{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1222,"total_is_capped":false,"direct_labels_cover":16,"predictions_cover":1222,"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":"6a52b7c41d45","filters":{"topic":"Statistical Methods and Bayesian Inference"}},"results":[{"id":"W2112669742","doi":"10.1093/aje/kwh090","title":"A Modified Poisson Regression Approach to Prospective Studies with Binary Data","year":2004,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":9468,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Robarts Clinical Trials","funders":"","keywords":"Poisson regression; Statistics; Poisson distribution; Mathematics; Regression analysis; Binary data; Regression; Variance (accounting); Linear regression; Binary number; Econometrics; Medicine; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.2762250419605384,"gpt":0.4846306984267521,"spread":0.2084056564662137,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003397528,0.0001895984,0.001263315,0.0001305655,0.00007105953,0.000005070047,0.000501465,0.0000420323,0.000004168719],"category_scores_gemma":[0.02508166,0.0001026688,0.00005372099,0.0003347114,0.0005844352,0.0001037203,0.0001785794,0.0003596336,0.000002574355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001111602,"about_ca_system_score_gemma":0.0001198996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005173358,"about_ca_topic_score_gemma":0.00000393049,"domain_scores_codex":[0.9974795,0.0009249825,0.0007525263,0.0003436656,0.0001600495,0.000339261],"domain_scores_gemma":[0.9920251,0.005962345,0.0009774392,0.0005419645,0.0002809013,0.0002122255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001621371,0.0006027612,0.007160989,0.00009262705,0.0006411837,0.0001344995,0.002365283,0.0004908515,0.0001634011,0.9104509,0.004279952,0.07199612],"study_design_scores_gemma":[0.0006973088,0.004138838,0.006323478,0.0003916386,0.0001275058,0.0005060117,0.002171206,0.0002500153,0.00003319407,0.9850485,0.0001130732,0.0001992096],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04639384,0.0002996455,0.9495149,0.002951707,0.00008304986,0.0001775623,0.00001628456,0.00001496733,0.0005481019],"genre_scores_gemma":[0.2334933,0.00008237365,0.765772,0.0005117934,0.0001092839,0.000007112059,0.000001473536,0.00001409172,0.00000857639],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1870995,"threshold_uncertainty_score":0.9831305,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2577537660","doi":"10.18637/jss.v076.i01","title":"<i>Stan</i> : A Probabilistic Programming Language","year":2017,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7378,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"National Center for Research Resources; Institute of Education Sciences; U.S. Department of Energy; National Science Foundation; National Institutes of Health; Harvard University","keywords":"Python (programming language); Computer science; Markov chain Monte Carlo; Algorithm; Hybrid Monte Carlo; Monte Carlo method; Probabilistic logic; Bayesian inference; Importance sampling; Statistical inference; Inference; Monte Carlo integration; Applied mathematics; Bayesian probability; Mathematical optimization; Mathematics; Programming language; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05011962462799613,"gpt":0.3917699605443133,"spread":0.3416503359163172,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009102275,0.0001796903,0.0005167201,0.00005041066,0.0003021774,0.0002846674,0.0005245472,0.00008582782,0.0003789667],"category_scores_gemma":[0.04616964,0.0001300549,0.0001060301,0.00004811689,0.0003206751,0.0001867744,0.0001020683,0.0004133105,0.00001356263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000619938,"about_ca_system_score_gemma":0.0001206942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001502556,"about_ca_topic_score_gemma":0.00000945792,"domain_scores_codex":[0.9981489,0.0001209969,0.0006905821,0.0001780416,0.0005147245,0.0003467572],"domain_scores_gemma":[0.9949358,0.00324235,0.0007584486,0.0004370284,0.0003340052,0.0002923604],"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":[0.00008834963,0.0002058261,0.001925253,0.0003019515,0.0000539069,0.0007744918,0.0002793355,1.809188e-7,0.00005466072,0.4832549,0.00231745,0.5107437],"study_design_scores_gemma":[0.0006205324,0.0003817022,0.008532214,0.0002878917,0.000143816,0.0002051896,0.0001206169,0.00006645682,0.00007319434,0.9879004,0.001456292,0.0002116362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004052805,0.00005663355,0.9945754,0.0002112842,0.000263792,0.000163598,0.0001181129,0.00003427111,0.0005241047],"genre_scores_gemma":[0.09834418,0.000005574368,0.9012851,0.00004603297,0.0002159208,0.000005895943,0.000001359335,0.00002455867,0.00007138465],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5105321,"threshold_uncertainty_score":0.9618649,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2065974896","doi":"10.1136/bmj.b2393","title":"Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls","year":2009,"lang":"en","type":"article","venue":"BMJ","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7164,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute of Infection and Immunity","funders":"Economic and Social Research Council; British Heart Foundation","keywords":"Imputation (statistics); Missing data; Computer science; Data science; Data mining; Statistics; Econometrics; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.6024689602522153,"gpt":0.6126207473716742,"spread":0.01015178711945885,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008056374,0.00006346559,0.0002377333,0.00003818938,0.00006661652,0.00003819627,0.000108633,0.000104544,0.000005879981],"category_scores_gemma":[0.08060896,0.00004779556,0.00001645061,0.00005568168,0.0001238547,0.00006531506,0.00009662811,0.0001853739,8.656174e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007673807,"about_ca_system_score_gemma":0.00002460152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001230737,"about_ca_topic_score_gemma":0.00000915081,"domain_scores_codex":[0.9982978,0.0006473713,0.0004432456,0.0003018704,0.0001059125,0.0002038012],"domain_scores_gemma":[0.9823049,0.01727213,0.0000650315,0.0002229695,0.00004915411,0.00008578762],"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":[0.0001332933,0.0001359556,0.009765897,0.00005183253,0.000007169888,0.00001985833,0.00005237448,2.408597e-7,0.0001611356,0.1332167,0.004596924,0.8518586],"study_design_scores_gemma":[0.0004779777,0.0001718548,0.1356533,0.00004167476,0.000007903982,0.000006818824,0.00002671436,0.07176483,0.000004464757,0.7916702,0.0001159907,0.00005825026],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05215557,0.00006078216,0.9429917,0.004133062,0.00004667403,0.0004497636,0.00003701284,0.0000140852,0.0001113987],"genre_scores_gemma":[0.2729811,0.00002521329,0.7267508,0.0001108916,0.0001089262,0.000004468088,0.00000897654,0.000003295906,0.000006300633],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8518003,"threshold_uncertainty_score":0.9271355,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133959349","doi":"10.1093/aje/kwf215","title":"Statistical Analysis of Correlated Data Using Generalized Estimating Equations: An Orientation","year":2003,"lang":"en","type":"article","venue":"American Journal of Epidemiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2200,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Gee; Generalized estimating equation; Binary data; Binary number; Multivariate statistics; Simple (philosophy); Orientation (vector space); Set (abstract data type); Longitudinal data; Data set; Statistics; Estimating equations; Computer science; Mathematics; Multivariate analysis; Applied mathematics; Algorithm; Data mining; Maximum likelihood; Arithmetic","retraction":null,"screen_n_in":null,"score":{"opus":0.307497116676916,"gpt":0.5219258977512772,"spread":0.2144287810743611,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006975682,0.0001266635,0.001268811,0.000313068,0.00005879046,0.000006756279,0.0002797454,0.00005221494,0.0002816918],"category_scores_gemma":[0.1109185,0.0001007993,0.00008814912,0.000858534,0.0004310443,0.0001540211,0.00003224881,0.0002142062,6.627515e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004652723,"about_ca_system_score_gemma":0.000151002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002142571,"about_ca_topic_score_gemma":0.00001224516,"domain_scores_codex":[0.99339,0.004263887,0.00170658,0.0002316034,0.0001646219,0.0002433736],"domain_scores_gemma":[0.9708365,0.02579286,0.002388658,0.0004685782,0.0003477095,0.0001657482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000069838,0.0001336151,0.02772903,0.00001436032,0.0008526364,0.00001135783,0.0002116906,0.004040651,0.000260785,0.9250364,0.00008070854,0.04155893],"study_design_scores_gemma":[0.0002360301,0.0003714183,0.003033951,0.00002499881,0.001672339,0.00003753651,0.000254876,0.5874426,0.00001096955,0.4068079,0.00001295399,0.00009440867],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09253222,0.00003882723,0.9070409,0.00003928143,0.0001640664,0.00005140189,0.00009386767,0.000005783595,0.00003363014],"genre_scores_gemma":[0.2054089,0.000009132702,0.7944027,0.00009713351,0.00003215945,6.705389e-7,0.00003905359,0.000009246775,9.321872e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.583402,"threshold_uncertainty_score":0.8965706,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133470535","doi":"","title":"A multivariate technique for multiply imputing missing values using a sequence of regression models","year":2001,"lang":"en","type":"article","venue":"Survey methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1995,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Missing data; Imputation (statistics); Statistics; Mathematics; Logistic regression; Multivariate statistics; Regression analysis; Regression; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.6952655713588801,"gpt":0.5554953450934195,"spread":0.1397702262654607,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01731374,0.0002320629,0.0007861007,0.0001498129,0.0001465292,0.00001498883,0.000243806,0.0002638219,0.00001902199],"category_scores_gemma":[0.05322669,0.0001880308,0.0001169717,0.0002996124,0.0001884152,0.0000966208,0.0001111639,0.0002104684,3.008097e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005136448,"about_ca_system_score_gemma":0.0001134847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00109249,"about_ca_topic_score_gemma":0.00002295808,"domain_scores_codex":[0.9910111,0.007218135,0.0007354728,0.0004342387,0.0001561006,0.0004449659],"domain_scores_gemma":[0.9546812,0.04396953,0.000493488,0.0003654598,0.0004039466,0.00008640467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005854881,0.0001104266,0.001702416,0.0003494326,0.00006160983,0.00001554044,0.0008114954,0.00009653245,0.8243917,0.08490388,0.00001904194,0.08695244],"study_design_scores_gemma":[0.0003547673,0.00009055543,0.000764198,0.0002566096,0.00003887838,0.00005139301,0.0000473184,0.1433366,0.03906141,0.8158058,0.000003571666,0.0001889286],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01733645,0.00004547577,0.9815258,0.0000261799,0.0001765981,0.0006199842,0.0001160219,0.00005793044,0.00009557391],"genre_scores_gemma":[0.05859389,0.000006914779,0.9412245,0.00002791279,0.00004685922,0.00003688822,0.000008265373,0.00003867888,0.00001616592],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7853303,"threshold_uncertainty_score":0.9547484,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1484712862","doi":"10.1002/0471667196.ess0731","title":"Small Area Estimation","year":2003,"lang":"en","type":"book","venue":"Encyclopedia of Statistical Sciences","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1169,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Small area estimation; Mathematics; Statistics; Exponential family; Estimator; Linear model; Generalized linear mixed model; Generalized linear model; Bayes' theorem; Multivariate statistics; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.08328228167444557,"gpt":0.3568004655121695,"spread":0.273518183837724,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001125864,0.0003664481,0.0007785193,0.0001495123,0.0001547171,0.00005570255,0.0004856377,0.0002715155,0.002717725],"category_scores_gemma":[0.008350574,0.0002862691,0.00008990425,0.00021138,0.002531268,0.00007225332,0.00007927169,0.0003616133,0.00006354153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007903859,"about_ca_system_score_gemma":0.0008794633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007920076,"about_ca_topic_score_gemma":0.000007154952,"domain_scores_codex":[0.9971311,0.000184293,0.0008533313,0.0005859425,0.0008005464,0.0004447802],"domain_scores_gemma":[0.9903773,0.008511572,0.0004605374,0.0002950009,0.0001434798,0.0002121177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000004132333,0.00004907081,0.00001946037,0.0002367532,0.00001347829,0.00001373608,0.00005928372,9.256705e-7,8.025166e-7,0.8978393,0.04343656,0.05832647],"study_design_scores_gemma":[0.0001041239,0.0002400726,0.00005730015,0.0002577025,0.000111082,0.000007779869,0.00001224137,0.0008514487,0.000006040478,0.9773644,0.02064299,0.0003448162],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000004188146,0.00004810619,0.5239148,0.00002559116,0.0002195839,0.0001708545,0.0002757086,0.00002453108,0.4753167],"genre_scores_gemma":[0.000021461,0.0001476627,0.8922656,0.00004279833,0.00007447657,0.00001897073,0.00002704432,0.00002531378,0.1073767],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3683509,"threshold_uncertainty_score":0.9999589,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135760566","doi":"10.1016/j.jclinepi.2014.12.014","title":"The number of subjects per variable required in linear regression analyses","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1043,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"","keywords":"Statistics; Linear regression; Confidence interval; Mathematics; Regression analysis; Regression dilution; Standard error; Regression; Population; Segmented regression; Statistic; Linear model; Proper linear model; Standard deviation; Polynomial regression; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.6415066932237838,"gpt":0.6428740076196767,"spread":0.001367314395892882,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04954595,0.0001218461,0.002025786,0.00005077617,0.00003166608,0.000004548729,0.0003435565,0.0002899169,0.00009483183],"category_scores_gemma":[0.496775,0.00005873999,0.0002973753,0.000178787,0.0003637662,0.0000682057,0.00007662733,0.000761232,0.00001105569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002433086,"about_ca_system_score_gemma":0.0003244648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003743033,"about_ca_topic_score_gemma":0.000007405153,"domain_scores_codex":[0.9857101,0.008753437,0.004832412,0.000164158,0.0002438375,0.0002960123],"domain_scores_gemma":[0.837486,0.1582838,0.003112083,0.0003191407,0.0005433549,0.0002556275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001327958,0.0004225902,0.3212742,0.00006744874,0.0001561981,0.00004551138,0.0001089729,0.00002922449,0.00008212155,0.6353695,0.01523833,0.02587794],"study_design_scores_gemma":[0.0008359525,0.0003271981,0.02097146,0.0001932364,0.00006063806,0.00005687734,0.0000821918,0.001657058,0.00002560003,0.9741181,0.001606188,0.00006552201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.128018,0.0004554573,0.8615987,0.003755742,0.001965586,0.0001170795,0.00000561056,0.000008339763,0.004075577],"genre_scores_gemma":[0.08733977,0.0003094772,0.9114112,0.0003401587,0.0004566621,0.000001456911,3.328153e-7,0.00001050098,0.0001304314],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.447229,"threshold_uncertainty_score":0.9786925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2885675882","doi":"10.1002/jrsm.1316","title":"A comparison of heterogeneity variance estimators in simulated random‐effects meta‐analyses","year":2018,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1026,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Michael's Hospital","funders":"Medical Research Council; National Institute for Health and Care Research","keywords":"Estimator; Meta-analysis; Random effects model; Variance (accounting); Econometrics; Statistics; Variance components; Computer science; Estimation; Mathematics; Economics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.6474146937413818,"gpt":0.6854525192511277,"spread":0.03803782550974588,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02236141,0.0002797965,0.001963798,0.0005537727,0.0001634962,0.00005599243,0.0005677435,0.0002227799,0.0004566901],"category_scores_gemma":[0.1355134,0.000204033,0.0002899603,0.001517424,0.0007661665,0.00009889595,0.0002089316,0.0005259208,0.00002048288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007538885,"about_ca_system_score_gemma":0.0001260695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002296973,"about_ca_topic_score_gemma":0.00003856561,"domain_scores_codex":[0.9779407,0.01893757,0.0009715584,0.0005543361,0.0008652472,0.0007306358],"domain_scores_gemma":[0.8570858,0.1411158,0.0002399805,0.0007948888,0.0005513271,0.0002122692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002154699,0.003336794,0.008820699,0.004135055,0.008067599,0.00009514541,0.002069505,0.0001745987,0.2083574,0.1830657,0.0007368717,0.5789859],"study_design_scores_gemma":[0.0004587591,0.0001965463,0.001295963,0.0002170085,0.0006916628,0.000001442721,0.00005030613,0.06695732,0.6171876,0.312678,0.00006592388,0.0001994331],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02582819,0.0005073066,0.971609,0.00006613418,0.00008925358,0.0005744242,0.00001385561,0.000047701,0.001264126],"genre_scores_gemma":[0.3884794,0.000009485066,0.611362,0.000005738482,0.00003519854,0.00007265902,2.876575e-7,0.00002331767,0.00001191104],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5787865,"threshold_uncertainty_score":0.8717685,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3109682927","doi":"10.1016/j.cjca.2020.11.010","title":"Missing Data in Clinical Research: A Tutorial on Multiple Imputation","year":2020,"lang":"en","type":"review","venue":"Canadian Journal of Cardiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":956,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"University Health Network; Institute for Clinical Evaluative Sciences; University of Toronto; Sunnybrook Hospital","funders":"Medical Research Council; Canadian Institutes of Health Research; Chest Heart and Stroke Scotland; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Missing data; Imputation (statistics); Statistics; Medicine; Regression analysis; Sample size determination; Data mining; Confidence interval; Computer science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.6879125250333257,"gpt":0.5908263245184462,"spread":0.09708620051487948,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007856463,0.0002083614,0.002576699,0.0005480204,0.0000704566,0.00006017316,0.0009411808,0.0005149866,0.00001584937],"category_scores_gemma":[0.1068922,0.0001635705,0.0003283074,0.0003488769,0.0002603248,0.0000548128,0.00007467175,0.00232762,0.00001967829],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003135643,"about_ca_system_score_gemma":0.00678382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002478487,"about_ca_topic_score_gemma":0.0007912807,"domain_scores_codex":[0.9921883,0.00510613,0.001652515,0.0003586963,0.0002547582,0.0004395464],"domain_scores_gemma":[0.9756448,0.02231802,0.0005557279,0.0005292455,0.0002239687,0.0007281979],"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":[0.0000167702,0.000002357765,0.00005125565,0.0007547569,0.0001059376,0.001100187,0.00002333432,4.047828e-7,1.860345e-8,0.008990096,0.01181148,0.9771434],"study_design_scores_gemma":[0.000269322,0.0002437394,0.00004255507,0.00344538,0.0001825844,0.0002327727,0.00001216718,0.00002630212,1.329397e-8,0.06957008,0.9258446,0.0001304935],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000002160275,0.8559799,0.1363281,0.0003851944,0.004185071,0.0003740148,0.0005429314,0.000005825888,0.002196766],"genre_scores_gemma":[0.0001028378,0.866201,0.1232513,0.00004528441,0.01027739,0.000005900592,0.0000474894,0.00005987473,0.000008879722],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9770129,"threshold_uncertainty_score":0.9999741,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130845266","doi":"10.1177/0962280211427759","title":"Extension of the modified Poisson regression model to prospective studies with correlated binary data","year":2011,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":745,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Statistics; Binary data; Estimator; Poisson distribution; Mathematics; Poisson regression; Logistic regression; Econometrics; Variance (accounting); Regression analysis; Cluster (spacecraft); Binary number; Computer science; Population; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.6529093814670139,"gpt":0.6393137010129344,"spread":0.01359568045407955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01804409,0.0002438039,0.0007742554,0.0002338764,0.0001828236,0.00001471166,0.001411315,0.0002439995,0.0003916312],"category_scores_gemma":[0.2318256,0.0001231512,0.00003222159,0.001482217,0.001774276,0.00007994386,0.001934842,0.001680538,0.000006429558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001239034,"about_ca_system_score_gemma":0.0004903477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001341799,"about_ca_topic_score_gemma":0.0000511098,"domain_scores_codex":[0.9895895,0.005487652,0.0008293383,0.0008817919,0.002484043,0.0007276913],"domain_scores_gemma":[0.9634731,0.03325433,0.0001385084,0.001703592,0.0009118504,0.0005186638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001092283,0.0004988915,0.0003371124,0.0002681276,0.00005212335,0.0001540343,0.001803915,0.000003086187,0.0005184634,0.7806562,0.001982179,0.2126336],"study_design_scores_gemma":[0.0005317297,0.0005402137,0.006427182,0.001379739,0.00003351434,0.00001032996,0.0006000091,0.1362593,0.0009272619,0.8531279,0.000008963104,0.0001539076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003359865,0.0001131653,0.9917343,0.0006589983,0.0001323839,0.0009387397,0.0001216951,0.00002758097,0.002913261],"genre_scores_gemma":[0.07525264,0.00006772597,0.9243379,0.00007285537,0.00002435081,0.0000927905,0.000003575194,0.00003390488,0.0001142694],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2137815,"threshold_uncertainty_score":0.7746451,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2618058430","doi":"10.1002/sim.7336","title":"Intermediate and advanced topics in multilevel logistic regression analysis","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":657,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Sunnybrook Hospital; University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Vetenskapsrådet; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Marginal model; Logistic regression; Covariate; Multilevel model; Statistics; Hierarchical clustering; Econometrics; Regression analysis; Population; Odds ratio; Regression; Cluster analysis; Computer science; Mathematics; Demography","retraction":null,"screen_n_in":null,"score":{"opus":0.1141231773850907,"gpt":0.4782803494377693,"spread":0.3641571720526786,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007417856,0.0001655243,0.0006113496,0.0002487255,0.00009099644,0.00002700602,0.0002408098,0.00007906852,0.0001525876],"category_scores_gemma":[0.02324446,0.0001205914,0.00001686387,0.0001295237,0.0004990573,0.00005300714,0.0001149757,0.0002833541,0.000001824644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004516376,"about_ca_system_score_gemma":0.00002129416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002118792,"about_ca_topic_score_gemma":0.0009492463,"domain_scores_codex":[0.998592,0.0001187662,0.0005108292,0.0003010044,0.0002274729,0.0002499479],"domain_scores_gemma":[0.9969254,0.002163521,0.0002552666,0.0004885613,0.00006779583,0.00009948996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005892026,0.00006520665,0.07124351,0.000214306,0.00004261253,0.0003053071,0.00089358,0.000001845389,0.00004839401,0.5168502,0.000439163,0.4098369],"study_design_scores_gemma":[0.0008455173,0.00007113545,0.3587915,0.0003048706,0.00009436935,0.000001386816,0.00009716185,0.01334464,0.000008733343,0.626288,0.00004762696,0.0001050439],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01492543,0.00007295243,0.9828474,0.0003974565,0.0002591764,0.0001724363,0.0001134776,0.00001258844,0.001199091],"genre_scores_gemma":[0.3864107,0.0001723577,0.6131126,0.00005077052,0.00006029159,0.00001312711,0.00001160717,0.000009490599,0.0001589875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4097319,"threshold_uncertainty_score":0.9849831,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1603573412","doi":"10.1186/1471-2288-6-57","title":"Dealing with missing data in a multi-question depression scale: a comparison of imputation methods","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":655,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; University of Calgary","funders":"Canadian Institutes of Health Research; Fondation pour la Recherche Médicale; Government of Canada; Heart and Stroke Foundation of Canada","keywords":"Missing data; Statistics; Imputation (statistics); Statistic; Cohen's kappa; Standard deviation; Population; Mathematics; Kappa; Regression; Psychology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.7482629066797014,"gpt":0.6934678501720167,"spread":0.05479505650768468,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0614525,0.0001637932,0.0008105234,0.0003968479,0.0001092726,0.00002513565,0.0006524046,0.0003501677,0.0001744554],"category_scores_gemma":[0.1861279,0.0001195027,0.00003412448,0.0006304182,0.0006709506,0.0001025035,0.000420532,0.0009452135,0.000002316255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006289201,"about_ca_system_score_gemma":0.0005451152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001733915,"about_ca_topic_score_gemma":0.002781688,"domain_scores_codex":[0.963995,0.03192572,0.001175436,0.0007200871,0.001515305,0.000668406],"domain_scores_gemma":[0.8646073,0.1338,0.0002662509,0.000711589,0.0003657909,0.0002490053],"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":[0.0004629173,0.0004696494,0.05056434,0.0006848171,0.000013419,0.00003055239,0.000299217,0.00002095181,0.006642275,0.1133977,0.00008435826,0.8273298],"study_design_scores_gemma":[0.001317865,0.000220393,0.02561892,0.001033324,0.00003189185,0.00003639409,0.000371057,0.3448774,0.008535251,0.6177282,0.00005471434,0.000174603],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01445299,0.0003283146,0.984243,0.0001799353,0.0000631984,0.0003485667,0.00001044914,0.00003486113,0.0003386263],"genre_scores_gemma":[0.05135386,0.0000180745,0.9484555,0.00001181389,0.00006781305,0.00002957707,0.00002623367,0.00002443223,0.00001274977],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8271552,"threshold_uncertainty_score":0.9664322,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2122717603","doi":"10.1503/cmaj.110977","title":"Missing covariate data in clinical research: when and when not to use the missing-indicator method for analysis","year":2012,"lang":"en","type":"article","venue":"Canadian Medical Association Journal","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":542,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Economic and Social Research Council; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Cancer Research UK","keywords":"Missing data; Covariate; Computer science; Data mining; Data science; Statistics; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4423327546156466,"gpt":0.5402522117396086,"spread":0.09791945712396194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05719739,0.0001244267,0.0004737746,0.000415175,0.0004769428,0.0004080615,0.0006416744,0.0003468595,0.0008015709],"category_scores_gemma":[0.1713247,0.00008933635,0.00009305359,0.0004615692,0.00009127757,0.0002526727,0.0001218968,0.001300089,0.00001309332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004163189,"about_ca_system_score_gemma":0.001440295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003501461,"about_ca_topic_score_gemma":0.01546278,"domain_scores_codex":[0.9934254,0.003216762,0.0009439742,0.000291803,0.001282493,0.0008395507],"domain_scores_gemma":[0.9666796,0.02957958,0.0003079035,0.0004380333,0.0003397668,0.00265516],"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":[0.00004856485,0.00010987,0.1657085,0.0000298813,0.0006979112,0.00004816166,0.003262933,1.629106e-7,0.000006726113,0.05625748,0.1349582,0.6388717],"study_design_scores_gemma":[0.001178826,0.00009586658,0.2837513,0.0001709367,0.000718121,0.00006459319,0.0006772706,0.01692821,0.000006794077,0.4137874,0.2822537,0.0003669875],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00317325,0.00004889499,0.9051214,0.09069853,0.0003128845,0.0002665872,0.0002407935,0.000007406542,0.0001302197],"genre_scores_gemma":[0.01401086,0.0000224752,0.9763623,0.008359705,0.001072684,0.000009677621,0.00001282013,0.00002089135,0.0001285678],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6385047,"threshold_uncertainty_score":0.9708137,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2068225985","doi":"10.1111/j.0006-341x.2001.00158.x","title":"Bayesian Approaches to Modeling the Conditional Dependence Between Multiple Diagnostic Tests","year":2001,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":531,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Bayesian probability; Statistics; Econometrics; Inference; Conditional dependence; Bayesian inference; A priori and a posteriori; Statistical hypothesis testing; Mathematics; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.3859403790451644,"gpt":0.3821515830412841,"spread":0.003788796003880324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007691923,0.0001754705,0.0002420576,0.0004528856,0.0002080684,0.0001004259,0.0004006812,0.0001006266,0.00007275699],"category_scores_gemma":[0.03158799,0.0001235286,0.00006151121,0.002771312,0.00007081053,0.00007455652,0.0001187005,0.0001802237,0.00006897553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005683054,"about_ca_system_score_gemma":0.00004236433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004039617,"about_ca_topic_score_gemma":0.00001248875,"domain_scores_codex":[0.998342,0.0001237358,0.0003524833,0.0003183541,0.0005008559,0.0003625391],"domain_scores_gemma":[0.980568,0.01870846,0.0000775226,0.000350656,0.00009431248,0.0002010382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002503149,0.0004152553,0.2391604,0.0001348237,0.0001086269,0.0000713199,0.000457692,0.0003261666,0.0001120514,0.4845804,0.001897543,0.2727107],"study_design_scores_gemma":[0.0002911586,0.0001097366,0.03724582,0.00004869591,0.00007696525,0.00002318753,0.0001133154,0.08938482,0.0001282143,0.8716113,0.0006044661,0.0003623498],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02111173,0.00006558136,0.9769057,0.0006195959,0.00009006885,0.0003526278,0.0001355581,0.00006818702,0.0006509505],"genre_scores_gemma":[0.6111028,0.000009193991,0.3885592,0.00008038792,0.0001590082,0.00004001081,0.00001125929,0.00001472611,0.0000234466],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5899911,"threshold_uncertainty_score":0.9765694,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157235443","doi":"10.1177/0962280214521348","title":"Multiple imputation of covariates by fully conditional specification: Accommodating the substantive model","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":491,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute on Aging; Economic and Social Research Council; University of California, San Diego; National Institutes of Health; Genentech; IXICO; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; University of California, Los Angeles; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Alzheimer's Association; Amorfix Life Sciences; F. Hoffmann-La Roche; Medpace; AstraZeneca; Eli Lilly and Company; Bristol-Myers Squibb; Novartis Pharmaceuticals Corporation; Synarc; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; Medical Research Council; Meso Scale Diagnostics; Foundation for the National Institutes of Health","keywords":"Covariate; Imputation (statistics); Missing data; Econometrics; Computer science; Statistics; Specification; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2276033325385271,"gpt":0.5725945814759557,"spread":0.3449912489374286,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02596157,0.0001796809,0.0005060642,0.0001539499,0.0002184502,0.00005549985,0.0006583232,0.0002181217,0.001526929],"category_scores_gemma":[0.2358185,0.0001242444,0.00005063929,0.0006987746,0.0015557,0.0000741524,0.0002030862,0.001291321,0.00001417664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008742861,"about_ca_system_score_gemma":0.0002843665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008356349,"about_ca_topic_score_gemma":0.00001958056,"domain_scores_codex":[0.9880795,0.007631482,0.00104557,0.0004722243,0.002164097,0.0006071259],"domain_scores_gemma":[0.8324588,0.1660668,0.0001726439,0.0004097353,0.0006027401,0.0002892961],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006642779,0.0001549998,0.0002055723,0.00008632043,0.00001330623,0.000003468845,0.0002095876,0.000006489765,0.001112429,0.7763035,0.002001504,0.2198364],"study_design_scores_gemma":[0.0003629684,0.00008012106,0.001167596,0.00006291507,0.000007657975,0.000002065339,0.0001435594,0.3583513,0.0008803408,0.638704,0.0001503216,0.00008720977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007212588,0.00003499243,0.9940387,0.001389893,0.00006699164,0.0004053279,0.0003252042,0.00002249679,0.002995135],"genre_scores_gemma":[0.1717995,0.00002314458,0.827825,0.00007907413,0.00007182942,0.0001005712,0.00005609067,0.00002177292,0.00002306485],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3583448,"threshold_uncertainty_score":0.9993858,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100697007","doi":"10.1177/0962280214558972","title":"Events per variable (EPV) and the relative performance of different strategies for estimating the out-of-sample validity of logistic regression models","year":2014,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":484,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; National Institute of Neurological Disorders and Stroke; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Statistics; Sample size determination; Logistic regression; Sample (material); Mathematics; Regression analysis; Econometrics; Mean squared error; Regression; Linear regression; Variance (accounting); Variables; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.3934446952715054,"gpt":0.579674810655022,"spread":0.1862301153835166,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03290375,0.000177432,0.0008481187,0.00009037222,0.0001726553,0.00001930212,0.0005253757,0.000176754,0.0002047556],"category_scores_gemma":[0.2396518,0.00008294976,0.00006006138,0.0002394961,0.002994153,0.00007345768,0.0003285731,0.000897509,2.885302e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000322099,"about_ca_system_score_gemma":0.0002409571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001186971,"about_ca_topic_score_gemma":0.000009171365,"domain_scores_codex":[0.9878017,0.0088264,0.001088635,0.0003376075,0.001465856,0.0004797842],"domain_scores_gemma":[0.7031545,0.2955875,0.0002611755,0.0004110624,0.0004396992,0.0001460556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003435344,0.0001197633,0.0001946041,0.00114782,0.00002272686,3.494843e-7,0.0006867333,0.00001395549,0.00006043642,0.8486877,0.00003172585,0.1486906],"study_design_scores_gemma":[0.0005507544,0.0002831066,0.0003452689,0.0004619404,0.00002867048,5.841314e-7,0.0001652232,0.4218926,0.0001462419,0.576071,0.000004828064,0.00004983165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003192432,0.00003326925,0.9945339,0.0002634128,0.00013959,0.0006872028,0.0001167371,0.000006094737,0.001027356],"genre_scores_gemma":[0.2263138,0.00003373444,0.7734734,0.00001004326,0.00003644657,0.0001068403,0.000002983891,0.00001315596,0.000009568374],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4218786,"threshold_uncertainty_score":0.9997191,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1845661996","doi":"10.6000/1929-6029.2015.04.03.7","title":"Multiple Imputation by Fully Conditional Specification for Dealing with Missing Data in a Large Epidemiologic Study","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":465,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Institutes of Health; U.S. President’s Emergency Plan for AIDS Relief; Centers for Disease Control and Prevention; Georgia State University","keywords":"Categorical variable; Missing data; Imputation (statistics); Computer science; Data mining; Multivariate statistics; Statistics; Econometrics; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.4574323852140853,"gpt":0.598124388630447,"spread":0.1406920034163617,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02132263,0.0001029848,0.0003233749,0.0003067552,0.00004673494,0.00007002141,0.0008613743,0.0000863978,0.0001383848],"category_scores_gemma":[0.1420067,0.00007878494,0.00001708838,0.0001671526,0.0001647642,0.0001681647,0.0001493966,0.0007323235,0.00000248398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002719307,"about_ca_system_score_gemma":0.0006021251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001397277,"about_ca_topic_score_gemma":0.0003793568,"domain_scores_codex":[0.9949177,0.0008529406,0.001078028,0.0002550675,0.002591292,0.000304965],"domain_scores_gemma":[0.9736225,0.02369394,0.0003427046,0.0001759187,0.001911428,0.000253514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00237444,0.003218415,0.1058509,0.00009308053,0.0001680631,0.001353184,0.001365149,0.00004972972,0.0001011477,0.6728046,0.01756712,0.1950542],"study_design_scores_gemma":[0.003966027,0.0006327599,0.01151376,0.0002524777,0.00001011782,0.00005086645,0.001030253,0.08535105,0.00001328756,0.8963863,0.000694152,0.00009889891],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01487548,0.00006103093,0.9818597,0.001799408,0.0001528996,0.0003343498,0.0008275141,0.000003941599,0.00008571769],"genre_scores_gemma":[0.479692,0.00003138863,0.519923,0.00004154784,0.000136989,0.00001301012,0.0001474411,0.000009673507,0.000005009229],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4648165,"threshold_uncertainty_score":0.8652205,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3102763196","doi":"10.7916/d8v99mjx","title":"The Prior Can Often Only Be Understood in the Context of the Likelihood","year":2017,"lang":"en","type":"article","venue":"Columbia Academic Commons (Columbia University)","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":464,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Context (archaeology); Computer science; Econometrics; Statistical physics; Mathematics; Biology; Physics; Paleontology","retraction":null,"screen_n_in":null,"score":{"opus":0.0614308441815082,"gpt":0.3068775392655041,"spread":0.2454466950839959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001285986,0.0001739217,0.0004167986,0.00005198391,0.00232063,0.0003460077,0.004060024,0.0002868828,0.00006881267],"category_scores_gemma":[0.003267342,0.0001580178,0.0001992146,0.0004245735,0.001354393,0.0001465961,0.0008047505,0.001329622,0.000003013205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002044773,"about_ca_system_score_gemma":0.000466126,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02823054,"about_ca_topic_score_gemma":0.5677982,"domain_scores_codex":[0.9973853,0.0008447017,0.0004473629,0.0003416541,0.0004501811,0.0005308564],"domain_scores_gemma":[0.9932776,0.004107842,0.0006161364,0.001747562,0.0001367255,0.0001141004],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008630932,0.0003070925,0.2387136,0.0001181772,0.0001816234,0.00006098113,0.004061101,2.177021e-7,0.0001263185,0.5566323,0.07715049,0.1225618],"study_design_scores_gemma":[0.001877452,0.0001475671,0.4507059,0.0003226628,0.0003081143,0.00002167785,0.01028251,0.000167337,0.00002856202,0.472531,0.06316774,0.0004394751],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8842499,0.0001347915,0.003091542,0.03388106,0.000851198,0.003132905,0.0004920233,0.0001064547,0.07406019],"genre_scores_gemma":[0.9919169,0.00006040743,0.001993552,0.0004910344,0.00004752875,0.000007166146,0.000001296038,0.00002416248,0.005457987],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5395676,"threshold_uncertainty_score":0.9989782,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2747622113","doi":"10.3390/e19100555","title":"The Prior Can Often Only Be Understood in the Context of the Likelihood","year":2017,"lang":"en","type":"article","venue":"Entropy","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":451,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Advanced Research Projects Agency; Office of Naval Research; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Inference; Bayesian probability; Context (archaeology); Entropy (arrow of time); Prior probability; Key (lock); Bayesian inference; Principle of maximum entropy","retraction":null,"screen_n_in":null,"score":{"opus":0.05894595154175716,"gpt":0.3561339327717054,"spread":0.2971879812299483,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006715433,0.00009296104,0.0001598312,0.000009435028,0.0004289037,0.0001042141,0.0009205987,0.00004144357,0.0000331343],"category_scores_gemma":[0.003563101,0.00003798055,0.00007019059,0.00004209553,0.000262136,0.00002638657,0.0001066277,0.0002024874,0.000003838387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000262953,"about_ca_system_score_gemma":0.00009650001,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002732458,"about_ca_topic_score_gemma":0.001248385,"domain_scores_codex":[0.9989257,0.0002699609,0.000228724,0.0001115762,0.0002500472,0.0002140123],"domain_scores_gemma":[0.9966835,0.002151384,0.0002199539,0.0008772885,0.0000404321,0.00002744584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001299834,0.0000482146,0.001477363,0.00001264141,0.000015294,0.0000022332,0.001551438,1.046203e-8,0.00009212564,0.9663414,0.002044114,0.02840212],"study_design_scores_gemma":[0.0004653579,0.00005682273,0.03923296,0.0000532059,0.00003595592,0.000003745429,0.002129799,0.00009642314,0.0005540428,0.9544344,0.002860351,0.00007694842],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4197882,0.0005809825,0.2073165,0.3113772,0.002813344,0.004461973,0.0004435482,0.00009780373,0.05312041],"genre_scores_gemma":[0.9827967,0.00001148121,0.01625036,0.0007064673,0.0000573605,0.00001362282,2.76173e-7,0.000009520063,0.0001541917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5630085,"threshold_uncertainty_score":0.4265622,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1666386643","doi":"10.1214/lnms/1215540964","title":"The Practical Implementation of Bayesian Model Selection","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes-monograph series","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":433,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Selection (genetic algorithm); Computer science; Bayesian probability; Bayesian inference; Model selection; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.05280911275820354,"gpt":0.3770241510213588,"spread":0.3242150382631553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004282385,0.000456414,0.0005677536,0.0001646833,0.0003335379,0.0001015948,0.0001931202,0.0004292357,0.0004372606],"category_scores_gemma":[0.0005979156,0.0003215405,0.0002767946,0.0001529321,0.000338888,0.0001375213,0.00005304278,0.0006525125,0.000004198974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005014353,"about_ca_system_score_gemma":0.0001950556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003298981,"about_ca_topic_score_gemma":0.0007792876,"domain_scores_codex":[0.9979532,0.000103268,0.0007244228,0.0003935291,0.0004544072,0.0003711859],"domain_scores_gemma":[0.996349,0.002235113,0.0006147075,0.000420322,0.0002861026,0.00009472903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001063293,0.00001643026,0.00005929585,0.0001044025,0.000168162,0.000004909964,0.000197952,0.000008710765,0.0000847643,0.924085,0.0007101021,0.07445391],"study_design_scores_gemma":[0.0001592823,0.0002793862,0.00003204928,0.00008478077,0.0002972412,0.00005362671,0.00003222868,0.0008775027,0.001210471,0.9891774,0.007458933,0.0003370901],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001820287,0.0001399573,0.9577532,0.0009481226,0.0001402938,0.0005052402,0.00008948411,0.00008933574,0.04031612],"genre_scores_gemma":[0.01031326,0.0009079449,0.9849054,0.0001366612,0.0002681079,0.00006476328,0.00004401667,0.0001420969,0.003217788],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07411682,"threshold_uncertainty_score":0.9999236,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2611208896","doi":"10.1101/132753","title":"Modeling zero-inflated count data with glmmTMB","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":428,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Count data; Laplace's method; Generalized linear mixed model; Negative binomial distribution; Overdispersion; Markov chain Monte Carlo; Computer science; Poisson distribution; Statistics; Quasi-likelihood; Range (aeronautics); Generalized linear model; Bayesian probability; Algorithm; Mathematics; Applied mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.08572515254872412,"gpt":0.3282695346689558,"spread":0.2425443821202317,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001584265,0.0008021289,0.001104548,0.0001653413,0.0003923317,0.0007427236,0.00256641,0.0006688045,0.00007763351],"category_scores_gemma":[0.002927915,0.0006989607,0.00008799443,0.000184326,0.000229857,0.0003031279,0.001853712,0.001305941,0.00005840872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001879444,"about_ca_system_score_gemma":0.0009932303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001697584,"about_ca_topic_score_gemma":0.000009214026,"domain_scores_codex":[0.9958674,0.0002088816,0.0007870269,0.001639405,0.0007352238,0.0007620025],"domain_scores_gemma":[0.9912704,0.0004105539,0.000678583,0.006437441,0.0008214221,0.0003815739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009503427,0.00205111,0.007776225,0.01331222,0.004451272,0.002648325,0.0001285188,0.001124177,0.1344863,0.8238757,0.008942115,0.0002536938],"study_design_scores_gemma":[0.003459495,0.0003601011,0.005970415,0.01064801,0.002724972,3.136038e-7,0.000009172031,0.9132987,0.02291899,0.02923165,0.004127423,0.007250715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05727527,0.0002740581,0.9386422,0.0001550657,0.0007226011,0.0008214062,0.001511208,0.0005342204,0.00006398548],"genre_scores_gemma":[0.4920247,0.00009521785,0.5073319,0.00005362128,0.000264538,0.00007103712,0.000001152007,0.0001539736,0.00000388154],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9121746,"threshold_uncertainty_score":0.9995462,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155013980","doi":"10.1002/nur.20100","title":"Handling missing data in self-report measures","year":2005,"lang":"en","type":"review","venue":"Research in Nursing & Health","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":408,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Wayne State University","keywords":"Missing data; Imputation (statistics); Computer science; Data mining; Statistics; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.6966503124980666,"gpt":0.6780807088257569,"spread":0.01856960367230975,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03188183,0.0004062871,0.002412652,0.001198175,0.0002778932,0.0002079806,0.001223009,0.0003870586,0.00003163497],"category_scores_gemma":[0.01038699,0.0003507988,0.0001011656,0.001623904,0.0002233068,0.0001500133,0.0002554475,0.003000417,0.00002245565],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002636374,"about_ca_system_score_gemma":0.005722195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004504799,"about_ca_topic_score_gemma":0.0002054934,"domain_scores_codex":[0.9876783,0.005648751,0.002112205,0.001215333,0.00160446,0.00174089],"domain_scores_gemma":[0.9877169,0.009273639,0.0004573865,0.001936454,0.0001561432,0.000459451],"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":[0.000005199591,0.0003530788,0.000008008304,0.02052057,0.00001431229,0.00026477,0.0002673067,4.435284e-8,2.687174e-8,0.01532132,0.001341193,0.9619042],"study_design_scores_gemma":[0.0002051427,0.00007094575,0.00001237459,0.2040314,0.00004326725,0.0002858611,0.00005816083,0.0004887634,8.302472e-8,0.2072142,0.5872388,0.0003509061],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.591268e-7,0.9395623,0.05510736,0.001074451,0.0002312079,0.001359429,0.00005947513,0.00006916137,0.00253628],"genre_scores_gemma":[0.000002266098,0.6033472,0.3961805,0.00001171751,0.0002918949,0.00003277783,0.00005110474,0.00006004789,0.00002247991],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9615533,"threshold_uncertainty_score":0.9999145,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2808363984","doi":"10.1002/ecm.1309","title":"Model averaging in ecology: a review of Bayesian, information‐theoretic, and tactical approaches for predictive inference","year":2018,"lang":"en","type":"review","venue":"Ecological Monographs","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":404,"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":"Seventh Framework Programme; Engineering and Physical Sciences Research Council; University of Melbourne; Bundesministerium für Bildung und Forschung; Deutsches Zentrum für integrative Biodiversitätsforschung Halle-Jena-Leipzig; Deutsche Forschungsgemeinschaft; Australian Research Council; Alexander von Humboldt-Stiftung","keywords":"Variance (accounting); Model selection; Bayesian inference; Covariance; Context (archaeology); Bayesian probability; Computer science; Ecology; Range (aeronautics); Inference; Econometrics; Mathematics; Statistics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1790280268289677,"gpt":0.4110813618337321,"spread":0.2320533350047644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001977625,0.0004885953,0.002667069,0.000321571,0.00008072153,0.00003907225,0.0003903763,0.0006219731,0.0001025155],"category_scores_gemma":[0.01350697,0.000341706,0.0003997333,0.0004796858,0.0006947353,0.0001913002,0.000235239,0.0005503598,0.000004199318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007063017,"about_ca_system_score_gemma":0.0002252974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.751436e-7,"about_ca_topic_score_gemma":0.000002714738,"domain_scores_codex":[0.9965823,0.0005884226,0.001671256,0.0004799343,0.0002036584,0.0004743869],"domain_scores_gemma":[0.9885989,0.009873382,0.0008124315,0.0003691949,0.0001840046,0.0001620401],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002347071,0.0002008347,0.00006425355,0.118411,0.00009434033,0.00000203089,0.00008749268,4.336308e-7,3.450437e-9,0.5480179,0.0005631251,0.3325352],"study_design_scores_gemma":[0.0002851156,0.000534862,0.00006771952,0.03039445,0.0007453104,0.00001327071,0.00002153747,0.01652355,1.58026e-7,0.9376498,0.01333755,0.0004267092],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.00000372023,0.4665725,0.5293609,0.00004818147,0.00005925796,0.002404292,0.0003200319,0.00003878241,0.001192282],"genre_scores_gemma":[0.00007790192,0.6556839,0.3430795,0.00009874666,0.00002022051,0.0009814417,0.00003943496,0.00001559795,0.000003219367],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.3896319,"threshold_uncertainty_score":0.9999035,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2006031679","doi":"10.1186/1471-2288-7-34","title":"A simulation study of sample size for multilevel logistic regression models","year":2007,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":400,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences; St. Michael's Hospital; University of Toronto","funders":"Ontario Ministry of Health and Long-Term Care","keywords":"Statistics; Sample size determination; Multilevel model; Logistic regression; Random effects model; Variance (accounting); Covariance; Mathematics; Hierarchical database model; Sample (material); Econometrics; Regression; Medicine; Computer science; Meta-analysis; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.8745461031859402,"gpt":0.6879301196957895,"spread":0.1866159834901506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06386741,0.0001654242,0.0007595498,0.0002405285,0.000158251,0.00001108761,0.0004762927,0.0003602869,0.0005399524],"category_scores_gemma":[0.8397517,0.0001169479,0.00009135276,0.0003499299,0.0005103262,0.00004634779,0.000244262,0.0005821232,0.000002250609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006427249,"about_ca_system_score_gemma":0.0004071246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003463426,"about_ca_topic_score_gemma":0.0004366847,"domain_scores_codex":[0.9860284,0.009764019,0.001056278,0.0005305533,0.001806435,0.0008143009],"domain_scores_gemma":[0.2488983,0.7491971,0.0001885849,0.0004714881,0.0008430945,0.0004015161],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002205864,0.001806573,0.00114456,0.0008837701,0.00005611546,0.0000297799,0.001936532,0.0002782462,0.0003765333,0.5951161,0.0002335729,0.3959323],"study_design_scores_gemma":[0.001276607,0.0009494951,0.001201363,0.0001025231,0.00002155092,0.000001782602,0.0009770017,0.2449096,0.000194568,0.7502479,0.00002880489,0.00008880534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03042248,0.00002575758,0.9678813,0.00005189094,0.0001558438,0.001222795,0.00002837555,0.00003411518,0.0001774542],"genre_scores_gemma":[0.3474437,0.000004620937,0.6522952,0.00001902112,0.0001078447,0.00007018898,0.000001601707,0.00001782322,0.00004000866],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7758843,"threshold_uncertainty_score":0.9639455,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W94208768","doi":"10.1002/jae.2508","title":"Wild Bootstrap Inference for Wildly Different Cluster Sizes","year":2016,"lang":"en","type":"article","venue":"Journal of Applied Econometrics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":373,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University; Queen's University","funders":"","keywords":"Estimator; Cluster (spacecraft); Econometrics; Statistics; Variance (accounting); Monte Carlo method; Inference; Mathematics; Computer science; Economics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1001847994653385,"gpt":0.3560613191813742,"spread":0.2558765197160357,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000830597,0.0002029041,0.000611045,0.0004664866,0.00006066844,0.00007101208,0.0003396762,0.0001179354,0.0002448556],"category_scores_gemma":[0.003155097,0.0001186596,0.0001819299,0.0002750047,0.00008345532,0.0001428172,0.00005394469,0.0001631488,0.00001233096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000113366,"about_ca_system_score_gemma":0.00006310038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.184344e-7,"about_ca_topic_score_gemma":0.000001362569,"domain_scores_codex":[0.9983181,0.00002671744,0.0009252542,0.0001985157,0.0002134744,0.0003179833],"domain_scores_gemma":[0.9894807,0.009143678,0.0007636725,0.0002239162,0.0001798451,0.0002082375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002156735,0.0001810501,0.001150406,0.0001079195,0.00009987585,0.000002142661,0.00007514793,0.000001324291,0.0003898415,0.7946407,0.003372194,0.1997637],"study_design_scores_gemma":[0.00156188,0.0003448732,0.002852589,0.00007394233,0.00007763135,0.00000974334,0.00004197139,0.00007349286,0.00137278,0.9904428,0.002933462,0.0002148479],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03860481,0.0000346295,0.957531,0.0005224494,0.0003213786,0.0002421376,0.00005301482,0.00001470313,0.002675882],"genre_scores_gemma":[0.5872669,0.0001039986,0.4120505,0.0001793362,0.0002780029,0.00001660092,4.079386e-7,0.00002462845,0.00007963023],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5486621,"threshold_uncertainty_score":0.4838798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002858652","doi":"10.1002/cjs.5550360302","title":"Bayesian analysis of elapsed times in continuous‐time Markov chains","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":344,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Prior probability; Frequentist inference; Bayesian probability; Posterior probability; Markov chain; Computer science; Mathematics; Bayesian inference; Econometrics; Statistics; Markov chain Monte Carlo","retraction":null,"screen_n_in":null,"score":{"opus":0.02815515843739064,"gpt":0.2897788057720888,"spread":0.2616236473346982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006578266,0.0001666123,0.000910152,0.001045478,0.00007226389,0.00002003577,0.0002644875,0.0000965951,0.001928563],"category_scores_gemma":[0.003440689,0.0001545699,0.0001331635,0.0008152457,0.000277885,0.00006163379,0.000009625639,0.0002696012,0.000005063014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001261072,"about_ca_system_score_gemma":0.0009806805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001753269,"about_ca_topic_score_gemma":0.009446041,"domain_scores_codex":[0.9980015,0.0002030117,0.001018298,0.0001332315,0.0002809426,0.0003630737],"domain_scores_gemma":[0.9965455,0.001730663,0.0005596856,0.0002133169,0.0004201994,0.0005306341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001031504,0.0002101798,0.115421,0.0001788402,0.001814445,0.005021671,0.00370788,0.00007095946,0.0002353897,0.8044726,0.03158034,0.03718347],"study_design_scores_gemma":[0.002375837,0.0008900326,0.2464408,0.0004521901,0.002865439,0.0004277307,0.0006364592,0.04359719,0.0002850629,0.6997663,0.001285963,0.0009770457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01465879,0.00007539492,0.9812043,0.0001070966,0.0001154435,0.0000988086,0.001272277,0.000004079326,0.002463749],"genre_scores_gemma":[0.3371997,0.00002329564,0.662316,0.00005372651,0.00003591991,9.797493e-7,0.000009682207,0.00001780736,0.0003428091],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3225409,"threshold_uncertainty_score":0.9989838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2000767414","doi":"10.1007/s10985-007-9065-x","title":"Generalized linear mixed models: a review and some extensions","year":2007,"lang":"en","type":"review","venue":"Lifetime Data Analysis","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":335,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University; Simon Fraser University","funders":"","keywords":"Computational statistics; Computer science; Generalized linear mixed model; Variety (cybernetics); Software; Generalized linear model; Statistical model; Data science; Programming language; Machine learning; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.3583324276125319,"gpt":0.4960117588798883,"spread":0.1376793312673564,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002522465,0.0006482131,0.005643281,0.0005436891,0.0001299831,0.00007641547,0.001187923,0.0003605184,0.0007056293],"category_scores_gemma":[0.003428661,0.0004632309,0.0007165368,0.001934223,0.0001333881,0.0002200504,0.0009855244,0.0005126754,0.00009009557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003223774,"about_ca_system_score_gemma":0.0001333453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005934886,"about_ca_topic_score_gemma":0.00001668289,"domain_scores_codex":[0.9953111,0.0008948141,0.001651438,0.001235027,0.0004495474,0.0004580191],"domain_scores_gemma":[0.9922221,0.003031042,0.0007083786,0.003556465,0.0001376017,0.0003443862],"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":[0.000001677998,0.00007440364,1.581802e-7,0.03391868,0.003826821,0.00004003148,0.000005450083,1.463928e-7,2.139818e-8,0.08917194,0.01626606,0.8566946],"study_design_scores_gemma":[0.00009098745,0.00001374358,2.64688e-7,0.01109457,0.1333031,0.00002408642,0.000002422261,0.007118806,2.575633e-8,0.08407862,0.7636524,0.00062088],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.277915e-8,0.6144845,0.38082,0.00004640058,0.00003022543,0.0003869817,0.00409324,0.00004615158,0.00009245652],"genre_scores_gemma":[3.453969e-9,0.5492252,0.4472371,0.0001913528,0.0001026512,0.0000275392,0.003005457,0.00003784061,0.0001728478],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8560737,"threshold_uncertainty_score":0.999782,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3175648361","doi":"10.1186/s40488-021-00121-4","title":"A comparison of zero-inflated and hurdle models for modeling zero-inflated count data","year":2021,"lang":"en","type":"review","venue":"Journal of Statistical Distributions and Applications","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":296,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Zero (linguistics); Count data; Mathematics; Statistics; Computer science; Applied mathematics; Poisson distribution; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.2947301090636834,"gpt":0.5048017762537285,"spread":0.2100716671900451,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007441539,0.0003228581,0.002174969,0.0001052791,0.0002426393,0.0001110465,0.0003691128,0.0002598948,0.0000272169],"category_scores_gemma":[0.001625995,0.000257756,0.0001532874,0.0003231723,0.0002417217,0.0001301892,0.0002056597,0.0004941475,7.035216e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006564389,"about_ca_system_score_gemma":0.0003903076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008621854,"about_ca_topic_score_gemma":0.000001522845,"domain_scores_codex":[0.9968145,0.0001560876,0.002078182,0.000393547,0.0002886351,0.0002690813],"domain_scores_gemma":[0.9930195,0.004303268,0.001062271,0.0005337712,0.0008117072,0.0002695212],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006500087,0.000203554,0.000001012635,0.0031637,0.0001825222,0.000001910953,0.00001352876,0.000009089615,0.000001552277,0.6968512,0.001412676,0.2981528],"study_design_scores_gemma":[0.0003498395,0.0001119319,0.000001799674,0.003534454,0.0031327,0.00008592563,0.00005214846,0.1482549,0.000001055912,0.7669367,0.07724016,0.000298435],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000001427509,0.3351647,0.6439303,0.00002297717,0.00002127191,0.0005209381,0.0203074,0.000007872063,0.00002312964],"genre_scores_gemma":[0.0004021067,0.4661532,0.5316992,0.000003312771,0.00004977106,0.00009019909,0.001571842,0.00002515469,0.00000520655],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2978543,"threshold_uncertainty_score":0.9999875,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2030605340","doi":"10.1111/cdep.12043","title":"Planned Missing Data Designs for Developmental Researchers","year":2013,"lang":"en","type":"article","venue":"Child Development Perspectives","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":292,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; University of Kansas; National Science Foundation","keywords":"Missing data; Data collection; Research design; Longitudinal data; Psychology; Computer science; Statistics; Data mining; Econometrics; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3455343248455911,"gpt":0.4424078329821734,"spread":0.0968735081365823,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008377778,0.0002359357,0.0002923412,0.0001244597,0.0004896231,0.000200349,0.0006577668,0.00008345112,0.0007475874],"category_scores_gemma":[0.004664945,0.0001990088,0.00003551918,0.0001798125,0.0001532886,0.0003396622,0.000290572,0.000193358,0.00009061241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002283618,"about_ca_system_score_gemma":0.0003564198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000111624,"about_ca_topic_score_gemma":0.000009306943,"domain_scores_codex":[0.9980134,0.0001127351,0.0003835523,0.0006343753,0.000333196,0.0005227196],"domain_scores_gemma":[0.9974642,0.001628652,0.00009274344,0.0004015898,0.0002048582,0.0002079352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002220362,0.0008646316,0.001859541,0.000482579,0.0006186779,0.00001614567,0.03618083,1.895338e-7,0.001451698,0.4764062,0.06419371,0.4177037],"study_design_scores_gemma":[0.001701293,0.0001723558,0.03556401,0.0005424463,0.00004466086,0.00004824063,0.03103351,0.0009012371,0.006786084,0.9062281,0.01573874,0.001239295],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004329252,0.0001848978,0.9768354,0.001732742,0.00008688988,0.001137813,0.00005113593,0.0001366103,0.01550522],"genre_scores_gemma":[0.0294392,0.00001211364,0.9696923,0.00009428203,0.00008727988,0.0001513138,0.0000496873,0.00003752662,0.0004363029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4298219,"threshold_uncertainty_score":0.8185558,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2007834077","doi":"10.1080/00949650008812035","title":"Comparison of permutation methods for the partial correlation and partial mantel tests","year":2000,"lang":"en","type":"article","venue":"Journal of Statistical Computation and Simulation","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":286,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Mathematics; Partial correlation; Permutation (music); Statistics; Type I and type II errors; Resampling; Outlier; Population; Covariance matrix; Partial permutation; Applied mathematics; Correlation; Permutation matrix; Algorithm; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1232763641789153,"gpt":0.5152636500600378,"spread":0.3919872858811226,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001071778,0.0001029311,0.0003312912,0.00005848016,0.0001383063,0.00005263144,0.00004270913,0.00006478988,0.00009171708],"category_scores_gemma":[0.002523795,0.00007216714,0.00004030037,0.0000887338,0.0001380442,0.0001279492,0.00000841796,0.000133886,5.238703e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000014931,"about_ca_system_score_gemma":0.00002829982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002957775,"about_ca_topic_score_gemma":6.98094e-7,"domain_scores_codex":[0.99842,0.0003314608,0.0008188128,0.0001131437,0.0002104091,0.000106179],"domain_scores_gemma":[0.9827918,0.01633797,0.0004299274,0.00005033072,0.0003165872,0.00007333876],"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":[0.0003459965,0.00008353344,0.001002294,0.0000837098,0.00003261158,6.006861e-7,0.0008320191,0.0286525,0.00008717166,0.1348991,0.0000579553,0.8339224],"study_design_scores_gemma":[0.0005693849,0.0003101793,0.01599217,0.00003039875,0.0001321235,0.000007835818,0.00009600834,0.7131891,0.00005413506,0.2694462,0.0001147499,0.00005774118],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02287192,0.00009947098,0.9764588,0.0001452134,0.0001081496,0.00024778,0.00002199807,0.000007060024,0.00003957032],"genre_scores_gemma":[0.5259181,0.000009647528,0.4739974,0.0000143878,0.00004541826,0.000001974296,0.000004133538,0.000005144973,0.000003769337],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8338647,"threshold_uncertainty_score":0.3021401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112200626","doi":"10.1186/1471-2288-12-82","title":"Interpreting the concordance statistic of a logistic regression model: relation to the variance and odds ratio of a continuous explanatory variable","year":2012,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":271,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Statistics; Mathematics; Statistic; Logistic regression; Sample size determination; Normal distribution; Standard deviation; Sampling distribution; PRESS statistic; Monte Carlo method; Variable (mathematics); Cumulative distribution function; Regression analysis; Econometrics; Ancillary statistic; F-test; Probability density function","retraction":null,"screen_n_in":null,"score":{"opus":0.5031041758697814,"gpt":0.5613378965208847,"spread":0.05823372065110333,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04448416,0.0001270187,0.000541539,0.00009257286,0.0001541563,0.00001290939,0.0004636037,0.0001732981,0.0002117715],"category_scores_gemma":[0.4205032,0.00006629209,0.00003387572,0.0003535995,0.001094917,0.00005645094,0.0003310838,0.0006908388,0.000003281677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003675538,"about_ca_system_score_gemma":0.0004785519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001570599,"about_ca_topic_score_gemma":0.00004367694,"domain_scores_codex":[0.9826901,0.01475744,0.0007447417,0.0002650896,0.001018946,0.0005237159],"domain_scores_gemma":[0.8122408,0.1864792,0.0002477326,0.0004345629,0.0003563781,0.0002412646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002388986,0.0000548915,0.0006699442,0.0003294735,0.00001931947,0.000002092122,0.001986678,0.00001638171,0.00145908,0.9713193,0.001030092,0.02287387],"study_design_scores_gemma":[0.0003365251,0.0002693946,0.002442401,0.0006926664,0.00004027951,0.00002734845,0.0009263704,0.1354298,0.0004255315,0.8591267,0.0001813765,0.0001015939],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004900067,0.0004523951,0.992688,0.0005532404,0.0001655631,0.0004677585,0.00002850211,0.00001160747,0.0007328856],"genre_scores_gemma":[0.3056449,0.00004722084,0.6939827,0.0001065162,0.00006340764,0.00007649522,0.00000113376,0.00001118517,0.00006639726],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.376019,"threshold_uncertainty_score":0.9839046,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111418884","doi":"10.1111/j.1461-0248.2007.01047.x","title":"Data cloning: easy maximum likelihood estimation for complex ecological models using Bayesian Markov chain Monte Carlo methods","year":2007,"lang":"en","type":"article","venue":"Ecology Letters","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":269,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; University of Alberta","funders":"","keywords":"Markov chain Monte Carlo; Frequentist inference; Computer science; Bayesian probability; Algorithm; Likelihood function; Data mining; Bayesian inference; Machine learning; Statistics; Mathematics; Estimation theory; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1971455189971549,"gpt":0.4442246778074805,"spread":0.2470791588103257,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004528049,0.0003199471,0.0006512835,0.0001686291,0.0002980759,0.00005876756,0.000661328,0.0002987725,0.0001623821],"category_scores_gemma":[0.003164686,0.0002976646,0.0001108257,0.0001889648,0.0002330634,0.0002150517,0.0003074946,0.0003368555,0.000003882681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002058499,"about_ca_system_score_gemma":0.00006588268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003730048,"about_ca_topic_score_gemma":0.0001922608,"domain_scores_codex":[0.9967975,0.0006329273,0.0007726158,0.00071439,0.0001837258,0.00089886],"domain_scores_gemma":[0.9912397,0.007387988,0.0003215856,0.0007589567,0.00008974392,0.0002020658],"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":[0.001003749,0.001809767,0.005960266,0.0009693066,0.001108111,0.0005431237,0.001120019,0.002657473,0.03483361,0.3868732,0.02822324,0.5348982],"study_design_scores_gemma":[0.0004989768,0.0001062628,0.003455307,0.0000157217,0.0001291455,0.00003144376,0.00003828744,0.6269995,0.0000806746,0.3682418,0.0001514762,0.0002513857],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01236014,0.00001107854,0.9836483,0.002019328,0.0004839417,0.00084078,0.0001941481,0.0001265284,0.0003157466],"genre_scores_gemma":[0.05065823,0.000001593023,0.9466133,0.002394573,0.0001782318,0.00003672202,0.00005852994,0.00004783748,0.00001100388],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.624342,"threshold_uncertainty_score":0.9999475,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102720558","doi":"10.1109/tsmca.2007.902631","title":"A Novel Framework for Imputation of Missing Values in Databases","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics - Part A Systems and Humans","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":250,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Imputation (statistics); Computer science; Missing data; Data mining; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.112459478147945,"gpt":0.3843434643980513,"spread":0.2718839862501063,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000991954,0.0001878956,0.000476028,0.0001753368,0.000146608,0.00008418934,0.00006124335,0.0001179396,0.000005122708],"category_scores_gemma":[0.00006720837,0.0001677779,0.00005000808,0.0001118343,0.0001113818,0.00006395507,0.000001748761,0.0001496226,6.059377e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000264402,"about_ca_system_score_gemma":0.00001988895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003735959,"about_ca_topic_score_gemma":0.0001552259,"domain_scores_codex":[0.9984553,0.00008178578,0.0007225899,0.0002918798,0.0001975963,0.0002508695],"domain_scores_gemma":[0.9974059,0.001978587,0.000214699,0.0002064647,0.00008885692,0.0001055261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000105822,0.0003647966,0.0001694149,0.002675744,0.00008524462,0.00000657901,0.002956733,0.0001036522,0.001058279,0.9770838,0.00008238714,0.01530757],"study_design_scores_gemma":[0.009350824,0.003274152,0.006469107,0.02704157,0.001376164,0.0004684032,0.02793946,0.1168394,0.006755183,0.7907033,0.006417445,0.003364972],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02446815,0.0003323749,0.9735233,0.00001493622,0.0005139208,0.0006739192,0.0002120377,0.00002791541,0.0002334648],"genre_scores_gemma":[0.8547139,0.00004188409,0.1449035,0.00001061156,0.00009871778,0.00006290413,0.000003007392,0.00002598758,0.000139465],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8302457,"threshold_uncertainty_score":0.6841785,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2084292194","doi":"10.1002/sim.2731","title":"Developments in cluster randomized trials and <i>Statistics in Medicine</i>","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":248,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Royal Society","keywords":"Sample size determination; Medical statistics; Statistics; Cluster (spacecraft); Cluster analysis; Randomized controlled trial; Computer science; Population; Psychological intervention; Research design; Medicine; Econometrics; Data science; Mathematics; Surgery","retraction":null,"screen_n_in":null,"score":{"opus":0.08618382227126765,"gpt":0.4329159356107219,"spread":0.3467321133394543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01372133,0.0003807597,0.003001541,0.0005611365,0.00004190807,0.00001869381,0.0001940343,0.000169865,0.0003504821],"category_scores_gemma":[0.07601936,0.0002714275,0.00002504262,0.000527877,0.0009022726,0.00005169497,0.00007354252,0.000502421,0.000005772247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001355855,"about_ca_system_score_gemma":0.0001038868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001657652,"about_ca_topic_score_gemma":0.002642845,"domain_scores_codex":[0.9930974,0.002153914,0.003073928,0.000486027,0.0006442686,0.0005445118],"domain_scores_gemma":[0.9511223,0.04789391,0.0004818187,0.0002482797,0.0001302867,0.0001234177],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002809743,0.0001136997,0.003322797,0.0003514935,0.00002204618,0.0003077955,0.001001249,0.000001884221,0.00004421327,0.9458554,0.01991514,0.02625452],"study_design_scores_gemma":[0.08762998,0.00009352931,0.006297548,0.001018479,0.00009503439,0.00001247236,0.0002116868,0.002544212,0.00001093846,0.901451,0.0003681415,0.0002669675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008020336,0.0004212901,0.9891431,0.000768577,0.0004356507,0.001210886,0.0002415548,0.00002212751,0.006954772],"genre_scores_gemma":[0.02428333,0.0004587295,0.9740484,0.0005040952,0.0002070984,0.000128123,0.00009529198,0.00003975461,0.0002351789],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08482024,"threshold_uncertainty_score":0.9999738,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1753146223","doi":"10.1016/j.jclinepi.2015.08.015","title":"Sample size calculations for stepped wedge and cluster randomised trials: a unified approach","year":2015,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":241,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Medical Research Council; National Institute for Health and Care Research","keywords":"Sample size determination; Cluster (spacecraft); Cluster randomised controlled trial; Wedge (geometry); Computer science; Cluster size; Statistics; Randomized controlled trial; Data mining; Mathematics; Medicine; Physics; Surgery","retraction":null,"screen_n_in":null,"score":{"opus":0.733403766534936,"gpt":0.6107111935731112,"spread":0.1226925729618248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1179756,0.0001639351,0.003997862,0.00005987161,0.00005318651,0.00001425761,0.0001849823,0.0003631874,0.00003989553],"category_scores_gemma":[0.912959,0.0001006317,0.0006534101,0.0000779876,0.0002724078,0.00006443853,0.00004837345,0.0005022063,0.00000149007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000201836,"about_ca_system_score_gemma":0.0002484215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001001801,"about_ca_topic_score_gemma":0.000002196489,"domain_scores_codex":[0.9781433,0.01491063,0.006262129,0.0002373415,0.0001491229,0.0002974184],"domain_scores_gemma":[0.3224176,0.6730393,0.003318646,0.0002128763,0.0004981002,0.0005135356],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01655633,0.0004399724,0.00519573,0.0001461094,0.0004396684,0.000003723538,0.0001723638,0.0000239784,0.000006125187,0.9037919,0.02892268,0.04430145],"study_design_scores_gemma":[0.02908545,0.0006142338,0.002605092,0.00003611617,0.0003278318,0.00003611533,0.00007621702,0.01724204,0.000001222116,0.9471189,0.002746654,0.0001101098],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004597011,0.0001121948,0.9899049,0.003395446,0.0006841099,0.0006832602,0.00004164195,0.00001041513,0.000571013],"genre_scores_gemma":[0.01430229,0.00005615978,0.9835397,0.001072637,0.0009142085,0.00002595101,0.000002058382,0.00001541785,0.0000716005],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7949834,"threshold_uncertainty_score":0.9082297,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134699177","doi":"10.1093/swr/30.1.19","title":"Imputing Missing Data: A Comparison of Methods for Social Work Researchers","year":2006,"lang":"en","type":"article","venue":"Social Work Research","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":233,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Missing data; Imputation (statistics); Computer science; Multivariate statistics; Data science; Data mining; Statistics; Mathematics; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.709767389951839,"gpt":0.6728735764746552,"spread":0.03689381347718379,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01739691,0.0001679194,0.0006371747,0.0001841223,0.001932782,0.0001847889,0.0009015171,0.0002788512,0.0001375792],"category_scores_gemma":[0.01457327,0.0001598339,0.0001367211,0.002575706,0.0007946987,0.00008563828,0.0006069309,0.0009591087,0.0000074958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000156323,"about_ca_system_score_gemma":0.0002720875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008954451,"about_ca_topic_score_gemma":0.00001009453,"domain_scores_codex":[0.9938267,0.003051586,0.0007172997,0.0005048954,0.0008323635,0.00106714],"domain_scores_gemma":[0.9787772,0.01984306,0.0002022525,0.0004103935,0.0006585296,0.0001085795],"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":[0.0002166644,0.0002007453,0.0009489643,0.0002460101,0.00004443912,0.000001361999,0.001499939,1.421334e-7,0.0005071202,0.3310403,0.05360696,0.6116874],"study_design_scores_gemma":[0.0004607796,0.0000712418,0.002603365,0.000118361,0.00003363966,2.209226e-7,0.001424368,0.0008173402,0.0006623688,0.9843711,0.009234363,0.0002028773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002458666,0.0002756666,0.9871567,0.003405111,0.000118841,0.0006928932,0.0000640554,0.00005458584,0.005773446],"genre_scores_gemma":[0.0712928,0.000001579551,0.927154,0.000007636433,0.0009404573,0.00004502112,0.00003020106,0.00004893337,0.0004793478],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6533308,"threshold_uncertainty_score":0.9993666,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2576106406","doi":"10.1016/j.prevetmed.2017.01.006","title":"STARD-BLCM: Standards for the Reporting of Diagnostic accuracy studies that use Bayesian Latent Class Models","year":2017,"lang":"en","type":"article","venue":"Preventive Veterinary Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":219,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Prince Edward Island; McGill University Health Centre","funders":"Canada Excellence Research Chairs, Government of Canada; Canada Research Chairs; McGill University","keywords":"Latent class model; Bayesian probability; Computer science; Test (biology); Checklist; Diagnostic accuracy; Class (philosophy); Artificial intelligence; Machine learning; Medical physics; Data mining; Medicine; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.5081186604439791,"gpt":0.523944825892012,"spread":0.01582616544803284,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004556349,0.00025562,0.0008571414,0.00005282278,0.0004873281,0.0000480124,0.0004307038,0.00006161891,0.00006278851],"category_scores_gemma":[0.1878083,0.0001463664,0.0001495202,0.00005000342,0.0006852417,0.0003245788,0.0003207405,0.0001783545,3.405053e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007146387,"about_ca_system_score_gemma":0.00008111208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006718739,"about_ca_topic_score_gemma":0.00001110585,"domain_scores_codex":[0.9972106,0.000274165,0.001289447,0.0003483122,0.0005508378,0.0003265993],"domain_scores_gemma":[0.9642126,0.03131035,0.002787029,0.0009370632,0.0006624176,0.00009053696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002284674,0.0007874406,0.01597345,0.008522649,0.003846577,0.0009456762,0.0164511,0.00003052379,0.004187886,0.4988666,0.02092715,0.4271763],"study_design_scores_gemma":[0.001346365,0.001881264,0.01542769,0.003256943,0.000671911,0.0000574689,0.001213967,0.005131402,0.0006449284,0.9687988,0.001290402,0.0002789269],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05082878,0.0009937545,0.9440897,0.001763842,0.0005963931,0.001231046,0.0002321821,0.00003390615,0.0002303817],"genre_scores_gemma":[0.8458716,0.0009351369,0.1525969,0.00004537034,0.0001521797,0.0001987319,0.000003865999,0.00003062837,0.0001655798],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7950428,"threshold_uncertainty_score":0.8190331,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2064422634","doi":"10.1111/1467-9868.00279","title":"Local Influence for Incomplete Data Models","year":2001,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":215,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Likelihood function; Variety (cybernetics); Computer science; Maximum likelihood; Algorithm; Mathematics; Applied mathematics; Mathematical optimization; Data mining; Estimation theory; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2733802088295864,"gpt":0.4303219885770805,"spread":0.1569417797474941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006037517,0.0004734627,0.001376431,0.0000429608,0.0004911177,0.0001275951,0.002011577,0.0003447334,0.0004230121],"category_scores_gemma":[0.04361138,0.0003078752,0.0003472806,0.0003328528,0.002083725,0.0003684452,0.0008061747,0.001109523,0.000007096431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001723101,"about_ca_system_score_gemma":0.0003256297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006704885,"about_ca_topic_score_gemma":0.00002421322,"domain_scores_codex":[0.9937642,0.002000401,0.001826867,0.0006164888,0.000885968,0.000906085],"domain_scores_gemma":[0.9549423,0.04195755,0.0008423313,0.001010129,0.0007514936,0.0004962013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007615114,0.0001762476,0.0001283962,0.0002243214,0.0002728757,0.00005451672,0.0001842213,0.0003602472,0.00005819964,0.9183571,0.03220154,0.04722077],"study_design_scores_gemma":[0.0008652771,0.0005840177,0.001726505,0.00009408416,0.0004981722,0.0002615327,0.0002703915,0.08643481,0.00004325945,0.9019166,0.006952683,0.0003527038],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005256863,0.00009259087,0.9934683,0.001929672,0.0007211927,0.0004805001,0.002429421,0.00004112822,0.000311539],"genre_scores_gemma":[0.01282559,0.00005559974,0.9856125,0.0008949785,0.0003393656,0.00002229508,0.00002454355,0.0000632346,0.0001618783],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08607456,"threshold_uncertainty_score":0.9999374,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2976405568","doi":"10.1002/bimj.201900036","title":"Meta‐analysis of the difference of medians","year":2019,"lang":"en","type":"article","venue":"Biometrical Journal","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":212,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research","keywords":"Median; Statistics; Meta-analysis; Weighting; Sample size determination; Mathematics; Standard deviation; Variance (accounting); Pooled variance; Outcome (game theory); Mean difference; Confidence interval; Medicine; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1875207696650769,"gpt":0.3957336478869019,"spread":0.208212878221825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007449082,0.00009285814,0.0008144354,0.0008782531,0.00002954314,0.00001567546,0.0004210208,0.00006498714,0.001578215],"category_scores_gemma":[0.002394286,0.00004497437,0.0008026572,0.005613039,0.0001137988,0.00002314759,0.00007234326,0.0001972894,0.000003887698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001612196,"about_ca_system_score_gemma":0.0000440919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001254412,"about_ca_topic_score_gemma":0.000001595228,"domain_scores_codex":[0.9983467,0.0002530194,0.0005389601,0.0001057977,0.0006016648,0.0001537911],"domain_scores_gemma":[0.9950426,0.003947239,0.0004308718,0.0002866911,0.0001968655,0.00009574449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007369053,0.001102854,0.08921005,0.0003005619,0.1922477,0.0000113457,0.0005290436,0.000004864495,0.02321266,0.6319978,0.0004685642,0.06084091],"study_design_scores_gemma":[0.0004190344,0.0002786825,0.2273801,0.0000277191,0.1439584,0.00002418231,0.0000740484,0.001240927,0.009260841,0.6170264,0.00008619888,0.0002234924],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05974948,0.0004056976,0.9377939,0.000287014,0.0002479198,0.0001152154,0.00008723492,0.000006319138,0.001307229],"genre_scores_gemma":[0.7804399,0.00002842591,0.2193582,0.00003149405,0.00001966647,0.000001066931,2.185238e-7,0.000005522979,0.0001155215],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7206904,"threshold_uncertainty_score":0.9993345,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2345476363","doi":"10.1080/10705511.2016.1169188","title":"Impact of Misspecifications of the Latent Variance–Covariance and Residual Matrices on the Class Enumeration Accuracy of Growth Mixture Models","year":2016,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":208,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Latent class model; Covariance; Mathematics; Statistics; Covariance matrix; Mixture model; Residual; Population; Variance (accounting); Econometrics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.1216457498936597,"gpt":0.3807370481958413,"spread":0.2590912983021816,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007431554,0.0001588531,0.0002668392,0.00007681494,0.0002866631,0.00003002498,0.000280603,0.00008039437,0.00003540604],"category_scores_gemma":[0.0020088,0.00006693589,0.0001349038,0.0001951293,0.0001499729,0.0002776216,0.00006879178,0.0002266206,2.99634e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005746892,"about_ca_system_score_gemma":0.0001458697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002146717,"about_ca_topic_score_gemma":0.000002181703,"domain_scores_codex":[0.9980938,0.0003758193,0.0007778541,0.0001721343,0.000426999,0.0001534282],"domain_scores_gemma":[0.9958776,0.002230281,0.0009408267,0.0002961392,0.0006021028,0.00005304014],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004285903,0.00008126589,0.002326178,0.0001166515,0.0001483699,9.054846e-7,0.003329624,0.03814512,0.06883204,0.8769968,0.00004586963,0.009548571],"study_design_scores_gemma":[0.000277168,0.00009106339,0.006667753,0.000242931,0.0000388504,0.00001433013,0.00006995721,0.4044947,0.001107751,0.586934,3.354574e-8,0.00006140881],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4590732,0.00004107664,0.539537,0.001034758,0.00006131759,0.000155094,0.00007732849,0.000003871392,0.00001639032],"genre_scores_gemma":[0.8373953,0.00008475832,0.1624264,0.000003060406,0.00006686014,0.000004366121,0.000001522981,0.0000102793,0.000007490376],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3783221,"threshold_uncertainty_score":0.2729566,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2756610413","doi":"10.1002/sim.7532","title":"Measures of clustering and heterogeneity in multilevel <scp>P</scp>oisson regression analyses of rates/count data","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":206,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Prince Edward Island; University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Vetenskapsrådet; Heart and Stroke Foundation of Canada","keywords":"Statistics; Poisson regression; Multilevel model; Poisson distribution; Hazard ratio; Proportional hazards model; Count data; Random effects model; Regression analysis; Cluster analysis; Confidence interval; Mathematics; Odds ratio; Rate ratio; Linear regression; Hierarchical clustering; Cluster (spacecraft); Econometrics; Medicine; Meta-analysis; Computer science; Internal medicine; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.4042531616015181,"gpt":0.5285301629397802,"spread":0.1242770013382621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001815571,0.0001650661,0.0007155885,0.0001529229,0.00005702112,0.00001388402,0.000471199,0.00007978216,0.00001518714],"category_scores_gemma":[0.04550336,0.0001187697,0.00001130118,0.00007465965,0.0004974941,0.00007783343,0.0003283753,0.0001941781,2.506839e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002212856,"about_ca_system_score_gemma":0.00003839452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001104852,"about_ca_topic_score_gemma":0.001943266,"domain_scores_codex":[0.9981558,0.0001992642,0.0007453185,0.000304192,0.0003951457,0.0002002705],"domain_scores_gemma":[0.9938189,0.004472902,0.0005664403,0.0009211642,0.0001483414,0.00007221516],"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":[0.0002651171,0.0008051959,0.3212843,0.007428375,0.000271404,0.0004213884,0.006697524,0.0000246419,0.0588426,0.1684965,0.006407223,0.4290557],"study_design_scores_gemma":[0.00244776,0.0002816924,0.4138441,0.003740715,0.0001614488,0.000009468451,0.0006479456,0.08211432,0.007656442,0.4888956,0.00006126775,0.0001392065],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07328229,0.0002937511,0.9250822,0.00004048678,0.0001251376,0.0001808646,0.0006493783,0.000005246029,0.000340628],"genre_scores_gemma":[0.5082842,0.0002253154,0.491415,0.000008362808,0.00002591371,0.000003060212,0.00001799677,0.00001011757,0.00001004181],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4350019,"threshold_uncertainty_score":0.9625368,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1973761476","doi":"10.1111/j.1541-0420.2008.01058.x","title":"Joint Regression Analysis of Correlated Data Using Gaussian Copulas","year":2008,"lang":"en","type":"article","venue":"Biometrics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":204,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Univariate; Copula (linguistics); Mathematics; Joint probability distribution; Regression analysis; Statistics; Generalized linear model; Logistic regression; Inference; Marginal model; Gaussian; Estimating equations; Multivariate statistics; Econometrics; Computer science; Estimator; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.4876392554906313,"gpt":0.460364406222413,"spread":0.02727484926821827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005762238,0.0001268468,0.0005241347,0.002118256,0.00009061584,0.00001267645,0.0003298335,0.0001202859,0.0002206589],"category_scores_gemma":[0.006313239,0.00009508031,0.00008610574,0.01206245,0.0001246714,0.00007185654,0.0002147341,0.0001086833,0.000005219754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004266105,"about_ca_system_score_gemma":0.00005508879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001078177,"about_ca_topic_score_gemma":0.000002847751,"domain_scores_codex":[0.998472,0.0001216731,0.0005209513,0.0002851976,0.0004117307,0.0001884831],"domain_scores_gemma":[0.9975913,0.0009672343,0.0003221898,0.0008750946,0.0001416871,0.0001025052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002326592,0.002817118,0.321124,0.001116226,0.006350444,0.0007462059,0.001586786,0.0000367331,0.04123376,0.3344223,0.02802678,0.2623071],"study_design_scores_gemma":[0.00130152,0.0003055566,0.2814996,0.000388419,0.006327394,0.00008819049,0.0001726371,0.6189803,0.004816142,0.08411794,0.0009521362,0.001050131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.101901,0.0001497561,0.8968605,0.00001472746,0.000152347,0.00008272076,0.000291941,0.00003159835,0.0005154512],"genre_scores_gemma":[0.2951652,0.00006509631,0.7046301,0.00001005091,0.0000179822,5.318666e-7,0.00005223657,0.00001136068,0.00004740802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6189436,"threshold_uncertainty_score":0.7557993,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2051129785","doi":"10.2202/1557-4679.1171","title":"Inference in Epidemic Models without Likelihoods","year":2009,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":194,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences","keywords":"Inference; Markov chain Monte Carlo; Computer science; Monte Carlo method; Econometrics; Data mining; Statistics; Machine learning; Artificial intelligence; Mathematics; Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.0851133174261388,"gpt":0.4263022439375115,"spread":0.3411889265113727,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001226296,0.0001296116,0.000287851,0.0001481721,0.00002999584,0.00006646725,0.0007406874,0.00005343722,0.00005669001],"category_scores_gemma":[0.006663634,0.00008375521,0.00006200882,0.000120177,0.00008266373,0.000142122,0.00004430631,0.0003789454,0.000005624951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000886325,"about_ca_system_score_gemma":0.0001304996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001610988,"about_ca_topic_score_gemma":0.00001038434,"domain_scores_codex":[0.9981885,0.0001595734,0.0007963693,0.0001002827,0.0005801216,0.0001751611],"domain_scores_gemma":[0.9950377,0.003747134,0.0004931925,0.0001519517,0.0004967853,0.0000732765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001041475,0.0001110821,0.000662819,0.000005569557,0.00003681379,0.00008888093,0.0004747477,0.00008775895,0.0003531793,0.9036787,0.001267859,0.09312851],"study_design_scores_gemma":[0.0004115716,0.0001432799,0.002378416,0.0001618479,0.000025144,0.00008718728,0.00006866024,0.01662766,0.00023318,0.9796422,0.0001224016,0.00009844663],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009609842,0.00006506276,0.9856867,0.00299146,0.0004279912,0.00007423157,0.00004557928,0.000008715397,0.001090373],"genre_scores_gemma":[0.5708339,0.00009533219,0.4283881,0.000528735,0.0001285337,6.136532e-7,8.954589e-7,0.000005730827,0.00001817748],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5612241,"threshold_uncertainty_score":0.7977474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2093789600","doi":"10.2202/1557-4679.1195","title":"Estimating Multilevel Logistic Regression Models When the Number of Clusters is Low: A Comparison of Different Statistical Software Procedures","year":2010,"lang":"en","type":"article","venue":"The International Journal of Biostatistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":192,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Statistics; Multilevel model; Logistic regression; Computer science; Variance (accounting); Statistical model; Hierarchical database model; Software; Bayesian probability; Mathematics; Data mining; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.08904626714055525,"gpt":0.4328148997691603,"spread":0.343768632628605,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007497697,0.0002170142,0.0005340399,0.00007016154,0.00009271872,0.00006146158,0.0009849741,0.00009186198,0.0003030743],"category_scores_gemma":[0.01226664,0.0001092037,0.0001114641,0.00005331852,0.0005708982,0.00007882264,0.0001836745,0.0006190457,0.000002380501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000397644,"about_ca_system_score_gemma":0.0001780941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003660335,"about_ca_topic_score_gemma":0.00001734294,"domain_scores_codex":[0.9969822,0.0001775019,0.001359315,0.0001467665,0.001138204,0.0001959781],"domain_scores_gemma":[0.9874063,0.009350559,0.001667622,0.0002763694,0.001207521,0.00009169439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000701734,0.001021688,0.006128696,0.0006475479,0.0005548641,0.00004113012,0.007462082,0.000323556,0.002349978,0.8672666,0.0147226,0.09877952],"study_design_scores_gemma":[0.0004564673,0.00009320024,0.001470519,0.0005519483,0.0001464859,0.0001058039,0.0002748773,0.1871037,0.001841233,0.807835,0.000008280462,0.0001124557],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04192529,0.0000167329,0.9556105,0.0006282754,0.000872044,0.0001624071,0.0007053079,0.000007998092,0.00007152057],"genre_scores_gemma":[0.4914946,0.000005038513,0.5083044,0.00006559656,0.00009846888,0.000002235667,0.000004265558,0.00001300378,0.00001236436],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4495693,"threshold_uncertainty_score":0.9960535,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2016919144","doi":"10.1002/sim.2711","title":"Bayesian sensitivity analysis for unmeasured confounding in observational studies","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":184,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Confounding; Statistics; Markov chain Monte Carlo; Bayesian probability; Observational study; Econometrics; Logistic regression; Prior probability; Sample size determination; Sensitivity (control systems); Mathematics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2203225194206481,"gpt":0.4762013753441512,"spread":0.2558788559235031,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00294536,0.0001768332,0.0008009552,0.0003628785,0.00006371525,0.00001171296,0.00007116511,0.00006606093,0.00006737946],"category_scores_gemma":[0.01805763,0.0001502257,0.00003818837,0.0008277185,0.0002536201,0.00003833509,0.00002152377,0.0001678869,8.42037e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001611168,"about_ca_system_score_gemma":0.00005240186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003665136,"about_ca_topic_score_gemma":0.005885283,"domain_scores_codex":[0.9979748,0.000286481,0.0007590422,0.0002980111,0.0003753425,0.0003063596],"domain_scores_gemma":[0.98395,0.01535692,0.0001767653,0.0001837016,0.0002851692,0.00004741342],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003397561,0.00006637172,0.05800291,0.0001833353,0.0001140439,0.00005978397,0.0003161396,0.0000754658,0.0001250078,0.9362516,0.002197913,0.002573407],"study_design_scores_gemma":[0.0008069526,0.00005678313,0.1207594,0.0001381655,0.0002324105,0.000001663247,0.0003050424,0.03279477,0.00001823679,0.8446822,0.00006386801,0.0001405755],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00247425,0.00008674066,0.9955192,0.0005225808,0.0001829299,0.0003179997,0.000318397,0.00002004719,0.0005578473],"genre_scores_gemma":[0.3052233,0.00001311953,0.6943384,0.00008847916,0.0001301022,0.0000382837,0.000082087,0.00001172839,0.00007450845],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.302749,"threshold_uncertainty_score":0.9902137,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2013385108","doi":"10.1198/jasa.2010.tm09757","title":"Estimability and Likelihood Inference for Generalized Linear Mixed Models Using Data Cloning","year":2010,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":177,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Generalized linear mixed model; Estimator; Likelihood function; Binary data; Random effects model; Restricted maximum likelihood; Mathematics; Quasi-likelihood; Frequentist inference; Computer science; Markov chain Monte Carlo; Generalized linear model; Statistics; Poisson distribution; Bayesian probability; Bayesian inference; Binary number; Count data; Estimation theory","retraction":null,"screen_n_in":null,"score":{"opus":0.1142586750573369,"gpt":0.4378968439773239,"spread":0.323638168919987,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002460235,0.0001308378,0.0004918395,0.00003711367,0.0001553256,0.00007329533,0.0003794555,0.00005985384,0.00001226319],"category_scores_gemma":[0.04174762,0.00008836607,0.00006099053,0.0001538314,0.0001825215,0.000194869,0.0001673457,0.0004454409,2.679442e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001031624,"about_ca_system_score_gemma":0.0001873685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009889706,"about_ca_topic_score_gemma":0.00004815514,"domain_scores_codex":[0.9981643,0.0003530796,0.0006289851,0.0001923867,0.0004061957,0.0002550704],"domain_scores_gemma":[0.9877523,0.009871079,0.00142353,0.0003451265,0.000475589,0.0001324151],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000466481,0.0004993326,0.03255085,0.0002177962,0.0004026577,0.000007142893,0.0004213327,0.0001104514,0.01899024,0.7376258,0.002407801,0.2063001],"study_design_scores_gemma":[0.0003280684,0.00009047442,0.009567684,0.00002263306,0.0002218979,0.000009470713,0.0000256711,0.3187701,0.0001128862,0.6707269,0.00003273026,0.00009154668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2063443,0.000005200161,0.7924123,0.0004407422,0.0002585527,0.0001303252,0.0003891164,0.000007363211,0.00001210829],"genre_scores_gemma":[0.2886828,0.000005241827,0.7110628,0.0000762312,0.0001524334,0.000001831815,0.000003163435,0.00001140096,0.000004038407],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3186596,"threshold_uncertainty_score":0.9663242,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2791458756","doi":"10.2196/medinform.8960","title":"Characterizing and Managing Missing Structured Data in Electronic Health Records: Data Analysis","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":174,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; University of Pennsylvania; National Institutes of Health; Pennsylvania Department of Health","keywords":"Missing data; Imputation (statistics); Health records; Computer science; Data science; Electronic health record; Data mining; Health care; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.08677746776859628,"gpt":0.4334871571936644,"spread":0.3467096894250681,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003003762,0.0001791736,0.0005578861,0.0002496297,0.0001280447,0.0001286018,0.001092804,0.0001242004,0.000307475],"category_scores_gemma":[0.002248151,0.0001465887,0.00001929797,0.0007025594,0.0002070679,0.0005718438,0.0009949419,0.0004946358,0.000006599061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006598208,"about_ca_system_score_gemma":0.0002903678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006948588,"about_ca_topic_score_gemma":0.0004598227,"domain_scores_codex":[0.9973879,0.0001676557,0.001035693,0.0002822892,0.0005649219,0.000561522],"domain_scores_gemma":[0.9970308,0.0007620195,0.0003523854,0.001515546,0.00003874646,0.0003005067],"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":[0.00002254849,0.00005224134,0.001702011,0.0006350051,0.000181626,0.000007894357,0.003868597,1.443559e-8,0.000004908723,0.04932584,0.001740091,0.9424592],"study_design_scores_gemma":[0.000823977,0.0001861368,0.008353455,0.00069359,0.0002208136,0.00004722894,0.001864535,0.6203794,0.00001412577,0.361256,0.005674283,0.0004864906],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0144456,0.00007652992,0.9822434,0.00183154,0.0001066844,0.0002802384,0.0001696598,0.00006744883,0.0007789119],"genre_scores_gemma":[0.09233689,0.0002667306,0.9045528,0.002107236,0.0002148677,0.000007023798,0.0004837643,0.00001975283,0.0000109418],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9419727,"threshold_uncertainty_score":0.5977713,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2594511273","doi":"10.1186/s13063-017-1833-7","title":"Analysis of cluster randomised stepped wedge trials with repeated cross-sectional samples","year":2017,"lang":"en","type":"article","venue":"Trials","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":173,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Institute for Health and Care Research","keywords":"Econometrics; Random effects model; Treatment effect; Confounding; Medicine; Statistics; Psychological intervention; Computer science; Mathematics; Meta-analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.4153827757707162,"gpt":0.5217674289473853,"spread":0.1063846531766691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02345492,0.0002007812,0.002901545,0.0002100765,0.0002576619,0.0002740865,0.0003390893,0.0001449851,0.002304083],"category_scores_gemma":[0.1459933,0.0001217626,0.0006237791,0.0001954138,0.0002593285,0.0001052982,0.0000557214,0.000105453,0.000008098487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002286894,"about_ca_system_score_gemma":0.00008708993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001153256,"about_ca_topic_score_gemma":0.00004102137,"domain_scores_codex":[0.9941499,0.002612226,0.002266101,0.0003419956,0.000410592,0.0002192289],"domain_scores_gemma":[0.9606328,0.03535005,0.00271508,0.0008674841,0.0003380647,0.00009650511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.1762675,0.0009945845,0.3425099,0.0006494524,0.03308455,0.00003763489,0.0008602028,0.00005900639,0.01402386,0.3956002,0.003102774,0.03281031],"study_design_scores_gemma":[0.09708585,0.0003196353,0.4503928,0.000141793,0.01120081,0.000005066411,0.00003560259,0.001291478,0.01040129,0.4283404,0.0002002056,0.000585057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1709266,0.00002279231,0.8231403,0.0000800125,0.0003134012,0.001879869,0.000690725,0.00005056764,0.002895708],"genre_scores_gemma":[0.5983335,0.00001436151,0.4004378,0.00003325406,0.0002994923,0.0001512986,0.00003719777,0.00002784417,0.0006651584],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4274069,"threshold_uncertainty_score":0.9986079,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4321788752","doi":"10.1002/icd.2407","title":"Best practices for addressing missing data through multiple imputation","year":2023,"lang":"en","type":"article","venue":"Infant and Child Development","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":172,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal","funders":"","keywords":"Missing data; Imputation (statistics); Attrition; Computer science; Data collection; Psychology; Statistics; Data science; Data mining; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3445098573815719,"gpt":0.4706630859148572,"spread":0.1261532285332853,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005868015,0.0001146632,0.0001662865,0.00004111422,0.0003400276,0.0001330389,0.0001447489,0.00005062292,0.00001341581],"category_scores_gemma":[0.003764332,0.00009411074,0.00001287578,0.0001250712,0.00003388674,0.0002536043,0.0001653489,0.00007792373,0.00001041356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001257103,"about_ca_system_score_gemma":0.00007223892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002574111,"about_ca_topic_score_gemma":0.00002942839,"domain_scores_codex":[0.9990146,0.00003668037,0.0002930728,0.0002897304,0.0001574419,0.000208518],"domain_scores_gemma":[0.9974822,0.001972763,0.0002358915,0.0002069372,0.00005304238,0.00004919293],"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":[0.00005041896,0.00008162297,0.002030586,0.0007002896,0.00008229733,0.00001105519,0.004335376,9.619241e-7,0.0001566333,0.02681447,0.003090904,0.9626454],"study_design_scores_gemma":[0.001941044,0.0000984331,0.01700914,0.002142525,0.0001415251,0.0000568641,0.001723929,0.03822938,0.004483095,0.7648445,0.168396,0.0009336172],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01248933,0.000134449,0.983656,0.0009482667,0.0001705595,0.0003696744,0.00007702002,0.0001077286,0.002046896],"genre_scores_gemma":[0.02866899,0.00004819325,0.970825,0.0001085916,0.0000864493,0.0000292773,0.0001345669,0.00001616152,0.00008280452],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9617118,"threshold_uncertainty_score":0.4506529,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2018795457","doi":"10.3758/bf03206555","title":"Fitting distributions using maximum likelihood: Methods and packages","year":2004,"lang":"en","type":"article","venue":"Behavior Research Methods, Instruments, & Computers","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":167,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Quantile; Weibull distribution; Log-normal distribution; Gumbel distribution; Mathematics; Statistics; Estimator; Gaussian; Applied mathematics; Algorithm; Computer science; Extreme value theory","retraction":null,"screen_n_in":null,"score":{"opus":0.2979135059293795,"gpt":0.5754612622245866,"spread":0.2775477562952071,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009384359,0.0004046997,0.0006825542,0.0004141647,0.0009093642,0.0004082819,0.0005760688,0.0002209773,0.00008542623],"category_scores_gemma":[0.004383332,0.0003762539,0.0001551098,0.0009022621,0.0007380805,0.0002920377,0.0008895952,0.001091303,0.000008312872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004515249,"about_ca_system_score_gemma":0.0002590641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000370745,"about_ca_topic_score_gemma":0.000006836894,"domain_scores_codex":[0.9918287,0.004327651,0.0008429921,0.0008824877,0.0008065407,0.001311604],"domain_scores_gemma":[0.9933458,0.004722816,0.0002144374,0.0007532095,0.0003687621,0.0005949693],"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":[0.00001622185,0.0002878653,0.001388293,0.0001108093,0.00005151794,0.000048002,0.0003259556,7.786618e-7,0.01349107,0.08703791,0.00006595204,0.8971756],"study_design_scores_gemma":[0.001064096,0.0002534745,0.004327308,0.0003726254,0.000124987,0.000150361,0.0006023913,0.0009866249,0.02314474,0.9677634,0.0006976937,0.0005122625],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1353057,0.00008389358,0.8627749,0.000241575,0.0004376856,0.0007892911,0.00008460204,0.0001302473,0.0001520375],"genre_scores_gemma":[0.0120696,0.00005602202,0.9874889,0.00004223742,0.0001268222,0.0001266068,0.0000146473,0.00006322606,0.00001193519],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8966634,"threshold_uncertainty_score":0.9998689,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}