{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":29,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":29,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"b933c51cc8d0","filters":{"venue":"Journal Of Big Data"}},"results":[{"id":"W3044719873","doi":"10.1186/s40537-020-00329-2","title":"Predictive big data analytics for supply chain demand forecasting: methods, applications, and research opportunities","year":2020,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":469,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Supply chain; Computer science; Predictive analytics; Demand forecasting; Supply chain management; Big data; Time series; Data science; Cluster analysis; Analytics; Support vector machine; Data mining; Machine learning; Operations research; Business; Engineering; Marketing","retraction":null,"screen_n_in":null,"score":{"opus":0.9012087118397553,"gpt":0.5583508521736629,"spread":0.3428578596660924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01959883,0.0001278355,0.0003781578,0.0003718391,0.0003635084,0.0004099064,0.004382971,0.00008413363,0.00001167673],"category_scores_gemma":[0.01322569,0.00009391445,0.0000496432,0.000928517,0.0003030689,0.0005571831,0.002605733,0.0003937353,0.000002566486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002137888,"about_ca_system_score_gemma":0.0003787256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001255163,"about_ca_topic_score_gemma":0.00001394824,"domain_scores_codex":[0.99668,0.0003475473,0.001050819,0.0005856419,0.001069129,0.0002668403],"domain_scores_gemma":[0.9908983,0.004487044,0.0008129843,0.002111883,0.001321719,0.0003680646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007591935,0.00004317691,0.0003452052,0.00002215181,0.00004262139,0.000004783934,0.0001782661,0.00001206831,0.0001490215,0.001242172,0.3175053,0.6803793],"study_design_scores_gemma":[0.0002673469,0.0002901985,0.0001235997,0.00004240382,0.00006646565,0.00007803121,0.001654397,0.1779857,0.000186269,0.03604237,0.7831591,0.000104091],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000530767,0.0009389503,0.9774029,0.01591966,0.0001128644,0.000574723,0.004150908,0.00002091165,0.0003482964],"genre_scores_gemma":[0.181841,0.001963675,0.8101884,0.0006910185,0.003824357,0.00007495681,0.000920751,0.00004944465,0.0004463969],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6802752,"threshold_uncertainty_score":0.9950863,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3081799531","doi":"10.1186/s40537-020-00333-6","title":"Short-term stock market price trend prediction using a comprehensive deep learning system","year":2020,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":370,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Carleton University","keywords":"Feature engineering; Computer science; Stock market; Stock (firearms); Artificial intelligence; Deep learning; Machine learning; Big data; Personalization; Stock market prediction; Econometrics; Data mining; Economics; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.4401202832170943,"gpt":0.4249298837676808,"spread":0.01519039944941347,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006365264,0.0002015666,0.0006193729,0.0003819555,0.0002390758,0.0003596591,0.002067556,0.0001021803,0.000108147],"category_scores_gemma":[0.009888594,0.0001526508,0.0001492446,0.001086061,0.00006667105,0.0008895806,0.0009625956,0.000651199,0.00001188748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001265111,"about_ca_system_score_gemma":0.0001247245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003070545,"about_ca_topic_score_gemma":0.000003009072,"domain_scores_codex":[0.9941157,0.001560639,0.001508989,0.0005179005,0.002004171,0.0002926757],"domain_scores_gemma":[0.9940764,0.002804996,0.001385511,0.0008156211,0.0005627522,0.0003546964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009701519,0.00005743655,0.06892932,0.0001164157,0.0002410435,0.0003975741,0.00127691,0.003475545,0.00474613,0.000007092907,0.02214641,0.897636],"study_design_scores_gemma":[0.001020032,0.0005249967,0.1422325,0.0004070127,0.000267209,0.002662706,0.003751342,0.8005726,0.00006941627,0.0000536754,0.04812706,0.0003114771],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4757818,0.0008359603,0.5160824,0.0003225169,0.003183528,0.0002608979,0.0001937635,0.00007026929,0.003268852],"genre_scores_gemma":[0.9592069,0.00002389375,0.03867051,0.00007690216,0.001885049,7.604288e-7,0.00001501357,0.00003037649,0.0000905307],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8973245,"threshold_uncertainty_score":0.9984515,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3081491601","doi":"10.1186/s40537-020-00345-2","title":"Prediction of probable backorder scenarios in the supply chain using Distributed Random Forest and Gradient Boosting Machine learning techniques","year":2020,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":160,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gradient boosting; Random forest; Computer science; Boosting (machine learning); Decision tree; Machine learning; CLARITY; Artificial intelligence; Flexibility (engineering); Metric (unit); Supply chain; Tree (set theory); Business process; Process (computing); Data mining; Work in process; Statistics; Mathematics; Operations management; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.3050417918781734,"gpt":0.3606107987158744,"spread":0.055569006837701,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004182409,0.00007924357,0.0002337981,0.0001214056,0.0001246892,0.0001111793,0.0009860735,0.0000397294,0.000005303412],"category_scores_gemma":[0.004246899,0.00004668433,0.0000374331,0.0006400753,0.0000718886,0.0002817745,0.0004132361,0.000309229,2.852347e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001794976,"about_ca_system_score_gemma":0.00005136656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004956459,"about_ca_topic_score_gemma":0.00008504075,"domain_scores_codex":[0.998268,0.0001683331,0.0007583998,0.0001826477,0.0005046913,0.0001179052],"domain_scores_gemma":[0.9982546,0.0004549752,0.0007086334,0.0003568399,0.0001779436,0.00004701908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007029925,0.0003544642,0.7688861,0.0000889256,0.00006001376,0.00004855553,0.003278608,0.007706327,0.01353649,0.0004501699,0.024157,0.1807303],"study_design_scores_gemma":[0.001596943,0.0006813547,0.01361465,0.000581023,0.00007774661,0.0004061211,0.001376282,0.9230399,0.001002193,0.005975795,0.05146945,0.0001785086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.561535,0.000655722,0.4282517,0.008192865,0.00007118162,0.0006696876,0.0005062061,0.00003812973,0.00007950405],"genre_scores_gemma":[0.9750419,0.00007963185,0.02463712,0.00007014467,0.0001107169,0.000002617494,0.00004949805,0.000005830571,0.000002542781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9153336,"threshold_uncertainty_score":0.5084242,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4210862833","doi":"10.1186/s40537-021-00468-0","title":"Big data quality framework: a holistic approach to continuous quality management","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Big data; Computer science; Data quality; Profiling (computer programming); Data science; Data mining; Quality (philosophy); Data management; Exploratory data analysis; Engineering; Operations management","retraction":null,"screen_n_in":null,"score":{"opus":0.7948772270531455,"gpt":0.5341265486844159,"spread":0.2607506783687296,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.04004332,0.0002755397,0.001019818,0.0004144787,0.000206228,0.001400647,0.01257665,0.0001231949,0.0001549446],"category_scores_gemma":[0.02683098,0.0002125618,0.000150117,0.00165884,0.0001337335,0.001328854,0.01508839,0.0005726027,0.0002915296],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007502545,"about_ca_system_score_gemma":0.0002600313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001562218,"about_ca_topic_score_gemma":0.0002152151,"domain_scores_codex":[0.988939,0.001935669,0.003011074,0.001415833,0.004177032,0.0005213502],"domain_scores_gemma":[0.9817297,0.002159789,0.00171538,0.01307151,0.0007946881,0.0005289462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001520835,0.0009380399,0.0004511293,0.0001076099,0.0002987403,0.0002294442,0.0003107419,0.00003254838,0.00002377781,0.02683655,0.3750104,0.5956089],"study_design_scores_gemma":[0.0007654497,0.00005569167,0.01954164,0.0001260307,0.0001702351,0.00006254426,0.007386626,0.0001672225,0.00001589714,0.02900648,0.9423463,0.0003558746],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00518036,0.0006649357,0.9570451,0.008075943,0.004759148,0.0003519765,0.006621786,0.00002873136,0.01727202],"genre_scores_gemma":[0.6252039,0.001131488,0.3299585,0.01897147,0.006124792,0.00001454051,0.005156794,0.00008357462,0.01335492],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6270866,"threshold_uncertainty_score":0.999636,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132987460","doi":"10.1186/s40537-014-0011-y","title":"Contextual anomaly detection framework for big sensor data","year":2015,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Anomaly detection; Context (archaeology); Toolbox; Data mining; Detector; Cluster analysis; Task (project management); False positive paradox; Anomaly (physics); Volume (thermodynamics); Big data; Process (computing); Content (measure theory); Artificial intelligence; Machine learning; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.2992592294446529,"gpt":0.3639286034466015,"spread":0.06466937400194861,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001082783,0.00009640427,0.0001777104,0.0001290356,0.0001067937,0.0001768681,0.003289838,0.00009120114,0.000001479038],"category_scores_gemma":[0.0005621223,0.00008166174,0.00004358792,0.0003139805,0.00003579898,0.0008816523,0.0009480381,0.0002255179,0.00001212696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003864148,"about_ca_system_score_gemma":0.0001797234,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002426236,"about_ca_topic_score_gemma":0.00002729499,"domain_scores_codex":[0.998812,0.00004149844,0.0004127987,0.0003102871,0.0002670496,0.0001563621],"domain_scores_gemma":[0.9966733,0.0001534176,0.0004558128,0.002237383,0.0003159121,0.0001641682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000596751,0.0001150796,0.00009564529,0.000009381334,0.00005352578,0.000009450145,0.00008604889,0.000008339404,0.001361936,0.004273592,0.03857737,0.9553499],"study_design_scores_gemma":[0.0007531003,0.000668313,0.0003780936,0.00005234512,0.00005685269,0.000568899,0.000182066,0.03737661,0.00660379,0.01977707,0.9333214,0.000261448],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001806405,0.000169413,0.9949761,0.001393204,0.001164781,0.0001470335,0.0001954597,0.000062293,0.00008528905],"genre_scores_gemma":[0.5638476,0.00005561239,0.4332547,0.0003447706,0.002340377,0.00000608235,0.00004284973,0.00001322497,0.00009473955],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9550885,"threshold_uncertainty_score":0.6113392,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391520039","doi":"10.1186/s40537-023-00842-0","title":"Survey of transformers and towards ensemble learning using transformers for natural language processing","year":2024,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Topic Modeling","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Carleton University","keywords":"Computer science; Transformer; Automatic summarization; Artificial intelligence; Language model; Question answering; Natural language processing; Classifier (UML); Natural language; Machine learning; Sentiment analysis; Natural language understanding; Ensemble forecasting","retraction":null,"screen_n_in":null,"score":{"opus":0.1431906889705772,"gpt":0.3509968199453188,"spread":0.2078061309747416,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001628014,0.00008617007,0.0002016147,0.0001574479,0.00005972106,0.0001501267,0.0004681423,0.00003961099,7.932728e-7],"category_scores_gemma":[0.0001096671,0.00006821084,0.00004615878,0.0002309484,0.00002607913,0.00111387,0.00006034916,0.0002442098,8.879871e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002533415,"about_ca_system_score_gemma":0.0003290109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001358799,"about_ca_topic_score_gemma":0.00006473976,"domain_scores_codex":[0.9989973,0.00004910258,0.00036108,0.000184373,0.0002436434,0.0001645327],"domain_scores_gemma":[0.9995009,0.0001001611,0.0001155514,0.000121017,0.0001060961,0.0000562802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001832403,0.000006620176,0.00009466807,0.000237742,0.00003132399,0.00001178416,0.001777833,0.0001539693,0.006455829,0.00001211063,0.00002173545,0.991178],"study_design_scores_gemma":[0.0003260229,0.00007820863,0.0004886768,0.0003404786,0.00003596707,0.0001487607,0.0003340053,0.9957077,0.001813676,0.00003055365,0.0005966764,0.0000992639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1449675,0.008952916,0.845322,0.0001769162,0.0004509864,0.00006001346,0.00002284529,0.00001215614,0.00003470244],"genre_scores_gemma":[0.9702448,0.0001003824,0.02949934,0.00001806013,0.0001020321,2.156669e-7,0.000009145097,0.000008755023,0.0000172565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9955537,"threshold_uncertainty_score":0.2781557,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4360827072","doi":"10.1186/s40537-023-00711-w","title":"Deep learning based deep-sea automatic image enhancement and animal species classification","year":2023,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Ichthyology and Marine Biology","field":"Environmental Science","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Centro para el Desarrollo Tecnológico Industrial; Ministerio de Ciencia, Innovación y Universidades","keywords":"Computer science; Artificial intelligence; Residual; Deep learning; Pipeline (software); Pattern recognition (psychology); Data set; Set (abstract data type); Convolutional neural network; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.06251843455730097,"gpt":0.2822145933443102,"spread":0.2196961587870092,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006591227,0.00006305272,0.0001115293,0.00005324215,0.00009356142,0.00001875992,0.0002929341,0.00004307379,0.0008172327],"category_scores_gemma":[0.000205978,0.00005025005,0.00001684627,0.0001220178,0.000146754,0.0002052316,0.0003553593,0.0001488504,0.0002960407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003775703,"about_ca_system_score_gemma":0.00001165932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001170526,"about_ca_topic_score_gemma":0.00005787033,"domain_scores_codex":[0.9992818,0.00008919636,0.0002172544,0.0001342421,0.0001352209,0.0001422661],"domain_scores_gemma":[0.9995019,0.00008148792,0.0001662827,0.00019119,0.000008741476,0.00005043689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000209897,0.0001831157,0.2632594,0.00005056012,0.00007550615,0.0001505208,0.0003893409,0.0002832701,0.4327768,0.00007454908,0.02007743,0.2824696],"study_design_scores_gemma":[0.0003561034,0.000281954,0.860217,0.000009875523,0.00003035532,0.00004394546,0.0001689931,0.1116876,0.0008751736,0.00007392238,0.02617035,0.00008479315],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9834175,0.00007005299,0.01203537,0.001756012,0.0003095865,0.00007411603,0.000006815417,0.00002429774,0.002306232],"genre_scores_gemma":[0.9968026,0.0001445447,0.002480838,0.0001017586,0.0001113767,0.000001071881,0.00007601889,0.000004843086,0.0002769271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5969576,"threshold_uncertainty_score":0.8948125,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4384821779","doi":"10.1186/s40537-023-00796-3","title":"Detecting bots in social-networks using node and structural embeddings","year":2023,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Broadcom (Canada); Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Metadata; Embedding; Class (philosophy); Node (physics); Machine learning; Social network (sociolinguistics); Feature (linguistics); Artificial intelligence; Anonymity; Focus (optics); Information retrieval; Data mining; Social media; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1361918284243414,"gpt":0.3333503352020518,"spread":0.1971585067777104,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089156,0.00006040858,0.0001220688,0.0001971883,0.0001506471,0.0002104069,0.0006125477,0.00004895274,7.424968e-7],"category_scores_gemma":[0.0001333248,0.00005426463,0.00001971035,0.000566077,0.00001534198,0.0008782762,0.0004719665,0.0002532635,7.349292e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003324679,"about_ca_system_score_gemma":0.00003183902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004383719,"about_ca_topic_score_gemma":0.00002659556,"domain_scores_codex":[0.9992413,0.00004767716,0.0002330222,0.0001428766,0.000177191,0.0001579178],"domain_scores_gemma":[0.9994296,0.00007963549,0.0002129534,0.000201717,0.00003569216,0.00004042407],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000595198,0.00001705318,0.03826426,0.00005363637,0.0000760317,0.0003909989,0.004141917,0.01376358,0.01323782,0.000183855,0.003268295,0.926543],"study_design_scores_gemma":[0.0002866891,0.00002536105,0.03898183,0.00006444661,0.00000797247,0.0002735649,0.00007862464,0.9586185,0.0001688638,0.001136853,0.0002653448,0.00009201881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9085861,0.0001299719,0.08971458,0.0002660933,0.001239617,0.00002221409,0.00000249492,0.00002388877,0.00001503732],"genre_scores_gemma":[0.9943591,0.00002320731,0.00483179,0.00005170112,0.0007245359,7.313924e-8,0.000001286993,0.000004976745,0.000003376939],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9448549,"threshold_uncertainty_score":0.2212847,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4324378562","doi":"10.1186/s40537-023-00710-x","title":"A semi-supervised short text sentiment classification method based on improved Bert model from unlabelled data","year":2023,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Bottleneck; Sentiment analysis; Artificial intelligence; Semi-supervised learning; Machine learning; Big data; Supervised learning; Language model; Function (biology); Natural language processing; Data mining; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.2707046506402733,"gpt":0.3750577178151738,"spread":0.1043530671749005,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002635949,0.0001852653,0.0003774836,0.0004093259,0.0001319078,0.0003147954,0.00482469,0.00007587069,0.00003392817],"category_scores_gemma":[0.0001644005,0.0001501176,0.0001060385,0.0008659955,0.00001703539,0.000997876,0.001582874,0.0002507654,0.00005409565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005193054,"about_ca_system_score_gemma":0.0002432363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002473267,"about_ca_topic_score_gemma":0.000008648751,"domain_scores_codex":[0.9972265,0.0001976997,0.000772727,0.0007002352,0.0008455376,0.0002572666],"domain_scores_gemma":[0.9952167,0.0003483774,0.0004032256,0.003719409,0.0001483916,0.0001639238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001912888,0.0007470266,0.001358422,0.00002488301,0.0008952962,0.00007443687,0.0005435708,0.02976087,0.08138376,0.0002326428,0.1957873,0.6890005],"study_design_scores_gemma":[0.0007380558,0.00005273505,0.0008227302,0.00006817859,0.0001190565,0.000002458113,0.00006875097,0.9925551,0.0008734606,0.0001161006,0.004421271,0.0001621265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005403598,0.0000953535,0.9890596,0.004123608,0.0006786087,0.0001209497,0.0002896982,0.00004960662,0.0001790298],"genre_scores_gemma":[0.3206645,0.0003397558,0.6700643,0.001533899,0.001050401,0.000005638697,0.005749079,0.00004904103,0.0005433843],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9627942,"threshold_uncertainty_score":0.8965554,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3155713909","doi":"10.1186/s40537-021-00455-5","title":"Domain randomization for neural network classification","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Classifier (UML); Convolutional neural network; Artificial intelligence; Artificial neural network; Task (project management); Domain (mathematical analysis); Machine learning; Pattern recognition (psychology); Randomization; Transfer of learning; Contextual image classification; Data mining; Image (mathematics); Clinical trial; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1690613487970136,"gpt":0.3181836121059016,"spread":0.149122263308888,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001171674,0.00005472811,0.0001389986,0.00004913981,0.0001032469,0.000199287,0.0007284728,0.00003116186,0.000007225144],"category_scores_gemma":[0.0003085131,0.00004779249,0.00005240319,0.0002802203,0.00001225853,0.0006895267,0.0001437147,0.0001072568,0.000003791434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001810472,"about_ca_system_score_gemma":0.0001426743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.604623e-7,"about_ca_topic_score_gemma":0.000003205485,"domain_scores_codex":[0.9990131,0.0001456506,0.0003527363,0.0001517555,0.000215898,0.0001209054],"domain_scores_gemma":[0.9986113,0.0002283573,0.0003841567,0.0004685621,0.0002446559,0.00006302131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000436625,0.0001308857,0.0007098176,0.0000301809,0.0001063954,0.00006532065,0.0006522614,0.02337131,0.003963123,0.06726897,0.08308787,0.8201773],"study_design_scores_gemma":[0.005031329,0.00006874519,0.00340159,0.00004362117,0.00002533259,0.0001998881,0.000144745,0.4987199,0.00008972841,0.006662323,0.4854831,0.0001296996],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001389245,0.0003624776,0.9932162,0.003305015,0.001334857,0.00006267464,0.00000498754,0.00001191979,0.0003126117],"genre_scores_gemma":[0.3301856,0.0001806956,0.6652441,0.001406144,0.002416423,0.000003274624,0.0001852592,0.00001472276,0.0003638123],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8200476,"threshold_uncertainty_score":0.1948921,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3022470673","doi":"10.1186/s40537-020-00302-z","title":"Leveraging machine learning and big data for optimizing medication prescriptions in complex diseases: a case study in diabetes management","year":2020,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Diabetes, Cardiovascular Risks, and Lipoproteins","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; Toronto Metropolitan University","funders":"","keywords":"Computer science; Bayesian network; Big data; Machine learning; Medical prescription; Variable (mathematics); Artificial intelligence; Bayesian probability; Data mining; Medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2050337070575335,"gpt":0.3363276992871178,"spread":0.1312939922295843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00141531,0.0001236378,0.0004713857,0.0002670499,0.00007466472,0.00006214757,0.000397398,0.00002644478,0.000006437796],"category_scores_gemma":[0.0006516185,0.0001079663,0.00005101901,0.0002397171,0.00003269713,0.0003326245,0.0006861353,0.0003053958,4.694243e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004144635,"about_ca_system_score_gemma":0.00005696666,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007418843,"about_ca_topic_score_gemma":0.0005468224,"domain_scores_codex":[0.9984334,0.0001547603,0.0005257669,0.0003440649,0.0003473512,0.0001947057],"domain_scores_gemma":[0.9987989,0.00008596526,0.0002022584,0.0006750652,0.00004597022,0.0001918448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001744823,0.0006461276,0.1363914,0.0006564864,0.0008482373,0.002770461,0.001614401,0.0002877135,0.00006160369,0.000001011189,0.001755762,0.8547923],"study_design_scores_gemma":[0.03309386,0.001805817,0.4392381,0.001776797,0.004698812,0.0009509247,0.03446658,0.3481633,0.00001663446,0.00005174518,0.1350871,0.0006502432],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9747171,0.008536033,0.01154587,0.002707196,0.0002610031,0.001617038,0.0005516615,0.00002380752,0.00004032681],"genre_scores_gemma":[0.9932399,0.0006394335,0.004418921,0.000204726,0.0005493708,0.00001453272,0.0009054556,0.00002061933,0.000007007467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.854142,"threshold_uncertainty_score":0.4402738,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1623534659","doi":"10.1186/s40537-015-0021-4","title":"Meta-MapReduce for scalable data mining","year":2015,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; Dalhousie University","funders":"","keywords":"Computer science; Scalability; Big data; AdaBoost; Machine learning; Node (physics); Programming paradigm; Cloud computing; Artificial intelligence; Data mining; Database; Programming language; Operating system; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.6436468009513665,"gpt":0.3948568341215879,"spread":0.2487899668297786,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.003717553,0.00008321714,0.0002316502,0.0001014981,0.00006249354,0.000255979,0.006078374,0.00003282447,0.000004188959],"category_scores_gemma":[0.00157337,0.00006043595,0.0000360789,0.0001960792,0.00001554142,0.002288494,0.001611671,0.0001410809,0.00001374574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001610972,"about_ca_system_score_gemma":0.000311215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001912882,"about_ca_topic_score_gemma":0.000008452446,"domain_scores_codex":[0.9987145,0.00009397454,0.0003736098,0.0003087303,0.0003594234,0.0001497298],"domain_scores_gemma":[0.9959646,0.000196579,0.0004605764,0.003005233,0.0002126818,0.0001603361],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002961203,0.00009486675,0.0003078636,0.00001900053,0.0003989414,0.0000104142,0.0001738729,0.0001030523,0.0001926153,0.0007281177,0.6457739,0.3521678],"study_design_scores_gemma":[0.0004929327,0.0001081492,0.0002124729,0.00001675188,0.0003094492,0.0001248153,0.00005063772,0.2155005,0.00007421103,0.0004606536,0.7825497,0.00009965597],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006409503,0.001396228,0.9891389,0.006779524,0.001139074,0.00006552815,0.0003387498,0.00002414708,0.000476882],"genre_scores_gemma":[0.09742723,0.00006890715,0.8990729,0.000378071,0.001384835,0.000002344654,0.001099309,0.00001506415,0.0005513693],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3520681,"threshold_uncertainty_score":0.9992992,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4302614395","doi":"10.1186/s40537-022-00608-0","title":"Adaptive multiple imputations of missing values using the class center","year":2022,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Thailand Research Fund; Natural Sciences and Engineering Research Council of Canada; Khon Kaen University","keywords":"Imputation (statistics); Missing data; Categorical variable; Computer science; Data mining; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1952227141855969,"gpt":0.3341741212312561,"spread":0.1389514070456592,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006495694,0.00004827424,0.00009989909,0.00007130521,0.0003132233,0.00007495211,0.002000107,0.000008574424,0.00000441755],"category_scores_gemma":[0.00007388121,0.00003463023,0.00003658468,0.0002962624,0.00004032668,0.0004606111,0.001236484,0.0001708593,5.629498e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003008649,"about_ca_system_score_gemma":0.0001545689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003449182,"about_ca_topic_score_gemma":0.000002411026,"domain_scores_codex":[0.9991197,0.00008649743,0.0002866445,0.0001209764,0.000295083,0.00009112215],"domain_scores_gemma":[0.9985976,0.0001814831,0.0004101214,0.0006779286,0.00009638965,0.00003646843],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000211902,0.0005139844,0.0007461506,0.000009719886,0.0001754748,0.0000376978,0.003225953,0.008379313,0.003243145,0.002181965,0.03057981,0.9508856],"study_design_scores_gemma":[0.0002638492,0.00006508599,0.0005914862,0.00002147033,0.00002230816,0.0002867542,0.0007602313,0.9752642,0.0001585321,0.001179961,0.0213286,0.00005755514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00732005,0.0001656757,0.9898129,0.001646024,0.0003987005,0.00005027437,0.0005435426,0.000006031073,0.00005686392],"genre_scores_gemma":[0.6129434,0.00001079455,0.3866013,0.0001766121,0.0002067699,0.000001340281,0.000038741,0.00000629078,0.00001480182],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9668849,"threshold_uncertainty_score":0.3716729,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2947950257","doi":"10.1186/s40537-019-0203-6","title":"Detecting taxi movements using Random Swap clustering and sequential pattern mining","year":2019,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Carleton University","keywords":"Cluster analysis; Computer science; Swap (finance); Silhouette; Data mining; Hierarchical clustering; k-means clustering; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1150805794770239,"gpt":0.2957330234356438,"spread":0.18065244395862,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001019602,0.00009883478,0.000188282,0.0001521651,0.00007818326,0.0004809629,0.001403267,0.00002297217,0.000007898645],"category_scores_gemma":[0.00004246044,0.00008581024,0.00002931659,0.000129152,0.00001168222,0.002239271,0.002485688,0.0001255884,0.000004875713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002101916,"about_ca_system_score_gemma":0.00002639058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003367235,"about_ca_topic_score_gemma":0.000008340235,"domain_scores_codex":[0.9988453,0.00004720776,0.0003538459,0.000238745,0.0003222753,0.0001926704],"domain_scores_gemma":[0.9988481,0.00004857783,0.0003928476,0.0006069253,0.00003873906,0.00006482734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002318964,0.00002419042,0.00566935,0.00005767358,0.0001138571,0.0001203354,0.0002571719,0.0002782364,0.006227304,0.000004479556,0.0002517714,0.9869725],"study_design_scores_gemma":[0.003167201,0.00009657031,0.00099652,0.0002949945,0.00003715287,0.0001578616,0.0001817488,0.989181,0.0004930212,0.00006328124,0.005118159,0.0002125132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2708989,0.0000849652,0.7273504,0.00007053907,0.001439163,0.00006114107,0.00001407283,0.000008945814,0.000071899],"genre_scores_gemma":[0.9274811,0.00006223134,0.07140731,0.0002577421,0.0006802068,2.433329e-7,0.00001256919,0.00001294829,0.00008570193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9889027,"threshold_uncertainty_score":0.4637936,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3181834696","doi":"10.1186/s40537-021-00489-9","title":"Examining the impact of cross-domain learning on crime prediction","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Crime Patterns and Interventions","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Memorial University of Newfoundland; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland; Dalhousie University","keywords":"Computer science; Generalization; Perspective (graphical); Domain (mathematical analysis); Transfer of learning; Data science; Domain knowledge; Task (project management); Machine learning; Baseline (sea); Crime analysis; Demographics; Artificial intelligence; Subject-matter expert; Data mining; Expert system","retraction":null,"screen_n_in":null,"score":{"opus":0.34207003076943,"gpt":0.4718022365358112,"spread":0.1297322057663812,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001654054,0.00004085381,0.0001001224,0.0000462985,0.0002454574,0.0001192092,0.0003732542,0.00003021223,0.0006675819],"category_scores_gemma":[0.0008896161,0.00002645536,0.0001096939,0.000138107,0.00009262469,0.0003047726,0.0001037437,0.0002273115,0.000005514125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005132078,"about_ca_system_score_gemma":0.0001858153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004971015,"about_ca_topic_score_gemma":0.00009236884,"domain_scores_codex":[0.9989937,0.0002510396,0.0002833169,0.00007678652,0.0002927743,0.0001023733],"domain_scores_gemma":[0.9990803,0.0001418248,0.0003039333,0.0002343382,0.0001937507,0.00004588187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001585393,0.0007740671,0.7584571,0.00003448391,0.0006123444,0.0001069901,0.01840889,0.001238589,0.01630148,0.001251073,0.08493681,0.1177196],"study_design_scores_gemma":[0.0004952573,0.0006789095,0.9398753,0.0003637566,0.00005270277,0.00004677548,0.01187967,0.000166187,0.0005898556,0.000472606,0.04530273,0.00007624715],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9875492,0.0002296683,0.0009099895,0.0002804456,0.0005352041,0.0000258475,0.00008560921,0.000003960343,0.01038009],"genre_scores_gemma":[0.9985142,0.0001010577,0.00005706086,0.00001491553,0.0006879074,1.683499e-7,0.00001508208,0.000003858496,0.0006057372],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1814182,"threshold_uncertainty_score":0.7309554,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2772611570","doi":"10.1186/s40537-017-0106-3","title":"A computing platform for pairs-trading online implementation via a blended Kalman-HMM filtering approach","year":2017,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; TD Bank Group","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Trading strategy; Kalman filter; Hidden Markov model; Pairs trade; Algorithmic trading; Analytics; High-frequency trading; Big data; Herding; Algorithm; Machine learning; Data mining; Artificial intelligence; Econometrics; Finance; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.270147184667116,"gpt":0.3335862340197416,"spread":0.06343904935262562,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001162059,0.0001170589,0.0004854884,0.0002080451,0.0004000454,0.000293437,0.0009197896,0.00003931411,0.00007701941],"category_scores_gemma":[0.00009964001,0.0001185698,0.0001623641,0.00006654785,0.00002131602,0.0007693277,0.000311414,0.0001166544,0.000004141941],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006436256,"about_ca_system_score_gemma":0.00002573595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004473205,"about_ca_topic_score_gemma":0.0002134659,"domain_scores_codex":[0.9984651,0.000005865154,0.001006367,0.0002448252,0.00005774358,0.000220141],"domain_scores_gemma":[0.9969751,0.00004177636,0.00208835,0.0007648104,0.00005861997,0.00007138841],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002860044,0.0006584238,0.06205266,0.0008117637,0.002993648,0.00003829732,0.002074473,0.000583233,0.0006777697,0.02152797,0.02003915,0.8882566],"study_design_scores_gemma":[0.003639326,0.0003379531,0.03146231,0.0001393957,0.0001500346,0.0001812486,0.001704796,0.7893321,0.00006195786,0.007866446,0.1645779,0.00054657],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1812582,0.001213818,0.8108064,0.0005690284,0.001360902,0.0003647085,0.00226424,0.000015933,0.002146761],"genre_scores_gemma":[0.9703258,0.00005010016,0.02811954,0.00003139781,0.001094366,0.000001378933,0.0002822826,0.0000180658,0.00007711853],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.88771,"threshold_uncertainty_score":0.4835137,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2952066860","doi":"10.1186/s40537-019-0218-z","title":"STVG: an evolutionary graph framework for analyzing fast-evolving networks","year":2019,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Tertiary Education Trust Fund; Cisco Systems","keywords":"Computer science; Theoretical computer science; Graph; Snapshot (computer storage); Graph database; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.0752406044275541,"gpt":0.3422732496091298,"spread":0.2670326451815757,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001044688,0.00005729358,0.0001316651,0.0001194517,0.0002466196,0.00008437791,0.0004791001,0.00009844081,0.00005838626],"category_scores_gemma":[0.0002483598,0.00005382911,0.0000513989,0.0002814386,0.00003614561,0.000967246,0.00001426456,0.0001822378,0.00000225292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002728997,"about_ca_system_score_gemma":0.0001516346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004715978,"about_ca_topic_score_gemma":0.0001294484,"domain_scores_codex":[0.9990853,0.00007525431,0.0002802718,0.000128272,0.0002670171,0.0001638889],"domain_scores_gemma":[0.9988739,0.0002285126,0.0003278056,0.0002317062,0.0002368114,0.0001012433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003149103,0.0002561891,0.4936802,0.00005033824,0.0002532807,0.0000175924,0.01155723,0.3686295,0.00004531489,0.02418209,0.02679307,0.07422026],"study_design_scores_gemma":[0.003134343,0.001001168,0.4360406,0.001629065,0.0006579864,0.00002781811,0.02316801,0.2913387,0.000009872745,0.03593634,0.2058002,0.001255931],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02460136,0.0009017043,0.9714366,0.0006795396,0.001823222,0.0001312085,0.00008274918,0.00002350547,0.0003200734],"genre_scores_gemma":[0.9175208,0.0002449384,0.08044328,0.00008616572,0.001327732,6.526311e-7,0.0002533085,0.000009633359,0.0001135316],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8929194,"threshold_uncertainty_score":0.2195087,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4415383695","doi":"10.1186/s40537-025-01280-w","title":"Digital twins in healthcare: a review of AI-powered practical applications across health domains","year":2025,"lang":"en","type":"review","venue":"Journal Of Big Data","topic":"Digital Transformation in Industry","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Health care; Digital health; Mental healthcare; Selection (genetic algorithm); Mental health; Virtual patient","retraction":null,"screen_n_in":null,"score":{"opus":0.1670042130554316,"gpt":0.4465265295323191,"spread":0.2795223164768875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001165321,0.0002984106,0.001995599,0.0002869175,0.00003054979,0.0001069434,0.001126017,0.0002509647,0.000007436335],"category_scores_gemma":[0.0004092062,0.000259711,0.0002788204,0.001080105,0.00005472633,0.001145949,0.0001924138,0.001576012,0.00001696312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003571859,"about_ca_system_score_gemma":0.002266892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005108566,"about_ca_topic_score_gemma":0.00001224792,"domain_scores_codex":[0.9959701,0.00009211269,0.00293118,0.0002034477,0.0004701386,0.0003330755],"domain_scores_gemma":[0.9972119,0.0003716654,0.0009487252,0.001097256,0.0001573791,0.0002130267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001515859,0.00006691862,0.000002178773,0.2110796,0.00008691513,0.000008302125,0.00001015517,0.000002078894,4.247762e-9,0.0002140997,0.01666186,0.7718664],"study_design_scores_gemma":[0.0001405826,0.0000299688,0.000001376207,0.1665194,0.00007212967,0.0002821286,0.00001473505,0.000003529388,5.600383e-8,0.00004817099,0.8327554,0.0001325861],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.974381e-8,0.9780898,0.007918846,0.002125214,0.0004625403,0.0008401735,0.007894289,0.00002460067,0.002644492],"genre_scores_gemma":[0.000009510645,0.9977496,0.000498738,0.0002546964,0.0002215687,0.00003324401,0.001163202,0.00003553644,0.00003396184],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8160935,"threshold_uncertainty_score":0.9999855,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390759017","doi":"10.1186/s40537-023-00866-6","title":"RPf-GCNs: reciprocal perspective driven fused GCNs for rumor detection on social media","year":2024,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Reciprocal; Computer science; Rumor; Perspective (graphical); Graph; Social media; Convolutional neural network; Profiling (computer programming); Artificial intelligence; Machine learning; Data science; World Wide Web; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.29748346181366,"gpt":0.4248955531956444,"spread":0.1274120913819843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001276544,0.00007629584,0.0001458237,0.0001956316,0.0003398758,0.0002510063,0.0004114009,0.00009218039,0.00009422374],"category_scores_gemma":[0.002131863,0.00006109343,0.00008999366,0.0002642381,0.000083853,0.0009213607,0.00004211767,0.0002428766,0.00004498331],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003042135,"about_ca_system_score_gemma":0.000514932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005482658,"about_ca_topic_score_gemma":0.0009629489,"domain_scores_codex":[0.9987834,0.00008119752,0.0002914616,0.0001146936,0.0005347622,0.0001944892],"domain_scores_gemma":[0.9990091,0.0003133783,0.0001881857,0.0001296302,0.0002242144,0.0001354737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004686886,0.0001337985,0.000009741714,0.0000470354,0.0001881019,0.00002289916,0.2102291,0.000007020857,0.0007782124,0.02175819,0.1853675,0.5809897],"study_design_scores_gemma":[0.001580284,0.0005291864,0.001723162,0.0002794467,0.0001648515,0.00003625049,0.1953698,0.002056612,0.001007333,0.009005213,0.7879035,0.0003443192],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.63806,0.001847005,0.04800692,0.1183993,0.05221674,0.002552775,0.003819578,0.0005808007,0.1345169],"genre_scores_gemma":[0.9938844,0.0001733126,0.0002276666,0.0002495134,0.005210879,8.189626e-7,0.00002121182,0.00001014989,0.0002220006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.602536,"threshold_uncertainty_score":0.2614084,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4393112045","doi":"10.1186/s40537-024-00898-6","title":"Multi-sample $$\\zeta $$-mixup: richer, more realistic synthetic samples from a p-series interpolant","year":2024,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Compute Canada; Simon Fraser University; Nvidia","keywords":"Algorithm; Computer science; Machine learning; Artificial intelligence; Series (stratigraphy)","retraction":null,"screen_n_in":null,"score":{"opus":0.1817104695287353,"gpt":0.3345108908799068,"spread":0.1528004213511714,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007541192,0.0001554689,0.0002670012,0.0002112887,0.00009160002,0.0006868809,0.002110638,0.00005384419,0.00005697152],"category_scores_gemma":[0.001193753,0.000120523,0.00008641571,0.0003175712,0.00007606616,0.001137393,0.0006904796,0.0003766805,0.00005045704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004790119,"about_ca_system_score_gemma":0.0001962938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003848189,"about_ca_topic_score_gemma":0.0001163229,"domain_scores_codex":[0.9983478,0.0001342194,0.0005253986,0.0003575933,0.000415452,0.0002195822],"domain_scores_gemma":[0.9977788,0.0007614201,0.0002451088,0.0009665096,0.00009366071,0.0001545019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002011997,0.0004666362,0.001418642,0.0002447147,0.000961406,0.002646601,0.01675872,0.0005487728,0.009023111,0.02764556,0.05536313,0.8847215],"study_design_scores_gemma":[0.0006876604,0.0001955299,0.006126833,0.0009468712,0.0001298347,0.0007458985,0.001219316,0.4748622,0.0001680978,0.00501341,0.5094625,0.0004417592],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001912013,0.003248543,0.9898955,0.00223624,0.002016361,0.000052863,0.0004610408,0.00008114592,0.00009633015],"genre_scores_gemma":[0.5859845,0.0007112929,0.4114087,0.000505156,0.0008444877,0.000002100525,0.0001999347,0.0000344332,0.0003094186],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8842797,"threshold_uncertainty_score":0.6623608,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4200412035","doi":"10.1186/s40537-021-00547-2","title":"Dynamic order Markov model for categorical sequence clustering","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Hidden Markov model; Cluster analysis; Pattern recognition (psychology); Markov chain; Markov model; Sequence (biology); Categorical variable; Suffix tree; Data mining; Artificial intelligence; Algorithm; Data structure; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1343751196579093,"gpt":0.3358048966184071,"spread":0.2014297769604978,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004107699,0.00008467925,0.0001700866,0.00005498738,0.00008458018,0.0001744508,0.001914084,0.00004279893,0.000003834075],"category_scores_gemma":[0.0001640897,0.0000668822,0.00004084378,0.0002052561,0.00001499083,0.001134425,0.001681459,0.0001623099,0.000002501674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004265122,"about_ca_system_score_gemma":0.0003947739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005230826,"about_ca_topic_score_gemma":0.0000158753,"domain_scores_codex":[0.9989398,0.00002923724,0.0003196306,0.0002550377,0.0002795002,0.0001768545],"domain_scores_gemma":[0.9983215,0.00007659817,0.0001935053,0.001014515,0.0002919176,0.0001019928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004458869,0.0001681841,0.00003447989,0.00006609669,0.00005835019,0.0004749766,0.0001898733,0.01045334,0.006274268,0.0008829067,0.02727417,0.9540788],"study_design_scores_gemma":[0.0003053111,0.00002964313,0.00003534748,0.0000340367,0.000009977809,0.0005245124,0.0000096958,0.9903805,0.00007298675,0.001828299,0.006682993,0.00008674018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004565541,0.0003755108,0.9969351,0.001210313,0.0008296912,0.00003603932,0.0001082009,0.00001055797,0.00003807827],"genre_scores_gemma":[0.06092351,0.0002183138,0.9380301,0.0002955986,0.0002009466,0.000001041323,0.00009264482,0.000008896141,0.0002289825],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9799271,"threshold_uncertainty_score":0.3556877,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4311824268","doi":"10.1186/s40537-022-00667-3","title":"Chromatin state distribution of residue-specific histone acetylation in early myoblast differentiation","year":2022,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Southeast University","keywords":"Epigenetics; Chromatin; Histone; Histone acetyltransferase; Acetylation; Computational biology; Biology; Regulation of gene expression; Histone Acetyltransferases; Histone methyltransferase; Cell biology; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02572657874015361,"gpt":0.2479546704509838,"spread":0.2222280917108302,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004262767,0.00006893593,0.0001333466,0.00006191557,0.00004837739,0.00001291923,0.0003564229,0.00003353108,0.00001098837],"category_scores_gemma":[0.00004671273,0.00007078018,0.00003786014,0.0001047085,0.00002235347,0.00001016718,0.0003046085,0.0001220807,5.06009e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007608011,"about_ca_system_score_gemma":0.00007329936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000227947,"about_ca_topic_score_gemma":0.00005810354,"domain_scores_codex":[0.9990368,0.00008180231,0.0004535374,0.0001302968,0.0002025785,0.00009498986],"domain_scores_gemma":[0.9989723,0.000008621178,0.0005463674,0.0003556564,0.00008899697,0.00002804343],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003265781,0.0002675653,0.009220301,0.00003205394,0.00005429571,0.000007403998,0.0002177101,0.002618187,0.9700097,0.00004494507,0.006119636,0.01108159],"study_design_scores_gemma":[0.003228193,0.001454701,0.8991333,0.00006685461,0.00004984015,0.00009831179,0.0003788691,0.005184841,0.06513254,0.0006808653,0.02423399,0.0003576695],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993067,0.0004384733,0.005345832,0.00009233099,0.000253742,0.00006228621,0.0007240633,0.000001058512,0.00001520582],"genre_scores_gemma":[0.9968446,0.0002819867,0.0002722869,0.000009376086,0.0001104657,0.000001304951,0.002431931,0.000008818521,0.00003920299],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9048772,"threshold_uncertainty_score":0.2886332,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3162192441","doi":"10.1186/s40537-021-00539-2","title":"Integration of image segmentation and fuzzy theory to improve the accuracy of damage detection areas in traffic accidents","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Machine vision; Computer science; Process (computing); Field (mathematics); Artificial intelligence; Fuzzy logic; Segmentation; Image processing; Computer vision; Machine learning; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.04525610434908552,"gpt":0.2922994329218837,"spread":0.2470433285727981,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009911434,0.00006266293,0.0001574118,0.0001540373,0.00002854142,0.00003049396,0.0001272222,0.00005250784,0.000005073234],"category_scores_gemma":[0.0006186928,0.00004512071,0.00002982068,0.0002658372,0.00001058349,0.000420434,0.00006348621,0.0001644646,6.742392e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000380751,"about_ca_system_score_gemma":0.00002849735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002650278,"about_ca_topic_score_gemma":0.0001631833,"domain_scores_codex":[0.9991015,0.0001172419,0.0004744474,0.00007552371,0.0001719561,0.00005930476],"domain_scores_gemma":[0.9992156,0.0001555232,0.0002339337,0.0002363507,0.0001315091,0.00002706752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007822338,0.00001470947,0.00005062085,0.00002794414,0.00002169131,0.000003792306,0.0005151375,0.0009081808,0.669711,0.00000327677,0.0000778398,0.3285876],"study_design_scores_gemma":[0.001527551,0.0002828808,0.02514539,0.0004508423,0.00007751134,0.0001132774,0.00516154,0.008226726,0.958326,0.0001925241,0.0003673934,0.0001283005],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981187,0.000137748,0.01769603,0.00002169001,0.0007562448,0.0001218597,0.0000310109,0.000004435761,0.00004396237],"genre_scores_gemma":[0.9994913,0.00007237541,0.0002422145,0.000006202587,0.0001636951,0.000001318301,0.000008941298,0.000007288646,0.000006611715],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3284593,"threshold_uncertainty_score":0.1839969,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4416285692","doi":"10.1186/s40537-025-01307-2","title":"UniqueNOSD: a novel framework for NoSQL over SQL databases","year":2025,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"NoSQL; SQL; Scalability; Relational database; Relational database management system; Redundancy (engineering); Consistency (knowledge bases); View; Query by Example","retraction":null,"screen_n_in":null,"score":{"opus":0.1547059754666002,"gpt":0.3786632370180599,"spread":0.2239572615514597,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006963774,0.0001337708,0.0002938411,0.0001830692,0.0001165232,0.00008371654,0.001814886,0.00004710576,0.000007422972],"category_scores_gemma":[0.001028009,0.0001048455,0.00006722007,0.0003815147,0.00004496414,0.001902918,0.001227191,0.0002250001,0.000003044609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003390594,"about_ca_system_score_gemma":0.0003402447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003530489,"about_ca_topic_score_gemma":0.00003110088,"domain_scores_codex":[0.9986674,0.00003047787,0.0005179127,0.0003009611,0.0002638642,0.0002193423],"domain_scores_gemma":[0.9969479,0.0005208136,0.000414134,0.001834755,0.0001951821,0.00008717781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005060309,0.0001185189,0.0002464501,0.00009036137,0.00008477334,0.0000251909,0.00005308287,0.00002209893,0.001069335,0.8945347,0.06727058,0.03643427],"study_design_scores_gemma":[0.0005712867,0.00006919015,0.0003726598,0.0006070426,0.0000271549,0.00006611161,0.00004233074,0.00268141,0.0009837,0.007085732,0.9873493,0.0001440683],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002554925,0.0008840111,0.9935324,0.001398063,0.00211456,0.0001323162,0.001517835,0.0000231434,0.000142214],"genre_scores_gemma":[0.005077938,0.0001424388,0.9926579,0.001139213,0.0006426268,0.000004029383,0.0001156973,0.000009574002,0.0002105617],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9200788,"threshold_uncertainty_score":0.4275474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3169194364","doi":"10.1186/s40537-021-00504-z","title":"The LRA Workbench: an IDE for efficient REST API composition through linked metadata","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Athabasca University; University of Alberta","funders":"","keywords":"Computer science; Workbench; Algorithm; Metadata; Database; Data mining; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1187062142502125,"gpt":0.3237130792915089,"spread":0.2050068650412964,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00100118,0.0001345223,0.0002183939,0.00005771982,0.0003953167,0.0007240642,0.003942464,0.00005070898,0.000002385921],"category_scores_gemma":[0.00005273908,0.00008594119,0.00008489186,0.0004811646,0.00003320583,0.001382364,0.001091691,0.0002655578,0.000003819845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002067828,"about_ca_system_score_gemma":0.0002123303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002865861,"about_ca_topic_score_gemma":0.0002598479,"domain_scores_codex":[0.9982012,0.0001856122,0.0005025847,0.0003505888,0.0004947088,0.0002652928],"domain_scores_gemma":[0.9965515,0.0004839031,0.0004175555,0.002063181,0.0003700505,0.0001138525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001070541,0.002953566,0.0003788298,0.0004023934,0.00169572,0.001010168,0.0152856,0.01290765,0.07668114,0.160188,0.03481932,0.6926071],"study_design_scores_gemma":[0.003412014,0.0008679042,0.004275101,0.0006277585,0.0004052017,0.001523868,0.002116389,0.1370725,0.01985619,0.02425763,0.8048335,0.0007519784],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03833552,0.003631883,0.9410405,0.01365608,0.002710819,0.0001871252,0.0001664755,0.00003342073,0.000238241],"genre_scores_gemma":[0.6893101,0.0008349589,0.2960921,0.008859466,0.00390126,0.000008131931,0.0008703573,0.00004023969,0.00008349084],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7700142,"threshold_uncertainty_score":0.7326144,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4410234140","doi":"10.1186/s40537-025-01141-6","title":"FunDa: scalable serverless data analytics and in situ query processing","year":2025,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; New Brunswick Innovation Foundation","keywords":"Computer science; Scalability; Analytics; Database; SQL; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.1064535844711244,"gpt":0.3074975679074904,"spread":0.201043983436366,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001539928,0.00008627311,0.0002052884,0.0002675851,0.0000841517,0.0003705563,0.003526324,0.00003381938,4.768441e-7],"category_scores_gemma":[0.0001075688,0.0000699689,0.00001469776,0.0006559904,0.00003251858,0.0002415906,0.00533659,0.0002247025,0.000001027072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003314971,"about_ca_system_score_gemma":0.0001803112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003321762,"about_ca_topic_score_gemma":0.0001287605,"domain_scores_codex":[0.998815,0.00005680575,0.0003917495,0.0003102638,0.0002538919,0.000172303],"domain_scores_gemma":[0.9981832,0.00007261376,0.0002197771,0.00140373,0.00006532273,0.00005537532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002210856,0.00019488,0.01069926,0.0002736864,0.00008015262,0.0002161311,0.0001956732,0.002634108,0.0001287681,0.0003390359,0.02150936,0.9637069],"study_design_scores_gemma":[0.0007820956,0.00003441746,0.02426467,0.0009192125,0.00005142618,0.00007330112,0.000179226,0.9060994,0.00004004388,0.0007659592,0.0666237,0.000166526],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4203678,0.00780425,0.554845,0.01184405,0.001501594,0.0001622886,0.00003184899,0.00005428032,0.003388959],"genre_scores_gemma":[0.9872948,0.00008603506,0.0116935,0.0003651545,0.0001819543,1.130081e-7,0.000008828777,0.000004190912,0.0003654168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9635403,"threshold_uncertainty_score":0.6651678,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3124386847","doi":"10.1186/s40537-021-00418-w","title":"CaReAl: capturing read alignments in a BAM file rapidly and conveniently","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"National Institute of Food and Drug Safety Evaluation; Ministry of Food and Drug Safety","keywords":"Computer science; Snapshot (computer storage); Visualization; Multithreading; Data mining; Database; Operating system; Thread (computing)","retraction":null,"screen_n_in":null,"score":{"opus":0.05366287355894767,"gpt":0.2675212990260544,"spread":0.2138584254671067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001594729,0.00006744526,0.0001318906,0.00002649234,0.00002280441,0.00001730265,0.0001776734,0.00004249906,0.00001891009],"category_scores_gemma":[0.0001052587,0.00006108594,0.00002489198,0.00003626271,0.00002526434,0.000001398799,0.0003785183,0.00005762564,6.139813e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006799028,"about_ca_system_score_gemma":0.000081822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002880869,"about_ca_topic_score_gemma":0.0001313937,"domain_scores_codex":[0.9994155,0.00003210154,0.0002081196,0.0001572419,0.0000792935,0.0001077482],"domain_scores_gemma":[0.9994773,0.00001368421,0.0001066048,0.0002900083,0.00006221776,0.00005013992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000130929,0.0001600573,0.0375852,0.00005552156,0.0003853428,0.0003221824,0.0004619758,0.00003493467,0.8627143,0.000009643411,0.0518727,0.04626724],"study_design_scores_gemma":[0.003130251,0.0004431403,0.1427369,0.0001789597,0.0001024736,0.0008427097,0.001626382,0.00005324177,0.09826853,0.0002199781,0.7519963,0.0004011081],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9886786,0.00966638,0.00003764766,0.0001910496,0.0002810096,0.00003318327,0.0007031975,2.892312e-7,0.0004086625],"genre_scores_gemma":[0.9955238,0.002992275,0.0007251432,0.0001469189,0.0002573952,8.115396e-7,0.0002142604,0.000007394997,0.0001319913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7644457,"threshold_uncertainty_score":0.2491012,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409069510","doi":"10.1186/s40537-025-01122-9","title":"SPINEX-anomaly: similarity-based predictions with explainable neighbors exploration for anomaly and outlier detection","year":2025,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Clemson University","keywords":"Anomaly detection; Anomaly (physics); Outlier; Computer science; Similarity (geometry); Data mining; Computational Science and Engineering; Artificial intelligence; Pattern recognition (psychology); Machine learning; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.06406157203631375,"gpt":0.2900970408861074,"spread":0.2260354688497937,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004312897,0.0001084596,0.0001618379,0.0003163216,0.0003125457,0.0001976887,0.0006045735,0.00006681051,0.000001592422],"category_scores_gemma":[0.00006548352,0.00009010408,0.00004155068,0.000543386,0.00004260776,0.00133054,0.0001421281,0.0001464903,5.332716e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005200487,"about_ca_system_score_gemma":0.0001887999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002126088,"about_ca_topic_score_gemma":0.0000594053,"domain_scores_codex":[0.9990622,0.00003051994,0.0003448442,0.0002701671,0.0001556646,0.0001366057],"domain_scores_gemma":[0.9986086,0.00007354277,0.0002952071,0.0006711386,0.0002826588,0.00006884602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009473196,0.00147394,0.006855431,0.0004787468,0.0006145846,0.00003580056,0.000506711,0.004924221,0.0201544,0.05630731,0.04150248,0.8661991],"study_design_scores_gemma":[0.003261829,0.002584611,0.008819968,0.0002623007,0.0003318261,0.0001540719,0.0003307115,0.5778081,0.05174675,0.02000281,0.3341492,0.0005478757],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004415309,0.00008387558,0.9918205,0.002892514,0.0002070479,0.0002930763,0.0000384106,0.00007294071,0.0001763305],"genre_scores_gemma":[0.8552772,0.00004076646,0.1439798,0.0003004461,0.0001672411,0.00005804913,0.00001922596,0.000008680406,0.0001485226],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8656512,"threshold_uncertainty_score":0.3674338,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2806417635","doi":"10.1186/s40537-018-0128-5","title":"A non-parametric maximum for number of selected features: objective optima for FDR and significance threshold with application to ordinal survey analysis","year":2018,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Capilano University; Simon Fraser University","funders":"","keywords":"False discovery rate; Statistical hypothesis testing; Mathematics; False positives and false negatives; Statistics; Multiple comparisons problem; Parametric statistics; Ordinal data; False positive paradox; Computer science; Nonparametric statistics; Set (abstract data type); Data mining; Artificial intelligence; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.1602111434238936,"gpt":0.446176169199242,"spread":0.2859650257753483,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001293777,0.0001217852,0.0005145443,0.0001974823,0.00006273317,0.00002515388,0.0003041308,0.000054943,0.000003247316],"category_scores_gemma":[0.002671272,0.00008662682,0.00004596146,0.001196316,0.00006837662,0.0001342771,0.00006238055,0.0001012836,2.816706e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003106191,"about_ca_system_score_gemma":0.00009884604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003569887,"about_ca_topic_score_gemma":0.0002474695,"domain_scores_codex":[0.9988946,0.0000460856,0.0004047393,0.0002665484,0.0002158001,0.0001722586],"domain_scores_gemma":[0.995625,0.001900081,0.0005241724,0.0004257991,0.001413987,0.0001109518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.07754666,0.005506692,0.08509144,0.003740457,0.02372628,0.00003314076,0.003676146,0.004047901,0.02982047,0.0483909,0.0778136,0.6406063],"study_design_scores_gemma":[0.01045505,0.01037036,0.1280876,0.0005046689,0.009742493,0.0002101751,0.0006484392,0.1894241,0.01517014,0.631594,0.002210553,0.001582367],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02976881,0.00002140995,0.9679906,0.00003776098,0.00003280671,0.0005629644,0.001546714,0.000003600187,0.00003536273],"genre_scores_gemma":[0.3501691,0.000006719081,0.6496083,0.0000174213,0.00009274998,0.00001941403,0.0000441093,0.00001280506,0.00002947995],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.639024,"threshold_uncertainty_score":0.3532539,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}