{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":82,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":82,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"12114726b7e6","filters":{"venue":"Biostatistics"}},"results":[{"id":"W2109802067","doi":"10.1093/biostatistics/1.4.441","title":"Monitoring surgical performance using risk-adjusted cumulative sum charts","year":2000,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":473,"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":"CUSUM; Context (archaeology); Computer science; Quality (philosophy); Surgical procedures; Statistics; Variable (mathematics); Medicine; Surgery; Mathematics","authors":[{"name":"Stefan H. Steiner","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1950489529157844,"gpt":0.4331799175942861,"spread":0.2381309646785017,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009734448,0.0003069532,0.0004409318,0.0001685926,0.000587786,0.0002299589,0.0005403832,0.0001236288,0.0009114675],"category_scores_gemma":[0.003030225,0.0002596203,0.00006804789,0.0008876569,0.0002611114,0.0005119849,0.0001026437,0.0004021311,0.0007091048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001437586,"about_ca_system_score_gemma":0.00007723223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006034223,"about_ca_topic_score_gemma":0.000002450477,"domain_scores_codex":[0.9958203,0.000225081,0.0009498041,0.0007124726,0.001656006,0.0006362683],"domain_scores_gemma":[0.9953519,0.002982126,0.0003467984,0.0005336165,0.0004752809,0.0003103526],"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":[0.0001933465,0.00008299267,0.1246063,0.00002314697,0.00002615634,0.0001936078,0.0005925929,0.01633832,0.0001194232,0.0009097556,0.000235199,0.8566791],"study_design_scores_gemma":[0.002473486,0.0004197203,0.2656032,0.0003207403,0.0001466847,0.0001418749,0.0009835425,0.6486214,0.00582102,0.04089521,0.03280447,0.001768543],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.90031,0.0002770767,0.09464999,0.00003536553,0.001097739,0.0002291535,0.0003791697,0.0001298709,0.00289166],"genre_scores_gemma":[0.9211321,0.0002548294,0.07640991,0.000009731538,0.0005614497,0.000006100987,0.000006006022,0.00003623377,0.001583593],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8549106,"threshold_uncertainty_score":0.9999856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165213086","doi":"10.1093/biostatistics/kxj007","title":"Hybrid hierarchical clustering with applications to microarray data","year":2005,"lang":"en","type":"article","venue":"Biostatistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":161,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Acadia University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Mitacs; National Institutes of Health; National Science Foundation","keywords":"Cluster analysis; Computer science; Hierarchical clustering; Data mining; Single-linkage clustering; Correlation clustering; Identification (biology); Cluster (spacecraft); CURE data clustering algorithm; Consensus clustering; Brown clustering; Artificial intelligence","authors":[{"name":"Hugh Chipman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02578921853755773,"gpt":0.2994561798657921,"spread":0.2736669613282344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005973092,0.00008799963,0.0000609722,0.00003041511,0.00006981022,0.000027438,0.0003082989,0.00003295869,0.00002007124],"category_scores_gemma":[0.00002560066,0.00007762099,0.000009257311,0.00006064141,0.00003873948,0.000002675653,0.0001645295,0.00004790463,0.00004737614],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001187303,"about_ca_system_score_gemma":0.00006442649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002938585,"about_ca_topic_score_gemma":0.00003976091,"domain_scores_codex":[0.9992809,0.00001702781,0.0001205136,0.0003488025,0.00009314002,0.0001396484],"domain_scores_gemma":[0.9990804,0.000007215912,0.000037008,0.0007135177,0.00004941837,0.000112463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001083089,0.00008227721,0.0002631565,0.00001729821,0.00002379758,0.000001367316,0.00003249607,0.0002731814,0.7777805,0.0007661826,0.09208328,0.1285682],"study_design_scores_gemma":[0.0002062909,0.00007529495,0.0007591657,0.000006925877,0.000009515743,0.00001393374,0.00001939482,0.0006842291,0.06105863,0.00002019804,0.9370084,0.0001380713],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007671525,0.0001306462,0.9893462,0.00111408,0.00004282963,0.0002483823,0.0004506383,0.00001705213,0.0009786349],"genre_scores_gemma":[0.7438335,0.00007185816,0.2510813,0.001329191,0.0005190701,0.00007685903,0.001591306,0.00002617219,0.001470643],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8449251,"threshold_uncertainty_score":0.3165292,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2171600077","doi":"10.1093/biostatistics/kxp050","title":"Confidence intervals that match Fisher's exact or Blaker's exact tests","year":2009,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Exact test; Exact statistics; Confidence interval; Mathematics; Statistics; Credible interval; Coverage probability; Robust confidence intervals; CDF-based nonparametric confidence interval; Tolerance interval; Binomial proportion confidence interval; Confidence region; Confidence distribution; Poisson distribution","authors":[{"name":"Michael P. Fay","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1830855602638954,"gpt":0.4425573308257128,"spread":0.2594717705618174,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004920517,0.0003940533,0.0006044026,0.00007523508,0.0001401022,0.0001223562,0.0003630824,0.0001613983,0.0007640657],"category_scores_gemma":[0.006250305,0.000306167,0.00008560779,0.0001854493,0.0001536617,0.000187144,0.00007040457,0.0002944036,0.0000775456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008638298,"about_ca_system_score_gemma":0.00008952928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000218622,"about_ca_topic_score_gemma":0.00004096565,"domain_scores_codex":[0.9976326,0.0001844881,0.0006074898,0.0005104932,0.0004657856,0.0005991904],"domain_scores_gemma":[0.9939487,0.00467184,0.000284061,0.0006191847,0.0001805356,0.0002957076],"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":[0.0002353725,0.0003938925,0.0001516617,0.0002312426,0.00006710109,0.0005492585,0.0005647254,0.00001066149,0.00127529,0.8230228,0.05403729,0.1194607],"study_design_scores_gemma":[0.0005668552,0.0006466093,0.002096925,0.0002269472,0.00009370653,0.00007195934,0.000147138,0.001730468,0.001516424,0.9883245,0.004053721,0.0005248055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00202844,0.00006117324,0.9925421,0.0005423069,0.0003180297,0.0004590328,0.0005971782,0.0002104862,0.003241223],"genre_scores_gemma":[0.2437182,0.00008812795,0.7529731,0.0008693583,0.0001122309,0.00001475567,0.00001762826,0.00004682553,0.002159714],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2416898,"threshold_uncertainty_score":0.999939,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2095702029","doi":"10.1093/biostatistics/kxn034","title":"Exact and efficient inference procedure for meta-analysis and its application to the analysis of independent 2 x 2 tables with all available data but without artificial continuity correction","year":2008,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Group for Research in Decision Analysis; Université du Québec à Montréal","funders":"U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases; National Heart, Lung, and Blood Institute","keywords":"Computer science; Inference; Simple (philosophy); Meta-analysis; Data mining; Continuity correction; Statistics; Econometrics; Mathematics; Artificial intelligence; Medicine; Internal medicine","authors":[{"name":"Lü Tian","is_ca":false},{"name":"Tianrun Cai","is_ca":false},{"name":"Michael Pfeffer","is_ca":false},{"name":"Nikita Piankov","is_ca":false},{"name":"Pierre‐Yves Crémieux","is_ca":true},{"name":"Lee‐Jen Wei","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5257705219849328,"gpt":0.5038448131116642,"spread":0.02192570887326861,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002498799,0.0002080494,0.001261611,0.0002023349,0.0001585785,0.00004811703,0.0002717632,0.0001005555,0.00008741433],"category_scores_gemma":[0.0294248,0.0001297805,0.0001147783,0.001019031,0.0001677355,0.00004084632,0.000167759,0.0001236644,0.000002634743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002184863,"about_ca_system_score_gemma":0.00007791476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001569429,"about_ca_topic_score_gemma":0.001457241,"domain_scores_codex":[0.9976062,0.0002873314,0.000802589,0.0006364569,0.0004554474,0.000212013],"domain_scores_gemma":[0.9816052,0.01643497,0.000588758,0.0007572257,0.0004879808,0.0001259067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00585093,0.004215956,0.05289887,0.002315576,0.61929,0.00002588331,0.005923623,0.01586412,0.006984565,0.2310822,0.01774308,0.03780521],"study_design_scores_gemma":[0.0005957601,0.0003711851,0.01682932,0.00001331504,0.4367052,0.000006964473,0.0002168361,0.5282235,0.003273784,0.01278426,0.0005151564,0.0004648072],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03421656,0.00009659882,0.9565046,0.0001265775,0.00005149193,0.001402277,0.007552418,0.00002246685,0.00002704406],"genre_scores_gemma":[0.6339833,0.00003515729,0.3654271,0.00006202205,0.00003115612,0.0001692241,0.0001005484,0.00001525095,0.0001762795],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5997667,"threshold_uncertainty_score":0.9787508,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163628937","doi":"10.1093/biostatistics/kxn044","title":"Bias in 2-part mixed models for longitudinal semicontinuous data","year":2009,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":111,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"University of Toronto","keywords":"Random effects model; Mixed model; Censoring (clinical trials); Statistics; Missing data; Econometrics; Monte Carlo method; Independence (probability theory); Mathematics; Variance (accounting); Computer science; Medicine; Meta-analysis","authors":[{"name":"Li Su","is_ca":false},{"name":"Brian D. M. Tom","is_ca":false},{"name":"Vernon T. Farewell","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4566833157976524,"gpt":0.4407942544428088,"spread":0.01588906135484358,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007977887,0.0001877539,0.00037048,0.00007179427,0.00005507528,0.00005550156,0.0004137697,0.00009467952,0.00004265748],"category_scores_gemma":[0.007580447,0.0001710379,0.00002951887,0.0001502087,0.00005818434,0.00009648411,0.00008323654,0.000133653,0.00000921945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003431637,"about_ca_system_score_gemma":0.00006801661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002114114,"about_ca_topic_score_gemma":0.00005999307,"domain_scores_codex":[0.9983932,0.00008715456,0.0005220519,0.0004222359,0.0001991537,0.000376187],"domain_scores_gemma":[0.9960042,0.002929587,0.0001392938,0.0007027226,0.0001222167,0.0001019484],"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":[0.00005006781,0.0001776888,0.0002464791,0.00006782379,0.00001195838,0.00002288795,0.00007992418,0.00001194805,0.00008663034,0.8890145,0.0532106,0.05701952],"study_design_scores_gemma":[0.0005546626,0.0001828231,0.001538809,0.00008078473,0.00004496294,0.000007156122,0.0000411092,0.1117658,0.0001420706,0.8832265,0.002177239,0.0002380662],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005491724,0.00007225349,0.9890261,0.0002393624,0.0002734569,0.0004047995,0.003155357,0.00005552687,0.001281451],"genre_scores_gemma":[0.1221642,0.00003111747,0.8771074,0.0001529486,0.000120828,0.00001272468,0.0001825246,0.00002017402,0.0002080825],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1166725,"threshold_uncertainty_score":0.907505,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163976725","doi":"10.1093/biostatistics/3.3.407","title":"A generalized mover-stayer model for panel data","year":2002,"lang":"en","type":"article","venue":"Biostatistics","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":65,"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":"National Heart, Lung, and Blood Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Markov model; Markov chain; Markov process; Mathematics; Applied mathematics; Markov property; Computer science; Maximum likelihood; Statistics; Econometrics","authors":[{"name":"Richard J. Cook","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3134674546004446,"gpt":0.3641039722663774,"spread":0.05063651766593286,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002166121,0.0001002672,0.0001186811,0.00001096835,0.0001469429,0.00002394441,0.0003053657,0.00005980056,0.001327488],"category_scores_gemma":[0.0002526281,0.00009337496,0.00001584376,0.00006390885,0.00008436686,0.0001410199,0.0001759432,0.00005704799,0.0004405794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006931081,"about_ca_system_score_gemma":0.00001088275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001667977,"about_ca_topic_score_gemma":0.0001323246,"domain_scores_codex":[0.9989792,0.00002565893,0.000207345,0.000267791,0.0001971046,0.0003229457],"domain_scores_gemma":[0.9991384,0.0001072459,0.00006916663,0.0005013571,0.000006966194,0.0001768523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000234706,0.0001006896,0.0003768255,0.0000394524,0.000006535756,0.000002978081,0.0006741227,0.002719121,0.0000939832,0.005770703,0.9514099,0.0387822],"study_design_scores_gemma":[0.000358184,0.0000340874,0.0005354428,0.000002889652,0.00001164514,0.000001343272,0.00001255505,0.8448123,0.00001329395,0.00385868,0.1502421,0.0001174043],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004907133,0.00009649763,0.9804803,0.004474774,0.0001631727,0.0005190211,0.005599692,0.00006707994,0.003692365],"genre_scores_gemma":[0.1434196,0.0002561361,0.8283409,0.0165745,0.0001324189,0.00002468703,0.00046132,0.00003886221,0.0107516],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8420932,"threshold_uncertainty_score":0.9995854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2795107686","doi":"10.1093/biostatistics/kxx036","title":"Lagged kernel machine regression for identifying time windows of susceptibility to exposures of complex mixtures","year":2017,"lang":"en","type":"article","venue":"Biostatistics","topic":"Air Quality Monitoring and Forecasting","field":"Environmental Science","cited_by":61,"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":"FAS Division of Science, Harvard University; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Environmental Health Sciences; National Science Foundation; National Institutes of Health; Harvard University","keywords":"Regression; Kernel (algebra); Kernel regression; Statistics; Computer science; Regression analysis; Econometrics; Machine learning; Artificial intelligence; Mathematics","authors":[{"name":"Shelley H. Liu","is_ca":false},{"name":"Jennifer F. Bobb","is_ca":false},{"name":"Kyu Ha Lee","is_ca":false},{"name":"Chris Gennings","is_ca":false},{"name":"Birgit Claus Henn","is_ca":false},{"name":"Christine Austin","is_ca":false},{"name":"Lourdes Schnaas","is_ca":false},{"name":"Martha María Téllez‐Rojo","is_ca":false},{"name":"Howard Hu","is_ca":true},{"name":"Robert O. Wright","is_ca":false},{"name":"Manish Arora","is_ca":false},{"name":"Brent A. Coull","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0819267791111343,"gpt":0.3532885025019369,"spread":0.2713617233908026,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004634504,0.0001070489,0.0002184893,0.00001976906,0.0002563297,0.00002518454,0.0003095239,0.00004891307,0.0002792428],"category_scores_gemma":[0.000967365,0.00009102438,0.00005062421,0.00003365464,0.0002351212,0.00004797248,0.0002259265,0.00004985552,0.00002316277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002997719,"about_ca_system_score_gemma":0.000006625641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007997832,"about_ca_topic_score_gemma":0.0001029277,"domain_scores_codex":[0.9990057,0.00004408893,0.0003294388,0.0002099698,0.0002418993,0.0001688853],"domain_scores_gemma":[0.9989153,0.000205764,0.0003660655,0.000407353,0.00003135597,0.00007419512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002181368,0.0001530748,0.239441,0.0002580462,0.00002337429,0.000002592126,0.001486867,0.0001905799,0.700949,0.0001319064,0.01136586,0.04577957],"study_design_scores_gemma":[0.0005722875,0.0003109756,0.8771849,0.0001698603,0.00003448311,0.000001357111,0.0001128695,0.005651112,0.1136006,0.0009168768,0.001222957,0.0002216507],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9740325,0.00002216832,0.02332681,0.0001306335,0.0002307464,0.0004039491,0.0009394572,0.00002174554,0.0008919482],"genre_scores_gemma":[0.9332465,0.000001783167,0.06618242,0.00001243827,0.0000456564,0.000004417031,0.00003117298,0.00001037672,0.0004652713],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6377439,"threshold_uncertainty_score":0.3711866,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4311239350","doi":"10.1093/biostatistics/kxac047","title":"Inference after latent variable estimation for single-cell RNA sequencing data","year":2022,"lang":"en","type":"article","venue":"Biostatistics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Simons Foundation","keywords":"Inference; Latent variable; Count data; Computer science; Type I and type II errors; Latent variable model; Context (archaeology); Poisson distribution; Statistical inference; Data set; Data mining; Algorithm; Latent class model; Statistics; Mathematics; Machine learning; Artificial intelligence; Biology","authors":[{"name":"Anna Neufeld","is_ca":false},{"name":"Lucy L. Gao","is_ca":true},{"name":"Joshua M Popp","is_ca":false},{"name":"Alexis Battle","is_ca":false},{"name":"Daniela Witten","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04935330434777099,"gpt":0.2670004868434502,"spread":0.2176471824956792,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001791741,0.0001291998,0.0001082989,0.00002836209,0.000168053,0.00004300407,0.00030641,0.00005860226,0.0000584708],"category_scores_gemma":[0.0001481624,0.0001424528,0.00002622752,0.00007280815,0.00003499511,0.000006185353,0.0002338471,0.00008220421,0.000003321527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005353442,"about_ca_system_score_gemma":0.0001610957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004502813,"about_ca_topic_score_gemma":0.00001450278,"domain_scores_codex":[0.9990435,0.00003894103,0.0002117882,0.0003532149,0.0001339556,0.0002185672],"domain_scores_gemma":[0.9992736,0.00004927474,0.00008170665,0.0004679295,0.00007213606,0.00005536532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002106583,0.0002353805,0.0004537728,0.0001399324,0.00002936932,0.000007646642,0.00008619254,0.003339101,0.9865986,0.0004581719,0.00444275,0.003998461],"study_design_scores_gemma":[0.004112302,0.003058633,0.0003267885,0.00006560612,0.0003283598,0.0000530171,0.0003071061,0.3567523,0.3967856,0.003111081,0.2334918,0.001607438],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08322625,0.0004521738,0.9095521,0.00006367347,0.0007244315,0.0004887124,0.004921126,0.00002782281,0.0005436917],"genre_scores_gemma":[0.8666774,0.00002473085,0.1284118,0.0002855922,0.0001071556,0.00007739298,0.00403861,0.00002738924,0.0003499439],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7834511,"threshold_uncertainty_score":0.5809055,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168126634","doi":"10.1093/biostatistics/kxs028","title":"Testing multiple variance components in linear mixed-effects models","year":2012,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":53,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Mathematics; Statistics; Test statistic; Null distribution; Estimator; Variance (accounting); Statistical hypothesis testing; Variance-based sensitivity analysis; One-way analysis of variance; Context (archaeology); Analysis of variance","authors":[{"name":"Reza Drikvandi","is_ca":false},{"name":"Geert Verbeke","is_ca":false},{"name":"Abbas Ali Khodadadi","is_ca":false},{"name":"Vahid Partovi Nia","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.178299709455031,"gpt":0.3677664905725939,"spread":0.1894667811175629,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005312062,0.0002083698,0.0003383442,0.00007372894,0.0000757434,0.00002493809,0.000160711,0.0001030407,0.0000189912],"category_scores_gemma":[0.01049407,0.0001942176,0.00002655234,0.0002678356,0.0000753455,0.0001327622,0.00008257385,0.0002148668,0.00004719768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005978022,"about_ca_system_score_gemma":0.00002534824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008504954,"about_ca_topic_score_gemma":0.000008914762,"domain_scores_codex":[0.9983423,0.000226049,0.0004207176,0.0002198458,0.0002436612,0.0005474719],"domain_scores_gemma":[0.9902945,0.009022687,0.0001368392,0.0002662193,0.00009222258,0.0001875591],"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":[0.00001989065,0.0004220424,0.0273788,0.0003736289,0.00001560142,0.00003789537,0.0003301798,0.00001312416,0.001867949,0.9342376,0.0008470415,0.03445625],"study_design_scores_gemma":[0.0006478045,0.00006324928,0.07043312,0.0002251893,0.00003383165,0.00001195125,0.00002932106,0.1716207,0.0006343875,0.7558316,0.0001303018,0.0003385839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01287924,0.00006442446,0.9848731,0.00001778725,0.0006567786,0.0003011605,0.0001862077,0.00007434246,0.0009470058],"genre_scores_gemma":[0.4166419,0.00000269168,0.5831574,0.00004489686,0.00009047231,0.00001618669,0.000008368973,0.00002126139,0.00001688979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4037626,"threshold_uncertainty_score":0.9978409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2123633327","doi":"10.1093/biostatistics/kxm025","title":"Regression analysis of multivariate panel count data","year":2007,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":47,"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":"Multivariate statistics; Covariate; Statistics; Count data; Regression analysis; Econometrics; Regression; Marginal model; Event (particle physics); Multivariate analysis; Reliability (semiconductor); Mathematics","authors":[{"name":"Xin He","is_ca":false},{"name":"X. Tong","is_ca":false},{"name":"Jianguo Sun","is_ca":false},{"name":"Richard J. Cook","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3188325730028094,"gpt":0.4725805692580174,"spread":0.153747996255208,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001411691,0.0001380857,0.0004258426,0.0001695191,0.00005034887,0.00001561154,0.0003670451,0.00008335063,0.0002224386],"category_scores_gemma":[0.008204971,0.0001044327,0.00004140738,0.0005940326,0.0001260017,0.00003487663,0.0001835329,0.0001052586,0.000006500243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002441994,"about_ca_system_score_gemma":0.00003626519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001298401,"about_ca_topic_score_gemma":0.00007489056,"domain_scores_codex":[0.9984717,0.00008550464,0.0005791015,0.0002799476,0.0003478054,0.0002359646],"domain_scores_gemma":[0.9937393,0.004771648,0.0003021256,0.000877086,0.0002067234,0.0001031339],"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":[0.00006366891,0.00020048,0.002730574,0.0001128284,0.0004855104,0.00003421151,0.0002775456,0.000002541258,0.002391095,0.9308612,0.003458705,0.05938159],"study_design_scores_gemma":[0.001202841,0.0002842576,0.2794641,0.0002682072,0.006190666,0.000006671907,0.0005079592,0.2284486,0.004554555,0.468572,0.009599261,0.0009009034],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007160999,0.00003293001,0.9882907,0.00002467947,0.0001543597,0.0001026449,0.002661506,0.00002944832,0.001542703],"genre_scores_gemma":[0.2280145,0.00001714065,0.7715826,0.00003617052,0.00003009008,7.70199e-7,0.0001901596,0.00001245505,0.0001161393],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4622892,"threshold_uncertainty_score":0.982271,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121713677","doi":"10.1093/biostatistics/kxq067","title":"Functional mixture regression","year":2010,"lang":"en","type":"article","venue":"Biostatistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Regression; Functional principal component analysis; Regression analysis; Computer science; Principal component analysis; Functional data analysis; Scalar (mathematics); Linear regression; Artificial intelligence; Machine learning; Econometrics; Mathematics; Statistics","authors":[{"name":"Fang Yao","is_ca":true},{"name":"Yuejiao Fu","is_ca":true},{"name":"Thomas C. M. Lee","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0154008044571233,"gpt":0.2671184447815994,"spread":0.2517176403244761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001739725,0.00009409017,0.00008218046,0.00004184342,0.00009947536,0.00007572865,0.0002893593,0.00009242862,0.00007460444],"category_scores_gemma":[0.0001159734,0.00007051943,0.00002772192,0.0001309942,0.00003797326,0.0001056461,0.0000884097,0.0002343689,0.00006440125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005637859,"about_ca_system_score_gemma":0.00005229668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002801586,"about_ca_topic_score_gemma":0.000005601333,"domain_scores_codex":[0.9993039,0.00003359988,0.0001102708,0.0002232735,0.0001744096,0.0001545423],"domain_scores_gemma":[0.9992948,0.0001043286,0.00004901352,0.0003772414,0.00007813203,0.00009644566],"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":[0.000002010858,0.00001664168,0.00006017929,0.000003951957,0.000002671268,0.00001245265,0.00004623274,2.203669e-7,0.0119732,0.7751918,0.05033075,0.1623598],"study_design_scores_gemma":[0.0006090283,0.0001017392,0.01710529,0.00002779689,0.00001625632,0.0001754477,0.000004737904,0.03474798,0.01722231,0.7057236,0.2236838,0.0005820002],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003698563,0.00003529653,0.9934241,0.00101538,0.001928512,0.00004919361,0.00001630867,0.00008957952,0.003071817],"genre_scores_gemma":[0.04736201,0.000006267626,0.9507889,0.0004961089,0.0002177587,0.000002920787,0.000009022011,0.000006441692,0.001110555],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.173353,"threshold_uncertainty_score":0.2875699,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128514707","doi":"10.1093/biostatistics/kxm029","title":"Joint inference for nonlinear mixed-effects models and time to event at the presence of missing data","year":2007,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":46,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health","keywords":"Covariate; Inference; Missing data; Event (particle physics); Computer science; Econometrics; Proportional hazards model; Mixed model; Process (computing); Statistical inference; Longitudinal data; Counting process; Event data; Statistics; Data mining; Artificial intelligence; Mathematics; Machine learning","authors":[{"name":"Lang Wu","is_ca":true},{"name":"X. Joan Hu","is_ca":true},{"name":"Huaiqing Wu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1306562297644288,"gpt":0.4138406325020826,"spread":0.2831844027376538,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001338082,0.000155503,0.0003030476,0.00004137023,0.0001222842,0.00003514384,0.0003118467,0.00006136353,0.00003677754],"category_scores_gemma":[0.01282862,0.0001093508,0.00002274377,0.000112812,0.0001644152,0.00005629981,0.0004352104,0.000082117,0.00001052047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002709963,"about_ca_system_score_gemma":0.00005084425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001693537,"about_ca_topic_score_gemma":0.00001822814,"domain_scores_codex":[0.9986217,0.00009015496,0.0004439459,0.0003069498,0.0002491419,0.0002880911],"domain_scores_gemma":[0.9863611,0.01252114,0.0001696667,0.0006359782,0.0001646577,0.0001474357],"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":[0.0001190297,0.0001391736,0.00004301988,0.0009189491,0.00004656073,0.0000168265,0.0004684517,0.000008921218,0.005377179,0.5740626,0.01663039,0.4021689],"study_design_scores_gemma":[0.0002954506,0.0002471077,0.0007051636,0.0002789236,0.000102276,0.00001056954,0.0000346762,0.198341,0.00899775,0.7896129,0.001148524,0.0002256685],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001324204,0.00007275902,0.9952772,0.0002320875,0.00009222819,0.0006676343,0.002104554,0.0000178778,0.000211471],"genre_scores_gemma":[0.01659848,0.000008978365,0.9830117,0.00009788621,0.0000524097,0.000009973479,0.0000440026,0.00001996587,0.0001566152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4019432,"threshold_uncertainty_score":0.9954867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135189416","doi":"10.1093/biostatistics/kxg041","title":"Analysis of longitudinal marginal structural models","year":2004,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":45,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Estimator; Censoring (clinical trials); Inverse probability; Marginal structural model; Confounding; Statistics; Econometrics; Mathematics; Computer science","authors":[{"name":"Jennifer Bryan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1574998226005316,"gpt":0.4178060521425315,"spread":0.260306229542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001027893,0.0001453607,0.0003597991,0.0002247385,0.00004083445,0.00001301055,0.0001613193,0.00006445198,0.00009019829],"category_scores_gemma":[0.0002385999,0.0001317709,0.00008715982,0.0005319308,0.0001304231,0.0001102193,0.00004962579,0.00009758246,0.000002401308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008435136,"about_ca_system_score_gemma":0.00004838907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006711926,"about_ca_topic_score_gemma":0.00008406286,"domain_scores_codex":[0.9990025,0.00001818276,0.0003495504,0.0001818103,0.0002514008,0.000196586],"domain_scores_gemma":[0.9990315,0.0002094441,0.0002009848,0.0003140497,0.0001842382,0.00005973114],"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":[0.00001583814,0.0000306353,0.001616385,0.0000389739,0.0002680783,0.0000157791,0.0001641005,0.002741324,0.0003888974,0.993771,0.00008819301,0.0008608267],"study_design_scores_gemma":[0.000174856,0.00008495282,0.005529739,0.00002147775,0.0006771577,0.000005050642,0.00004407864,0.008599961,0.003125367,0.9815626,0.000008937463,0.0001658609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1217793,0.00002526735,0.8768933,0.00002940401,0.00003493088,0.0001059637,0.0003523798,0.0001051602,0.0006742587],"genre_scores_gemma":[0.6052962,0.000008639602,0.3946113,0.00001009013,0.00001044963,0.000003206768,0.00002813487,0.000009938022,0.00002200698],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4835169,"threshold_uncertainty_score":0.5373463,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2890289581","doi":"10.1093/biostatistics/kxy041","title":"Pointless spatial modeling","year":2018,"lang":"en","type":"article","venue":"Biostatistics","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Cancer Institute; Medical Research Council; National Institutes of Health; Applied Molecular Biosciences Unit; Kurdistan University Of Medical Sciences; Mekelle University; Đại học Quốc gia Hà Nội; University of Peradeniya; Addis Ababa University; University of Gondar; University of Tabriz; Universidade Federal de Sergipe; Universitatea de Medicină şi Farmacie \"Carol Davila\" Bucureşti; Universidade do Porto; Bahir Dar University; Alexandria University; Bill and Melinda Gates Foundation; Karolinska Institutet; Tabriz University of Medical Sciences; Shahroud University of Medical Sciences; Babol University of Medical Sciences; Tehran University of Medical Sciences and Health Services; Mazandaran University of Medical Sciences; Universität Bielefeld; Aksum University; Public Health Foundation of India; Kaiser Permanente; Australian Catholic University; Mansoura University; Hamadan University of Medical Sciences; University of Oxford; Universidad Autónoma de Sinaloa; Maragheh University of Medical Sciences; Universidad Nacional Autónoma de México; Indian Institute of Technology Delhi; Istituto di Ricerche Farmacologiche Mario Negri - IRCCS; University of Southampton; University of Washington; A.T. Still University; Simon Fraser University; University of Ottawa; U.S. Department of Veterans Affairs","keywords":"Computer science; Laplace's method; Bayesian inference; Smoothing; Random field; Markov random field; Bayesian probability; Variable-order Bayesian network; Algorithm; Theoretical computer science; Applied mathematics; Mathematics; Artificial intelligence; Statistics","authors":[{"name":"Katie Wilson","is_ca":false},{"name":"Jon Wakefield","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05952637799047564,"gpt":0.2377130916369566,"spread":0.1781867136464809,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001425483,0.00008946798,0.0001932344,0.0001030018,0.0001004089,0.00005308544,0.0001491525,0.00005114554,0.001439849],"category_scores_gemma":[0.0001394982,0.0001001582,0.00004228321,0.0001428969,0.00005767101,0.00006148244,0.00004534009,0.00005219608,0.003090015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002347821,"about_ca_system_score_gemma":0.000009644209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00331803,"about_ca_topic_score_gemma":0.0004331828,"domain_scores_codex":[0.9992136,0.000005954452,0.0003346212,0.0002372238,0.00002869057,0.0001798603],"domain_scores_gemma":[0.9995153,0.00002355939,0.0001064232,0.0002414844,0.00005025012,0.00006298506],"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":[0.00004988215,0.000126001,0.03326787,0.00003897327,0.0001742246,0.00001954066,0.00078255,0.0003165294,0.0001052691,0.9321737,0.01356819,0.01937723],"study_design_scores_gemma":[0.0002604956,0.0001033486,0.002926896,0.000008436476,0.00001958268,0.000002872348,0.00004595927,0.8805181,0.0001441999,0.08343822,0.0321955,0.000336332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02097716,0.0001485243,0.9621801,0.0001931819,0.0005563706,0.00005241015,0.00168974,0.00003346555,0.01416903],"genre_scores_gemma":[0.9884331,0.0000446852,0.01022885,0.0002681406,0.0004876775,0.000002551046,0.0001612192,0.00001410006,0.0003596727],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9674559,"threshold_uncertainty_score":0.999473,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159353629","doi":"10.1093/biostatistics/5.1.129","title":"Tests for multivariate recurrent events in the presence of a terminal event","year":2004,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":34,"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; Canadian Institutes of Health Research","keywords":"Univariate; Multivariate statistics; Medicine; Event (particle physics); Inference; Statistical hypothesis testing; Statistics; Breast cancer; Multivariate analysis; Econometrics; Cancer; Computer science; Internal medicine; Mathematics; Artificial intelligence","authors":[{"name":"Bingshu E. Chen","is_ca":true},{"name":"Richard J. Cook","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5050057957657591,"gpt":0.5862204328749212,"spread":0.0812146371091621,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002645954,0.0001557146,0.0003967787,0.00005187522,0.00004255592,0.000008423995,0.0003850931,0.00009030328,0.00001583023],"category_scores_gemma":[0.1339389,0.0001068176,0.00008702905,0.0001835357,0.0001263127,0.00002504631,0.00006323808,0.0001685011,0.000005104196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005577249,"about_ca_system_score_gemma":0.0000985982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003277063,"about_ca_topic_score_gemma":0.00003337533,"domain_scores_codex":[0.9977071,0.0004412963,0.0009458718,0.000252576,0.0003778317,0.0002753668],"domain_scores_gemma":[0.9521536,0.04693279,0.0003486928,0.0003764613,0.0001312649,0.00005718036],"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":[0.0004986702,0.002017998,0.0009090003,0.0008353828,0.00005502657,0.00003661433,0.00160107,0.00003846359,0.0005048243,0.9513928,0.001569173,0.04054099],"study_design_scores_gemma":[0.001818121,0.0004604106,0.0107792,0.0003091326,0.00006568938,0.000006183954,0.00008097186,0.0004629865,0.0004551825,0.9852738,0.0001566375,0.0001316504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02305116,0.0000307359,0.9727254,0.0004742497,0.0006638001,0.001785846,0.001158879,0.00002014103,0.00008982123],"genre_scores_gemma":[0.3194219,0.000009469637,0.6803173,0.00004824804,0.00007419078,0.00009558794,0.000003803801,0.00001413884,0.00001539909],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2963707,"threshold_uncertainty_score":0.8733563,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156745572","doi":"10.1093/biostatistics/kxp041","title":"Bayesian random-effects threshold regression with application to survival data with nonproportional hazards","year":2009,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Institute for Occupational Safety and Health","keywords":"Bayesian probability; Regression; Statistics; Proportional hazards model; Regression analysis; Econometrics; Computer science; Mathematics","authors":[{"name":"Michael L. Pennell","is_ca":false},{"name":"G. À. Whitmore","is_ca":true},{"name":"Mei‐Ling Ting Lee","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03665299856253803,"gpt":0.3592125109534628,"spread":0.3225595123909248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002727573,0.0002463153,0.0002962121,0.00006769978,0.000233345,0.00007715284,0.0003533108,0.00006538976,0.00007064237],"category_scores_gemma":[0.0006173083,0.000172072,0.00001881063,0.0004317725,0.000101461,0.0001115564,0.00005185499,0.0001446066,0.000048326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006270405,"about_ca_system_score_gemma":0.0001356563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007863588,"about_ca_topic_score_gemma":0.00003494596,"domain_scores_codex":[0.9981394,0.00004472166,0.00036912,0.0005213807,0.0006439452,0.000281439],"domain_scores_gemma":[0.9977766,0.0005458815,0.0001949787,0.0009370524,0.0002781688,0.0002673256],"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":[0.0003944169,0.0004074502,0.0002869928,0.00006390447,0.00003244472,0.00001968915,0.00004500007,0.00007757792,0.0003680368,0.9208125,0.0576074,0.01988452],"study_design_scores_gemma":[0.01276666,0.002385586,0.0642473,0.0008637654,0.0008144298,0.0001663009,0.0002395336,0.4855921,0.002916364,0.3939749,0.03344145,0.002591595],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006965548,0.000009153455,0.9918276,0.003337659,0.00004005581,0.001072329,0.001645013,0.0001726904,0.001198934],"genre_scores_gemma":[0.6561767,0.000004248261,0.340302,0.0007899307,0.00006486179,0.0001005046,0.002390127,0.00002650134,0.0001451795],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6554801,"threshold_uncertainty_score":0.7016894,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138916823","doi":"10.1093/biostatistics/kxs024","title":"Targeted maximum likelihood estimation for marginal time-dependent treatment effects under density misspecification","year":2012,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":29,"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":"Canadian Institutes of Health Research; McGill University","keywords":"Estimator; Statistics; Generalized estimating equation; Mathematics; Econometrics; Delta method; Parametric statistics; Confounding; Random effects model; Variance (accounting); Computer science; Medicine; Meta-analysis","authors":[{"name":"Mireille E. Schnitzer","is_ca":true},{"name":"Erica E. M. Moodie","is_ca":true},{"name":"Robert W. Platt","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08074750171030778,"gpt":0.3757055195828782,"spread":0.2949580178725704,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002580829,0.000247597,0.0002665504,0.00007567987,0.0001250582,0.00003331451,0.00009523938,0.000125664,0.00005983941],"category_scores_gemma":[0.0006104006,0.0002257658,0.00005491481,0.00008503012,0.00004650179,0.0001603592,0.00002586997,0.00007038184,0.0001260711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004425945,"about_ca_system_score_gemma":0.00004541226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009375449,"about_ca_topic_score_gemma":0.000005874192,"domain_scores_codex":[0.9987628,0.00007339808,0.0003064167,0.0002249704,0.0002157987,0.000416625],"domain_scores_gemma":[0.9980484,0.001076199,0.0002148015,0.0003397797,0.0001699495,0.0001509019],"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":[0.0003701899,0.002555545,0.001108853,0.0008228617,0.0003050932,0.0000145811,0.001214841,0.00005080237,0.09557272,0.6640241,0.02415452,0.209806],"study_design_scores_gemma":[0.0008218311,0.0005189106,0.002617773,0.00005193333,0.0002369252,0.00001597575,0.00005019232,0.004841069,0.1811121,0.8083027,0.001010154,0.0004204303],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01036624,0.00008969312,0.9873368,0.000111751,0.0001842053,0.001165623,0.0001745657,0.000354675,0.000216422],"genre_scores_gemma":[0.3552912,0.00002065643,0.6438456,0.00004524639,0.0001142487,0.0001522264,0.0002343792,0.0000440663,0.0002524536],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3449249,"threshold_uncertainty_score":0.9206463,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105004777","doi":"10.1093/biostatistics/kxr005","title":"Weighted scores method for regression models with dependent data","year":2011,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Univariate; Copula (linguistics); Statistics; Mathematics; Weighting; Multivariate statistics; Negative binomial distribution; Regression; Regression analysis; Inference; Binomial regression; Econometrics; Computer science; Poisson distribution; Artificial intelligence; Medicine","authors":[{"name":"Aristidis K. Nikoloulopoulos","is_ca":false},{"name":"Harry Joe","is_ca":true},{"name":"N. Rao Chaganty","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2664853473612795,"gpt":0.4255545416501072,"spread":0.1590691942888277,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006130314,0.0002237742,0.0003388656,0.00006082726,0.000120285,0.00003913417,0.0005022145,0.00009562854,0.0001455474],"category_scores_gemma":[0.001235682,0.0001462109,0.00002301418,0.0001100831,0.00009172683,0.000128805,0.0001693007,0.0001204214,0.000006629196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002146587,"about_ca_system_score_gemma":0.00008749293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007115286,"about_ca_topic_score_gemma":0.00005654832,"domain_scores_codex":[0.9984241,0.000147473,0.0003578548,0.0004683329,0.0002830009,0.0003192355],"domain_scores_gemma":[0.9961622,0.002380366,0.0001988314,0.0009048082,0.0002110094,0.0001427924],"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":[0.0001986099,0.0001170282,0.00007817786,0.0001542515,0.00004533664,0.00002599394,0.0002361547,1.439143e-7,0.00007008245,0.9206553,0.005335905,0.07308307],"study_design_scores_gemma":[0.0005098063,0.0002425832,0.000127167,0.0001292735,0.0001643359,0.00001757399,0.00006779291,0.08027188,0.001484638,0.9165183,0.0002205286,0.0002460988],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006037907,0.0000390438,0.9945168,0.00003486695,0.0001333997,0.000468645,0.002832598,0.00007821245,0.001836066],"genre_scores_gemma":[0.003652023,0.0000197173,0.995856,0.00006685209,0.00005998012,0.00003839084,0.0001274502,0.00004625109,0.0001333646],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08027174,"threshold_uncertainty_score":0.5962307,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170016983","doi":"10.1093/biostatistics/kxm054","title":"A simulation-based marginal method for longitudinal data with dropout and mismeasured covariates","year":2008,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":24,"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":"National Heart, Lung, and Blood Institute","keywords":"Covariate; Missing data; Estimator; Observational error; Statistics; Computer science; Econometrics; Dropout (neural networks); Framingham Heart Study; Data set; Inference; Mathematics; Artificial intelligence; Machine learning","authors":[{"name":"Grace Y. Yi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1887898403860769,"gpt":0.4263550214561171,"spread":0.2375651810700403,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005483729,0.0002050945,0.0003417351,0.00005711436,0.0002303667,0.00004988938,0.0002034247,0.00007358916,0.00006045162],"category_scores_gemma":[0.008088784,0.0001616056,0.00001933523,0.0001267281,0.0001980894,0.00006228821,0.00004964814,0.00009957419,0.000002605718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002151031,"about_ca_system_score_gemma":0.0001805865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003869481,"about_ca_topic_score_gemma":0.00002371732,"domain_scores_codex":[0.9985952,0.0001305595,0.0003033619,0.0004372695,0.0002694435,0.000264201],"domain_scores_gemma":[0.9835678,0.01537905,0.0001502616,0.0004938663,0.0002797989,0.0001292534],"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":[0.0009673245,0.000362369,0.01466574,0.0008518093,0.0002132903,0.0001709617,0.0002865019,0.0003239131,0.0001597521,0.9422089,0.004798123,0.03499129],"study_design_scores_gemma":[0.001219217,0.0002894839,0.004300213,0.00006030785,0.0001915934,0.00002322752,0.00001997701,0.7749585,0.0000782042,0.2177952,0.0007827732,0.0002813558],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002324989,0.00003332461,0.996365,0.0001666736,0.00005753211,0.0004080248,0.00261963,0.00005275391,0.00006452938],"genre_scores_gemma":[0.09244496,0.000003451008,0.9071747,0.00007630724,0.00006414667,0.00001871261,0.0001473077,0.00003072499,0.00003970124],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7746345,"threshold_uncertainty_score":0.9683615,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3196024289","doi":"10.1093/biostatistics/kxab032","title":"Predicting the onset of breast cancer using mammogram imaging data with irregular boundary","year":2021,"lang":"en","type":"article","venue":"Biostatistics","topic":"AI in cancer detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Breast Cancer Research Foundation","keywords":"Breast cancer; Computer science; Artificial intelligence; Mammography; Pattern recognition (psychology); Benchmark (surveying); Breast cancer screening; Boundary (topology); Machine learning; Medicine; Cancer; Mathematics","authors":[{"name":"Shu Jiang","is_ca":false},{"name":"Jiguo Cao","is_ca":true},{"name":"Graham A. Colditz","is_ca":false},{"name":"Bernard Rosner","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02508658907445413,"gpt":0.2886221632118421,"spread":0.2635355741373879,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002201984,0.0001040767,0.0001133394,0.00003252683,0.0002174131,0.0001790706,0.0007120217,0.00002167011,0.00001312965],"category_scores_gemma":[0.00004686746,0.00007951217,0.000014179,0.0004554068,0.0001783228,0.0003030362,0.0005372582,0.0001231888,8.66026e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008553967,"about_ca_system_score_gemma":0.0006232313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006501518,"about_ca_topic_score_gemma":0.0003008989,"domain_scores_codex":[0.9988573,0.0000744207,0.0001903648,0.0003482807,0.0003293031,0.000200387],"domain_scores_gemma":[0.9983574,0.0001314156,0.0001667511,0.001079615,0.0002235714,0.00004127465],"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":[0.00007553364,0.0001575265,0.2306684,0.0003643109,0.0003100655,0.0005152583,0.001950582,0.002785411,0.005217794,0.004551267,0.008768682,0.7446352],"study_design_scores_gemma":[0.0003320103,0.00003008956,0.0489377,0.0002552911,0.0001021808,0.001375445,0.000341842,0.9400447,0.002503857,0.0007995823,0.005022906,0.0002544108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01358042,0.0007707403,0.9825446,0.001035996,0.0006090642,0.00009860457,0.001255375,0.00006187687,0.00004332933],"genre_scores_gemma":[0.6590741,0.00006463503,0.3403669,0.0002354459,0.0001631577,0.000005001659,0.00004575408,0.00002073618,0.00002427871],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9372593,"threshold_uncertainty_score":0.3242412,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2095887717","doi":"10.1093/biostatistics/3.2.229","title":"A Bayesian approach to case-control studies with errors in covariables","year":2002,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bayesian probability; Computer science; Control (management); Econometrics; Statistics; Artificial intelligence; Mathematics","authors":[{"name":"Paul Gustafson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1371729806175621,"gpt":0.361720640302282,"spread":0.2245476596847199,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000395525,0.0002141185,0.0004409621,0.0001113077,0.00008150886,0.00003417386,0.0001146468,0.00006408412,0.0001039988],"category_scores_gemma":[0.004984142,0.0001593105,0.00001914859,0.0003512218,0.0001170183,0.00003148122,0.00003360312,0.0001505871,0.00002019849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006372792,"about_ca_system_score_gemma":0.00001788348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005036111,"about_ca_topic_score_gemma":0.00009008117,"domain_scores_codex":[0.9985739,0.0001694434,0.0003732512,0.0003122864,0.0002129184,0.000358196],"domain_scores_gemma":[0.9965531,0.002802959,0.00008477837,0.0002826477,0.0001325661,0.0001438987],"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":[0.00006695469,0.0004468562,0.001265431,0.0003696451,0.0001561614,0.001437781,0.003450128,0.0001065174,0.00002713621,0.9632318,0.01410117,0.01534044],"study_design_scores_gemma":[0.005281338,0.001659676,0.002244623,0.0005911821,0.0006246601,0.002027957,0.008594589,0.2604175,0.0001187281,0.7144409,0.002085137,0.001913705],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002209556,0.0001446043,0.9913793,0.0001814307,0.00007357489,0.0004743149,0.0003803603,0.00005139864,0.00510544],"genre_scores_gemma":[0.3328751,0.00001040095,0.6666384,0.0002107024,0.000027264,0.00005105754,0.000001193533,0.00002109885,0.0001648044],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3306656,"threshold_uncertainty_score":0.6496491,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127195807","doi":"10.1093/biostatistics/4.3.479","title":"Conditional analysis of mixed Poisson processes with baseline counts: implications for trial design and analysis","year":2003,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"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":"Statistics; Baseline (sea); Sample size determination; Count data; Negative binomial distribution; Multiple baseline design; Poisson distribution; Randomization; Mathematics; Computer science; Econometrics; Clinical trial; Medicine; Internal medicine","authors":[{"name":"Richard J. Cook","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4690235198847609,"gpt":0.5372107865117601,"spread":0.06818726662699925,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001528041,0.0001127612,0.0005863684,0.0002085734,0.00005587524,0.00001908036,0.00006927474,0.0000716982,0.0002198032],"category_scores_gemma":[0.08793072,0.00008960946,0.00008131832,0.001238247,0.0001487896,0.00001798756,0.000007044959,0.00004434704,0.000001174453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000016349,"about_ca_system_score_gemma":0.0001562014,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001711348,"about_ca_topic_score_gemma":0.00001080645,"domain_scores_codex":[0.9985889,0.0003274641,0.0005655847,0.0002284305,0.000165348,0.0001243077],"domain_scores_gemma":[0.9353122,0.0635751,0.0003138401,0.0002070087,0.0005222781,0.00006954045],"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":[0.002241322,0.0003842437,0.001115225,0.0002387074,0.005567445,9.724079e-7,0.00002535064,0.0001302675,0.0000345568,0.9831302,0.005841576,0.001290153],"study_design_scores_gemma":[0.006287516,0.0005412538,0.002406667,0.00001631977,0.02381996,9.696606e-7,0.00002250254,0.004033095,0.0003552604,0.9616125,0.0006856323,0.0002183553],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005008145,0.00002975597,0.9923706,0.00007336487,0.00004436851,0.0005629467,0.006285072,0.00001757499,0.0001154991],"genre_scores_gemma":[0.03500222,0.00002936666,0.9645604,0.00003570163,0.00002860806,0.00008893089,0.000172308,0.0000134943,0.00006896687],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08640268,"threshold_uncertainty_score":0.919752,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3186606527","doi":"10.1093/biostatistics/kxab028","title":"Bayesian adaptive model selection design for optimal biological dose finding in phase I/II clinical trials","year":2021,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute","keywords":"Bayesian probability; Selection (genetic algorithm); Computer science; Model selection; Maximum tolerated dose; Adaptive design; Econometrics; Clinical trial; Statistics; Artificial intelligence; Mathematics; Medicine; Internal medicine","authors":[{"name":"Ruitao Lin","is_ca":false},{"name":"Guosheng Yin","is_ca":false},{"name":"Haolun Shi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8908728524028277,"gpt":0.6664937251343948,"spread":0.2243791272684329,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02438619,0.0003625704,0.001949607,0.0001216952,0.000206932,0.00006682968,0.0002398582,0.0006444564,0.0002171493],"category_scores_gemma":[0.5255703,0.000312419,0.0003744748,0.0004241072,0.0002380795,0.00006451648,0.0001498037,0.0005757834,0.000009114299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001407284,"about_ca_system_score_gemma":0.0005129743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002487665,"about_ca_topic_score_gemma":0.000006091979,"domain_scores_codex":[0.9880872,0.006543791,0.003549714,0.0008700064,0.0003321315,0.0006171061],"domain_scores_gemma":[0.7970266,0.201191,0.0007914509,0.0003321385,0.0003888042,0.0002699799],"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":[0.008612515,0.006640166,0.0002037286,0.0001887551,0.0004663024,0.0002205654,0.0003683491,0.003975763,0.003114506,0.7750022,0.02299013,0.1782171],"study_design_scores_gemma":[0.005946103,0.001750451,0.00002811242,0.00006280166,0.0001623041,0.000006674365,0.00005614398,0.4448297,0.001303948,0.5454979,0.00008538425,0.0002704897],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003962457,0.00003965545,0.9917418,0.0002154732,0.0007368213,0.00173216,0.001368112,0.00009932699,0.0001042127],"genre_scores_gemma":[0.0538286,0.00008840015,0.9449158,0.0002096315,0.0005119452,0.0001897819,0.00003364792,0.00005636731,0.0001658651],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5011842,"threshold_uncertainty_score":0.9999328,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1994381110","doi":"10.1093/biostatistics/kxl035","title":"A hierarchical clustering method for estimating copy number variation","year":2006,"lang":"en","type":"article","venue":"Biostatistics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Hospital for Sick Children; Lunenfeld-Tanenbaum Research Institute; SickKids Foundation; Mount Sinai Hospital","funders":"National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research","keywords":"Cluster analysis; Outlier; Computer science; Statistic; Tree (set theory); Change detection; Data mining; Scan statistic; Hierarchical clustering; Copy-number variation; Statistics; Pattern recognition (psychology); Mathematics; Artificial intelligence; Genome; Biology; Genetics","authors":[{"name":"Bin Xing","is_ca":true},{"name":"Celia M.T. Greenwood","is_ca":true},{"name":"Shelley B. Bull","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009536162042363535,"gpt":0.2802942228825624,"spread":0.2707580608401989,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001461697,0.00009932019,0.00009176383,0.00001530678,0.0001237871,0.00004095452,0.00006994392,0.00008190302,0.000027198],"category_scores_gemma":[0.0001000128,0.000102583,0.00004077237,0.00003471039,0.00002083397,0.000002389653,0.0000438676,0.0000355771,0.000007821991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001602055,"about_ca_system_score_gemma":0.00004712919,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001376376,"about_ca_topic_score_gemma":0.00005664755,"domain_scores_codex":[0.9993304,0.00003446623,0.0002095889,0.0001871463,0.0000643959,0.0001740255],"domain_scores_gemma":[0.9996277,0.00005654898,0.00007655138,0.0001279107,0.0000802659,0.00003099117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000607953,0.0005884549,0.02015795,0.0007315336,0.0003650708,0.00001649595,0.00106527,0.04046412,0.5443173,0.293037,0.0593363,0.03931258],"study_design_scores_gemma":[0.00375747,0.0007009409,0.0239395,0.00005836484,0.0002314835,0.0002095102,0.000220716,0.7612213,0.06871587,0.04786121,0.09167802,0.001405556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01419002,0.00001653294,0.9841039,0.00008455435,0.0002313509,0.0001584617,0.0003296303,0.0000146855,0.000870816],"genre_scores_gemma":[0.3630773,0.000001462064,0.6354251,0.00007064153,0.0004243861,0.00002608612,0.000449127,0.0000132521,0.0005126398],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7207572,"threshold_uncertainty_score":0.4183213,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2986102733","doi":"10.1093/biostatistics/kxz047","title":"Independence conditions and the analysis of life history studies with intermittent observation","year":2019,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Independence (probability theory); Econometrics; Statistics; Computer science; Psychology; Mathematics","authors":[{"name":"Richard J. Cook","is_ca":true},{"name":"Jerald F. Lawless","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1519331405211475,"gpt":0.370486172072266,"spread":0.2185530315511185,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000380443,0.00008863615,0.0003710799,0.00007374522,0.00003172924,0.000007853649,0.000081326,0.00003077565,0.0001296011],"category_scores_gemma":[0.003416357,0.00005112119,0.00003017904,0.0001853627,0.0004237354,0.00002864086,0.00004128703,0.00008454799,0.000002805083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004276273,"about_ca_system_score_gemma":0.00005558268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003853712,"about_ca_topic_score_gemma":0.00004207304,"domain_scores_codex":[0.9991641,0.0001220083,0.000282919,0.0001343049,0.0002118095,0.00008485983],"domain_scores_gemma":[0.9948968,0.004344101,0.0002238189,0.0002146407,0.0002841642,0.00003644668],"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":[0.0000619842,0.00002739608,0.0192332,0.0001229326,0.0007627748,0.000001185228,0.001094793,0.000007024196,0.00004972409,0.9763357,0.001172315,0.001130968],"study_design_scores_gemma":[0.001953785,0.0003025825,0.5739023,0.0001710178,0.003751216,0.000003162042,0.003318363,0.02809711,0.00005739057,0.3876536,0.0004616611,0.0003277749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6513607,0.0007369148,0.3454547,0.0003995628,0.0002523735,0.0005141477,0.0004169346,0.00002988367,0.0008348128],"genre_scores_gemma":[0.8419638,0.00008750741,0.1574109,0.0002154944,0.000008312763,0.00001418894,0.00001019806,0.000006876267,0.0002827129],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5886821,"threshold_uncertainty_score":0.4089946,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107721271","doi":"10.1093/biostatistics/kxv012","title":"Semiparametric likelihood inference for left-truncated and right-censored data","year":2015,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Health Canada; Medical Research Council; Pfizer Canada; University of Ottawa; National Cancer Institute; National Institutes of Health; Pfizer","keywords":"Mathematics; Censoring (clinical trials); Estimator; Truncation (statistics); Multiplicative function; Statistics; Semiparametric model; Parametric statistics; Test statistic; Parametric model; Applied mathematics; Statistical hypothesis testing","authors":[{"name":"Chiung‐Yu Huang","is_ca":false},{"name":"Jing Ning","is_ca":false},{"name":"Jing Qin","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2017710970634466,"gpt":0.422136311699616,"spread":0.2203652146361693,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008452356,0.0002262411,0.000380307,0.0001073598,0.00009037444,0.0001066449,0.0004141935,0.0001264473,0.0000662852],"category_scores_gemma":[0.03918627,0.000189068,0.00001842387,0.0002404778,0.0001609045,0.00009354492,0.0002591696,0.0001439246,0.00002315357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003812157,"about_ca_system_score_gemma":0.0001837408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004273084,"about_ca_topic_score_gemma":0.0000276969,"domain_scores_codex":[0.9982955,0.0001135963,0.0004454218,0.0004641637,0.0002867132,0.0003945597],"domain_scores_gemma":[0.9923299,0.005980176,0.00017134,0.0007450415,0.0004248999,0.0003486742],"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":[0.00009261935,0.0002046341,0.002322372,0.0003052579,0.00007192116,0.00001806579,0.0003445148,6.103334e-7,0.0001885229,0.8596416,0.08479442,0.05201543],"study_design_scores_gemma":[0.001079473,0.0003349527,0.001662136,0.00005061154,0.0001487677,0.0000162069,0.0001100349,0.03932233,0.000404022,0.9467729,0.009716434,0.000382132],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005904623,0.000172195,0.987694,0.000160076,0.0003201166,0.0004832516,0.004235667,0.0001023242,0.0009277401],"genre_scores_gemma":[0.1047353,0.0000447455,0.8945823,0.000113296,0.00008802456,0.00001227803,0.0002413291,0.00003220375,0.0001505002],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09883066,"threshold_uncertainty_score":0.9689071,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153510570","doi":"10.1093/biostatistics/kxq048","title":"Feature selection in finite mixture of sparse normal linear models in high-dimensional feature space","year":2010,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; McGill University","funders":"","keywords":"Feature selection; Curse of dimensionality; Computer science; Bayesian information criterion; Maximization; Feature vector; Feature (linguistics); Boosting (machine learning); Bayesian probability; Data mining; Machine learning; Algorithm; Artificial intelligence; Mathematical optimization; Mathematics","authors":[{"name":"Abbas Khalili","is_ca":true},{"name":"Jie Chen","is_ca":true},{"name":"Shili Lin","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03465438392887245,"gpt":0.3177505091851537,"spread":0.2830961252562813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004031589,0.0002211216,0.0003933822,0.0001739661,0.00003702161,0.00001562176,0.0001400661,0.0003744772,0.0001027615],"category_scores_gemma":[0.003047716,0.0001955024,0.00003714299,0.0004449543,0.0001016834,0.00007276233,0.00005626041,0.0009622055,0.000006515458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003243254,"about_ca_system_score_gemma":0.0001130874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001580603,"about_ca_topic_score_gemma":0.001030375,"domain_scores_codex":[0.9986579,0.000124461,0.0003131857,0.0002807075,0.0003081333,0.0003156426],"domain_scores_gemma":[0.9976394,0.001694236,0.0001731561,0.0001962421,0.0002009477,0.00009605123],"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":[0.0002166833,0.0003891384,0.003597424,0.000275788,0.00002106877,0.00007670955,0.000402697,0.001246175,0.01420382,0.958584,0.01682086,0.004165708],"study_design_scores_gemma":[0.001642133,0.0002821676,0.03288563,0.0002474061,0.00005588562,0.00003245592,0.00004544267,0.333384,0.006318812,0.6235054,0.001038285,0.0005624535],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3744988,0.00007566534,0.6189557,0.002152999,0.0008537216,0.0006953945,0.001846831,0.00007636912,0.0008446194],"genre_scores_gemma":[0.2994526,0.000008960307,0.6999804,0.00008324857,0.0000821548,0.000006964753,0.00003258912,0.0000217758,0.0003312977],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3350786,"threshold_uncertainty_score":0.7972355,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3010419042","doi":"10.1093/biostatistics/kxaa009","title":"Geographically dependent individual-level models for infectious diseases transmission","year":2020,"lang":"en","type":"article","venue":"Biostatistics","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto; University of Calgary","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Transmission (telecommunications); Computer science; Econometrics; Statistics; Mathematics","authors":[{"name":"Md Mahsin","is_ca":true},{"name":"Rob Deardon","is_ca":true},{"name":"Patrick Brown","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3138084584422574,"gpt":0.3969915532220246,"spread":0.08318309477976721,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002384256,0.0002395786,0.0004467334,0.00004338177,0.0002071635,0.00003732793,0.000218611,0.000124291,0.00004228716],"category_scores_gemma":[0.006026518,0.0001881573,0.0001542444,0.0001714254,0.0001012278,0.00005307754,0.0001191412,0.0001406283,0.000007706565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003414583,"about_ca_system_score_gemma":0.00005063525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001963581,"about_ca_topic_score_gemma":0.00001396759,"domain_scores_codex":[0.9983702,0.00009612882,0.0004759574,0.0004006873,0.0003103177,0.0003467411],"domain_scores_gemma":[0.9949204,0.004331802,0.000150395,0.0001666395,0.00013445,0.0002962704],"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":[0.0004896745,0.001103822,0.03174679,0.002745652,0.0008416311,0.00007825861,0.002158601,0.001704579,0.0004428772,0.7479918,0.1079783,0.102718],"study_design_scores_gemma":[0.001151448,0.0004796242,0.009656057,0.0000395083,0.0003761738,0.000001790363,0.00005077675,0.01989736,0.00005354227,0.9623743,0.005518707,0.000400676],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003899616,0.0003078436,0.9884353,0.00327718,0.00007230355,0.0006953464,0.002943796,0.0002679665,0.0001006998],"genre_scores_gemma":[0.8258728,0.0003024787,0.1686994,0.00461896,0.0001715625,0.0001389463,0.0001126794,0.00004558163,0.00003752006],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8219732,"threshold_uncertainty_score":0.7672834,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2254245873","doi":"10.1093/biostatistics/kxv015","title":"Methods to assess an exercise intervention trial based on 3-level functional data","year":2015,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":19,"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":"National Cancer Institute; Ministerio de Ciencia e Innovación; National Science Foundation","keywords":"Random effects model; Functional data analysis; Inference; Principal component analysis; Model selection; Functional principal component analysis; Mathematics; Computer science; Statistics; Artificial intelligence; Medicine; Meta-analysis","authors":[{"name":"Haocheng Li","is_ca":true},{"name":"Sarah Kozey Keadle","is_ca":false},{"name":"John Staudenmayer","is_ca":false},{"name":"Houssein Assaad","is_ca":false},{"name":"Jianhua Z. Huang","is_ca":false},{"name":"Raymond J. Carroll","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.7722899850188043,"gpt":0.5685272321347117,"spread":0.2037627528840926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003167478,0.0001993415,0.0003274174,0.0001154399,0.00006789426,0.0001064267,0.0004304977,0.00009881103,0.000421995],"category_scores_gemma":[0.02259997,0.0001745907,0.0000378824,0.000200963,0.00005263037,0.000101353,0.0001669112,0.0001651379,0.0001013067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007311,"about_ca_system_score_gemma":0.0001620404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003554863,"about_ca_topic_score_gemma":0.0000154108,"domain_scores_codex":[0.9975894,0.0006997319,0.0004963091,0.0004645384,0.0005047165,0.0002452648],"domain_scores_gemma":[0.9951539,0.002981188,0.0001476564,0.0009890925,0.0003294542,0.0003987297],"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":[0.01146349,0.001576263,0.00005785134,0.0001218794,0.00003220899,0.00002015983,0.0001116433,0.00004744703,0.0001360889,0.3794132,0.1317081,0.4753116],"study_design_scores_gemma":[0.02438934,0.004215588,0.002556195,0.0003075748,0.0003166399,0.000004751627,0.0003156572,0.2652135,0.001013905,0.6863954,0.01443006,0.0008413472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006490716,0.000006100659,0.9930816,0.0001120201,0.001461025,0.0004824876,0.003131303,0.00007431965,0.001002116],"genre_scores_gemma":[0.006620752,7.645668e-7,0.9919819,0.0002377399,0.0002508111,0.00004209246,0.0005601206,0.00003359019,0.0002722496],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4744703,"threshold_uncertainty_score":0.9856331,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2097681968","doi":"10.1093/biostatistics/2.3.323","title":"Efficiency considerations in the analysis of inter-observer agreement","year":2001,"lang":"en","type":"article","venue":"Biostatistics","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Cohen's kappa; Replicate; Statistics; Inter-rater reliability; Reliability (semiconductor); Statistic; Kappa; Mathematics; Binary number; Computer science; Binomial distribution; Econometrics; Arithmetic; Physics","authors":[{"name":"Mohamed M. Shoukri","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2311350697927032,"gpt":0.4052181703110456,"spread":0.1740831005183424,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004319277,0.00008682029,0.0002377495,0.0003296162,0.00008877992,0.0001056768,0.0004231104,0.00002945979,0.001534852],"category_scores_gemma":[0.004057399,0.00005031153,0.0001043881,0.001960257,0.0001331708,0.00005766561,0.00005186372,0.00007584735,0.00005976952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003395672,"about_ca_system_score_gemma":0.00004335622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001271858,"about_ca_topic_score_gemma":0.001570632,"domain_scores_codex":[0.9971741,0.000366862,0.0008408043,0.0002481063,0.001213861,0.0001562207],"domain_scores_gemma":[0.9964512,0.00238932,0.0002057274,0.0005977027,0.0003241496,0.00003192056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002989111,0.001337467,0.8517873,0.00001135858,0.0002852141,0.00005321368,0.006254009,0.01117279,0.00062281,0.07529371,0.03256236,0.02058984],"study_design_scores_gemma":[0.000325485,0.000136518,0.9363446,0.00001395574,0.0002635985,0.000001976379,0.003478397,0.01547083,0.0001123691,0.03575355,0.007955147,0.0001436077],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8273057,0.0001551022,0.1594759,0.004708446,0.0003560438,0.0005287644,0.000199894,0.000009547115,0.007260562],"genre_scores_gemma":[0.9968457,0.00002063823,0.002471318,0.0004735602,0.00001235852,0.000007414286,0.000009034284,0.000001651852,0.0001583866],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1695399,"threshold_uncertainty_score":0.9993779,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W939145883","doi":"10.1093/biostatistics/kxw049","title":"Inequality in treatment benefits: Can we determine if a new treatment benefits the many or the few?","year":2016,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of Neurological Disorders and Stroke; Patient-Centered Outcomes Research Institute; U.S. Food and Drug Administration; National Institute on Aging; National Institutes of Health; Hamilton Health Sciences Foundation","keywords":"Randomized controlled trial; Estimator; Fraction (chemistry); Computer science; Statistics; Econometrics; Randomized response; Outcome (game theory); Mathematics; Medicine; Mathematical optimization; Mathematical economics","authors":[{"name":"Emily J. Huang","is_ca":false},{"name":"Ethan X. Fang","is_ca":false},{"name":"Daniel F. Hanley","is_ca":false},{"name":"Michael Rosenblum","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2502387195907997,"gpt":0.4054696846381312,"spread":0.1552309650473315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000214979,0.0004007481,0.0004138493,0.00006667107,0.0001392935,0.0000485306,0.0003367215,0.0001094389,0.0001329771],"category_scores_gemma":[0.000755597,0.0001390306,0.00007307849,0.0002151426,0.0001429006,0.00006763846,0.00009097594,0.00008357588,0.00002558547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007889955,"about_ca_system_score_gemma":0.0002329595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009943891,"about_ca_topic_score_gemma":0.01235679,"domain_scores_codex":[0.9982081,0.0001463597,0.0005736999,0.0003497249,0.0002588545,0.000463231],"domain_scores_gemma":[0.9957225,0.002893072,0.0002585994,0.000920674,0.00007724101,0.0001279431],"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":[0.0001232969,0.0003348755,0.001300696,0.0000245722,0.00007214468,0.00004955851,0.001969274,0.000006724904,0.0002114516,0.2163973,0.001642969,0.7778672],"study_design_scores_gemma":[0.006045599,0.005686139,0.01372785,0.001101701,0.0005380912,0.0001240198,0.00129407,0.0005119481,0.0339375,0.8852222,0.05030303,0.001507835],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5996963,0.002769901,0.2891898,0.07818333,0.001080264,0.01196212,0.0135077,0.001963117,0.001647484],"genre_scores_gemma":[0.8904461,0.006849898,0.09357225,0.0004888586,0.0003278439,0.0005925299,0.00003909538,0.0001304675,0.007553008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7763593,"threshold_uncertainty_score":0.6895381,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2271845266","doi":"10.1093/biostatistics/kxv042","title":"Sieve estimation in a Markov illness-death process under dual censoring","year":2015,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":18,"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; Canadian Institutes of Health Research","keywords":"Censoring (clinical trials); Estimator; Statistics; Inference; Sieve (category theory); Imputation (statistics); Markov chain; Mathematics; Computer science; Parametric statistics; Econometrics; Missing data; Artificial intelligence","authors":[{"name":"Audrey Boruvka","is_ca":true},{"name":"Richard J. Cook","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1501214199318977,"gpt":0.4187033755424467,"spread":0.268581955610549,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005619571,0.000181662,0.0002730815,0.00008992495,0.00004124987,0.00005352995,0.000109784,0.00009562835,0.00005968796],"category_scores_gemma":[0.007502854,0.0001648065,0.00001898178,0.0002377842,0.00005216646,0.00007884058,0.00004618249,0.0001720016,0.00003692761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001143641,"about_ca_system_score_gemma":0.0001405729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004518511,"about_ca_topic_score_gemma":0.00002128521,"domain_scores_codex":[0.9985339,0.0001257396,0.0004154838,0.0002524147,0.000356859,0.0003155774],"domain_scores_gemma":[0.9979896,0.001292411,0.0001268841,0.0002106075,0.0002116549,0.0001688407],"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":[0.00005592259,0.0001606199,0.001662378,0.0002005479,0.00001444108,0.00006584769,0.001335442,0.0001686059,0.00005358365,0.9712963,0.001400593,0.02358576],"study_design_scores_gemma":[0.0006347391,0.000106064,0.005364156,0.0001038165,0.00002963147,0.00001710322,0.0008187909,0.04797777,0.0003801388,0.9441546,0.0001085157,0.0003046395],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06907449,0.00002703082,0.9260029,0.0001398026,0.0002918675,0.0002666778,0.0001455542,0.00007926928,0.003972454],"genre_scores_gemma":[0.5060496,0.000003131111,0.4937262,0.0000556388,0.00003497371,0.00001705831,0.00001065147,0.00001976292,0.00008304176],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4369751,"threshold_uncertainty_score":0.8982159,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3015827596","doi":"10.1093/biostatistics/kxaa012","title":"Two-part joint model for a longitudinal semicontinuous marker and a terminal event with application to metastatic colorectal cancer data","year":2020,"lang":"en","type":"article","venue":"Biostatistics","topic":"Colorectal Cancer Treatments and Studies","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"National Cancer Institute; Canadian Institutes of Health Research","keywords":"Biomarker; Event (particle physics); Colorectal cancer; Proportional hazards model; Outcome (game theory); Oncology; Computer science; Statistics; Cancer; Medicine; Internal medicine; Mathematics; Biology; Physics","authors":[{"name":"Denis Rustand","is_ca":false},{"name":"Laurent Briollais","is_ca":true},{"name":"Christophe Tournigand","is_ca":false},{"name":"Virginie Rondeau","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0662028208738954,"gpt":0.3436616069784594,"spread":0.277458786104564,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006528984,0.0001585141,0.0003148166,0.00002534278,0.00007776202,0.00002072,0.00005746237,0.00001569388,0.00001219223],"category_scores_gemma":[0.00008448749,0.0001168521,0.00001956589,0.00009093777,0.00005390841,0.00003464326,0.0001021256,0.00005196624,0.000002461934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007354038,"about_ca_system_score_gemma":0.0001462719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001348696,"about_ca_topic_score_gemma":0.0007495551,"domain_scores_codex":[0.9990436,0.000008905476,0.0001921533,0.00041343,0.000154575,0.0001873392],"domain_scores_gemma":[0.9994178,0.00005261955,0.0000728568,0.0001619292,0.0001137804,0.0001810421],"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":[0.04942705,0.002001402,0.1771698,0.004198041,0.00623362,0.0008610855,0.01416709,0.002515242,0.02445889,0.003090146,0.1781378,0.5377398],"study_design_scores_gemma":[0.006127214,0.003702403,0.049231,0.0002077963,0.002322293,0.0001398487,0.0004716687,0.9285445,0.0006669526,0.0001276286,0.007992572,0.0004661735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4585156,0.001118318,0.5201591,0.006970064,0.00008496191,0.003755311,0.00915348,0.00007058256,0.0001726311],"genre_scores_gemma":[0.9409569,0.00008019894,0.05726889,0.0006473523,0.0001034849,0.0005060742,0.0002879598,0.00002299564,0.00012616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9260292,"threshold_uncertainty_score":0.4765089,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107365898","doi":"10.1093/biostatistics/kxp029","title":"Second-order estimating equations for the analysis of clustered current status data","year":2009,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Covariate; Copula (linguistics); Marginal model; Quantile; Marginal distribution; Estimating equations; Statistics; Generalized estimating equation; Econometrics; Mathematics; Joint probability distribution; Order statistic; Regression analysis; Maximum likelihood","authors":[{"name":"Richard J. Cook","is_ca":true},{"name":"Danilo V. Tolusso","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3129426196990909,"gpt":0.4887470645144166,"spread":0.1758044448153258,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006305359,0.0001344237,0.0003451002,0.0001015041,0.0001406879,0.00004644051,0.0003814517,0.00003906906,0.0002533006],"category_scores_gemma":[0.01997304,0.00009484386,0.0000556824,0.0005726797,0.00008441645,0.00004683016,0.00008680888,0.0001030651,0.000002128676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000216593,"about_ca_system_score_gemma":0.00009589044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001348321,"about_ca_topic_score_gemma":0.00006585229,"domain_scores_codex":[0.9986218,0.00008383096,0.0005624263,0.0002450238,0.0002268421,0.0002601381],"domain_scores_gemma":[0.9856326,0.01285012,0.0003066134,0.0008092687,0.0003304297,0.00007096739],"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":[0.00001556653,0.0001230535,0.00006860359,0.00009962473,0.0003004928,3.706089e-7,0.0003004295,0.0001694372,0.00004513643,0.6214309,0.006013915,0.3714325],"study_design_scores_gemma":[0.0002055852,0.00006422412,0.003368501,0.00002232319,0.001439624,1.964007e-7,0.00007174186,0.7859244,0.0000184192,0.2071036,0.001668771,0.0001126215],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002470447,0.0001762002,0.9885695,0.0001571196,0.0002385228,0.0003548044,0.01005884,0.00002305811,0.000174889],"genre_scores_gemma":[0.04416894,0.00002209528,0.9551704,0.00007739639,0.00006114352,0.00001189016,0.0004406292,0.0000104928,0.00003701968],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.785755,"threshold_uncertainty_score":0.9882821,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2795350022","doi":"10.1093/biostatistics/kxx047","title":"A joint model for mixed and truncated longitudinal data and survival data, with application to HIV vaccine studies","year":2017,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Bill and Melinda Gates Foundation","keywords":"Inference; Computer science; Likelihood function; Missing data; Generalized estimating equation; Statistics; Longitudinal data; Statistical inference; Algorithm; Maximum likelihood; Mathematics; Data mining; Estimation theory; Artificial intelligence","authors":[{"name":"Tingting Yu","is_ca":true},{"name":"Lang Wu","is_ca":true},{"name":"Peter B. Gilbert","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3364128028645132,"gpt":0.4557809294285878,"spread":0.1193681265640746,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006586105,0.0001677931,0.0003713263,0.0000296728,0.0002996127,0.0001233363,0.000427184,0.00003913511,0.000001935638],"category_scores_gemma":[0.007712347,0.000125126,0.000005012421,0.00003093268,0.0001204333,0.0001140878,0.0007940657,0.00006279368,0.00000164392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000126375,"about_ca_system_score_gemma":0.00003857332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002802014,"about_ca_topic_score_gemma":0.0003350797,"domain_scores_codex":[0.9988322,0.00003102381,0.0002683143,0.0005297103,0.0001477374,0.0001910036],"domain_scores_gemma":[0.9967492,0.001188234,0.0001899774,0.001529822,0.0002224055,0.000120424],"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":[0.0005914635,0.0002175027,0.00840406,0.001441516,0.0004151612,0.00001352026,0.0007794862,0.00001115406,0.0006559719,0.8049242,0.05370733,0.1288386],"study_design_scores_gemma":[0.001022771,0.0001860904,0.02132854,0.00008651053,0.0002823386,0.000007452451,0.0001766031,0.7915935,0.00005510731,0.1845129,0.0004724716,0.0002756831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007575327,0.00007209003,0.9816746,0.0007285029,0.00005448724,0.0005411034,0.009300874,0.00002374947,0.00002922611],"genre_scores_gemma":[0.1579399,0.00007409599,0.8414961,0.00003090885,0.00004812476,0.00003510069,0.0002824169,0.00002064843,0.00007272438],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7915823,"threshold_uncertainty_score":0.9232956,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134647083","doi":"10.1093/biostatistics/kxn037","title":"Statistical monitoring of clinical trials with multivariate response and/or multiple arms: a flexible approach","year":2008,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Institute of Allergy and Infectious Diseases; ACT Government","keywords":"Interim; Multivariate statistics; Clinical trial; Robustness (evolution); Computer science; Randomized controlled trial; Interim analysis; Multivariate analysis; Statistics; Medicine; Mathematics; Machine learning; Internal medicine","authors":[{"name":"Lihui Zhao","is_ca":true},{"name":"X. Joan Hu","is_ca":true},{"name":"Stephen W. Lagakos","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8559835100558566,"gpt":0.644237374207395,"spread":0.2117461358484616,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02340293,0.0004451883,0.002830984,0.0001472932,0.0001700645,0.00003651802,0.0003137706,0.0003916028,0.0001052451],"category_scores_gemma":[0.629181,0.0002950654,0.0001692872,0.0003546556,0.00135179,0.00007553144,0.0001672423,0.000620198,0.00001130771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004106017,"about_ca_system_score_gemma":0.0004451608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000424498,"about_ca_topic_score_gemma":0.000001736209,"domain_scores_codex":[0.9847631,0.008692994,0.004287093,0.0008294447,0.0008563355,0.0005710188],"domain_scores_gemma":[0.6825101,0.315048,0.001146631,0.0005794104,0.0003119875,0.000403943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.2461676,0.009590223,0.3115653,0.003703408,0.00308989,0.002122219,0.004679816,0.00005139089,0.003339944,0.2734306,0.01148663,0.1307731],"study_design_scores_gemma":[0.04035088,0.01021797,0.5279213,0.001216029,0.00226572,0.0005399532,0.002369328,0.01729994,0.006714161,0.3870822,0.001418152,0.002604374],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09901484,0.00004561792,0.8968894,0.00006602363,0.0005710262,0.001090738,0.002035609,0.0001421296,0.0001445635],"genre_scores_gemma":[0.2086388,0.0001365123,0.7904837,0.00003002459,0.0003575648,0.00005686839,0.000007907564,0.00007422724,0.0002144129],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.605778,"threshold_uncertainty_score":0.9999502,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2320372797","doi":"10.1093/biostatistics/kxt057","title":"Monitoring risk-adjusted medical outcomes allowing for changes over time","year":2013,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Chart; Computer science; Variety (cybernetics); Failure rate; Measure (data warehouse); Data mining; Statistics; Artificial intelligence; Mathematics","authors":[{"name":"Stefan H. Steiner","is_ca":true},{"name":"Robert J. MacKay","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1030140580449314,"gpt":0.4256607621804991,"spread":0.3226467041355677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001262204,0.0002806483,0.0005070049,0.000180892,0.0003293609,0.0003128381,0.0007872921,0.0001780184,0.001128703],"category_scores_gemma":[0.05623329,0.0002117283,0.00008869148,0.0003774459,0.0001580604,0.0003158646,0.0002165528,0.0002675648,0.001052746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000826791,"about_ca_system_score_gemma":0.0000776819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009175008,"about_ca_topic_score_gemma":0.00001708081,"domain_scores_codex":[0.9956871,0.0001240026,0.0007544123,0.0006228305,0.002199278,0.0006123954],"domain_scores_gemma":[0.985795,0.01230052,0.000346417,0.0004832172,0.0006289382,0.0004458904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003162303,0.00009220483,0.2214084,0.00004375733,0.0000845245,0.00003247747,0.0003528879,0.00006832063,0.0007321706,0.002981221,0.01820036,0.7559721],"study_design_scores_gemma":[0.002160436,0.0003234525,0.7381245,0.0001734558,0.0001212708,0.000008317335,0.0007125675,0.08159984,0.002200895,0.1560097,0.01740598,0.001159532],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07068125,0.0002201148,0.9233178,0.001173014,0.002568764,0.0007843681,0.0005962771,0.0002123646,0.0004460747],"genre_scores_gemma":[0.7249315,0.00006094134,0.2700365,0.000247663,0.000904308,0.0001768112,0.00001905372,0.00007534471,0.003547806],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7548126,"threshold_uncertainty_score":0.9997844,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963817914","doi":"10.1093/biostatistics/kxy049","title":"Bayesian model averaging for the X-chromosome inactivation dilemma in genetic association study","year":2018,"lang":"en","type":"article","venue":"Biostatistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Bayesian probability; Association (psychology); Dilemma; Genetics; Chromosome; Genetic association; Genetic model; Computer science; Biology; Computational biology; Statistics; Econometrics; Mathematics; Artificial intelligence; Psychology; Genotype; Gene; Single-nucleotide polymorphism","authors":[{"name":"Bo Chen","is_ca":true},{"name":"Radu V. Craiu","is_ca":true},{"name":"Lei Sun","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01820559865629581,"gpt":0.2923468390028399,"spread":0.2741412403465441,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051521,0.0001133711,0.0001302024,0.00003997526,0.0001802288,0.00002388176,0.0001327723,0.0001203571,0.00000715307],"category_scores_gemma":[0.001181546,0.00009659433,0.00003426132,0.0001008086,0.00003635368,0.000002779368,0.00005144063,0.0000629182,0.000005009903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001014144,"about_ca_system_score_gemma":0.00007651112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008721905,"about_ca_topic_score_gemma":0.0005382943,"domain_scores_codex":[0.9989894,0.0001026894,0.0002869973,0.0002557267,0.0001055464,0.0002596286],"domain_scores_gemma":[0.9991702,0.0001894388,0.0001788287,0.0002277817,0.0002032708,0.00003047464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001193987,0.0003958016,0.9328117,0.00001826303,0.0002208591,0.000001621539,0.001082283,0.01303363,0.02273373,0.0007256223,0.01922449,0.009632574],"study_design_scores_gemma":[0.00129926,0.0007598614,0.692337,0.000006510531,0.00007114022,0.000001416844,0.0004534038,0.2973728,0.001005692,0.002583074,0.003837113,0.0002726875],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5709965,0.0000373346,0.4277974,0.0003299139,0.0001768545,0.0004966854,0.00007682907,0.000006387055,0.00008203859],"genre_scores_gemma":[0.9825072,0.000033255,0.01631624,0.0002977902,0.00032923,0.0001031412,0.00008555022,0.00001836419,0.0003092629],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4115106,"threshold_uncertainty_score":0.3939002,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2465707019","doi":"10.1093/biostatistics/kxw022","title":"Prediction of cancer drug sensitivity using high-dimensional omic features","year":2016,"lang":"en","type":"article","venue":"Biostatistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"National Institute of General Medical Sciences; National Cancer Institute","keywords":"Feature selection; Sensitivity (control systems); Curse of dimensionality; Computational biology; Omics; Computer science; Set (abstract data type); Personalized medicine; Machine learning; Bioinformatics; Artificial intelligence; Biology","authors":[{"name":"Ting-Huei Chen","is_ca":true},{"name":"Wei Sun","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01758613482010847,"gpt":0.2701356347164022,"spread":0.2525494998962938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007904086,0.00008016867,0.00007992897,0.00002981432,0.00004106864,0.000004254964,0.00003818623,0.00006777669,0.00002718426],"category_scores_gemma":[0.00005576956,0.00005811388,0.00002669123,0.00004310902,0.00007089804,0.000002367653,0.00003471327,0.00002525338,0.000001766021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002449781,"about_ca_system_score_gemma":0.00009718528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001178886,"about_ca_topic_score_gemma":0.00005573016,"domain_scores_codex":[0.9994127,0.00005213117,0.0001311142,0.0001889853,0.0001157237,0.00009936286],"domain_scores_gemma":[0.9995466,0.00001760221,0.0001050609,0.0001685584,0.0001201138,0.00004206584],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005636657,0.0000207115,0.003517109,0.000009500916,0.00001875818,6.685866e-7,0.000008504611,0.0000677081,0.9772186,0.000366864,0.01262982,0.006085437],"study_design_scores_gemma":[0.0004179729,0.00003688166,0.09214196,0.00004590975,0.00002391007,0.000004595151,0.00001095381,0.000227841,0.9028862,0.0001390567,0.003975607,0.00008915382],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9691054,0.0003345772,0.02847427,0.000283054,0.0004760808,0.00008546333,0.001196345,0.000008811129,0.00003604347],"genre_scores_gemma":[0.99607,0.0001466237,0.002759842,0.00008724583,0.0001810467,0.000004511382,0.00007425009,0.00001112309,0.0006653718],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08862486,"threshold_uncertainty_score":0.2369815,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2198637531","doi":"10.1093/biostatistics/kxv028","title":"Double robust and efficient estimation of a prognostic model for events in the presence of dependent censoring","year":2015,"lang":"en","type":"article","venue":"Biostatistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":15,"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":"National Institutes of Health; National Institute of Allergy and Infectious Diseases; ACT Government","keywords":"Censoring (clinical trials); Inverse probability weighting; Inverse probability; Estimator; Computer science; Inference; Statistics; Econometrics; Weighting; Missing data; Estimation; Causal inference; Parametric model; Parametric statistics; Mathematics; Artificial intelligence; Posterior probability","authors":[{"name":"Mireille E. Schnitzer","is_ca":true},{"name":"Judith J. Lok","is_ca":false},{"name":"Ronald J. Bosch","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2544352714323289,"gpt":0.4149531699672734,"spread":0.1605178985349445,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004726081,0.00007518083,0.0001453271,0.00004643354,0.00001513172,0.00000420447,0.0001088032,0.00003497576,3.224488e-7],"category_scores_gemma":[0.001801657,0.00005705328,0.00001104673,0.00007567147,0.00004930429,0.00003590872,0.00003958551,0.00004789505,1.271059e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000284159,"about_ca_system_score_gemma":0.00004430723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001550274,"about_ca_topic_score_gemma":0.00001927478,"domain_scores_codex":[0.9992647,0.00002605372,0.0002795479,0.00009991386,0.0002187192,0.0001110997],"domain_scores_gemma":[0.9987301,0.0007572192,0.0001742255,0.0001560092,0.0001566942,0.00002581133],"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":[0.0001814916,0.0004251735,0.002211078,0.0009258334,0.00001370532,0.000002053535,0.006348228,0.3873461,0.0006256136,0.5996433,0.0001706504,0.002106746],"study_design_scores_gemma":[0.0004335544,0.00009299423,0.0002264701,0.0001076764,0.00002243991,0.000001690718,0.0002689888,0.7896598,0.002385626,0.2067446,6.731377e-7,0.00005546036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1659946,0.00002422222,0.8331329,0.00001741522,0.00001856662,0.0006934373,0.00006165053,0.00001463361,0.00004267407],"genre_scores_gemma":[0.6299356,0.000003167034,0.3699932,0.000001889014,0.000002592972,0.00004470617,0.00000380218,0.000005736115,0.000009306256],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.463941,"threshold_uncertainty_score":0.2326565,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102283511","doi":"10.1093/biostatistics/kxv007","title":"Hypothesis testing at the extremes: fast and robust association for high-throughput data","year":2015,"lang":"en","type":"article","venue":"Biostatistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute; National Institute of Mental Health; Ontario Genomics Institute; Cystic Fibrosis Canada; National Institute of Environmental Health Sciences; Genome Canada; Ontario Genomics; Cystic Fibrosis Foundation","keywords":"Computer science; Throughput; Association (psychology); Data mining; Statistics; Mathematics; Psychology","authors":[{"name":"Yubin Zhou","is_ca":false},{"name":"Fred A. Wright","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1521403879759942,"gpt":0.3005252873365745,"spread":0.1483848993605803,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.000800385,0.0001054524,0.0001288229,0.00001160069,0.0001700713,0.00002600904,0.0001844422,0.0001306211,0.000003586676],"category_scores_gemma":[0.01148706,0.00008241407,0.00001467443,0.00005263755,0.0000553207,0.000002836203,0.0002750949,0.00003962277,0.000007843449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005928698,"about_ca_system_score_gemma":0.00007969995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001114644,"about_ca_topic_score_gemma":0.0003797872,"domain_scores_codex":[0.9990777,0.00009448673,0.0002040192,0.0003070921,0.00009569569,0.000220974],"domain_scores_gemma":[0.9984339,0.0006980362,0.0002020704,0.0003996063,0.0002041364,0.00006218583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00006069069,0.00006405262,0.174633,0.00003049872,0.0002235208,0.000001324536,0.0001442723,0.0009145054,0.009283296,0.0005548674,0.7758807,0.03820934],"study_design_scores_gemma":[0.005202282,0.001666543,0.5251685,0.00004259741,0.0008238914,0.0000590914,0.001920414,0.0389838,0.004377543,0.0166337,0.4035549,0.001566705],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6132035,0.003314543,0.3575422,0.008863742,0.001357815,0.001513309,0.01160052,0.00006647018,0.002537959],"genre_scores_gemma":[0.6294985,0.0002650314,0.3611007,0.0009027051,0.0007604787,0.00004616548,0.002124863,0.00004346749,0.005258085],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3723258,"threshold_uncertainty_score":0.9968396,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4210676319","doi":"10.1093/biostatistics/kxac007","title":"Semiparametric Bayesian inference for optimal dynamic treatment regimes via dynamic marginal structural models","year":2022,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University Health Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; ViiV Healthcare; Gilead Sciences","keywords":"Frequentist inference; Inference; Bayesian probability; Computer science; Bayesian inference; Posterior probability; Econometrics; Marginal structural model; Machine learning; Causal inference; Artificial intelligence; Mathematics","authors":[{"name":"Daniel Rodriguez Duque","is_ca":true},{"name":"David A. Stephens","is_ca":true},{"name":"Erica E. M. Moodie","is_ca":true},{"name":"Marina B. Klein","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05764133595221096,"gpt":0.379869733491707,"spread":0.3222283975394961,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002926243,0.0003716881,0.0005151935,0.0002103262,0.0004650661,0.00007447557,0.0003402279,0.00008023909,0.0004119458],"category_scores_gemma":[0.001157464,0.0003374129,0.0001161,0.0004004411,0.0001353099,0.00007224447,0.0001523099,0.0002234801,0.000005145368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005731914,"about_ca_system_score_gemma":0.000190749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006021877,"about_ca_topic_score_gemma":0.00001863884,"domain_scores_codex":[0.9977401,0.0002052973,0.0005480485,0.0005175525,0.0004180068,0.0005709226],"domain_scores_gemma":[0.9950792,0.003861678,0.0002702728,0.0004619075,0.0001465991,0.0001804063],"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":[0.0002783931,0.0002585986,0.0001570426,0.0002134801,0.0001567077,0.00005587538,0.0006008599,0.003466166,0.0001828436,0.8440613,0.000947739,0.149621],"study_design_scores_gemma":[0.0004987972,0.0007487025,0.0002111652,0.000008405876,0.00009713799,0.00002761571,0.0001180016,0.5608788,0.00002616105,0.4368974,0.0002274743,0.0002603214],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01617624,0.0001393636,0.9776201,0.0001217123,0.0003776246,0.0007962551,0.004394223,0.0001035407,0.0002709849],"genre_scores_gemma":[0.4434891,0.00002059043,0.5555202,0.00003656743,0.00001755792,0.0001850671,0.0001449402,0.0000380839,0.0005478967],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5574126,"threshold_uncertainty_score":0.9999078,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3011802598","doi":"10.1093/biostatistics/kxaa011","title":"Assessing the accuracy of predictive models with interval-censored data","year":2020,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":13,"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":"Canadian Institutes of Health Research; University of Waterloo; National Natural Science Foundation of China","keywords":"Estimator; Inverse probability; Statistics; Computer science; Event (particle physics); Imputation (statistics); Context (archaeology); Receiver operating characteristic; Inverse probability weighting; Coverage probability; Confidence interval; Mathematics; Bayesian probability; Missing data; Posterior probability","authors":[{"name":"Ying Wu","is_ca":false},{"name":"Richard J. Cook","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.337170611191294,"gpt":0.4496314092164307,"spread":0.1124607980251368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0003071839,0.0001412893,0.0002753499,0.00001481953,0.00006697226,0.00007422647,0.0005498271,0.0000414294,0.00005854718],"category_scores_gemma":[0.01043532,0.00008221291,0.00001813536,0.0001659412,0.000236924,0.0002017987,0.0002712103,0.0001762479,0.000003578038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001152225,"about_ca_system_score_gemma":0.0001018579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001800121,"about_ca_topic_score_gemma":0.000002523663,"domain_scores_codex":[0.9987285,0.000174669,0.0003633615,0.0002649573,0.0002980474,0.0001704972],"domain_scores_gemma":[0.9935856,0.005256106,0.0002723383,0.0005895974,0.000203769,0.00009258685],"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":[0.0001246464,0.0001178147,0.000333577,0.000365061,0.0001514996,0.00002357739,0.002197591,0.00007957745,0.0003795905,0.948433,0.01322888,0.03456522],"study_design_scores_gemma":[0.0004052348,0.000333729,0.001191073,0.0001658277,0.0002023689,0.000006250594,0.001295438,0.6660392,0.0005283309,0.3292907,0.0003551955,0.0001866676],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002106918,0.00002984942,0.9933653,0.0006926287,0.00005063415,0.000234719,0.00184806,0.00003937131,0.001632487],"genre_scores_gemma":[0.3980218,0.00001144025,0.6016794,0.0001898181,0.00004273121,0.000003482266,0.00002913339,0.0000161921,0.000006079853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6659596,"threshold_uncertainty_score":0.9979002,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098860533","doi":"10.1093/biostatistics/kxq016","title":"Surface shape analysis with an application to brain surface asymmetry in schizophrenia","year":2010,"lang":"en","type":"article","venue":"Biostatistics","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Asymmetry; Surface (topology); Bayesian probability; Shape analysis (program analysis); Mathematics; Artificial intelligence; Pattern recognition (psychology); Computer science; Principal component analysis; Scale (ratio); Geometry; Physics","authors":[{"name":"Christopher J. Brignell","is_ca":false},{"name":"Ian L. Dryden","is_ca":false},{"name":"Stefano Antonio Gattone","is_ca":false},{"name":"Brian Park","is_ca":false},{"name":"Sarah Leask","is_ca":false},{"name":"William J. Browne","is_ca":false},{"name":"Sean P. Flynn","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02034049229156815,"gpt":0.3054867589798436,"spread":0.2851462666882754,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005388862,0.0001936882,0.0003272287,0.000176453,0.00008662495,0.00007409849,0.0002571187,0.0001469219,0.0002169441],"category_scores_gemma":[0.0006013854,0.000159225,0.00004057109,0.001877811,0.00004887948,0.00007818758,0.00005387769,0.0002934058,0.0000627242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003180759,"about_ca_system_score_gemma":0.00004421514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001936114,"about_ca_topic_score_gemma":0.001886943,"domain_scores_codex":[0.9985849,0.00008315351,0.0003564379,0.0004255193,0.0002725921,0.0002774496],"domain_scores_gemma":[0.998238,0.0007070262,0.0001403264,0.0005921298,0.0001257319,0.0001967813],"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":[0.0003479842,0.001448144,0.1100793,0.00008463505,0.0003422898,0.00005946122,0.0004084147,0.002744145,0.0406185,0.8212351,0.006976886,0.0156552],"study_design_scores_gemma":[0.002912278,0.0009793261,0.6293355,0.00004002543,0.000859803,0.00002216146,0.0005135367,0.3041809,0.003418156,0.05013631,0.005704676,0.001897401],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6485675,0.000003658081,0.3501773,0.0003973096,0.00003594872,0.0002628357,0.0002094352,0.00005990233,0.0002860717],"genre_scores_gemma":[0.5590819,7.38862e-7,0.4405715,0.0001494676,0.0000248162,0.000005949048,0.00007562992,0.00001565206,0.00007438744],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7710987,"threshold_uncertainty_score":0.6493006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146901830","doi":"10.1093/biostatistics/kxu026","title":"Multiple comparison procedures for neuroimaging genomewide association studies","year":2014,"lang":"en","type":"article","venue":"Biostatistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"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; University of California, San Diego; Canadian Institutes of Health Research; University of California, Los Angeles; National Institutes of Health; Genentech; IXICO; 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; Wellcome Trust; Synarc; Bayer HealthCare; Alzheimer's Disease Neuroimaging Initiative; National Center for Advancing Translational Sciences; Meso Scale Diagnostics; National Science Foundation","keywords":"Neuroimaging; Imaging genetics; Univariate; False discovery rate; Computer science; Alzheimer's Disease Neuroimaging Initiative; Multiple comparisons problem; Dimensionality reduction; Genome-wide association study; Brain size; Statistical power; Computational biology; Artificial intelligence; Machine learning; Single-nucleotide polymorphism; Neuroscience; Magnetic resonance imaging; Biology; Multivariate statistics; Medicine; Statistics; Genetics; Gene; Genotype; Mathematics; Cognition","authors":[{"name":"Wen‐Yu Hua","is_ca":false},{"name":"Thomas E. Nichols","is_ca":false},{"name":"Debashis Ghosh","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03238930918415187,"gpt":0.3310335732112797,"spread":0.2986442640271278,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004313058,0.000115802,0.0002085642,0.0000261863,0.000144529,0.00001603979,0.00009031414,0.00009776873,0.000001518985],"category_scores_gemma":[0.01420033,0.000114082,0.00005024489,0.00004052021,0.00003242735,0.000001468241,0.00004950224,0.00004645661,0.000007415411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004097455,"about_ca_system_score_gemma":0.00003975583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007450411,"about_ca_topic_score_gemma":0.00009787112,"domain_scores_codex":[0.9990538,0.00009024058,0.0002742322,0.0002460378,0.00007610203,0.0002596227],"domain_scores_gemma":[0.9987506,0.0005695962,0.0002340661,0.0001472782,0.0002550796,0.00004343045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003753817,0.00006816727,0.7596996,0.00009572175,0.0001997253,1.865774e-7,0.000177835,0.0008481422,0.03432302,0.0007804967,0.1980958,0.005673798],"study_design_scores_gemma":[0.00202567,0.0008888318,0.4897586,0.00002357703,0.0001914016,0.000004061652,0.0005294672,0.0287551,0.008967101,0.004062353,0.4641142,0.0006796853],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5484458,0.001742406,0.4452849,0.002197187,0.0009505617,0.0006411397,0.0003393577,0.00004758499,0.0003510457],"genre_scores_gemma":[0.9477929,0.0001684864,0.0498687,0.0008629338,0.0003474993,0.00004879386,0.0002901298,0.00001947302,0.000601058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3993472,"threshold_uncertainty_score":0.9941035,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117015589","doi":"10.1093/biostatistics/kxu011","title":"Composite likelihood for joint analysis of multiple multistate processes via copulas","year":2014,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":12,"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":"Copula (linguistics); Inference; Computer science; Joint (building); Econometrics; Markov model; Markov chain; Machine learning; Mathematics; Artificial intelligence","authors":[{"name":"Liqun Diao","is_ca":false},{"name":"Richard J. Cook","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07492729461245784,"gpt":0.3572960560384245,"spread":0.2823687614259666,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004818273,0.000207538,0.0007060208,0.0001833548,0.00009041814,0.00003077553,0.0001619849,0.00007793548,0.00005465023],"category_scores_gemma":[0.01214065,0.0001808212,0.0001161997,0.0005379656,0.0001329818,0.00002900814,0.00004788104,0.00007850039,0.000006138586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002512175,"about_ca_system_score_gemma":0.00004526227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008474614,"about_ca_topic_score_gemma":0.0001508909,"domain_scores_codex":[0.9983231,0.0001158783,0.0007013337,0.0002959483,0.0002490037,0.0003147274],"domain_scores_gemma":[0.9919018,0.006588691,0.0003917294,0.0003305636,0.0006522501,0.0001349455],"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":[0.0005081958,0.00191799,0.02619505,0.008447324,0.003651405,0.0000120542,0.002104619,0.0002461293,0.03416224,0.6302718,0.009730759,0.2827525],"study_design_scores_gemma":[0.001330965,0.0005289915,0.01745942,0.0001283,0.002720797,0.000002072049,0.00006457541,0.5357099,0.0167107,0.4231072,0.001709375,0.0005276983],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01147288,0.00002744951,0.9851882,0.00003610596,0.0001531119,0.0003603644,0.002526407,0.0000512448,0.0001842034],"genre_scores_gemma":[0.3569037,0.000009656256,0.6428114,0.00004848413,0.00002949245,0.00002708115,0.0001042263,0.00002142286,0.00004448294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5354638,"threshold_uncertainty_score":0.9961805,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126930228","doi":"10.1093/biostatistics/4.3.365","title":"A closer look at the distribution of number needed to treat (NNT): a Bayesian approach","year":2003,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Number needed to treat; Point estimation; Posterior probability; Bayesian probability; Mathematics; Statistics; Prior probability; Econometrics; Computer science; Confidence interval; Relative risk","authors":[{"name":"Lehana Thabane","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2803283646051815,"gpt":0.4902424701533613,"spread":0.2099141055481799,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00187974,0.0002585411,0.000601402,0.00002606835,0.000137092,0.00003328362,0.0002563727,0.0001806641,0.0007246483],"category_scores_gemma":[0.07882766,0.0001759264,0.0001315785,0.0003893379,0.0002953956,0.0000238175,0.0001064917,0.0001883063,0.0001412936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001411343,"about_ca_system_score_gemma":0.00007268114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003928067,"about_ca_topic_score_gemma":0.000008023766,"domain_scores_codex":[0.9967859,0.001001904,0.0009573048,0.0003819188,0.0004794747,0.0003935422],"domain_scores_gemma":[0.9769889,0.02156945,0.0002930605,0.000727247,0.0002088628,0.0002124944],"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":[0.0001774115,0.0003863674,0.0005621281,0.0002154285,0.00006278856,0.000009160707,0.0002654702,0.000005836242,0.0002683178,0.8699244,0.1246448,0.003477887],"study_design_scores_gemma":[0.001402182,0.0002162528,0.0005381785,0.00006227921,0.0003744145,0.00003130155,0.000429984,0.0003897302,0.00967009,0.9772959,0.009173545,0.0004161703],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01292235,0.00001626567,0.9703987,0.0003365202,0.0003072615,0.0009235407,0.002417342,0.00005183037,0.01262625],"genre_scores_gemma":[0.09978774,0.00001051247,0.8976184,0.0003331615,0.00009990313,0.00006852095,0.00004567634,0.00004887949,0.001987268],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1154713,"threshold_uncertainty_score":0.9289318,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4229024550","doi":"10.1093/biostatistics/kxac029","title":"A flexible approach for predictive biomarker discovery","year":2022,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Computer science; False positive paradox; Estimator; Inference; Identification (biology); Nonparametric statistics; False positives and false negatives; Metric (unit); Biomarker discovery; Multiple comparisons problem; Predictive inference; Biomarker; Data mining; False discovery rate; Truncation (statistics); Machine learning; Artificial intelligence; Statistics; Frequentist inference; Mathematics; Bayesian probability; Bayesian inference","authors":[{"name":"Philippe Boileau","is_ca":false},{"name":"Nina Ting Qi","is_ca":false},{"name":"Mark J. van der Laan","is_ca":false},{"name":"Sandrine Dudoit","is_ca":false},{"name":"Ning Leng","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5564742844991701,"gpt":0.5379670415846817,"spread":0.01850724291448846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002352662,0.0002154687,0.0005068977,0.00008806228,0.0003520396,0.0000652887,0.0003550282,0.00008013376,0.0002737933],"category_scores_gemma":[0.04407732,0.0002012856,0.000152611,0.0002986236,0.0001886299,0.00006244162,0.0003145435,0.0002487088,0.0000045918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001421209,"about_ca_system_score_gemma":0.0001206574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005763402,"about_ca_topic_score_gemma":3.080478e-7,"domain_scores_codex":[0.997259,0.0006025428,0.0007280234,0.0004941092,0.0005109782,0.0004053166],"domain_scores_gemma":[0.9653872,0.03364698,0.0002844793,0.0004508413,0.0001112302,0.0001193206],"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":[0.0009384062,0.0007887019,0.0001456417,0.0002930538,0.0002128813,0.00001136739,0.0001588398,0.00006385383,0.000233092,0.8488368,0.1377421,0.01057534],"study_design_scores_gemma":[0.001328412,0.0005638342,0.0002771264,0.000008812118,0.0001976488,0.000009783034,0.000329225,0.01628281,0.0002667394,0.9727488,0.007691543,0.0002953025],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002054326,0.00003621521,0.9808348,0.0001164749,0.0008797644,0.001298468,0.01269792,0.0001519419,0.003778973],"genre_scores_gemma":[0.01749525,0.00000600271,0.9787448,0.000253806,0.0002067643,0.0008528697,0.0001046083,0.00007007119,0.002265849],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1300505,"threshold_uncertainty_score":0.9639748,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3026963084","doi":"10.1093/biostatistics/kxaa020","title":"Causal inference for recurrent event data using pseudo-observations","year":2020,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; HEC Montréal; Jewish General Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Institut de Valorisation des Données","keywords":"Estimator; Inverse probability weighting; Statistics; Inverse probability; Mathematics; Weighting; Regression; Event (particle physics); Regression analysis; Computer science; Econometrics; Bayesian probability; Medicine","authors":[{"name":"Chien‐Lin Su","is_ca":true},{"name":"Robert W. Platt","is_ca":true},{"name":"Jean‐François Plante","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5969398403880808,"gpt":0.4979805900281105,"spread":0.09895925035997033,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0003110614,0.000179146,0.0002819567,0.00002499219,0.000136993,0.00006223905,0.0004399447,0.00006750043,0.000102923],"category_scores_gemma":[0.02198687,0.000166913,0.00003105758,0.0001845272,0.00007501293,0.00008246743,0.0002539709,0.0001377736,0.00001243402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000358843,"about_ca_system_score_gemma":0.0001768796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001781652,"about_ca_topic_score_gemma":0.00001463641,"domain_scores_codex":[0.9985112,0.00008681904,0.0004918482,0.0003937796,0.0002345974,0.0002817559],"domain_scores_gemma":[0.9955509,0.003319554,0.0001843972,0.0005035601,0.0002382484,0.0002033292],"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":[0.0000499162,0.0001032753,0.0003953455,0.0003424342,0.00003928903,0.000005867277,0.0002774438,0.0000179371,0.0007781119,0.951691,0.02470402,0.02159538],"study_design_scores_gemma":[0.0003876748,0.0003095273,0.000769938,0.000075664,0.0001543925,0.000002275917,0.00008274344,0.6756305,0.000138565,0.3157644,0.006379098,0.0003052415],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002223145,0.0000315437,0.988116,0.0007815579,0.000310613,0.000433156,0.007975884,0.00006446961,0.00006365574],"genre_scores_gemma":[0.04005379,0.00001863328,0.9589221,0.0004313563,0.0002190152,0.00001709059,0.000290532,0.00002893656,0.00001854682],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6756126,"threshold_uncertainty_score":0.9862514,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2259606755","doi":"10.1093/biostatistics/kxv054","title":"Augmented composite likelihood for copula modeling in family studies under biased sampling","year":2016,"lang":"en","type":"article","venue":"Biostatistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":10,"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; Canadian Institutes of Health Research; National Psoriasis Foundation","keywords":"Copula (linguistics); Statistics; Quasi-maximum likelihood; Marginal likelihood; Econometrics; Heritability; Maximum likelihood; Sampling bias; Sampling scheme; Marginal model; Importance sampling; Computer science; Mathematics; Sample size determination; Likelihood function; Regression analysis; Biology; Estimator; Genetics; Monte Carlo method","authors":[{"name":"Yujie Zhong","is_ca":true},{"name":"Richard J. Cook","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4362143197409914,"gpt":0.4642472793848855,"spread":0.02803295964389407,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000514428,0.0002107959,0.0004217924,0.0001010527,0.00009546463,0.00002861666,0.0001324764,0.00007893045,0.00002061118],"category_scores_gemma":[0.004389909,0.0001475131,0.00004752505,0.000133732,0.00008531779,0.00004084341,0.00006324717,0.00007936078,0.00001007332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001287286,"about_ca_system_score_gemma":0.00005311925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002279668,"about_ca_topic_score_gemma":0.00003120635,"domain_scores_codex":[0.998404,0.00009930503,0.0005820213,0.0003068851,0.0001993219,0.0004084311],"domain_scores_gemma":[0.9929072,0.006382298,0.0001212162,0.000224309,0.0002720016,0.00009297126],"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":[0.0002237212,0.0002983749,0.0006518672,0.0005409918,0.0001859942,0.00001351278,0.0004843216,0.0001268188,0.03089735,0.8622015,0.0021727,0.1022029],"study_design_scores_gemma":[0.001540434,0.0001455668,0.000600337,0.0005619719,0.00007114837,0.000001476221,0.0004108758,0.06113174,0.0006176158,0.9344915,0.0001208097,0.00030654],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04542081,0.0002297353,0.9525399,0.0002471939,0.0002626446,0.0003931537,0.0007796329,0.00006134807,0.00006559172],"genre_scores_gemma":[0.2771753,0.00009926638,0.7223971,0.0001595237,0.00004798852,0.00004486216,0.000009303432,0.00003076341,0.00003588899],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2317545,"threshold_uncertainty_score":0.6015409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}