0012010366,0.00011596136,0.00006455218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003039383,0.000205967,0.0001580493,0.00016459936,0.00026683864,0.00012985505,0.0016149036,0.000053223976,0.00011085167],"category_scores_gemma":[0.00032478815,0.00024295381,0.000025437179,0.00015568477,0.00003324553,0.0003419517,0.00052813,0.00032446824,0.000028358087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012481418,0.00009329485,0.000014125671,0.000054423283,0.00009505347,0.000019505796,0.000041547915,0.86725533,0.0110350195,0.00092416955,0.047893807,0.07244891],"study_design_scores_gemma":[0.00054930465,0.00007433213,0.0001021236,0.00001677016,0.000024150366,0.000014952428,0.000036387162,0.9459896,0.001850154,0.0008023729,0.05029869,0.00024113365],"about_ca_topic_score_codex":0.000044165932,"about_ca_topic_score_gemma":0.000047721533,"teacher_disagreement_score":0.9423352,"about_ca_system_score_codex":0.0001696457,"about_ca_system_score_gemma":0.000048683505,"threshold_uncertainty_score":0.9907369},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3417629011562336,"score_gpt":0.3747394520079122,"score_spread":0.03297655085167861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318185064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92893004,0.0003948493,0.009005869,0.0020324143,0.02551983,0.0010325813,0.009146845,0.00022483424,0.023712726],"genre_scores_gemma":[0.99611956,0.0005807385,0.00014168411,0.00021854693,0.0012948825,0.000093191855,0.001191882,0.000022949647,0.00033655134],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99602956,0.0004415661,0.0005059559,0.0009962355,0.0014261086,0.0006006003],"domain_scores_gemma":[0.9981846,0.00028360967,0.00032722185,0.0010263538,0.00007979861,0.0000983867],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023462044,0.00024170498,0.00028834527,0.0003574794,0.0005978295,0.00029571622,0.003196319,0.00009032535,0.00036419113],"category_scores_gemma":[0.00083401916,0.0002944719,0.000042488864,0.00081056956,0.0001628123,0.0011436332,0.0017786253,0.0008798298,0.00001757591],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051350007,0.0003591914,0.005642018,0.000032424916,0.00007473586,0.00010577935,0.00927934,0.0016182691,0.0013096263,0.0058630817,0.0066045057,0.96859753],"study_design_scores_gemma":[0.0038536612,0.00039459663,0.021917878,0.00068260817,0.000049764283,0.00003344763,0.10663246,0.22078322,0.0009503551,0.004252809,0.6382857,0.0021635129],"about_ca_topic_score_codex":0.051989466,"about_ca_topic_score_gemma":0.29662326,"teacher_disagreement_score":0.966434,"about_ca_system_score_codex":0.0008896123,"about_ca_system_score_gemma":0.00062362954,"threshold_uncertainty_score":0.99995077},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.9445247924110595,"score_gpt":0.5941263284283097,"score_spread":0.35039846398274976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318185132","genre_codex":"dataset","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.4829404e-7,0.45608628,0.004004519,0.0021729474,0.009992622,0.0015395446,0.52148074,0.00010096643,0.004622118],"genre_scores_gemma":[0.0000029208466,0.60721445,0.00043149482,0.0028948393,0.0015518144,0.00017462394,0.38533476,0.000050449184,0.0023446302],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97974664,0.002583426,0.0033330678,0.006373909,0.0072983913,0.0006645376],"domain_scores_gemma":[0.9574002,0.004158267,0.0022596095,0.035281073,0.00039333847,0.0005075001],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.012021707,0.0010835255,0.0033660799,0.0009694112,0.00038338167,0.002031271,0.0844325,0.00020239461,0.018055383],"category_scores_gemma":[0.009123594,0.0008831522,0.00024101867,0.0018470454,0.00021904576,0.0026327898,0.06154928,0.0015585796,0.01191348],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020784662,0.00015718206,2.5254454e-7,0.0004495791,0.00032789877,0.00006297513,0.00003756451,8.5131984e-7,7.606146e-8,0.0007144516,0.5003039,0.49792445],"study_design_scores_gemma":[0.00026607176,0.00007629258,0.0000017329043,0.00914134,0.0006437727,0.000016156719,0.00030455462,0.00057533634,1.5896894e-7,0.00075039355,0.9872922,0.00093202636],"about_ca_topic_score_codex":0.0012387198,"about_ca_topic_score_gemma":0.0045828274,"teacher_disagreement_score":0.49699244,"about_ca_system_score_codex":0.00031306178,"about_ca_system_score_gemma":0.0014855758,"threshold_uncertainty_score":0.99936193},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Big data; Computer science; Data modeling; Quality (philosophy); Data mining; Database; Physics","score_opus":0.7505477363862263,"score_gpt":0.4080711581157322,"score_spread":0.3424765782704941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318185157","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029409085,0.00008346818,0.6129281,0.0075448547,0.030408906,0.001241568,0.3410549,0.00025344177,0.0035438845],"genre_scores_gemma":[0.67102706,0.00015117935,0.0009029489,0.003928367,0.009516309,0.00019357182,0.31336358,0.00008316475,0.0008338011],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99330884,0.000050039136,0.0010748281,0.002262869,0.0026951924,0.0006082271],"domain_scores_gemma":[0.99089944,0.0001312753,0.0009334378,0.0070011886,0.00097573054,0.000058936923],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0038086213,0.00052308186,0.0005241804,0.00043060494,0.00069252227,0.0011652453,0.015581623,0.00010778352,0.00061627175],"category_scores_gemma":[0.0016879762,0.00053666526,0.00006724057,0.0005040185,0.00015081416,0.003019417,0.01423682,0.0006236541,0.00021406998],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011914186,0.0020630788,0.0006978903,0.0003821337,0.00047885545,0.000028373528,0.000051369087,0.00030423026,0.0079772035,0.031198135,0.43450475,0.5211226],"study_design_scores_gemma":[0.00072862423,0.000018808036,0.0005257921,0.000073582254,0.000108183325,0.000008436114,0.0001184559,0.50609577,0.000028684743,0.0011055643,0.49061683,0.00057129865],"about_ca_topic_score_codex":0.0017910076,"about_ca_topic_score_gemma":0.0025604889,"teacher_disagreement_score":0.6680862,"about_ca_system_score_codex":0.00021380773,"about_ca_system_score_gemma":0.0005341115,"threshold_uncertainty_score":0.9998716},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.6250192258128631,"score_gpt":0.46840426658816997,"score_spread":0.1566149592246931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318185484","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13051797,0.00012637042,0.15427232,0.020011008,0.07257748,0.002622449,0.23118536,0.00071536587,0.3879717],"genre_scores_gemma":[0.9702075,0.000015302747,0.000081860664,0.00040762144,0.00032197498,0.0000632993,0.027096009,0.00002264619,0.0017837578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967946,0.00045892276,0.00082941965,0.00076969096,0.0009329778,0.000214437],"domain_scores_gemma":[0.9973664,0.00019596318,0.0005585425,0.0016595123,0.00015975798,0.00005978644],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012442843,0.0001992462,0.00025968163,0.0007198633,0.00026694135,0.0001180167,0.002263458,0.00007600211,0.021900399],"category_scores_gemma":[0.00017745758,0.00022955773,0.000032415894,0.00051813445,0.000075151074,0.00072162494,0.0007905795,0.0004972906,0.0001375625],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008842895,0.0019067723,0.0027488691,0.00005407105,0.0005294778,0.000094826864,0.0050339596,0.0015526495,0.018829288,0.6637772,0.25533304,0.049255606],"study_design_scores_gemma":[0.012523865,0.0011738857,0.053132884,0.00040136182,0.00014331396,0.00014445669,0.040866878,0.5011687,0.0014189713,0.018913195,0.3679589,0.0021535635],"about_ca_topic_score_codex":0.00034467457,"about_ca_topic_score_gemma":0.0020333296,"teacher_disagreement_score":0.83968955,"about_ca_system_score_codex":0.0005292599,"about_ca_system_score_gemma":0.00020573281,"threshold_uncertainty_score":0.9789937},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.44863126012549726,"score_gpt":0.407795632811187,"score_spread":0.04083562731431023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318186065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.803276,0.0011698531,0.06040262,0.023273097,0.009932373,0.0040455037,0.032133017,0.00053326995,0.065234244],"genre_scores_gemma":[0.97100496,0.0003406804,0.0004588048,0.000721988,0.00084880367,0.00007832232,0.025550202,0.000043041793,0.0009531935],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99614763,0.00019022272,0.00038080435,0.0010422717,0.0018404598,0.0003986181],"domain_scores_gemma":[0.9972209,0.00008047247,0.0001806126,0.0020757716,0.00026054523,0.00018172745],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00068143813,0.00026951745,0.00029542175,0.00030466524,0.00042581165,0.00018610415,0.002285618,0.000097414,0.0016575141],"category_scores_gemma":[0.0000987049,0.00023177412,0.00004981194,0.00045687408,0.00019675253,0.00050253887,0.00043453535,0.0012145372,0.000060974635],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010302752,0.002437305,0.0036695867,0.00014617623,0.0022842663,0.0012987107,0.00064529205,0.00060936454,0.33252114,0.010397529,0.050397605,0.58529025],"study_design_scores_gemma":[0.014674439,0.0051784744,0.032893375,0.0007158867,0.0010560751,0.0023521564,0.0072686416,0.2607358,0.019645598,0.0009714478,0.65216976,0.0023383363],"about_ca_topic_score_codex":0.00018389778,"about_ca_topic_score_gemma":0.00046849975,"teacher_disagreement_score":0.6017721,"about_ca_system_score_codex":0.0002785333,"about_ca_system_score_gemma":0.0008159592,"threshold_uncertainty_score":0.9992551},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.27825448653320733,"score_gpt":0.35604696893970694,"score_spread":0.07779248240649961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318186088","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014061941,0.00009474752,0.88559335,0.0267104,0.017307803,0.0006973483,0.064859115,0.0006826976,0.0026483666],"genre_scores_gemma":[0.8927077,0.00033167578,0.033000592,0.0036935755,0.00092311564,0.00059956143,0.06695841,0.000077515346,0.0017078185],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947531,0.0003273642,0.00059153384,0.0022882512,0.0014579492,0.00058178854],"domain_scores_gemma":[0.9786849,0.0006681751,0.00040670705,0.019798478,0.00031501395,0.00012670463],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0024214087,0.00038390144,0.0003398061,0.00038495904,0.00074579,0.00082137325,0.11659752,0.000114471455,0.0007594126],"category_scores_gemma":[0.009589282,0.00040962905,0.000055080436,0.00066420337,0.00021007277,0.002019586,0.18514635,0.0008215796,0.00011875271],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001935906,0.00027391274,0.000086567125,0.000021709524,0.0001767002,0.0000841457,0.000049791586,0.000037364953,0.0019508217,0.09356381,0.70217806,0.20138353],"study_design_scores_gemma":[0.0009881699,0.000176847,0.00008381361,0.000036455665,0.000018685741,0.00005539127,0.0001513798,0.6100502,0.001586391,0.19700947,0.18922582,0.0006173671],"about_ca_topic_score_codex":0.00010816441,"about_ca_topic_score_gemma":0.00008944605,"teacher_disagreement_score":0.8913015,"about_ca_system_score_codex":0.00023804189,"about_ca_system_score_gemma":0.00063053047,"threshold_uncertainty_score":0.99983555},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Vector Institute","funders":"","keywords":"Series (stratigraphy); Time series; Computer science; Machine learning; Geology","score_opus":0.762746653460341,"score_gpt":0.45772942114912724,"score_spread":0.30501723231121375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318186095","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045029618,0.0000679587,0.39697015,0.020718144,0.010758556,0.0035623861,0.22118941,0.0011547317,0.30054906],"genre_scores_gemma":[0.93660986,0.000011925313,0.017812686,0.001211875,0.0011417662,0.0004142558,0.03297188,0.00005423248,0.009771528],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99405235,0.00021936692,0.000897464,0.0018267715,0.0026004764,0.00040358037],"domain_scores_gemma":[0.9940458,0.00031722637,0.00046531833,0.0046021417,0.00037563033,0.00019391144],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0031532417,0.00029074357,0.00034173045,0.00052923977,0.0008441776,0.00080391986,0.013905242,0.000058031837,0.0017842618],"category_scores_gemma":[0.0014732649,0.00027157887,0.00006727108,0.0009186195,0.00013180947,0.00080780865,0.008966708,0.0005031244,0.00045980734],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001818464,0.0005756721,0.00022424878,0.000005533592,0.000071470335,0.000020250505,0.00020323525,0.0002434057,0.0038575472,0.03845256,0.7675487,0.18861555],"study_design_scores_gemma":[0.000531631,0.00029591954,0.00020866614,0.000044415945,0.000024130915,0.00012650003,0.00077134033,0.23706798,0.00035284,0.020219509,0.7397473,0.0006097516],"about_ca_topic_score_codex":0.0001832291,"about_ca_topic_score_gemma":0.000148956,"teacher_disagreement_score":0.8915802,"about_ca_system_score_codex":0.0001389728,"about_ca_system_score_gemma":0.000199038,"threshold_uncertainty_score":0.99997365},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Matching (statistics); Statistics; Mathematics","score_opus":0.6664563814827509,"score_gpt":0.4557380255016488,"score_spread":0.21071835598110206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318187137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037671443,0.000051204417,0.58079004,0.029684363,0.02680365,0.0012514273,0.27326807,0.0003333516,0.050146453],"genre_scores_gemma":[0.9421769,0.000027335718,0.0008851946,0.0030008208,0.00055055844,0.00007188579,0.049754392,0.000024431656,0.0035085245],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9911465,0.00060547673,0.00076645956,0.0019078131,0.005200207,0.00037355564],"domain_scores_gemma":[0.9922483,0.0006265891,0.000530135,0.0061526997,0.0002854757,0.00015681979],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0063508744,0.00028675687,0.0003435746,0.0005316997,0.00058336137,0.0013517684,0.016823674,0.000042586566,0.0060702134],"category_scores_gemma":[0.0008768787,0.00024246966,0.000050077742,0.00072403037,0.00017429804,0.0017404582,0.0084126005,0.00057270017,0.00070077024],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079204363,0.0010272501,0.0013144709,0.000024888837,0.00025435557,0.00025650262,0.00021745198,0.0016403192,0.00039331007,0.09533767,0.5560572,0.34268454],"study_design_scores_gemma":[0.0011599958,0.00017693636,0.0013182109,0.00004421529,0.00003428354,0.000015264332,0.002329668,0.036200147,0.00009883745,0.012399021,0.9457222,0.0005011918],"about_ca_topic_score_codex":0.0011803901,"about_ca_topic_score_gemma":0.0030879127,"teacher_disagreement_score":0.90450543,"about_ca_system_score_codex":0.00015164698,"about_ca_system_score_gemma":0.0005706901,"threshold_uncertainty_score":0.99968493},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.29481025468805927,"score_gpt":0.3133429269993256,"score_spread":0.01853267231126632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318187617","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6218552,0.000052552958,0.011377994,0.034499772,0.016280154,0.0039264974,0.042227123,0.0009076263,0.26887307],"genre_scores_gemma":[0.97065705,0.000010672232,0.000089749956,0.0057237316,0.0015405768,0.00023027438,0.021359082,0.00004808642,0.00034076095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99614704,0.000119512704,0.0004573491,0.0012641745,0.0015877477,0.0004242077],"domain_scores_gemma":[0.99655354,0.00033233073,0.00028236484,0.002561943,0.00021876825,0.000051082436],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015543202,0.00036493974,0.00027467683,0.00049639546,0.0005044445,0.0008307067,0.005895653,0.000050065017,0.0019850892],"category_scores_gemma":[0.0006912812,0.00031300794,0.00006384016,0.00075479597,0.00006174979,0.00077169103,0.0037812097,0.0007245895,0.00012953237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00265482,0.0036442438,0.08715586,0.00031494946,0.00060709583,0.0001715624,0.0005303037,0.0012318254,0.00449306,0.019609744,0.3635896,0.51599693],"study_design_scores_gemma":[0.0017998574,0.00008212047,0.009161007,0.00020045867,0.00021293688,0.000010021819,0.00223652,0.83199185,0.000074010015,0.00036964726,0.15296303,0.0008985682],"about_ca_topic_score_codex":0.0021077488,"about_ca_topic_score_gemma":0.00031428557,"teacher_disagreement_score":0.83076,"about_ca_system_score_codex":0.00010341082,"about_ca_system_score_gemma":0.00018985529,"threshold_uncertainty_score":0.9999322},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.6416240419164759,"score_gpt":0.4430536513876135,"score_spread":0.19857039052886244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318187680","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060152584,0.0002600123,0.35117197,0.19728698,0.027379133,0.004408914,0.40973186,0.00044089148,0.0033049735],"genre_scores_gemma":[0.90384775,0.00022199456,0.0039577796,0.008348281,0.0011687337,0.00031065766,0.08126599,0.00004849856,0.00083029736],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936911,0.0007715561,0.0011592774,0.0018311606,0.0016449095,0.00090200314],"domain_scores_gemma":[0.99386525,0.00018028625,0.00078210176,0.004429485,0.00005958672,0.0006832809],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.007118542,0.00034772136,0.00056519266,0.0003006907,0.0011884199,0.00017338735,0.007673989,0.00006661446,0.0002551307],"category_scores_gemma":[0.000750949,0.0003627701,0.00008117536,0.0005786031,0.00011716029,0.0012266284,0.007615218,0.0005505866,0.00016673042],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030862473,0.0020151054,0.016985692,0.0009541257,0.0002658121,0.000007675963,0.000990159,0.0018154748,0.000033336415,0.00678435,0.5147369,0.45510274],"study_design_scores_gemma":[0.0019413861,0.00075885374,0.08956577,0.00037731952,0.000022651204,0.000043909746,0.0056740367,0.06447575,0.00000335047,0.00012575075,0.8361799,0.00083131145],"about_ca_topic_score_codex":0.006564627,"about_ca_topic_score_gemma":0.0049181986,"teacher_disagreement_score":0.8978325,"about_ca_system_score_codex":0.0020253516,"about_ca_system_score_gemma":0.0008740486,"threshold_uncertainty_score":0.9998824},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2539979832914212,"score_gpt":0.37115651489714635,"score_spread":0.11715853160572515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024021","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26161376,0.0001632976,0.6978266,0.014175231,0.007875231,0.0012740586,0.0148841385,0.00024638145,0.0019412617],"genre_scores_gemma":[0.98577327,0.00006843157,0.0012098926,0.00027794528,0.0001594196,0.00006967019,0.012298395,0.000008522232,0.00013448106],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967165,0.00022616226,0.0004401158,0.0009718127,0.0013824123,0.000262992],"domain_scores_gemma":[0.9967681,0.0002245786,0.0003788739,0.0021303708,0.0004056574,0.00009238906],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00166766,0.00019089831,0.00020843322,0.0003809528,0.0007296043,0.0004268448,0.0062341774,0.000049258146,0.000060334234],"category_scores_gemma":[0.0003087125,0.00016358559,0.000024735898,0.0008142921,0.000086259686,0.0011422085,0.0017751167,0.00035542558,0.00001751127],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003562506,0.00057003263,0.0006175959,0.000015625692,0.0006535724,0.000036629262,0.0016061486,0.0012349364,0.0027786,0.08992799,0.004991137,0.8972115],"study_design_scores_gemma":[0.00061470055,0.00040175335,0.0050265607,0.000052472085,0.00010041053,0.000022759323,0.0030414173,0.866309,0.03197844,0.005367869,0.08639202,0.0006926274],"about_ca_topic_score_codex":0.0001019392,"about_ca_topic_score_gemma":0.0016057742,"teacher_disagreement_score":0.8965188,"about_ca_system_score_codex":0.00015144872,"about_ca_system_score_gemma":0.00039667965,"threshold_uncertainty_score":0.9991426},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2510556575753,"score_gpt":0.3345477456942415,"score_spread":0.08349208811894149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4317868,0.0004708806,0.11826912,0.050267596,0.03556304,0.0054253265,0.32917082,0.0010866147,0.0279598],"genre_scores_gemma":[0.862228,0.00037719274,0.015643345,0.0014149752,0.0009426644,0.000021931792,0.11751378,0.000056464683,0.0018016773],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952173,0.0002936213,0.0004745035,0.0021347043,0.001490973,0.00038890267],"domain_scores_gemma":[0.9945236,0.00014868473,0.000375948,0.0047037113,0.000069086534,0.00017900784],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010233251,0.00036346423,0.00028581297,0.000080730504,0.00038605504,0.00024031186,0.005884828,0.00007726631,0.0016300183],"category_scores_gemma":[0.00031975107,0.0003111062,0.000020891302,0.0003673344,0.00031359927,0.0011883309,0.0068490794,0.0007114765,0.00023493066],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008039586,0.0009977078,0.004080283,0.000023783321,0.00021537136,0.00014099693,0.00022468812,0.0020103487,0.1437413,0.0004690842,0.3838893,0.4634032],"study_design_scores_gemma":[0.0020826962,0.00017982716,0.024342217,0.000066807625,0.00007126615,0.00013609987,0.0006513781,0.61663085,0.00058591523,0.000103414364,0.354338,0.00081150857],"about_ca_topic_score_codex":0.00037581002,"about_ca_topic_score_gemma":0.00093586964,"teacher_disagreement_score":0.6146205,"about_ca_system_score_codex":0.00025863847,"about_ca_system_score_gemma":0.000091989845,"threshold_uncertainty_score":0.9999341},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.6122670306410279,"score_gpt":0.4310872843677545,"score_spread":0.18117974627327343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024084","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19257598,0.0006116975,0.11401815,0.030044992,0.052117493,0.001997547,0.604129,0.00030373223,0.004201384],"genre_scores_gemma":[0.80240595,0.00009249244,0.003430693,0.00048492648,0.0003747916,0.000041042847,0.18884282,0.000020255176,0.0043070405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9901613,0.00053627905,0.0009935346,0.0025933124,0.005350038,0.00036551204],"domain_scores_gemma":[0.9856824,0.0023223928,0.000685914,0.010696018,0.00044803403,0.0001652038],"candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.009355021,0.00027198394,0.00042217306,0.00086806953,0.0013382002,0.0009508677,0.01477543,0.000043877262,0.0010488488],"category_scores_gemma":[0.0023361421,0.00019671272,0.00008127001,0.0020498415,0.00040067302,0.0011318316,0.034534916,0.00042639757,0.00008796015],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026743402,0.0005229602,0.004274483,0.0000031400205,0.0011642404,0.00002059857,0.00007242993,0.0022806276,0.00022348265,0.004515918,0.4314239,0.5552308],"study_design_scores_gemma":[0.00034658174,0.000050144237,0.005646142,0.000010926259,0.00018811412,0.0000071755567,0.0006474024,0.5892569,0.000005081983,0.0003610839,0.40331256,0.00016792602],"about_ca_topic_score_codex":0.0005612059,"about_ca_topic_score_gemma":0.0028946428,"teacher_disagreement_score":0.60982996,"about_ca_system_score_codex":0.00006848728,"about_ca_system_score_gemma":0.0003167267,"threshold_uncertainty_score":0.9999619},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.5787873684648848,"score_gpt":0.3602816516620805,"score_spread":0.21850571680280428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0105914585,0.000058652364,0.7591844,0.01200454,0.015320424,0.0018704348,0.12780143,0.00007811449,0.07309054],"genre_scores_gemma":[0.9728423,0.000016396045,0.0012418181,0.00041513905,0.00067486515,0.00024413333,0.022819206,0.000014628279,0.0017315224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980396,0.00007432543,0.0005296582,0.00046470505,0.0007547849,0.00013693943],"domain_scores_gemma":[0.9979466,0.00047411353,0.00036495662,0.000988163,0.00019171764,0.0000344433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009805611,0.00014767055,0.00015104312,0.0001292102,0.0004838148,0.00016434894,0.0027046925,0.0000102341355,0.0006031023],"category_scores_gemma":[0.000065052984,0.0001008287,0.000051475257,0.00005249211,0.00019162914,0.00038435718,0.0008501663,0.00018963579,0.000008144265],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021128122,0.0004911661,0.000008286247,0.00001911842,0.000285483,2.887093e-7,0.0017636874,0.00022025446,0.00042835265,0.63883525,0.009474627,0.3482622],"study_design_scores_gemma":[0.0004351096,0.00015327902,0.002018672,0.000038920778,0.00005568569,0.0000027943204,0.009738395,0.16952129,0.00017375418,0.0054839915,0.812203,0.00017510797],"about_ca_topic_score_codex":0.00019574621,"about_ca_topic_score_gemma":0.0016589041,"teacher_disagreement_score":0.9622508,"about_ca_system_score_codex":0.00006755489,"about_ca_system_score_gemma":0.00023752917,"threshold_uncertainty_score":0.66035473},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.3307912242688666,"score_gpt":0.395012270814312,"score_spread":0.06422104654544541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7064985,0.00014622857,0.25210324,0.0024585582,0.01288454,0.0022343467,0.022409199,0.0005863353,0.0006790644],"genre_scores_gemma":[0.92607874,0.000026543226,0.065935634,0.00020052973,0.0010396179,0.00027625414,0.0063233697,0.00004570705,0.000073608484],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969487,0.000113719216,0.0004549931,0.0011148303,0.00095789565,0.00040983548],"domain_scores_gemma":[0.99719673,0.00030947838,0.0003717291,0.0016578467,0.00031538834,0.0001488518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000784617,0.00027941406,0.0003476862,0.00035946115,0.00050554995,0.00007533772,0.0016686787,0.00009769273,0.00003130625],"category_scores_gemma":[0.00021789008,0.00026700782,0.00003909138,0.00026344566,0.00005547838,0.00036760053,0.0016504161,0.0010000733,0.0000080903865],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004171872,0.0010812903,0.04155746,0.00020039268,0.00088925473,0.00018517481,0.0014208897,0.00017518997,0.046204224,0.0019896328,0.001014455,0.9011102],"study_design_scores_gemma":[0.024603818,0.026580373,0.055846345,0.0038434213,0.0016579633,0.0015469205,0.014576002,0.70004857,0.06673801,0.0006586957,0.09956502,0.0043348726],"about_ca_topic_score_codex":0.0009752652,"about_ca_topic_score_gemma":0.00007557623,"teacher_disagreement_score":0.8967753,"about_ca_system_score_codex":0.00033271872,"about_ca_system_score_gemma":0.0004683886,"threshold_uncertainty_score":0.9999782},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.15820750215485105,"score_gpt":0.3135448753019634,"score_spread":0.15533737314711235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024124","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015126028,0.00022394703,0.9249254,0.006785614,0.016889349,0.00047087503,0.02884995,0.0003235827,0.006405284],"genre_scores_gemma":[0.96042305,0.00042196762,0.010084714,0.0012504138,0.00039074433,0.000066526554,0.025363935,0.000029130413,0.001969503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969995,0.00019524433,0.00032316684,0.0012601243,0.0009213287,0.000300639],"domain_scores_gemma":[0.99677426,0.00011673658,0.00017267729,0.002699526,0.00010966032,0.00012713257],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0009428939,0.00022518689,0.0001911905,0.00033335033,0.00050541724,0.00054681295,0.0083199665,0.000044267676,0.00037765148],"category_scores_gemma":[0.00008134788,0.0002388949,0.000030081363,0.0005438657,0.00013688934,0.0014238514,0.006648605,0.0004345763,0.000050504776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015011217,0.0005800648,0.00056433014,0.000024127696,0.00026547973,0.00020951671,0.00029915446,0.0010461535,0.0022306994,0.45309046,0.034442548,0.50709736],"study_design_scores_gemma":[0.00075655297,0.00018116525,0.00057706673,0.000029713663,0.000018767247,0.000113556125,0.0001915017,0.9121439,0.000117781296,0.019217383,0.06617222,0.00048041434],"about_ca_topic_score_codex":0.000054106953,"about_ca_topic_score_gemma":0.000055768927,"teacher_disagreement_score":0.94529706,"about_ca_system_score_codex":0.000052066014,"about_ca_system_score_gemma":0.00018166692,"threshold_uncertainty_score":0.9970455},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2687715235562875,"score_gpt":0.32970328184096914,"score_spread":0.06093175828468167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024146","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2278501,0.0023880021,0.6112442,0.04017305,0.020309968,0.0034920094,0.08807025,0.0013020807,0.0051703774],"genre_scores_gemma":[0.99469674,0.0005077266,0.0012149061,0.00020277004,0.00013659557,0.00009016684,0.0031099587,0.000009206451,0.00003193718],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966937,0.0004951597,0.0005116986,0.0010287504,0.0010354755,0.00023526188],"domain_scores_gemma":[0.99001694,0.0004626565,0.00037419205,0.00899102,0.00011143118,0.000043767468],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0021296365,0.0001905769,0.00024076816,0.00030296904,0.00027467564,0.00029720398,0.026164547,0.0000648416,0.000017458122],"category_scores_gemma":[0.00048333284,0.00016439124,0.00001795921,0.0006912286,0.0001765518,0.00065222284,0.016659409,0.0007994567,0.000006376441],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010170517,0.00026178587,0.00031412943,0.00004585882,0.00006856353,0.000029015866,0.0003533336,0.000088182955,0.0026953935,0.036403228,0.005917411,0.9537214],"study_design_scores_gemma":[0.0011376876,0.00019072986,0.0012743246,0.00016641607,0.000019210982,0.0001098048,0.0028827386,0.9425863,0.0014794262,0.0012340015,0.04853343,0.00038592375],"about_ca_topic_score_codex":0.0009804952,"about_ca_topic_score_gemma":0.0014679732,"teacher_disagreement_score":0.95333546,"about_ca_system_score_codex":0.00006970309,"about_ca_system_score_gemma":0.00023362553,"threshold_uncertainty_score":0.99129367},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"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","score_opus":0.38674126848575496,"score_gpt":0.38499527520446797,"score_spread":0.001745993281286995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024165","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02747599,0.00009751681,0.7545375,0.027087986,0.013344307,0.0010300532,0.17500639,0.0006858466,0.00073439645],"genre_scores_gemma":[0.8573691,0.00032933234,0.0424503,0.0007177923,0.00086046534,0.0003356466,0.09775686,0.00003641898,0.00014402981],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99514794,0.00021262799,0.0006534471,0.0021512844,0.0013115251,0.00052317145],"domain_scores_gemma":[0.98342806,0.00054969016,0.0005129602,0.0151644815,0.00021253318,0.00013228679],"candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001716541,0.00038715237,0.0003379281,0.00050398626,0.00054857443,0.0009713388,0.07500989,0.00010621436,0.00010904252],"category_scores_gemma":[0.009435008,0.00040881825,0.000042153533,0.00043193047,0.00014373983,0.0024135653,0.15267153,0.0007318861,0.000012438482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000864143,0.00019813879,0.0037970797,0.000046889476,0.00009788869,0.000035957764,0.0001751233,0.000010679221,0.0009334297,0.0032090833,0.52829945,0.46310985],"study_design_scores_gemma":[0.0011919433,0.00035078175,0.001144459,0.00020645266,0.000027238053,0.00007179662,0.0005490216,0.8085216,0.0010841715,0.018990595,0.16703399,0.0008279249],"about_ca_topic_score_codex":0.00029632682,"about_ca_topic_score_gemma":0.00033203445,"teacher_disagreement_score":0.8298932,"about_ca_system_score_codex":0.00018543695,"about_ca_system_score_gemma":0.00038438226,"threshold_uncertainty_score":0.9998364},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.21622871598344806,"score_gpt":0.35008913582646745,"score_spread":0.13386041984301938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024183","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027430044,0.00008416266,0.8068509,0.008618482,0.016372057,0.0015926608,0.15211204,0.0008211672,0.010805503],"genre_scores_gemma":[0.827562,0.00017910899,0.08799274,0.0020254266,0.00068456726,0.00068958197,0.078836106,0.00006373208,0.0019667295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957039,0.00016010806,0.00057790853,0.0018095652,0.001251207,0.00049732387],"domain_scores_gemma":[0.9930424,0.0005188845,0.00038097228,0.0057037747,0.00019171661,0.0001622677],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0011045538,0.0003629104,0.0003348027,0.00029352415,0.00035431804,0.0004384728,0.016654907,0.00007283949,0.00030611258],"category_scores_gemma":[0.0004513334,0.00039538968,0.00006487243,0.00031327188,0.00013961134,0.0012560337,0.008948982,0.00044837207,0.000055978853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023220143,0.0005641511,0.000052606603,0.000029090419,0.00024325115,0.00010824361,0.0001664618,0.00009098757,0.0047751036,0.09421953,0.27284002,0.62667835],"study_design_scores_gemma":[0.002184832,0.0009827001,0.00043542244,0.000103389066,0.00006230748,0.00017503586,0.00042307598,0.72708553,0.0011888456,0.01414893,0.25216338,0.0010465446],"about_ca_topic_score_codex":0.00021500807,"about_ca_topic_score_gemma":0.00071489374,"teacher_disagreement_score":0.82481897,"about_ca_system_score_codex":0.0002919731,"about_ca_system_score_gemma":0.0006375826,"threshold_uncertainty_score":0.9998498},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4424567085698399,"score_gpt":0.42876867080501857,"score_spread":0.013688037764821304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024230","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19984958,0.00052966014,0.09106721,0.032187372,0.013893917,0.008903537,0.6502448,0.0005801612,0.002743797],"genre_scores_gemma":[0.8304764,0.00027290982,0.011446854,0.00084838644,0.0008695051,0.0009010861,0.15488902,0.000044982866,0.00025084423],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965592,0.0000851325,0.0006282393,0.0014397491,0.0008784895,0.0004091581],"domain_scores_gemma":[0.99569505,0.00044965968,0.0003129491,0.0031707662,0.00024412417,0.00012744652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001714527,0.00029892454,0.00044681065,0.0002980354,0.00025188233,0.00019779113,0.003915959,0.00006644527,0.00025089784],"category_scores_gemma":[0.00089903886,0.00029439933,0.000059654318,0.00019200023,0.000087483364,0.00066619355,0.0031640672,0.0005088277,0.000013020474],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042889793,0.0067429123,0.04956658,0.0008929188,0.0014241586,0.00058811664,0.0003850787,0.000028230656,0.03366287,0.020431994,0.575272,0.30671614],"study_design_scores_gemma":[0.022876011,0.006643583,0.025470037,0.0047361073,0.0015521212,0.0009977712,0.004140732,0.2736922,0.044634998,0.009816465,0.6026727,0.0027672886],"about_ca_topic_score_codex":0.0011567321,"about_ca_topic_score_gemma":0.0008101901,"teacher_disagreement_score":0.63062686,"about_ca_system_score_codex":0.00028481134,"about_ca_system_score_gemma":0.0004242978,"threshold_uncertainty_score":0.9999508},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.8077064389291911,"score_gpt":0.5061207953285485,"score_spread":0.30158564360064266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320024352","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001490502,0.005669428,0.0188944,0.11308918,0.02354572,0.0015441999,0.79181635,0.00014336422,0.04514833],"genre_scores_gemma":[0.025111338,0.070449896,0.0025733763,0.073307976,0.002118886,0.00016579134,0.80585146,0.000081982,0.020339303],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9871895,0.0013284273,0.0021439143,0.0028614919,0.005934084,0.0005425894],"domain_scores_gemma":[0.9789383,0.0009062659,0.0015668478,0.01765819,0.00061887724,0.00031151433],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.022832815,0.00034461226,0.0007724446,0.0006014536,0.00041365082,0.0007487819,0.038791616,0.000054727014,0.013330643],"category_scores_gemma":[0.0076445923,0.0003099359,0.00007111667,0.0013102505,0.00021712077,0.0024261512,0.035109952,0.0006791715,0.001720524],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046300007,0.00028333158,0.00003851975,0.00015143456,0.00007721219,0.000011252767,0.000017220764,0.0000022420993,0.000018642999,0.006074741,0.6461211,0.34715798],"study_design_scores_gemma":[0.00046444836,0.00014757545,0.00011679161,0.0005437565,0.000029547151,0.000016262404,0.00030931755,0.006916731,0.000007550864,0.0019215718,0.9892234,0.0003030168],"about_ca_topic_score_codex":0.0013941182,"about_ca_topic_score_gemma":0.0017527373,"teacher_disagreement_score":0.34685498,"about_ca_system_score_codex":0.00016477212,"about_ca_system_score_gemma":0.0016151189,"threshold_uncertainty_score":0.99993527},"labels":[],"label_agreement":null}]}