{"meta":{"query_hash":"e941b4fc72db","filters":{"venue":"Statistics in Medicine"},"cohort_total":708,"direct_labels_cover":5,"predictions_cover":708,"exported":708,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/e941b4fc72db","api":"https://metacan.xera.ac/api/v1/cohort?venue=Statistics+in+Medicine"},"results":[{"id":"W1541729297","doi":"10.1002/sim.4334","title":"Variance estimation and confidence intervals for the standardized mortality ratio with application to the assessment of a cancer screening program","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Centre hospitalier universitaire de Québec; Institut National de Santé Publique du Québec; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Confidence interval; Statistics; Standardized mortality ratio; Estimator; Statistic; Variance (accounting); Standard error; Medicine; Mathematics","score_opus":0.050999920586490166,"score_gpt":0.42048881365164414,"score_spread":0.369488893065154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541729297","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010039121,0.00018557342,0.98639023,0.0009963042,0.00007653258,0.002102693,0.000056953875,0.000018178418,0.0001343912],"genre_scores_gemma":[0.811828,0.000047948663,0.18678214,0.00015400775,0.000060653125,0.0010912443,0.000012834476,0.000006955654,0.000016218817],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99917936,0.000037008205,0.0002574646,0.00016249108,0.0002645564,0.000099089186],"domain_scores_gemma":[0.9989933,0.00031602482,0.00014797297,0.00019336755,0.00030825761,0.000041103885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008823834,0.00008064034,0.00021065227,0.000040234292,0.00007009192,0.0000068790073,0.000059525322,0.00002262627,0.000016462036],"category_scores_gemma":[0.00039930962,0.000041697745,0.0000099101935,0.00020696793,0.00016877828,0.000026552736,0.0000153863,0.0001110093,6.501674e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0044469526,0.000084585845,0.039365485,0.00038817312,0.00021450841,0.0000029371336,0.004736564,0.0013621576,0.00047670145,0.014467094,0.00071996974,0.9337349],"study_design_scores_gemma":[0.001994894,0.0040186835,0.5871102,0.00055855897,0.000329146,0.000006059233,0.0005692715,0.40280205,0.0005011212,0.0015010635,0.00053421146,0.000074735704],"about_ca_topic_score_codex":0.0025969557,"about_ca_topic_score_gemma":0.0034142544,"teacher_disagreement_score":0.93366015,"about_ca_system_score_codex":0.000048396334,"about_ca_system_score_gemma":0.0000916587,"threshold_uncertainty_score":0.39258376},"labels":[],"label_agreement":null},{"id":"W1633467982","doi":"10.1002/sim.4326","title":"An informed reference prior for between‐study heterogeneity in meta‐analyses of binary outcomes","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Prior probability; Variance (accounting); Vagueness; Bayesian probability; Computer science; Inference; Bayesian inference; Econometrics; Meta-analysis; Statistics; Mathematics; Artificial intelligence; Fuzzy logic; Medicine","score_opus":0.5384232542332547,"score_gpt":0.40781236794008474,"score_spread":0.13061088629316991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1633467982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9894417,0.0002265363,0.008530227,0.000024986239,0.00007945339,0.00044660945,0.00045891883,0.000005007389,0.000786576],"genre_scores_gemma":[0.9855527,0.00009787714,0.014059479,0.00004912501,0.000014939197,0.0000694511,0.000116151255,0.0000110549445,0.000029179046],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99853265,0.000027786677,0.0009984556,0.00024468117,0.00003844553,0.00015796526],"domain_scores_gemma":[0.99907994,0.0002380135,0.00036488174,0.0002575789,0.000011985209,0.00004759291],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010222668,0.00012689177,0.00076037546,0.000285556,0.00002284614,0.0000028735437,0.00016537913,0.00005150188,0.0003787093],"category_scores_gemma":[0.00026725087,0.00011396707,0.000035324858,0.00010074449,0.00009706219,0.0001252082,0.000026918146,0.00008199787,0.000014161618],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019677916,0.00019351131,0.9907596,0.00003408294,0.00021626943,0.0000011990019,0.0014365063,0.00004554768,0.000012035172,0.006844148,0.000023175284,0.00041422131],"study_design_scores_gemma":[0.0013264522,0.0006922088,0.9810259,0.0000075700054,0.0001432198,1.0774815e-7,0.00058151875,0.00058569794,0.000058022142,0.01544354,0.000027895429,0.00010791653],"about_ca_topic_score_codex":0.0020693145,"about_ca_topic_score_gemma":0.0013366468,"teacher_disagreement_score":0.009733776,"about_ca_system_score_codex":0.00008245657,"about_ca_system_score_gemma":0.000012987938,"threshold_uncertainty_score":0.46474424},"labels":[],"label_agreement":null},{"id":"W1748097147","doi":"10.1002/sim.6584","title":"Joint estimation of multiple disease‐specific sensitivities and specificities via crossed random effects models for correlated reader‐based diagnostic data: application of data cloning","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Random effects model; Computer science; Maximum likelihood; Bayesian probability; Maximization; Expectation–maximization algorithm; Statistics; Artificial intelligence; Marginal likelihood; Machine learning; Mathematics; Medicine; Mathematical optimization; Pathology","score_opus":0.19629008733233633,"score_gpt":0.402939802217801,"score_spread":0.20664971488546469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1748097147","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016112885,0.0004191959,0.9920463,0.00008651696,0.00016317949,0.0010815929,0.004539119,0.00002398352,0.000028809067],"genre_scores_gemma":[0.41315848,0.00004195777,0.584997,0.000011895611,0.000044079956,0.000032779146,0.0016927863,0.000018089027,0.0000029685123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979379,0.0002310827,0.0008315841,0.00041023522,0.00039238154,0.00019677656],"domain_scores_gemma":[0.9671586,0.031156618,0.00041188856,0.0008661185,0.00027973083,0.00012704967],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018821566,0.0001923383,0.0007153549,0.00014085369,0.000047012316,0.000014815356,0.00023764455,0.00006718602,0.000003995656],"category_scores_gemma":[0.03063595,0.00016459204,0.000012065288,0.00015871967,0.00060608634,0.00017134713,0.00012474727,0.000133485,3.5101607e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002573543,0.0005704665,0.0019289786,0.00908585,0.0001232821,0.00006571284,0.00353097,0.0050649038,0.0015935572,0.80543816,0.008168537,0.16185606],"study_design_scores_gemma":[0.0027967351,0.000112755966,0.0008946888,0.0005633676,0.000112027235,0.0000012901639,0.00021087502,0.5844199,0.00017434439,0.41061226,0.00000899333,0.00009273128],"about_ca_topic_score_codex":0.00019055844,"about_ca_topic_score_gemma":0.000046149187,"teacher_disagreement_score":0.57935506,"about_ca_system_score_codex":0.00003457343,"about_ca_system_score_gemma":0.00008791588,"threshold_uncertainty_score":0.9775294},"labels":[],"label_agreement":null},{"id":"W1873375728","doi":"10.1002/sim.6314","title":"EM for regularized zero‐inflated regression models with applications to postoperative morbidity after cardiac surgery in children","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Montreal Children's Hospital","funders":"National Center for Advancing Translational Sciences; National Institute of Environmental Health Sciences; National Heart, Lung, and Blood Institute; National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; National Institutes of Health; Charles H. Hood Foundation","keywords":"Poisson regression; Count data; Poisson distribution; Expectation–maximization algorithm; Regression; Medicine; Likelihood function; Statistics; Overdispersion; Regression analysis; Zero-inflated model; Cardiac surgery; Model selection; Computer science; Econometrics; Mathematics; Maximum likelihood; Surgery; Population","score_opus":0.05210787311159458,"score_gpt":0.3740036816381332,"score_spread":0.3218958085265386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1873375728","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03459457,0.000030442829,0.9626361,0.00030802973,0.00006958315,0.0014757361,0.0006275983,0.000026881897,0.00023105931],"genre_scores_gemma":[0.288027,0.000019734112,0.71058255,0.0002365208,0.00007606776,0.00080345705,0.00013312146,0.00003162854,0.00008993972],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99813193,0.00029278846,0.00056905876,0.00038234936,0.00031160528,0.00031228916],"domain_scores_gemma":[0.99470043,0.0043760333,0.0001247657,0.00039774156,0.00025326273,0.00014776293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015340594,0.00022055993,0.0007448362,0.00019904893,0.000054122225,0.000014185925,0.00012304907,0.0000963821,0.000051652583],"category_scores_gemma":[0.003998294,0.00015212625,0.000025775626,0.00035557657,0.00012733148,0.00004296303,0.000038849244,0.00022296651,0.0000033906874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078019506,0.00019567752,0.012242472,0.00022215776,0.00007055104,0.000010408092,0.0026379763,0.00010085608,0.0003731939,0.9139463,0.012770495,0.056649726],"study_design_scores_gemma":[0.0011506836,0.00032859523,0.040410586,0.00067963975,0.0000779965,0.0000032413423,0.00012863475,0.016294142,0.00013967416,0.94025654,0.00020208348,0.00032820308],"about_ca_topic_score_codex":0.00015149868,"about_ca_topic_score_gemma":0.0001235799,"teacher_disagreement_score":0.25343242,"about_ca_system_score_codex":0.000071708084,"about_ca_system_score_gemma":0.000061588515,"threshold_uncertainty_score":0.6203528},"labels":[],"label_agreement":null},{"id":"W1909579684","doi":"10.1002/sim.6582","title":"A joint model for interval‐censored functional decline trajectories under informative observation","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Inference; Bivariate analysis; Computer science; Bayesian inference; Disease; Econometrics; Joint probability distribution; Statistics; Interval (graph theory); Bayesian probability; Process (computing); Random effects model; Bayes' theorem; Machine learning; Artificial intelligence; Medicine; Mathematics; Meta-analysis","score_opus":0.1438789696419815,"score_gpt":0.3567442275512428,"score_spread":0.2128652579092613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1909579684","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002565739,0.00007063,0.99537176,0.0027189387,0.0006984684,0.0002720137,0.000053322703,0.000043458007,0.00051483384],"genre_scores_gemma":[0.038841687,0.000012661706,0.9584787,0.001955229,0.0001497352,0.00004759268,0.00008715414,0.000009316379,0.0004179619],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866176,0.0000652135,0.00047962932,0.00021371325,0.00036650986,0.00021315874],"domain_scores_gemma":[0.9987467,0.00030969214,0.00014028285,0.00023582371,0.00044445423,0.000123035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012388765,0.0001421579,0.00028341293,0.0001364207,0.00004511919,0.000027094573,0.0002297295,0.00006277532,0.000006542623],"category_scores_gemma":[0.00096396654,0.00011168825,0.000022762355,0.00024091703,0.000097799304,0.00030011384,0.00008633168,0.0001549437,0.0000023468572],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050204297,0.000027416747,0.000048870636,0.000032617707,0.000012582622,0.0000020111966,0.0059843115,0.0039836145,0.00004329295,0.9504852,0.018382506,0.020947367],"study_design_scores_gemma":[0.00089329627,0.00011850951,0.0006604059,0.000030393678,0.0000061335368,0.0000025002323,0.000110438705,0.5289862,0.00002014157,0.46891114,0.0001921493,0.00006869083],"about_ca_topic_score_codex":0.000038252518,"about_ca_topic_score_gemma":0.00009332276,"teacher_disagreement_score":0.5250026,"about_ca_system_score_codex":0.00011477757,"about_ca_system_score_gemma":0.00020107979,"threshold_uncertainty_score":0.45545146},"labels":[],"label_agreement":null},{"id":"W1910761353","doi":"10.1002/sim.6529","title":"Bias in progression‐free survival analysis due to intermittent assessment of progression","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Survival analysis; Clinical endpoint; Progression-free survival; Estimator; Medicine; Kaplan–Meier estimator; Confidence interval; Endpoint Determination; Imputation (statistics); Tumor progression; Clinical trial; Statistics; Oncology; Econometrics; Overall survival; Internal medicine; Cancer; Mathematics; Missing data","score_opus":0.6145995339197039,"score_gpt":0.6510660572099151,"score_spread":0.03646652329021116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1910761353","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024791429,0.000051434166,0.9681013,0.0014027597,0.0010140842,0.0012444857,0.00033255375,0.0000404957,0.0030214507],"genre_scores_gemma":[0.13967246,0.0000127522,0.85986173,0.00008839612,0.00015106217,0.00010041409,0.000016887905,0.000029049774,0.00006726461],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9932576,0.0017778858,0.002328598,0.0005172769,0.0016980004,0.00042068606],"domain_scores_gemma":[0.96801406,0.029828485,0.00059205364,0.00074660475,0.00043167366,0.0003870969],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014724493,0.00027264914,0.0018459699,0.00076767855,0.000020068313,0.000012119459,0.00056830636,0.00015481829,0.0002560852],"category_scores_gemma":[0.241273,0.00019369791,0.00007062626,0.0018526107,0.0003448645,0.000032955104,0.0003756447,0.0004923645,0.0000041023613],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080591365,0.0024036332,0.22126463,0.00089392764,0.000572109,0.0012057853,0.0031337445,0.00016390401,0.00016709155,0.5101888,0.021969028,0.2372314],"study_design_scores_gemma":[0.003847221,0.0013515495,0.09953153,0.0013019324,0.00043934834,0.0000030762994,0.0007562579,0.0064829253,0.0000670099,0.8858349,0.00012898755,0.00025528608],"about_ca_topic_score_codex":0.000105162966,"about_ca_topic_score_gemma":0.0004993503,"teacher_disagreement_score":0.37564605,"about_ca_system_score_codex":0.00022748859,"about_ca_system_score_gemma":0.00018603039,"threshold_uncertainty_score":0.7898772},"labels":[],"label_agreement":null},{"id":"W1918133462","doi":"10.1002/sim.4320","title":"Modeling continuous diagnostic test data using approximate Dirichlet process distributions","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; McGill University Health Centre; Royal Victoria Regional Health Centre; McGill University","funders":"","keywords":"Nonparametric statistics; Dirichlet process; Computer science; Context (archaeology); Hierarchical Dirichlet process; Latent Dirichlet allocation; Parametric statistics; Identifiability; Cluster analysis; Bayesian probability; Data mining; Econometrics; Mathematics; Statistics; Machine learning; Artificial intelligence; Topic model","score_opus":0.09951210076774852,"score_gpt":0.36345671379794736,"score_spread":0.26394461303019884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1918133462","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005451012,0.0003175704,0.99729115,0.00014470656,0.00031055685,0.00023934327,0.00041699328,0.00006645076,0.00066815113],"genre_scores_gemma":[0.27169588,0.00006953253,0.7278955,0.00010549286,0.000084495914,0.000010789268,0.000114770686,0.0000118546095,0.000011710637],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823844,0.000091995505,0.0004618968,0.00053035055,0.00029366824,0.0003836465],"domain_scores_gemma":[0.9976237,0.00096508843,0.00010369919,0.0010099617,0.0001628418,0.00013471098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010353995,0.0001829389,0.00034150342,0.00011086028,0.0001104334,0.000030299527,0.0012615253,0.00006116108,0.000022774413],"category_scores_gemma":[0.0055947085,0.00015079406,0.000009981279,0.0004541707,0.00014802242,0.00027404155,0.000349655,0.00026252153,0.0000026541447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017747803,0.00070654036,0.0060168193,0.00039705422,0.0000499377,0.00083225744,0.00852656,0.00076499843,0.00026644464,0.86658865,0.0026650291,0.11316796],"study_design_scores_gemma":[0.00033103957,0.00005621851,0.00014392154,0.00015802117,0.000028757055,0.000025438267,0.000046607485,0.7843422,0.00002045582,0.21467786,0.00002393642,0.00014554315],"about_ca_topic_score_codex":0.0002879171,"about_ca_topic_score_gemma":0.00004503204,"teacher_disagreement_score":0.7835772,"about_ca_system_score_codex":0.000037976697,"about_ca_system_score_gemma":0.00010277379,"threshold_uncertainty_score":0.66977924},"labels":[],"label_agreement":null},{"id":"W1922077132","doi":"10.1002/sim.6972","title":"Joint modelling of longitudinal and multi‐state processes: application to clinical progressions in prostate cancer","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute","keywords":"Prostate cancer; Covariate; Longitudinal data; Random effects model; Proportional hazards model; Longitudinal study; Joint (building); Baseline (sea); Prostate-specific antigen","score_opus":0.29581018521558533,"score_gpt":0.5043951133576747,"score_spread":0.2085849281420894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1922077132","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.053178046,0.00013249154,0.9451587,0.00055472716,0.00007368928,0.0006430896,0.00021309522,0.000011849524,0.00003431594],"genre_scores_gemma":[0.39694962,0.0006579134,0.6021035,0.000031904456,0.00003200396,0.00015559641,0.000002241867,0.000013789269,0.00005343661],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981158,0.00011790802,0.0009622482,0.00032920483,0.00024017041,0.00023469963],"domain_scores_gemma":[0.9966852,0.0025006006,0.00022532657,0.00018578712,0.00026744264,0.00013564034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013477409,0.00013627647,0.00048421827,0.00013364779,0.000022050497,0.000004251717,0.00009206326,0.00004320732,0.000034554425],"category_scores_gemma":[0.007882439,0.0000822354,0.0000085628635,0.0002922536,0.0002976187,0.000031926134,0.000057389367,0.00015771507,0.0000016967733],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031781083,0.00058621215,0.24242382,0.002166205,0.00003202121,0.000047950398,0.004772304,0.00021056802,0.00072516437,0.11990574,0.0005548158,0.6282574],"study_design_scores_gemma":[0.0032927515,0.00063135976,0.06541233,0.0055347043,0.00005047665,0.000004038381,0.00030410785,0.07208772,0.00031424165,0.85195667,0.000097671975,0.00031391924],"about_ca_topic_score_codex":0.00023906295,"about_ca_topic_score_gemma":0.00051235687,"teacher_disagreement_score":0.73205096,"about_ca_system_score_codex":0.00004153217,"about_ca_system_score_gemma":0.00010689534,"threshold_uncertainty_score":0.9436584},"labels":[],"label_agreement":null},{"id":"W1940783033","doi":"10.1002/sim.6110","title":"Shift-invariant target in allocation problems","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Invariant (physics); Scale invariance; Computer science; Mathematical optimization; Optimal allocation; Mathematics; Statistics","score_opus":0.10073763129737792,"score_gpt":0.4457221730689747,"score_spread":0.34498454177159676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1940783033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029360862,0.0001539038,0.980892,0.0014756591,0.0006680117,0.00036648108,0.000015141968,0.000017046948,0.013475696],"genre_scores_gemma":[0.5223239,0.000014420307,0.47680235,0.00039586448,0.00010655999,0.00004212634,0.000019337282,0.000012998452,0.00028241982],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996263,0.0008511324,0.0009688251,0.0004505407,0.0011798951,0.00028660204],"domain_scores_gemma":[0.99477303,0.004379948,0.00018827323,0.0004439641,0.0001048358,0.00010994662],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01153594,0.00014499544,0.00041677136,0.00045856385,0.00003471802,0.0000353867,0.00048655106,0.00007107073,0.0009022531],"category_scores_gemma":[0.020138092,0.00010568843,0.000013677191,0.0009168888,0.00023069282,0.00011868111,0.000072308525,0.00023138423,0.00013696354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011295514,0.00027868757,0.03978525,0.000045704677,0.0000097191605,0.00007736907,0.010331881,0.005049238,0.014162682,0.8081876,0.017032547,0.10492636],"study_design_scores_gemma":[0.001482693,0.0004457093,0.07327709,0.00011993083,0.0000045487363,0.000003897174,0.0005493037,0.12924705,0.00049696333,0.7825622,0.011607573,0.00020304201],"about_ca_topic_score_codex":0.000473505,"about_ca_topic_score_gemma":0.00036705338,"teacher_disagreement_score":0.51938784,"about_ca_system_score_codex":0.0000946958,"about_ca_system_score_gemma":0.000049731734,"threshold_uncertainty_score":0.9881157},"labels":[],"label_agreement":null},{"id":"W1953290087","doi":"10.1002/sim.6733","title":"Development of a diagnostic test based on multiple continuous biomarkers with an imperfect reference test","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health; U.S. Department of Defense","keywords":"Test (biology); Computer science; Imperfect; Statistics; Diagnostic test; Medicine; Mathematics; Biology; Pediatrics","score_opus":0.07780357091141932,"score_gpt":0.3776192654494842,"score_spread":0.2998156945380649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1953290087","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01484996,0.000016233866,0.9815049,0.00008738129,0.00008968135,0.00045384694,0.000397184,0.000041342704,0.0025594404],"genre_scores_gemma":[0.38876942,0.0000027875733,0.61104137,0.000056315894,0.000023855306,0.00003395395,0.000042614367,0.000019795518,0.000009867608],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99791616,0.00015697643,0.0006780772,0.00033253073,0.00060003053,0.00031624548],"domain_scores_gemma":[0.94280994,0.056018576,0.0002344515,0.00037025765,0.00030675874,0.000259988],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001381057,0.00025063442,0.00057917327,0.0001733799,0.00004386335,0.0000103985785,0.00021179878,0.00007519464,0.00011099393],"category_scores_gemma":[0.15767564,0.00017190987,0.000008927047,0.00031287438,0.00036748117,0.000030970277,0.000026876329,0.00022614712,0.000006385261],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015655053,0.005027592,0.35599682,0.0016661058,0.0001274966,0.0010748844,0.0065516713,0.000022569675,0.002695923,0.29110986,0.009118806,0.32504275],"study_design_scores_gemma":[0.025952395,0.030825961,0.21696615,0.008852929,0.00047166756,0.000056341836,0.0054297983,0.1006772,0.0045221923,0.6022583,0.001780273,0.002206758],"about_ca_topic_score_codex":0.00012555716,"about_ca_topic_score_gemma":0.00060207053,"teacher_disagreement_score":0.37391946,"about_ca_system_score_codex":0.00009862532,"about_ca_system_score_gemma":0.00034280214,"threshold_uncertainty_score":0.8494196},"labels":[],"label_agreement":null},{"id":"W1960011844","doi":"10.1002/sim.6123","title":"Extending the Bayesian Adjustment for Confounding algorithm to binary treatment covariates to estimate the effect of smoking on carotid intima-media thickness: the Multi-Ethnic Study of Atherosclerosis","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"National Center for Advancing Translational Sciences; National Heart, Lung, and Blood Institute; Fonds de Recherche du Québec - Santé; National Center for Research Resources; Natural Sciences and Engineering Research Council of Canada","keywords":"Confounding; Covariate; Statistics; Bayesian probability; Sample size determination; Medicine; Mathematics; Weighting; Algorithm; Econometrics; Radiology","score_opus":0.10143956355485871,"score_gpt":0.46787909410228273,"score_spread":0.366439530547424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1960011844","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07959876,0.000055753215,0.91457576,0.0003481655,0.00038746838,0.004849413,0.0001035087,0.000053425272,0.000027752325],"genre_scores_gemma":[0.7481006,0.000036582518,0.25025478,0.00011573982,0.00011821248,0.0012913082,0.000011938405,0.000053341242,0.000017554901],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99751943,0.0005722384,0.00074152264,0.0003174125,0.00050301437,0.00034636023],"domain_scores_gemma":[0.97917396,0.01951472,0.00037249917,0.00072640873,0.00014174609,0.00007064029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035166242,0.0003318896,0.0007410901,0.00016215598,0.00018285956,0.000011867986,0.00047920118,0.00006021411,0.000014344617],"category_scores_gemma":[0.0066988533,0.00014737136,0.000053863758,0.00037734484,0.00023786124,0.000028066766,0.00012544196,0.00023669138,9.0602936e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009891313,0.0023689822,0.013845601,0.0012890577,0.0012609895,0.000013767339,0.2046039,0.009456728,0.01894476,0.27426437,0.001620893,0.47134185],"study_design_scores_gemma":[0.031603843,0.15818019,0.14849605,0.014686241,0.006026082,0.00002869001,0.06344428,0.2041562,0.06881506,0.3018004,0.00036938913,0.0023935586],"about_ca_topic_score_codex":0.00034347572,"about_ca_topic_score_gemma":0.00036645125,"teacher_disagreement_score":0.6685018,"about_ca_system_score_codex":0.00025274412,"about_ca_system_score_gemma":0.000023789311,"threshold_uncertainty_score":0.80196375},"labels":[],"label_agreement":null},{"id":"W1964213907","doi":"10.1002/sim.1026","title":"An improved CML estimation procedure for the Rasch model with item response data","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Heritage Foundation for Medical Research","keywords":"Rasch model; Estimator; Item response theory; Polytomous Rasch model; Computer science; Ordinal data; Statistics; Conditional independence; Independence (probability theory); Goodness of fit; Local independence; Econometrics; Mathematics; Psychometrics","score_opus":0.5951936693828095,"score_gpt":0.5402817360493364,"score_spread":0.054911933333473106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964213907","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063227066,0.0002848752,0.98900485,0.0031824897,0.0001986633,0.0005097385,0.0002698137,0.000026981565,0.0001998752],"genre_scores_gemma":[0.27270392,0.000036862537,0.72605586,0.00038855374,0.000094827206,0.000035308592,0.000039741266,0.00001340612,0.0006315366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974725,0.00033224814,0.0005855599,0.000523016,0.0008356152,0.00025106166],"domain_scores_gemma":[0.92254645,0.07542081,0.0002875696,0.001351831,0.00031173648,0.00008158735],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0147936335,0.00012975637,0.00028753668,0.000287114,0.00017653682,0.00007139347,0.0013005811,0.00005136018,0.000104334424],"category_scores_gemma":[0.33036822,0.0000622226,0.000008549298,0.001255861,0.00021703837,0.00019515124,0.00008297922,0.00019195197,0.0000034674201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016066656,0.00013230243,0.0048831063,0.000049702692,0.000028415388,0.0000173801,0.0031467734,0.026031042,0.0005597884,0.0046166647,0.14180453,0.81712365],"study_design_scores_gemma":[0.0009492328,0.00047642173,0.0081775645,0.000034485136,0.000022466087,0.000009516651,0.0010243148,0.9540553,0.000004134343,0.034402452,0.0007586796,0.00008540965],"about_ca_topic_score_codex":0.000029480283,"about_ca_topic_score_gemma":0.00006544147,"teacher_disagreement_score":0.9280243,"about_ca_system_score_codex":0.000025240366,"about_ca_system_score_gemma":0.000061513456,"threshold_uncertainty_score":0.6752724},"labels":[],"label_agreement":null},{"id":"W1964475341","doi":"10.1002/sim.3150","title":"A critical appraisal of propensity‐score matching in the medical literature between 1996 and 2003","year":2007,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1250,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Wilcoxon signed-rank test; Statistics; Observational study; Matching (statistics); Selection bias; Logistic regression; Sample size determination; Statistical significance; Medicine; Mathematics; Mann–Whitney U test","score_opus":0.2610013184506083,"score_gpt":0.5385518179316583,"score_spread":0.27755049948105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964475341","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000023897848,0.8471528,0.15052512,0.00013599114,0.00018194476,0.0010049988,0.0002986965,0.00003714857,0.0006393584],"genre_scores_gemma":[0.000092466355,0.8832279,0.11592955,0.00008253232,0.00033030077,0.000058893977,0.00021293393,0.000052662777,0.000012795826],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99605024,0.00057562615,0.001539771,0.0003873369,0.0010481885,0.00039882286],"domain_scores_gemma":[0.97870207,0.020145297,0.00033543305,0.00045795544,0.00023006814,0.00012919214],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004457467,0.00042904716,0.0024102915,0.00040834825,0.000032493997,0.000014250727,0.000513162,0.0005737967,0.00005300863],"category_scores_gemma":[0.04742031,0.00024653197,0.00003858292,0.0009533892,0.0008578071,0.00006270395,0.00015627529,0.0023704416,0.0000011374929],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007285114,0.00008025152,0.00015144087,0.035943996,0.000030003373,0.001268713,0.002018572,9.882061e-9,1.7622652e-7,0.3921306,0.002840202,0.56552875],"study_design_scores_gemma":[0.0005263903,0.00041779105,0.00022267608,0.16966456,0.00060877576,0.00048702862,0.000338661,0.000009597476,7.240726e-7,0.7095591,0.11762336,0.00054134976],"about_ca_topic_score_codex":0.000050213224,"about_ca_topic_score_gemma":0.000113415386,"teacher_disagreement_score":0.5649874,"about_ca_system_score_codex":0.00006538287,"about_ca_system_score_gemma":0.00023372969,"threshold_uncertainty_score":0.9999987},"labels":[],"label_agreement":null},{"id":"W1964786254","doi":"10.1002/sim.4005","title":"Flexible modeling of competing risks in survival analysis","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Proportional hazards model; Estimator; Statistics; Econometrics; Hazard; Event (particle physics); Regression analysis; Hazard ratio; Survival analysis; Regression; Accelerated failure time model; Computer science; Mathematics; Confidence interval","score_opus":0.20323835890471878,"score_gpt":0.4819807042041127,"score_spread":0.2787423452993939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964786254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11352405,0.000017749013,0.88105065,0.00005650103,0.00022102828,0.00009334788,0.000084262116,0.000012945294,0.004939489],"genre_scores_gemma":[0.5490781,0.0000122161055,0.45083132,0.000011814756,0.00003560234,0.0000033794493,0.000009192417,0.0000074439617,0.000010942604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99823,0.00016520405,0.0008037649,0.00020804262,0.00035575815,0.00023725626],"domain_scores_gemma":[0.99467033,0.004672135,0.00015880923,0.00027854185,0.0001503696,0.00006978934],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025621739,0.00012660387,0.0006828846,0.00038630696,0.00002267912,0.0000048002844,0.00016942662,0.000074433876,0.0005774045],"category_scores_gemma":[0.014439848,0.00010538524,0.000025477215,0.0008201189,0.00017898146,0.000017559561,0.000044836408,0.00049841043,0.0000016753753],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021961212,0.00008344551,0.0432995,0.00013482115,0.000048798625,0.000018905095,0.0010042748,0.0010711555,0.00062857155,0.94726616,0.000033204233,0.0063892053],"study_design_scores_gemma":[0.00043990221,0.00004484935,0.012284008,0.00007806994,0.000111161375,5.0288907e-7,0.0004975656,0.46873316,0.00004219274,0.51767886,0.000004433335,0.0000852962],"about_ca_topic_score_codex":0.0021645043,"about_ca_topic_score_gemma":0.002443082,"teacher_disagreement_score":0.467662,"about_ca_system_score_codex":0.000019000958,"about_ca_system_score_gemma":0.000036232323,"threshold_uncertainty_score":0.9938619},"labels":[],"label_agreement":null},{"id":"W1966338615","doi":"10.1002/sim.1877","title":"Two‐stage adaptive strategy for superiority and non‐inferiority hypotheses in active controlled clinical trials","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"National Cancer Institute","keywords":"Sample size determination; Interim; Type I and type II errors; Flexibility (engineering); Computer science; Margin (machine learning); Adaptive design; Stage (stratigraphy); Early stopping; Statistical hypothesis testing; Statistics; Econometrics; Clinical trial; Mathematics; Medicine; Artificial intelligence; Machine learning","score_opus":0.7120274947519263,"score_gpt":0.6475429193750869,"score_spread":0.06448457537683938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1966338615","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069865964,0.0001368929,0.9183394,0.0006171965,0.0012438485,0.006023938,0.0024523884,0.000049169204,0.0012712069],"genre_scores_gemma":[0.3043965,0.0003001381,0.69406223,0.00020362857,0.0006319446,0.0002916728,0.00000935475,0.00004393605,0.00006056977],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98952407,0.003997046,0.0045365226,0.00078815676,0.00055140594,0.0006028059],"domain_scores_gemma":[0.7289475,0.2693967,0.0007603608,0.0003674587,0.00026627665,0.00026170223],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03832008,0.00042710674,0.0046313195,0.00022288815,0.00007786651,0.000030183128,0.00025959805,0.00035676121,0.00021178824],"category_scores_gemma":[0.6027522,0.0003203613,0.00016175381,0.00028645858,0.0011601076,0.000084332394,0.00008720239,0.0009798094,0.0000035723008],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0137485415,0.0009209234,0.0037228628,0.00033163524,0.00026700276,0.00020835293,0.00093213737,0.000045048128,0.00017846763,0.9418347,0.00022809162,0.037582245],"study_design_scores_gemma":[0.06440975,0.0022397453,0.014534292,0.00039203683,0.00027710272,0.0000025970273,0.0012293934,0.0015061293,0.00006878043,0.9150024,0.00004207176,0.0002956773],"about_ca_topic_score_codex":0.00049213547,"about_ca_topic_score_gemma":0.0013626132,"teacher_disagreement_score":0.56443214,"about_ca_system_score_codex":0.0002009602,"about_ca_system_score_gemma":0.00039720212,"threshold_uncertainty_score":0.99992484},"labels":[],"label_agreement":null},{"id":"W1967330157","doi":"10.1002/sim.1015","title":"Identification of significant host factors for HIV dynamics modelled by non‐linear mixed‐effects models","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Covariate; Missing data; Bayes' theorem; Statistics; Linear model; Computer science; Bayes factor; Imputation (statistics); Model selection; Generalized linear mixed model; Data set; Econometrics; Mathematics; Bayesian probability","score_opus":0.022087407292849283,"score_gpt":0.29134701606028024,"score_spread":0.26925960876743094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1967330157","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016024414,0.00017371264,0.99619114,0.00041095773,0.00045187218,0.00059154653,0.0003603281,0.000029116225,0.0001889075],"genre_scores_gemma":[0.43605968,0.0001152629,0.5632087,0.000059377628,0.000034527136,0.00003237294,0.00007780673,0.000017009792,0.00039528022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813086,0.000109667984,0.0006695977,0.0004247584,0.0003695074,0.00029560938],"domain_scores_gemma":[0.99792373,0.0009816828,0.00027422514,0.0005182455,0.00018987418,0.000112253394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074060576,0.00020416937,0.000462454,0.00017801693,0.000058612968,0.000016018099,0.0005495753,0.00010047039,0.000007521651],"category_scores_gemma":[0.0004158783,0.00016906932,0.00003831281,0.0003199911,0.00013413894,0.00015496323,0.000055987744,0.00016413601,0.000002009946],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021902002,0.0003054317,0.000092501934,0.00048735613,0.000046745292,0.00001316671,0.0048243385,0.0038659356,0.015556922,0.9128855,0.02435914,0.037541095],"study_design_scores_gemma":[0.00081431604,0.00015391828,0.000044695666,0.000059849088,0.000024315139,7.406281e-7,0.00003856041,0.8718145,0.002398304,0.12448126,0.000024063638,0.00014548506],"about_ca_topic_score_codex":0.000040506016,"about_ca_topic_score_gemma":0.000009569858,"teacher_disagreement_score":0.86794853,"about_ca_system_score_codex":0.000074383075,"about_ca_system_score_gemma":0.000020954625,"threshold_uncertainty_score":0.68944466},"labels":[],"label_agreement":null},{"id":"W1968677777","doi":"10.1002/sim.3829","title":"Bayesian adjustment for exposure misclassification in case–control studies","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; BC Cancer Agency; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Bayesian probability; Statistics; Context (archaeology); Observational study; Econometrics; Computer science; Sample size determination; Observational error; Explanatory power; Mathematics","score_opus":0.08384288068993881,"score_gpt":0.43549343458039363,"score_spread":0.35165055389045485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968677777","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001588653,0.00026436627,0.9947712,0.001055771,0.00078002264,0.0007781253,0.00034961573,0.000022258435,0.00038998827],"genre_scores_gemma":[0.23405978,0.000051186107,0.76516247,0.00014347048,0.00024597274,0.00022517616,0.000012070457,0.000019714587,0.00008015807],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983063,0.00015183399,0.00070708804,0.00030204686,0.00022318769,0.0003095459],"domain_scores_gemma":[0.99079347,0.008464814,0.00016012922,0.00029947635,0.00019125953,0.00009087541],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015726347,0.0001880198,0.0005382794,0.00016944601,0.00005513777,0.000007815026,0.00012014271,0.00010260436,0.00017960984],"category_scores_gemma":[0.01732719,0.00014456235,0.000019516312,0.00018070177,0.00025846116,0.000030951713,0.000016304546,0.00035406664,0.0000021682285],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005116704,0.00010794012,0.0013975641,0.0003393368,0.00003514291,0.00028694994,0.0013345825,6.901092e-7,0.0005612881,0.8706219,0.0052434886,0.12001992],"study_design_scores_gemma":[0.00257135,0.00033263868,0.0062174927,0.00017746552,0.000103057646,0.000073534145,0.0014531453,0.0067572533,0.000034229426,0.9817972,0.00031235826,0.00017027109],"about_ca_topic_score_codex":0.000052015697,"about_ca_topic_score_gemma":0.0021031126,"teacher_disagreement_score":0.23247114,"about_ca_system_score_codex":0.00006629675,"about_ca_system_score_gemma":0.000046949655,"threshold_uncertainty_score":0.9909503},"labels":[],"label_agreement":null},{"id":"W1969898458","doi":"10.1002/sim.5980","title":"Dynamic prediction of risk of death using history of cancer recurrences in joint frailty models","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Cancer Research; Institut National Du Cancer; Cancer Research UK","keywords":"Breast cancer; Event (particle physics); Cancer; Medicine; Cancer recurrence; Clinical endpoint; Disease; Time point; Random effects model; Time horizon; Computer science; Statistics; Internal medicine; Clinical trial; Mathematics","score_opus":0.19265737789735804,"score_gpt":0.4183232547021625,"score_spread":0.22566587680480443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969898458","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20119469,0.0007911856,0.79611725,0.000011308541,0.0003273701,0.00021953133,0.0007502764,0.000004543126,0.0005838758],"genre_scores_gemma":[0.5383635,0.0005141977,0.46106476,0.0000045127636,0.000010637491,0.00001159381,0.000005822737,0.00000776386,0.00001717519],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99820095,0.00018845465,0.0009811297,0.00015430506,0.00033062606,0.00014451791],"domain_scores_gemma":[0.9971991,0.00171424,0.0005804644,0.00019178141,0.0002714635,0.000042940712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079199224,0.00011305681,0.00058235566,0.0002008736,0.000007209081,7.366633e-7,0.000100718804,0.0000679746,0.00044624796],"category_scores_gemma":[0.004945185,0.000090055655,0.000017877754,0.00015470202,0.00034764473,0.00004420938,0.000027543021,0.0002094846,2.1132688e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011513429,0.0006666947,0.06526843,0.0038679452,0.00013092547,0.000009041777,0.020476885,0.0027662711,0.012094055,0.7658996,0.0026473203,0.12605771],"study_design_scores_gemma":[0.00037646326,0.0001197808,0.03388334,0.0008559533,0.000053732125,3.223256e-7,0.00028341956,0.36688134,0.00007741591,0.59741783,0.0000023436567,0.000048055386],"about_ca_topic_score_codex":0.013574398,"about_ca_topic_score_gemma":0.0006488371,"teacher_disagreement_score":0.3641151,"about_ca_system_score_codex":0.00024342594,"about_ca_system_score_gemma":0.0001607511,"threshold_uncertainty_score":0.9929943},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"observational","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W1970654520","doi":"10.1002/sim.3701","title":"Flexible modeling of the cumulative effects of time‐dependent exposures on the hazard","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":162,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research; Faculty of Medicine, McGill University; McGill University","keywords":"Covariate; Proportional hazards model; Statistics; Econometrics; Hazard; Regression analysis; Medicine; Computer science; Mathematics","score_opus":0.2270755262068856,"score_gpt":0.43366854871840455,"score_spread":0.20659302251151895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970654520","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.460369,0.005239285,0.39739177,0.08371398,0.0023773601,0.0042923526,0.001034799,0.00005055233,0.04553092],"genre_scores_gemma":[0.99436027,0.00009018789,0.0017182758,0.0032599964,0.00011468748,0.000016001848,0.0000082347815,0.000010913559,0.00042141255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99685335,0.00033190494,0.0022413211,0.00021520637,0.00017381745,0.00018441293],"domain_scores_gemma":[0.9947907,0.003477198,0.0011747049,0.00044531608,0.000070322254,0.00004180211],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008124019,0.000118861906,0.0006887708,0.0001579461,0.00006770705,0.0000050795848,0.00028190916,0.0000595169,0.00015999167],"category_scores_gemma":[0.010488985,0.000085156105,0.00003807147,0.00016883208,0.00012972779,0.000044103857,0.000024865829,0.00018675532,0.00005070034],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044676985,0.00014651126,0.0051301415,0.0004141164,0.0000594708,0.0000015474325,0.007751571,0.040349726,0.000066003435,0.9268062,0.018684722,0.000545285],"study_design_scores_gemma":[0.0019495657,0.0008088883,0.02993267,0.0012075608,0.00002417473,0.0000013377471,0.0013610912,0.35578802,0.00035630382,0.60798836,0.00034856837,0.00023348969],"about_ca_topic_score_codex":0.00039284615,"about_ca_topic_score_gemma":0.000045415873,"teacher_disagreement_score":0.5339913,"about_ca_system_score_codex":0.00013950153,"about_ca_system_score_gemma":0.00006224096,"threshold_uncertainty_score":0.99784607},"labels":[],"label_agreement":null},{"id":"W1971149402","doi":"10.1002/sim.3104","title":"Using the bootstrap to improve estimation and confidence intervals for regression coefficients selected using backwards variable elimination","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Institute of Health Services and Policy Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Statistics; Confidence interval; Regression analysis; Mathematics; Regression; Percentile; Linear regression; Segmented regression; Robust confidence intervals; Variable (mathematics); Econometrics; Polynomial regression","score_opus":0.1800998728779016,"score_gpt":0.5190475704760493,"score_spread":0.3389476975981477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971149402","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064124954,0.000038283702,0.99211943,0.00009294094,0.00028172435,0.00084310485,0.0001233119,0.000017223118,0.000071489354],"genre_scores_gemma":[0.1297477,0.0000057089833,0.8699679,0.00012639113,0.0000650337,0.000011750702,0.000016367487,0.000020575202,0.00003857584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985008,0.0000960829,0.00054402184,0.00026373824,0.00029924326,0.00029608453],"domain_scores_gemma":[0.9950715,0.0040219054,0.00020173119,0.00017211,0.00043645882,0.000096322496],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002541361,0.00015313803,0.0003019296,0.00012118306,0.00014591706,0.000017261364,0.000093536706,0.000068820234,0.000013968169],"category_scores_gemma":[0.014807249,0.00010466891,0.000008601477,0.00031226783,0.00013845235,0.000060475522,0.00004066126,0.00015292117,1.852737e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028219522,0.000081831146,0.000032360025,0.00052734476,0.00002153509,0.000010276656,0.0024933834,0.0031168556,0.054383624,0.835196,0.00046897982,0.103385605],"study_design_scores_gemma":[0.0005555461,0.0001858271,0.00010676572,0.0004895768,0.000060028164,0.0000067898127,0.0002842033,0.5712724,0.0011904119,0.4257232,0.00003182719,0.00009346117],"about_ca_topic_score_codex":0.000062152285,"about_ca_topic_score_gemma":0.00002578591,"teacher_disagreement_score":0.5681555,"about_ca_system_score_codex":0.00012366353,"about_ca_system_score_gemma":0.00005185189,"threshold_uncertainty_score":0.9934915},"labels":[],"label_agreement":null},{"id":"W1971827711","doi":"10.1002/sim.789","title":"Incremental net benefit in randomized clinical trials","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University; St. Joseph's Hospital","funders":"","keywords":"Censoring (clinical trials); Computer science; Clinical trial; Statistics; Econometrics; Randomized controlled trial; Medicine; Mathematics; Surgery","score_opus":0.5807754213420423,"score_gpt":0.5744626345624336,"score_spread":0.00631278677960867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971827711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3938146,0.018897913,0.34464923,0.15803616,0.011388121,0.010178002,0.0026636382,0.00014689525,0.060225446],"genre_scores_gemma":[0.89889306,0.010422522,0.046668936,0.03733422,0.0032964041,0.00050338125,0.00059472915,0.000097523814,0.0021892285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97927976,0.0037197843,0.015763236,0.00059204554,0.00017147853,0.00047369953],"domain_scores_gemma":[0.96795446,0.028423015,0.0029867245,0.00039162108,0.000048598893,0.00019558628],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2517467,0.0002017983,0.004290165,0.0006173835,0.000050249873,0.000020752133,0.0002467042,0.0001765981,0.0030024943],"category_scores_gemma":[0.14728005,0.0002095347,0.00011318813,0.00030129627,0.0003031844,0.00013305392,0.000044141805,0.0003885593,0.0005866734],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035952001,0.00023045109,0.22891553,0.0001538271,0.00010535258,0.000039765182,0.0018164915,0.00012835277,8.09253e-7,0.6934448,0.06714833,0.0044210753],"study_design_scores_gemma":[0.24996054,0.00027403785,0.09183756,0.000507199,0.000039331637,0.000012217055,0.0017662479,0.04018792,4.3582853e-7,0.57583016,0.03903565,0.00054871006],"about_ca_topic_score_codex":0.004497928,"about_ca_topic_score_gemma":0.0025080652,"teacher_disagreement_score":0.50507843,"about_ca_system_score_codex":0.0004141585,"about_ca_system_score_gemma":0.00009602483,"threshold_uncertainty_score":0.9979089},"labels":[],"label_agreement":null},{"id":"W1971972523","doi":"10.1002/sim.1463","title":"Hierarchical Bayesian spatial modelling of small‐area rates of non‐rare disease","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"British Columbia Centre of Excellence for Women's Health; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Bayesian probability; Computer science; Bayesian hierarchical modeling; Statistics; Hierarchical database model; Bayesian inference; Econometrics; Artificial intelligence; Data mining; Mathematics","score_opus":0.02524430431112855,"score_gpt":0.30175547951473863,"score_spread":0.27651117520361007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971972523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15267178,0.00034592746,0.8458419,0.000118394215,0.00009537124,0.00010484953,0.000135566,0.0000012430979,0.0006849857],"genre_scores_gemma":[0.9321472,0.00023359139,0.067100294,0.00007551814,0.000057168476,0.00000728665,0.00025466387,0.000010270211,0.00011398338],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989723,0.00013041736,0.00043326497,0.00018991932,0.00010071221,0.0001733851],"domain_scores_gemma":[0.99933004,0.00011472317,0.00015001402,0.00020475383,0.00011043797,0.00009001185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003929634,0.00010184156,0.00028136768,0.00005879333,0.000021401544,8.9273175e-7,0.00009322482,0.00008688434,0.00006072795],"category_scores_gemma":[0.001348186,0.00008865331,0.000027623153,0.00007733908,0.00020097796,6.2634854e-7,0.000024399898,0.00008973055,4.041173e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004500901,0.0004883297,0.84636325,0.00049910747,0.00021130125,0.000043936707,0.0007953956,0.08513493,0.030381493,0.02132535,0.0055426415,0.008764174],"study_design_scores_gemma":[0.0069041783,0.0027120358,0.3766034,0.0005043757,0.00030481291,0.000011941318,0.00095855736,0.49075174,0.010358719,0.10656483,0.003444435,0.000880998],"about_ca_topic_score_codex":0.00013652886,"about_ca_topic_score_gemma":0.00012720034,"teacher_disagreement_score":0.77947545,"about_ca_system_score_codex":0.000008210692,"about_ca_system_score_gemma":0.000110071735,"threshold_uncertainty_score":0.36151773},"labels":[],"label_agreement":null},{"id":"W1972445384","doi":"10.1002/sim.5690","title":"On estimating average effects for multiple treatment groups","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"","keywords":"Covariate; Statistics; Propensity score matching; Robustness (evolution); Population; Econometrics; Observational study; Variable (mathematics); Average treatment effect; Instrumental variable; Mathematics; Medicine; Biology","score_opus":0.10760751865554542,"score_gpt":0.4506370219169127,"score_spread":0.3430295032613673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972445384","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013592341,0.00005133771,0.9841381,0.000052678293,0.00039647843,0.00088952435,0.00006482866,0.00012755835,0.0006871889],"genre_scores_gemma":[0.38432974,0.000009241334,0.6149774,0.00008726097,0.00021027814,0.00022999232,0.00003876751,0.000026668875,0.00009061086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99891776,0.000053111977,0.00031963724,0.00015968045,0.0001866882,0.0003631168],"domain_scores_gemma":[0.98969185,0.009800056,0.0001250805,0.00024244409,0.000045216253,0.00009534961],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00045582678,0.00019406341,0.0003690188,0.00010047293,0.00005529474,0.0000040803093,0.00007953839,0.000060171653,0.00004287949],"category_scores_gemma":[0.009383791,0.00014407157,0.000019341343,0.00008062042,0.00007688413,0.0000573506,0.000017610662,0.00011960859,0.0000075646967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056662735,0.00031496675,0.0010996264,0.00037670715,0.000023213655,0.000017771381,0.002295094,0.0000480418,0.0007933324,0.95719403,0.0051352447,0.032645334],"study_design_scores_gemma":[0.0018728095,0.0014032816,0.00040783285,0.00043476594,0.000045510827,0.000004082263,0.00007856427,0.01481785,0.0028686698,0.9776277,0.00025937508,0.00017953562],"about_ca_topic_score_codex":0.000022912125,"about_ca_topic_score_gemma":0.000027372784,"teacher_disagreement_score":0.3707374,"about_ca_system_score_codex":0.00024361904,"about_ca_system_score_gemma":0.000012213944,"threshold_uncertainty_score":0.9989606},"labels":[],"label_agreement":null},{"id":"W1972795335","doi":"10.1002/sim.3989","title":"Estimation of relative risk and prevalence ratio","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Estimator; Statistics; Mathematics; Binomial regression; Logistic regression; Binomial (polynomial); Negative binomial distribution; Confounding; Point estimation; Relative risk; Econometrics; Computer science; Confidence interval; Poisson distribution","score_opus":0.056982222668341694,"score_gpt":0.4327492605441972,"score_spread":0.3757670378758555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972795335","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05781436,0.00003970984,0.940701,0.000056771358,0.00006515989,0.0002178851,0.000062974446,0.00003455107,0.0010076076],"genre_scores_gemma":[0.47495788,0.00011964642,0.52480847,0.0000074742647,0.000014474924,0.000009342782,0.0000047755057,0.0000061705937,0.000071741466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992433,0.000049999933,0.00032899526,0.0001196496,0.00017069142,0.000087327746],"domain_scores_gemma":[0.9975757,0.0018908296,0.00022732806,0.00018412468,0.00008914509,0.000032891683],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006248485,0.00008269612,0.00019985877,0.00008197681,0.000022912103,0.0000020367115,0.00006519543,0.000055725457,0.00010656935],"category_scores_gemma":[0.011664962,0.00006738107,0.0000045498796,0.000101489575,0.00035937296,0.000088621724,0.00002403262,0.0003281997,9.879419e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008938409,0.000020874466,0.0030222544,0.00019464786,0.0000050248523,0.000003323901,0.0014299875,0.000008518454,0.0024409562,0.9680081,0.0004394016,0.024418],"study_design_scores_gemma":[0.00025036663,0.00015344564,0.005594871,0.000171975,0.00003577688,0.0000032774342,0.00006877559,0.0119521385,0.0022259015,0.9794637,0.000017300496,0.00006246008],"about_ca_topic_score_codex":0.000031900618,"about_ca_topic_score_gemma":0.00008375703,"teacher_disagreement_score":0.41714352,"about_ca_system_score_codex":0.0000132376035,"about_ca_system_score_gemma":0.000018930956,"threshold_uncertainty_score":0.99666023},"labels":[],"label_agreement":null},{"id":"W1972837603","doi":"10.1002/sim.2367","title":"Comparison of variance estimation approaches in a two-state Markov model for longitudinal data with misclassification","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Heritage Foundation for Medical Research","keywords":"Jackknife resampling; Unobservable; Statistics; Variance (accounting); Markov chain; Covariance; Resampling; Computer science; Mathematics; Econometrics; Observable; Estimator","score_opus":0.31867627678948385,"score_gpt":0.4844635956960856,"score_spread":0.16578731890660175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972837603","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006893356,0.0000449722,0.99727875,0.000402488,0.000028496677,0.0005034303,0.0005995983,0.000011979667,0.00044095042],"genre_scores_gemma":[0.32117757,0.00000672965,0.67852575,0.000011781229,0.000025825575,0.000040455445,0.0001653709,0.000013053462,0.000033435543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982708,0.00009393093,0.0007653578,0.00035146342,0.00030115573,0.00021728377],"domain_scores_gemma":[0.99646455,0.0025646866,0.000318143,0.00049620424,0.00010371256,0.000052674324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013444307,0.0001532742,0.0005174938,0.00013060424,0.00002851489,0.000009000303,0.0002728585,0.000035875244,0.00002258699],"category_scores_gemma":[0.0033961933,0.000119885815,0.0000071305435,0.00022396722,0.00022653703,0.00009564504,0.000039351882,0.00017762414,5.9801255e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027344323,0.00036192898,0.0059485645,0.0006282318,0.000019172572,0.0000032613038,0.0017552329,0.0047131027,0.000055242625,0.7412361,0.0015944224,0.24341133],"study_design_scores_gemma":[0.0010230965,0.000086112435,0.002977969,0.00022992003,0.00003740053,0.0000014058611,0.000093607356,0.64069355,0.000023684244,0.3547416,0.000007687162,0.000083987165],"about_ca_topic_score_codex":0.00005468863,"about_ca_topic_score_gemma":0.0011225719,"teacher_disagreement_score":0.6359804,"about_ca_system_score_codex":0.00006427142,"about_ca_system_score_gemma":0.00008415897,"threshold_uncertainty_score":0.48888016},"labels":[],"label_agreement":null},{"id":"W1973819936","doi":"10.1002/sim.5504","title":"Skew‐elliptical spatial random effect modeling for areal data with application to mapping health utilization rates","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Skew; Computer science; Spatial analysis; Random effects model; Statistics; Econometrics; Mathematics; Medicine","score_opus":0.12102258270912948,"score_gpt":0.3523455106071009,"score_spread":0.23132292789797143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973819936","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023336655,0.0005947675,0.9936031,0.00073270866,0.00017267426,0.00066794106,0.0017171446,0.000013524585,0.00016445317],"genre_scores_gemma":[0.93898225,0.0002077,0.05236241,0.00039277796,0.0005404242,0.00009894105,0.0073724077,0.00002199353,0.000021079346],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986644,0.000031878717,0.00058659335,0.0003456169,0.00006925572,0.00030226228],"domain_scores_gemma":[0.998866,0.00036679284,0.00018011875,0.00040441673,0.000038600207,0.00014405462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018406648,0.0001280726,0.00050718966,0.00022222947,0.000082379076,0.0000157209,0.00020250509,0.000042315503,0.000058194953],"category_scores_gemma":[0.0007424496,0.0001107566,0.000012619464,0.0002893465,0.00003525797,0.0001150741,0.00004703767,0.00008867747,0.00003243381],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017741312,0.00040861606,0.35113308,0.0013438254,0.0003521052,0.0000039940765,0.006105714,0.019218244,0.00005128284,0.34718594,0.013985662,0.2584374],"study_design_scores_gemma":[0.0020271803,0.0002622023,0.004425532,0.000066876695,0.000026970194,0.0000011016049,0.00007948455,0.9809318,0.0000037905832,0.0073469686,0.0046742517,0.00015381718],"about_ca_topic_score_codex":0.0043840036,"about_ca_topic_score_gemma":0.0011939796,"teacher_disagreement_score":0.96171355,"about_ca_system_score_codex":0.000068599926,"about_ca_system_score_gemma":0.000019296325,"threshold_uncertainty_score":0.66273314},"labels":[],"label_agreement":null},{"id":"W1974321986","doi":"10.1002/sim.4099","title":"On the three‐arm non‐inferiority trial including a placebo with a prespecified margin","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McMaster University","keywords":"Margin (machine learning); Assay sensitivity; Placebo; Medicine; Sample size determination; Randomized controlled trial; Statistics; Clinical trial; Randomization; Fraction (chemistry); Mathematics; Computer science; Surgery; Internal medicine; Machine learning","score_opus":0.4639363371681384,"score_gpt":0.5489701146468974,"score_spread":0.08503377747875895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974321986","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08610375,0.000008349808,0.8765298,0.0036788075,0.0034584184,0.004163902,0.0002977877,0.00010672192,0.02565243],"genre_scores_gemma":[0.16888502,0.00001362314,0.82836604,0.00055772054,0.0015536714,0.0002842255,0.000005399475,0.00007201712,0.0002623088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960101,0.00067465124,0.0012221882,0.00052212016,0.0010717505,0.0004991457],"domain_scores_gemma":[0.84744984,0.15096837,0.0003791941,0.00086450874,0.00016262467,0.00017545742],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009585055,0.00035280673,0.0010235676,0.00013908732,0.00016809042,0.000037752186,0.00056263304,0.0002239127,0.0028288483],"category_scores_gemma":[0.25050533,0.00019371684,0.000045767432,0.00040066586,0.0009555318,0.000031055333,0.00014388682,0.0019209024,0.000034671928],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02204589,0.00032339277,0.00017456656,0.00008288733,0.000057433153,0.00010905145,0.00040657967,0.0000016048971,0.0001748635,0.95668054,0.0143877715,0.005555437],"study_design_scores_gemma":[0.03639606,0.001899746,0.00082183885,0.00030838308,0.00011263597,0.0000064136975,0.00010961912,0.0012072459,0.000078857214,0.95822054,0.00059818965,0.00024045887],"about_ca_topic_score_codex":0.00008091607,"about_ca_topic_score_gemma":0.0009988153,"teacher_disagreement_score":0.24092028,"about_ca_system_score_codex":0.00006996157,"about_ca_system_score_gemma":0.00014459687,"threshold_uncertainty_score":0.9980827},"labels":[],"label_agreement":null},{"id":"W1974723978","doi":"10.1002/sim.6378","title":"A cautionary note concerning the use of stabilized weights in marginal structural models","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Hôpital du Sacré-Cœur de Montréal; Université Laval; Université du Québec à Montréal","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Marginal structural model; Inverse probability; Econometrics; Confounding; Inverse; Statistics; Computer science; Mathematics; Posterior probability; Bayesian probability","score_opus":0.20423091439008736,"score_gpt":0.4260492700041732,"score_spread":0.22181835561408583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974723978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10385992,0.000046937497,0.8948511,0.00027828617,0.000093265066,0.00036102254,0.00007746665,0.000043319684,0.00038866815],"genre_scores_gemma":[0.59827,0.00003269379,0.40149266,0.000075667,0.000036274458,0.000017960376,0.000019274712,0.000013903797,0.000041593474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984923,0.00021352647,0.0005659062,0.00017087178,0.0003462136,0.00021120875],"domain_scores_gemma":[0.9953154,0.0039967424,0.00021457257,0.0003082999,0.00012777327,0.000037257058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064240134,0.00014599388,0.00039342104,0.0001226268,0.00003439392,0.000004792307,0.00017295625,0.00006170406,0.00010886332],"category_scores_gemma":[0.0030454237,0.00009376363,0.000014066216,0.00018246098,0.0004531082,0.00011947905,0.000056336794,0.0003387396,6.0375675e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000653055,0.000016143564,0.0010582542,0.00009689721,0.0000057621287,0.000013693237,0.00277434,0.0010962851,0.0004450674,0.9903152,0.0004965016,0.0036165584],"study_design_scores_gemma":[0.0005930746,0.00010624364,0.0012088021,0.00023364933,0.000014590894,0.0000049997825,0.000096004514,0.19642927,0.00011893976,0.8008568,0.00025236545,0.00008523998],"about_ca_topic_score_codex":0.00031506215,"about_ca_topic_score_gemma":0.00039592234,"teacher_disagreement_score":0.49441007,"about_ca_system_score_codex":0.00010646278,"about_ca_system_score_gemma":0.000046732068,"threshold_uncertainty_score":0.382357},"labels":[],"label_agreement":null},{"id":"W1974830949","doi":"10.1002/sim.4435","title":"Global hypothesis testing for high‐dimensional repeated measures outcomes","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Center for Advancing Translational Sciences; National Institute of Dental and Craniofacial Research; National Institute on Drug Abuse; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; National Center for Research Resources; National Institute of Neurological Disorders and Stroke; National Institute on Alcohol Abuse and Alcoholism","keywords":"Sample size determination; Type I and type II errors; Covariate; False discovery rate; Multiple comparisons problem; Computer science; Inference; Univariate; Statistical power; Statistical hypothesis testing; Statistics; Statistical inference; Nominal level; Multivariate statistics; Mathematics; Machine learning; Artificial intelligence; Confidence interval","score_opus":0.7088825096546587,"score_gpt":0.5518508889249891,"score_spread":0.15703162072966959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1974830949","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007512093,0.0000366042,0.98306084,0.00041975043,0.0014579999,0.0010685608,0.0015558171,0.00016346539,0.0047248495],"genre_scores_gemma":[0.05857496,0.000003977922,0.9405084,0.00043285952,0.00021965243,0.000079857185,0.0000063462358,0.00004101258,0.0001328795],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99640745,0.00048920716,0.0015071151,0.00048142686,0.0006536271,0.0004611964],"domain_scores_gemma":[0.882557,0.115971684,0.00038314558,0.00045270676,0.0004568805,0.00017862667],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004790977,0.0002904917,0.0011029795,0.00010002711,0.00008314819,0.00000778704,0.00029611067,0.00016566161,0.00053322996],"category_scores_gemma":[0.60342205,0.00021462202,0.00005166339,0.00037792092,0.00043519252,0.000027575363,0.00007269686,0.00020624863,0.000012339247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040537733,0.00035153076,0.0430536,0.00024559317,0.00018205147,0.0001309946,0.00023431117,0.000003011991,0.00007431789,0.8411524,0.022120094,0.09204667],"study_design_scores_gemma":[0.0022735843,0.00049441133,0.074698746,0.00020615754,0.00020439031,0.000006478888,0.00004421374,0.0003296752,0.00006490529,0.92144024,0.000025369929,0.00021183272],"about_ca_topic_score_codex":0.00038127048,"about_ca_topic_score_gemma":0.00014239275,"teacher_disagreement_score":0.5986311,"about_ca_system_score_codex":0.00011901403,"about_ca_system_score_gemma":0.00008440169,"threshold_uncertainty_score":0.8752032},"labels":[],"label_agreement":null},{"id":"W1975313883","doi":"10.1002/sim.4329","title":"Testing the evolution process of prostate‐specific antigen in early stage prostate cancer: what is the proper underlying model?","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Prostate Cancer Diagnosis and Treatment","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; McMaster University; York University","funders":"","keywords":"Prostate-specific antigen; Stage (stratigraphy); Prostate; Prostate cancer; Process (computing); Cancer; Medicine; Oncology; Computer science; Internal medicine; Biology","score_opus":0.10325058714932615,"score_gpt":0.34510520111267246,"score_spread":0.2418546139633463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975313883","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9787972,0.011870582,0.0017397306,0.0026313309,0.00025197645,0.003591873,0.0002412662,0.000030824838,0.00084521726],"genre_scores_gemma":[0.98923385,0.0073038745,0.0022638175,0.00034190147,0.000047796097,0.00054908264,0.000027378894,0.00004110903,0.00019117941],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99782014,0.000081703314,0.0006991894,0.00040015142,0.0005588551,0.000439972],"domain_scores_gemma":[0.9985666,0.00023180971,0.0003006927,0.0004246277,0.000392846,0.00008341795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007637117,0.00025314782,0.00046148343,0.00015584912,0.00011537809,0.000023765182,0.0001925944,0.000058791862,0.000067412955],"category_scores_gemma":[0.0001756833,0.00013000642,0.000025305475,0.0007068277,0.00063370535,0.00020664209,0.00004732093,0.00038568006,0.000002962675],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007705977,0.00045244873,0.8136331,0.00087714155,0.0001123509,0.00016292115,0.12558214,0.0009449956,0.0011120151,0.004339809,0.00061972305,0.051392786],"study_design_scores_gemma":[0.0063896314,0.0025031453,0.9030884,0.007278005,0.00020633446,0.000015370273,0.033949368,0.022997562,0.0020220708,0.02085639,0.00030192672,0.00039179795],"about_ca_topic_score_codex":0.0046717273,"about_ca_topic_score_gemma":0.0004964644,"teacher_disagreement_score":0.09163278,"about_ca_system_score_codex":0.00041217942,"about_ca_system_score_gemma":0.0004548638,"threshold_uncertainty_score":0.7062285},"labels":[],"label_agreement":null},{"id":"W1975851557","doi":"10.1002/sim.3470","title":"Modeling conditional dependence between diagnostic tests: A multiple latent variable model","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Public Health Service; Centers for Disease Control and Prevention","keywords":"Latent class model; Latent variable; Latent variable model; Covariate; Conditional dependence; Statistics; Bayesian probability; Computer science; Econometrics; Measure (data warehouse); Mathematics; Data mining","score_opus":0.054047281841197406,"score_gpt":0.31789441846119393,"score_spread":0.26384713661999654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975851557","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016784483,0.00020530914,0.99672854,0.0003473532,0.00016769154,0.00019837769,0.00012517745,0.00006331517,0.00048579142],"genre_scores_gemma":[0.4019658,0.00009712536,0.59740645,0.00028624135,0.00009697081,0.000020594742,0.00004481872,0.000009206798,0.000072819355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805534,0.00010285266,0.00047824025,0.0004488349,0.00053447235,0.00038029044],"domain_scores_gemma":[0.99711996,0.0020578445,0.00007466627,0.000403451,0.00016707146,0.00017703002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070989266,0.00018946349,0.00036173064,0.00015820307,0.00014754065,0.00001570284,0.0005456737,0.0000874855,0.00002422888],"category_scores_gemma":[0.0023519725,0.0001651348,0.000018592753,0.00033201376,0.00013941895,0.00019840407,0.00013770655,0.00034844727,0.000010779924],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007645884,0.000099272664,0.008652434,0.00005469252,0.00002623322,0.0003839998,0.0014784592,0.21359563,0.00024145,0.76576984,0.0027113755,0.0069789505],"study_design_scores_gemma":[0.00051433704,0.00004497738,0.0010504922,0.00006760059,0.000009116437,0.00002625674,0.0000032225012,0.62390816,0.000010987757,0.37423626,0.000012224818,0.000116367235],"about_ca_topic_score_codex":0.00021187204,"about_ca_topic_score_gemma":0.00002770581,"teacher_disagreement_score":0.41031253,"about_ca_system_score_codex":0.00007806957,"about_ca_system_score_gemma":0.00020184486,"threshold_uncertainty_score":0.67340016},"labels":[],"label_agreement":null},{"id":"W1975994236","doi":"10.1002/sim.3854","title":"The performance of different propensity-score methods for estimating differences in proportions (risk differences or absolute risk reductions) in observational studies","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":359,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Confidence interval; Observational study; Estimator; Mean squared error; Relative risk; Matching (statistics); Inverse probability weighting; Mathematics; Econometrics; Medicine","score_opus":0.4011751616883879,"score_gpt":0.5200551633034011,"score_spread":0.11888000161501316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975994236","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7761584,0.00008380621,0.22167489,0.0002329681,0.00041971044,0.0011631511,0.00020838242,0.000039622766,0.00001906395],"genre_scores_gemma":[0.3462323,0.0007670073,0.6521072,0.0000068481663,0.000077587334,0.0006567338,0.000025792353,0.00001655622,0.000109972985],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973568,0.000315674,0.001313239,0.00032743596,0.00033757035,0.00034933563],"domain_scores_gemma":[0.98524135,0.013075667,0.00088028074,0.00036208294,0.00039397398,0.00004661301],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026317376,0.00026430312,0.0008062118,0.00023533778,0.00024419138,0.00001417905,0.00032534127,0.00009620264,0.000055214932],"category_scores_gemma":[0.037921865,0.000143284,0.000027221642,0.00043208522,0.0009272676,0.0001196024,0.000102319624,0.0008582094,2.4971754e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000309543,0.00046249456,0.7223801,0.0010471061,0.00011272729,0.0000066679922,0.0060770917,0.000057809404,0.0014079055,0.14728266,0.0012090448,0.119646825],"study_design_scores_gemma":[0.0005530612,0.0005105432,0.34951308,0.00087388314,0.000063270716,0.0000040796626,0.0011967294,0.04699414,0.0003690312,0.5997149,0.000019430769,0.00018784823],"about_ca_topic_score_codex":0.00013644459,"about_ca_topic_score_gemma":0.007370234,"teacher_disagreement_score":0.45243225,"about_ca_system_score_codex":0.00009533988,"about_ca_system_score_gemma":0.000121492856,"threshold_uncertainty_score":0.9701821},"labels":[],"label_agreement":null},{"id":"W1976786126","doi":"10.1002/sim.911","title":"A general goodness‐of‐fit approach for inference procedures concerning the kappa statistic","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Goodness of fit; Statistics; Polytomous Rasch model; Statistic; Cohen's kappa; Inference; Mathematics; Statistical inference; Test statistic; Multinomial distribution; Dirichlet distribution; Outcome (game theory); Kappa; Range (aeronautics); Confidence interval; Econometrics; Statistical hypothesis testing; Computer science; Item response theory; Psychometrics; Artificial intelligence","score_opus":0.2882924109126018,"score_gpt":0.4485972092231941,"score_spread":0.1603047983105923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976786126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020719312,0.00037117253,0.97362036,0.0008422169,0.00034496645,0.00086314685,0.00016797546,0.000011117264,0.0030597392],"genre_scores_gemma":[0.8879613,0.00015096123,0.11005801,0.00037840143,0.00022514242,0.00014898437,0.00004103414,0.000011419365,0.0010246992],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99614334,0.00024846086,0.0011142162,0.0004300747,0.0017397022,0.00032418757],"domain_scores_gemma":[0.9931344,0.005273756,0.0004028415,0.00048649468,0.00062172604,0.000080782775],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006128714,0.00017309579,0.00045718628,0.00014242234,0.0001483617,0.00004448042,0.00077723485,0.00005204178,0.00035103966],"category_scores_gemma":[0.027906502,0.00009391504,0.00003324876,0.0006110486,0.00062644616,0.00006799417,0.00007292936,0.0002024107,0.000006735288],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006151115,0.0006510035,0.21932468,0.0006463564,0.00011211949,0.000032289332,0.013955891,0.028376866,0.0015828973,0.4283963,0.12300453,0.18330196],"study_design_scores_gemma":[0.00373466,0.0011638519,0.070077,0.00035303217,0.000114899805,0.000014623267,0.0106649725,0.21134102,0.00011384635,0.67557806,0.026378945,0.000465109],"about_ca_topic_score_codex":0.00019023631,"about_ca_topic_score_gemma":0.0002347758,"teacher_disagreement_score":0.86724204,"about_ca_system_score_codex":0.000053832937,"about_ca_system_score_gemma":0.00018569734,"threshold_uncertainty_score":0.98028183},"labels":[],"label_agreement":null},{"id":"W1979134293","doi":"10.1002/sim.3310","title":"Estimating error rates in the classification of paired organs","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Estimator; Resampling; Statistics; Cross-validation; Word error rate; Computer science; Sample size determination; Contrast (vision); Autocorrelation; Artificial intelligence; Variance (accounting); Pattern recognition (psychology); Mathematics","score_opus":0.06777729135711709,"score_gpt":0.380192824480855,"score_spread":0.31241553312373793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979134293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90635496,0.0003743208,0.08013564,0.009707894,0.00011699738,0.00027523673,0.000014847592,0.000020612792,0.0029994808],"genre_scores_gemma":[0.9626355,0.000060208018,0.036701296,0.0002668722,0.00008375329,0.00000705886,0.000072184266,0.000007920579,0.00016516686],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99893373,0.00009221763,0.00041674136,0.00012696275,0.0003076874,0.00012264767],"domain_scores_gemma":[0.9991157,0.00043411262,0.000118626594,0.00020045353,0.00010082777,0.000030283085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006683433,0.000079094,0.0002942127,0.00016956117,0.00003509333,0.0000016856204,0.00008194541,0.000026385791,0.00006341385],"category_scores_gemma":[0.002098657,0.00004849041,0.000015743166,0.0005277322,0.0002932479,0.000017828985,0.0000068979252,0.00019309131,0.000004173576],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011569414,0.0003722575,0.92456585,0.0004584159,0.000054026117,0.0007042914,0.019329524,0.00021410664,0.01903023,0.00410021,0.016796708,0.014258703],"study_design_scores_gemma":[0.0014352498,0.00022746217,0.85271776,0.00055025524,0.00011377294,0.00009827538,0.0039361645,0.13854297,0.00018941378,0.001967433,0.00014407933,0.00007714375],"about_ca_topic_score_codex":0.00035057627,"about_ca_topic_score_gemma":0.000052863405,"teacher_disagreement_score":0.13832885,"about_ca_system_score_codex":0.000029022154,"about_ca_system_score_gemma":0.00005438083,"threshold_uncertainty_score":0.251244},"labels":[],"label_agreement":null},{"id":"W1979394579","doi":"10.1002/sim.1974","title":"Influence analysis for linear mixed‐effects models","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"National Cancer Institute","keywords":"Linear regression; Leverage (statistics); Mathematics; Measure (data warehouse); Linear model; Regression analysis; Statistics; Generalization; Regression; Applied mathematics; Simple linear regression; Generalized linear model; Infinitesimal; Simple (philosophy); Econometrics; Computer science; Data mining","score_opus":0.06358645407001984,"score_gpt":0.4203984667152716,"score_spread":0.35681201264525175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979394579","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051552323,0.000055769902,0.99336314,0.00021408348,0.00013402823,0.0004231053,0.00023901451,0.00003746133,0.00037819045],"genre_scores_gemma":[0.15821062,0.00003006762,0.8413119,0.00020438162,0.00008748273,0.000072785406,0.000031343254,0.000019027088,0.000032411815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99835,0.000088864406,0.0005598644,0.00031913252,0.0003387946,0.00034330162],"domain_scores_gemma":[0.99354184,0.005643038,0.00014021003,0.00032475704,0.00021530852,0.00013484994],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00082620146,0.00019480972,0.0006561613,0.0002760584,0.000061223625,0.000009369632,0.00019723101,0.00008744116,0.0000374338],"category_scores_gemma":[0.010725416,0.00015401466,0.00004656559,0.00071012584,0.00022514252,0.000055487657,0.000031948854,0.00019757898,0.0000044975545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024391727,0.00006906877,0.0003659011,0.00031011176,0.00010354882,0.00003984424,0.00046900936,0.002710856,0.00006533257,0.99022627,0.00038767108,0.005227968],"study_design_scores_gemma":[0.0012646249,0.00026543223,0.0032302027,0.00020051493,0.00045893554,0.0000020006016,0.000058836475,0.031854276,0.00014998892,0.9623134,0.000032745913,0.0001690051],"about_ca_topic_score_codex":0.00016472647,"about_ca_topic_score_gemma":0.00016612723,"teacher_disagreement_score":0.1530554,"about_ca_system_score_codex":0.00008124656,"about_ca_system_score_gemma":0.00005613663,"threshold_uncertainty_score":0.99760765},"labels":[],"label_agreement":null},{"id":"W1979949183","doi":"10.1002/(sici)1097-0258(20000215)19:3<323::aid-sim372>3.0.co;2-d","title":"Saddlepoint approximations for small sample logistic regression problems","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Cancer Institute","keywords":"Inference; Mathematics; Logistic regression; Sequence (biology); Applied mathematics; Binomial distribution; Statistics; Binomial regression; Econometrics; Computer science; Artificial intelligence","score_opus":0.33454370973748493,"score_gpt":0.5060935000628242,"score_spread":0.17154979032533924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979949183","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001397748,0.00028912516,0.9906279,0.00067347963,0.00043494327,0.0010290026,0.00039113662,0.00003538699,0.005121268],"genre_scores_gemma":[0.01912435,0.000062879444,0.97677296,0.0002842873,0.00015322356,0.00025911097,0.00011598076,0.000024158338,0.00320306],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969002,0.00026220077,0.0010741615,0.00053748215,0.00087134924,0.00035463177],"domain_scores_gemma":[0.9862924,0.012565968,0.00021150324,0.0005477025,0.0002322574,0.00015016488],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004664233,0.00019652749,0.0004912204,0.00028773892,0.00014043362,0.000055040342,0.00051701633,0.000082817,0.0047482],"category_scores_gemma":[0.027215404,0.0001292332,0.000038528557,0.00067464146,0.00039360102,0.00008282831,0.000046594825,0.00018488076,0.00010001028],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029358105,0.00030393808,0.0013484625,0.00010510345,0.000018440272,0.000028675739,0.0038826256,0.003411537,0.0038929384,0.1262474,0.041984297,0.818483],"study_design_scores_gemma":[0.0016928657,0.0006980078,0.0021364647,0.00020209183,0.000019542498,0.00001126417,0.00068874453,0.09709856,0.00035018966,0.85270154,0.044154648,0.00024608],"about_ca_topic_score_codex":0.00027401204,"about_ca_topic_score_gemma":0.00012251636,"teacher_disagreement_score":0.8182369,"about_ca_system_score_codex":0.00009269758,"about_ca_system_score_gemma":0.000062012696,"threshold_uncertainty_score":0.9961616},"labels":[],"label_agreement":null},{"id":"W1980747896","doi":"10.1002/sim.2326","title":"Checking stationarity of the incidence rate using prevalent cohort survival data","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University Health Centre; Montreal Children's Hospital; McGill University","funders":"","keywords":"Incidence (geometry); Cohort; Kaplan–Meier estimator; Estimator; Statistics; Survival analysis; Medicine; Econometrics; Demography; Mathematics","score_opus":0.18573745560773047,"score_gpt":0.466115744944905,"score_spread":0.2803782893371745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980747896","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018539835,0.00006872404,0.97930074,0.00035343945,0.0003186918,0.00032664152,0.0005534756,0.000010994113,0.0005274621],"genre_scores_gemma":[0.17971984,0.000055976245,0.8199225,0.00008551174,0.00014196207,0.000004396149,0.00002292967,0.000013906443,0.00003298486],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99771047,0.00047104637,0.0007296799,0.0002887889,0.0005777632,0.00022228039],"domain_scores_gemma":[0.9942028,0.0044524497,0.00031859605,0.0007745181,0.00019350683,0.000058137404],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003583039,0.00014082777,0.00040151368,0.000056791127,0.00007096074,0.00000863055,0.00057797,0.000049576396,0.00031963823],"category_scores_gemma":[0.018127512,0.000095485906,0.000012793839,0.00027386713,0.00032894913,0.0000822819,0.0002673523,0.0002733684,0.0000016441045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028667691,0.00011144211,0.063373946,0.0003992686,0.00003720912,0.000011985364,0.00074049865,0.000041075768,0.0008645094,0.9098454,0.0018557898,0.0226902],"study_design_scores_gemma":[0.00054021657,0.000041723393,0.13214155,0.0005773585,0.00013444512,0.0000059497493,0.00017016716,0.08670517,0.00020105194,0.77913535,0.00019909113,0.00014790751],"about_ca_topic_score_codex":0.00029888007,"about_ca_topic_score_gemma":0.00041661997,"teacher_disagreement_score":0.16118,"about_ca_system_score_codex":0.00008700987,"about_ca_system_score_gemma":0.00014247042,"threshold_uncertainty_score":0.99014324},"labels":[],"label_agreement":null},{"id":"W1982959065","doi":"10.1002/sim.5795","title":"Propensity scores used for analysis of cluster randomized trials with selection bias: a simulation study","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Propensity score matching; CRTS; Inverse probability weighting; Statistics; Selection bias; Weighting; Regression; Causal inference; Selection (genetic algorithm); Type I and type II errors; Matching (statistics); Randomization; Econometrics; Randomized controlled trial; Computer science; Mathematics; Medicine; Artificial intelligence; Internal medicine","score_opus":0.32206622457838024,"score_gpt":0.502459386483331,"score_spread":0.18039316190495075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982959065","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24543943,0.0000049667333,0.74939615,0.000039694616,0.000019971842,0.0050133835,0.000024853043,0.000040452564,0.000021083775],"genre_scores_gemma":[0.7375147,0.0000037238144,0.2618847,0.000021420796,0.000025262709,0.00046295128,0.000033388016,0.00001379364,0.000040089235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973118,0.0008303371,0.0011545098,0.00020660809,0.00035479656,0.00014195882],"domain_scores_gemma":[0.97643083,0.02185102,0.00078375894,0.00020689814,0.0006932798,0.000034229637],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006009087,0.00015460174,0.0020175464,0.00049592956,0.000031977463,0.00001014026,0.000077987,0.00005071025,0.0001348092],"category_scores_gemma":[0.037013765,0.000090891765,0.00005645108,0.00068995805,0.0001635674,0.00009049121,0.000016768046,0.00010368074,4.4363844e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.24775867,0.007520863,0.21609351,0.003321195,0.024529135,0.000031372143,0.0584238,0.12714763,0.009944974,0.26418948,0.011902966,0.029136397],"study_design_scores_gemma":[0.1001675,0.0018293341,0.0048639495,0.0002350871,0.0059866435,4.295905e-7,0.0008711296,0.4503499,0.0006976824,0.43477148,0.000003193251,0.00022366417],"about_ca_topic_score_codex":0.00042229035,"about_ca_topic_score_gemma":0.0013163375,"teacher_disagreement_score":0.49207523,"about_ca_system_score_codex":0.000057966186,"about_ca_system_score_gemma":0.000032884775,"threshold_uncertainty_score":0.9710979},"labels":[],"label_agreement":null},{"id":"W1983192352","doi":"10.1002/sim.3191","title":"A handbook of statistical analyses using Stata (2nd edn). Sophia Rabe‐Hesketh and Brian S. Everitt, Chapman &amp; Hall/CRC, Boca Raton, FL, 2007. No. of pages: ix + 342. Price: $49.46. ISBN 1‐58488‐756‐7","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Probability and Statistical Research","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Library science; Computer science","score_opus":0.23171456911003172,"score_gpt":0.4607068314387526,"score_spread":0.22899226232872086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983192352","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016811587,0.0027958143,0.97466725,0.00024130658,0.00023411145,0.00104318,0.002862839,0.00004150389,0.0013024291],"genre_scores_gemma":[0.19813338,0.005311934,0.7948854,0.00016548627,0.00028237564,0.000028708424,0.00039396333,0.00011441313,0.0006843194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99380535,0.00067201525,0.002041679,0.0007810676,0.0017725488,0.0009273514],"domain_scores_gemma":[0.9891866,0.007808085,0.0005364668,0.0008675816,0.0010602324,0.0005410683],"candidate_categories":["metaresearch","metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026499256,0.0005106351,0.001780931,0.000467102,0.00021074324,0.000024788207,0.00047451374,0.00024285767,0.0012481447],"category_scores_gemma":[0.027573625,0.00043912334,0.0000649784,0.00053446105,0.003303303,0.0001504543,0.0002833038,0.00082165084,0.000019647257],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006124914,0.006122212,0.020326177,0.038125597,0.002087096,0.0035986423,0.034982868,0.00016506446,0.041495558,0.5626488,0.27105042,0.013272702],"study_design_scores_gemma":[0.01023296,0.0033171282,0.015545929,0.004649802,0.00086652493,0.00023015162,0.0013116552,0.040092826,0.0012136586,0.91771734,0.0033478483,0.0014741542],"about_ca_topic_score_codex":0.001205248,"about_ca_topic_score_gemma":0.00081045605,"teacher_disagreement_score":0.3550686,"about_ca_system_score_codex":0.0001876245,"about_ca_system_score_gemma":0.0006642691,"threshold_uncertainty_score":0.99980605},"labels":[],"label_agreement":null},{"id":"W1984151175","doi":"10.1002/sim.1271","title":"Dealing with competing risks: testing covariates and calculating sample size","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Ontario Institute for Cancer Research","funders":"","keywords":"Covariate; Statistics; Econometrics; Proportional hazards model; Event (particle physics); Sample size determination; Hazard; Hazard ratio; Mathematics; Computer science; Confidence interval","score_opus":0.6075631836183745,"score_gpt":0.5529054365405092,"score_spread":0.054657747077865304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984151175","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01579949,0.00012718233,0.9794321,0.00038522357,0.00020364238,0.0004329456,0.00017983158,0.00010691081,0.003332657],"genre_scores_gemma":[0.15335162,0.000037079928,0.8461185,0.00017120707,0.00024323988,0.0000127494,0.0000017777742,0.000043787386,0.0000200042],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970893,0.00044594792,0.0011462462,0.00042140982,0.0004765555,0.0004205298],"domain_scores_gemma":[0.69547457,0.30365726,0.000340899,0.00022806766,0.00015818997,0.0001409874],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037273997,0.0002532134,0.00083868305,0.0000804114,0.00015961318,0.00002798158,0.00013914869,0.000095710515,0.0007141073],"category_scores_gemma":[0.56665295,0.00019227805,0.000013943025,0.00034456947,0.00047697368,0.00003400992,0.00008154739,0.00049758836,0.000003925706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010722284,0.00015922688,0.07408964,0.0008965912,0.00011946858,0.00033440688,0.0024344677,0.00017287153,0.000340428,0.8043495,0.0005541065,0.11644206],"study_design_scores_gemma":[0.0023162616,0.00036036104,0.0047241542,0.0011198649,0.00013383078,0.000027033147,0.0004969165,0.0674028,0.000017293005,0.9231017,0.000038132155,0.00026162993],"about_ca_topic_score_codex":0.00047698777,"about_ca_topic_score_gemma":0.00007577204,"teacher_disagreement_score":0.5629256,"about_ca_system_score_codex":0.000044900116,"about_ca_system_score_gemma":0.000013536484,"threshold_uncertainty_score":0.7840871},"labels":[],"label_agreement":null},{"id":"W1985369819","doi":"10.1002/sim.2403","title":"A workflow spatial scan statistic","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Scan statistic; Workflow; Statistic; Computer science; Completeness (order theory); Data mining; Statistics; Mathematics; Database","score_opus":0.010736343537186738,"score_gpt":0.3030262739491112,"score_spread":0.29228993041192447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985369819","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06875688,0.0024565144,0.85040015,0.0037459107,0.0024063606,0.0022540765,0.007513586,0.00054134766,0.061925195],"genre_scores_gemma":[0.92884624,0.00008448976,0.06441231,0.00074373075,0.00095856434,0.000039000734,0.0033184579,0.000057482164,0.0015397546],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9977361,0.00008977747,0.0006439203,0.0004050407,0.0006724796,0.000452708],"domain_scores_gemma":[0.99855673,0.00042966357,0.00013538188,0.0004963399,0.0001638592,0.00021802129],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041496908,0.0002386054,0.00061264023,0.00025358197,0.000047904985,0.000010701199,0.00013665861,0.000066955115,0.0022613148],"category_scores_gemma":[0.001250059,0.00020683582,0.000026856396,0.0004040952,0.00040508,0.000036304005,0.00004407301,0.00029700404,0.0001329779],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007743803,0.0005727906,0.31438068,0.0005751446,0.000082761966,0.0046063093,0.00024343141,0.00009870694,0.00066438416,0.034971897,0.4542191,0.18881042],"study_design_scores_gemma":[0.0060215946,0.0005044218,0.92995834,0.00063893915,0.00015297913,0.00006723111,0.000070924914,0.006842421,0.000026846474,0.030794328,0.02460032,0.0003216228],"about_ca_topic_score_codex":0.0034343959,"about_ca_topic_score_gemma":0.0036284653,"teacher_disagreement_score":0.8600893,"about_ca_system_score_codex":0.00018664969,"about_ca_system_score_gemma":0.0001890327,"threshold_uncertainty_score":0.9986507},"labels":[],"label_agreement":null},{"id":"W1986440280","doi":"10.1002/sim.3276","title":"The performance of different propensity score methods for estimating marginal odds ratios, <i>Statistics in Medicine</i> 2007; <b>26</b>:3078–3094","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Citation; Library science; Odds; Sociology; Medicine; Statistics; Mathematics; Computer science; Logistic regression","score_opus":0.19247240902296991,"score_gpt":0.4680823787825111,"score_spread":0.27560996975954116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986440280","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0222688,0.0001966231,0.9747572,0.00038253388,0.0004848087,0.0013609685,0.00011104465,0.00009258793,0.00034546497],"genre_scores_gemma":[0.071556084,0.00077343755,0.92669344,0.00016996816,0.00022432163,0.00020152378,0.00006148145,0.00007088732,0.000248862],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99638146,0.00034473787,0.0016372951,0.00040516924,0.0006467756,0.00058458775],"domain_scores_gemma":[0.98863745,0.009389437,0.0007388814,0.0006004172,0.00052268617,0.00011115289],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0030601656,0.0004095415,0.0011735132,0.00021187485,0.00024795753,0.0000081815515,0.00046782143,0.00012816986,0.000061153034],"category_scores_gemma":[0.014307525,0.0002637259,0.000029746083,0.00036130467,0.0014437668,0.000106621184,0.000121144345,0.0006385849,0.0000014356148],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008931606,0.0004272232,0.022132302,0.0035420298,0.00009830869,0.00014128823,0.0064406954,0.00021146318,0.007594073,0.79066145,0.059175324,0.10868269],"study_design_scores_gemma":[0.0043844637,0.0031707825,0.01473248,0.0034735466,0.00021018792,0.0001215954,0.0006731837,0.22578458,0.009636201,0.7361155,0.0008865321,0.0008109135],"about_ca_topic_score_codex":0.00009889554,"about_ca_topic_score_gemma":0.00022187544,"teacher_disagreement_score":0.22557312,"about_ca_system_score_codex":0.0002097405,"about_ca_system_score_gemma":0.00015094421,"threshold_uncertainty_score":0.9999815},"labels":[],"label_agreement":null},{"id":"W1986551913","doi":"10.1002/sim.3922","title":"Optimizing the response to surveillance alerts in automated surveillance systems","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Robustness (evolution); Robust optimization; Operations research; Data mining; Realization (probability); Machine learning; Mathematical optimization; Statistics; Engineering","score_opus":0.21525991537945466,"score_gpt":0.4328536458959758,"score_spread":0.21759373051652114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986551913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5506914,0.003864558,0.40879282,0.018376447,0.003592276,0.005430285,0.00060990505,0.0015095477,0.0071327016],"genre_scores_gemma":[0.96796834,0.00016218024,0.03072969,0.0007468619,0.00007953832,0.00011396886,0.0000063102025,0.000027847776,0.00016527929],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99626714,0.0015344691,0.00094532856,0.00039082533,0.0003610104,0.0005012015],"domain_scores_gemma":[0.9779539,0.021086825,0.00021201541,0.0005172663,0.0001317273,0.00009825957],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009291838,0.00024045495,0.0008118541,0.00015941139,0.00008384631,0.000008352167,0.0003854647,0.0000873985,0.00007300703],"category_scores_gemma":[0.05985379,0.00014601824,0.000020279404,0.000634008,0.00026420844,0.00002156918,0.00016438165,0.00030052243,0.000021238151],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036219081,0.00043886004,0.5784721,0.0010581856,0.00017701164,0.0015003143,0.04401796,0.0034956345,0.00047152978,0.11364829,0.25035322,0.0027450053],"study_design_scores_gemma":[0.0015390563,0.0004633346,0.9273051,0.000610796,0.000011596649,0.000013070208,0.0017989135,0.02958766,0.0000072504677,0.034615885,0.0036274474,0.00041987552],"about_ca_topic_score_codex":0.0021417893,"about_ca_topic_score_gemma":0.00329701,"teacher_disagreement_score":0.41727686,"about_ca_system_score_codex":0.00022630233,"about_ca_system_score_gemma":0.00004347665,"threshold_uncertainty_score":0.94806546},"labels":[],"label_agreement":null},{"id":"W1986927305","doi":"10.1002/sim.2782","title":"Methods for the statistical analysis of binary data in split‐mouth designs with baseline measurements","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Baseline (sea); Computer science; Context (archaeology); Binary number; Binary data; Outcome (game theory); Statistics; Statistical model; Statistical analysis; Artificial intelligence; Mathematics","score_opus":0.46426087040142916,"score_gpt":0.5858141738594048,"score_spread":0.12155330345797566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986927305","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008335083,0.00071054103,0.9955638,0.00027652862,0.00015204425,0.00062455446,0.0014762399,0.000007510513,0.0003552921],"genre_scores_gemma":[0.081468344,0.000015043542,0.9177305,0.00011568208,0.00004959842,0.000040628027,0.0004274618,0.000018469247,0.00013425804],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9932846,0.0022525233,0.0016022255,0.0007495187,0.0017445575,0.0003666014],"domain_scores_gemma":[0.9621985,0.035516914,0.00039338038,0.0014075283,0.00040029685,0.00008339951],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037652254,0.00022372465,0.0009615553,0.0009250014,0.000068491834,0.000031990792,0.0013184365,0.00006179615,0.00054034934],"category_scores_gemma":[0.023903245,0.00012225445,0.00003308874,0.0033811582,0.000692188,0.00011347503,0.00018705828,0.00020234894,0.0000025010877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004788393,0.0018206479,0.19527625,0.00016271695,0.0014862525,0.00019535588,0.0029782203,0.046817727,0.04121157,0.10346026,0.04311538,0.5586872],"study_design_scores_gemma":[0.0024088512,0.00060508726,0.2012737,0.00006981817,0.0010028332,0.00000227643,0.0017454216,0.75952256,0.000462509,0.03175549,0.00091407506,0.00023737726],"about_ca_topic_score_codex":0.0016501333,"about_ca_topic_score_gemma":0.0012757982,"teacher_disagreement_score":0.71270484,"about_ca_system_score_codex":0.00008959585,"about_ca_system_score_gemma":0.00013583327,"threshold_uncertainty_score":0.9909395},"labels":[],"label_agreement":null},{"id":"W1987001026","doi":"10.1002/sim.3882","title":"The analysis of treatment effects for recurring episodic conditions","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Randomized controlled trial; Migraine; Disease; Neurology; Clinical trial; Asthma; Chronic Migraine; Intensive care medicine; Pediatrics; Psychiatry; Internal medicine","score_opus":0.04607669157443555,"score_gpt":0.44360969574707126,"score_spread":0.3975330041726357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987001026","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006656025,0.000030878393,0.9912464,0.00018095445,0.0003507096,0.00038878774,0.0005145984,0.0000103246175,0.0006213056],"genre_scores_gemma":[0.16643637,0.000054160184,0.83312124,0.000028729584,0.000073130526,0.00013834325,0.000048468566,0.000011201992,0.000088340676],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990473,0.00008814958,0.00040887416,0.00013996995,0.00013593784,0.00017980285],"domain_scores_gemma":[0.9737039,0.025710214,0.00014660372,0.00026921814,0.00011285145,0.000057176658],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00071949675,0.00010485006,0.0004329413,0.00015152094,0.00009903665,0.000006610088,0.000111127956,0.00004366142,0.00010692678],"category_scores_gemma":[0.013069323,0.00006093,0.000043229724,0.00036646635,0.00033616004,0.0000099327635,0.0000112199905,0.0001214149,7.841455e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013180256,0.00004340235,0.000856934,0.000072452756,0.00019473246,0.0000035454188,0.0002723387,8.051727e-7,0.0007144101,0.9408486,0.00083292887,0.056146666],"study_design_scores_gemma":[0.0006231048,0.00036244438,0.009860262,0.000056190467,0.0010604238,7.862782e-7,0.0000831023,0.008149277,0.00023868907,0.9789789,0.00051968714,0.000067143745],"about_ca_topic_score_codex":0.000089937486,"about_ca_topic_score_gemma":0.0010270532,"teacher_disagreement_score":0.15978035,"about_ca_system_score_codex":0.000035034896,"about_ca_system_score_gemma":0.000037388898,"threshold_uncertainty_score":0.995244},"labels":[],"label_agreement":null},{"id":"W1987309974","doi":"10.1002/sim.1528","title":"Estimating the size of an illicit‐drug‐using population","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Census and Population Estimation","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Population; Confidence interval; Statistics; Computer science; Population size; Sampling (signal processing); Sample size determination; Selection bias; Interval (graph theory); Econometrics; Medicine; Mathematics; Environmental health","score_opus":0.05992622483707203,"score_gpt":0.39626810304054444,"score_spread":0.3363418782034724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987309974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6942251,0.000035648485,0.30431828,0.00011210809,0.0003388357,0.00025373473,0.000024292867,0.000019272957,0.0006727641],"genre_scores_gemma":[0.6166756,0.0000013877465,0.3831658,0.000035120313,0.000057509842,0.0000022024954,0.000023642828,0.00001095222,0.000027757678],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987125,0.00017539323,0.0005584851,0.00011892603,0.00030253272,0.00013217998],"domain_scores_gemma":[0.99804264,0.001283241,0.00029669123,0.00023538104,0.0001069731,0.000035093835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001142074,0.00009980097,0.00022620501,0.00006480859,0.00008336305,0.0000052545993,0.00007457764,0.00003475619,0.00017141872],"category_scores_gemma":[0.006149961,0.00007006407,0.000011841774,0.00022584753,0.00007598892,0.000060497416,0.0000081202825,0.00011456034,7.500052e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017694492,0.00010866027,0.03350194,0.0003038482,0.000015527368,0.0000073844267,0.0045392564,0.017072003,0.00043026774,0.9313614,0.0007157851,0.011926242],"study_design_scores_gemma":[0.0005138843,0.00004107227,0.036883675,0.00017212812,0.000045509638,0.000011111338,0.00025449682,0.38124457,0.00004872295,0.58064574,0.000047123278,0.00009199218],"about_ca_topic_score_codex":0.0005556491,"about_ca_topic_score_gemma":0.00028372946,"teacher_disagreement_score":0.36417258,"about_ca_system_score_codex":0.000048381742,"about_ca_system_score_gemma":0.000020489946,"threshold_uncertainty_score":0.73625225},"labels":[],"label_agreement":null},{"id":"W1987856141","doi":"10.1002/sim.986","title":"Maximum likelihood estimation of a survival function with a change point for truncated and interval‐censored data","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Statistics; Interval (graph theory); Point estimation; Estimation; Maximum likelihood; Interval estimation; Likelihood function; Survival function; Survival analysis; Confidence interval; Econometrics; Function (biology); Mathematics; Computer science; Biology; Combinatorics; Economics","score_opus":0.19020068248610117,"score_gpt":0.3979920695445226,"score_spread":0.20779138705842143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987856141","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002492177,0.00010654789,0.9951673,0.0004352755,0.00015671279,0.0005299072,0.00082685455,0.000019931807,0.00026529265],"genre_scores_gemma":[0.16217178,0.00006881276,0.8373233,0.00008131053,0.00007433195,0.000049051545,0.00018512478,0.000021933158,0.000024328343],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987611,0.0000944465,0.00044795783,0.0002600143,0.00024866423,0.00018782084],"domain_scores_gemma":[0.9969206,0.0023135722,0.00018810407,0.0003513708,0.00015692029,0.00006944948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008861077,0.0001394469,0.000431588,0.0001039804,0.00002845122,0.0000073096135,0.00012630137,0.00005076099,0.00020988708],"category_scores_gemma":[0.0062627867,0.00010047638,0.0000068045556,0.00016874194,0.00019196619,0.00006665724,0.00005260055,0.00011524399,0.0000011214094],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048019548,0.00026571006,0.00059901085,0.0014651075,0.00008115118,0.000014656715,0.0035159346,0.0000015940371,0.0001246349,0.41482934,0.005719956,0.57290274],"study_design_scores_gemma":[0.0022840197,0.0014737773,0.004167217,0.00049616443,0.00017087294,0.0000067431993,0.00048048364,0.3241019,0.00001687203,0.6665832,0.000087145425,0.00013161982],"about_ca_topic_score_codex":0.00012007287,"about_ca_topic_score_gemma":0.00014728452,"teacher_disagreement_score":0.5727711,"about_ca_system_score_codex":0.000020707557,"about_ca_system_score_gemma":0.000010451868,"threshold_uncertainty_score":0.7497593},"labels":[],"label_agreement":null},{"id":"W1987973071","doi":"10.1002/sim.5941","title":"Graphical assessment of internal and external calibration of logistic regression models by using loess smoothers","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":357,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Public Health Ontario; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Overfitting; Calibration; Logistic regression; Statistics; Computer science; Covariate; Loess; Econometrics; Mathematics; Artificial intelligence","score_opus":0.4241021929435487,"score_gpt":0.5779164790022724,"score_spread":0.15381428605872371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987973071","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049751174,0.00008036116,0.9491192,0.00007728522,0.0002367592,0.0003428982,0.00017134583,0.000008486106,0.00021249992],"genre_scores_gemma":[0.4347288,0.00005514966,0.56509906,0.000039542905,0.000040622235,0.0000074859654,0.000002692556,0.000014576803,0.000012076779],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99699086,0.00057949044,0.0014033922,0.000257527,0.00057755254,0.00019117809],"domain_scores_gemma":[0.9824188,0.016417727,0.0006209838,0.00024406666,0.00018152584,0.0001169259],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019246425,0.000172031,0.0008074914,0.00013590133,0.000021603739,0.000008488657,0.0001675667,0.00013092549,0.00035233254],"category_scores_gemma":[0.01609883,0.00012243453,0.00002708841,0.00015464702,0.0008586697,0.00007046431,0.00007646738,0.00030801483,1.3035267e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017058081,0.00049796223,0.017973794,0.0013142928,0.000097454445,0.00002710582,0.0005407127,0.00019361026,0.03140313,0.92211556,0.0037816109,0.021884194],"study_design_scores_gemma":[0.0010059485,0.00023967106,0.0015081642,0.00089317455,0.000061831655,0.0000030850517,0.00009869772,0.259879,0.00027447008,0.7359542,8.2276995e-7,0.00008094367],"about_ca_topic_score_codex":0.00046457403,"about_ca_topic_score_gemma":0.000007696043,"teacher_disagreement_score":0.38497764,"about_ca_system_score_codex":0.000040637253,"about_ca_system_score_gemma":0.00004377491,"threshold_uncertainty_score":0.992189},"labels":[],"label_agreement":null},{"id":"W1988018581","doi":"10.1002/sim.1748","title":"Simultaneous inference for longitudinal data with detection limits and covariates measured with errors, with application to AIDS studies","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Covariate; Censoring (clinical trials); Inference; Statistics; Computer science; Statistical inference; Gibbs sampling; Data set; Monte Carlo method; Observational error; Econometrics; Mathematics; Artificial intelligence; Bayesian probability","score_opus":0.054640807936469755,"score_gpt":0.3630267823652393,"score_spread":0.3083859744287695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1988018581","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010710335,0.00018713053,0.99705046,0.000744315,0.000046196146,0.00079988636,0.000046718767,0.00003189163,0.000022367249],"genre_scores_gemma":[0.44109434,0.000027136653,0.55866027,0.000106232044,0.000025619453,0.000057906873,0.0000145858685,0.0000074122718,0.000006496681],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986834,0.000043775402,0.00019855992,0.00058597384,0.00028230486,0.00020596322],"domain_scores_gemma":[0.9981514,0.0006969632,0.000107687294,0.00058955513,0.00035691538,0.00009744549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007194574,0.00017240139,0.00031961987,0.000098884055,0.00011329708,0.000046443995,0.00051704387,0.000033586504,2.990701e-7],"category_scores_gemma":[0.000747005,0.000104010556,0.0000023690557,0.0004333162,0.00016632947,0.00018960386,0.00013457367,0.00012059844,3.0115336e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001348611,0.00017020768,0.0019727973,0.00035651584,0.00023810127,0.00015296484,0.006969298,0.009406898,0.0012274893,0.3631569,0.000106697466,0.6148935],"study_design_scores_gemma":[0.021933261,0.035178743,0.011134677,0.0032634404,0.00069091824,0.00053649105,0.00135215,0.35670525,0.0027806528,0.56336266,0.0011665416,0.0018951972],"about_ca_topic_score_codex":0.00020852643,"about_ca_topic_score_gemma":0.0047387425,"teacher_disagreement_score":0.6129983,"about_ca_system_score_codex":0.000056043435,"about_ca_system_score_gemma":0.00010857511,"threshold_uncertainty_score":0.42414275},"labels":[],"label_agreement":null},{"id":"W1990732953","doi":"10.1002/sim.2435","title":"Pseudo-likelihood methods for longitudinal binary data with non-ignorable missing responses and covariates","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute; National Institute of General Medical Sciences; U.S. Public Health Service","keywords":"Covariate; Missing data; Categorical variable; Statistics; Parametric statistics; Estimating equations; Econometrics; Expectation–maximization algorithm; Outcome (game theory); Mathematics; Computer science; Maximum likelihood","score_opus":0.12276464088284904,"score_gpt":0.48109581167973214,"score_spread":0.3583311707968831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990732953","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047945528,0.00032670662,0.9961986,0.0014098831,0.00010869215,0.00042446287,0.0005762674,0.000029456602,0.00044647173],"genre_scores_gemma":[0.0032793812,0.00009783937,0.99596626,0.00017172689,0.00020809102,0.0000335134,0.000082095794,0.00003873966,0.00012236199],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997951,0.0003124926,0.00055524806,0.00052910467,0.00023521043,0.00041697553],"domain_scores_gemma":[0.98280853,0.016087107,0.00017508923,0.00060494075,0.0001597918,0.00016454609],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003673917,0.00024471557,0.00061787816,0.00015895482,0.00014178055,0.000038772734,0.00029953825,0.00008061857,0.00015429955],"category_scores_gemma":[0.013962552,0.00017543182,0.000009433907,0.00023610452,0.0003960676,0.00011938355,0.00012896399,0.00024467497,0.000001611244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008082117,0.00018885342,0.0019529313,0.0007653238,0.0000858157,0.00008968295,0.0009023229,0.0000015987266,0.0012156676,0.44326255,0.016125066,0.534602],"study_design_scores_gemma":[0.0021583214,0.0008362268,0.0035503604,0.0006507973,0.00024547975,0.000059612234,0.00027883306,0.07459253,0.00016524535,0.9156181,0.0015566121,0.00028783784],"about_ca_topic_score_codex":0.000075534284,"about_ca_topic_score_gemma":0.00008798606,"teacher_disagreement_score":0.53431416,"about_ca_system_score_codex":0.000041463558,"about_ca_system_score_gemma":0.0001349676,"threshold_uncertainty_score":0.9943433},"labels":[],"label_agreement":null},{"id":"W1990838844","doi":"10.1002/sim.714","title":"Testing for elevated disease rates using smoothed estimates","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Statistics; Econometrics; Mathematics","score_opus":0.2191181211047542,"score_gpt":0.4805154219191844,"score_spread":0.2613973008144302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990838844","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028859787,0.000090148176,0.96953,0.00017697294,0.00023073256,0.0004271765,0.0002168581,0.000058623737,0.00040973455],"genre_scores_gemma":[0.08342929,0.000010139129,0.9160636,0.00014657494,0.00017333667,0.000037755675,0.000032660482,0.000037541962,0.00006907472],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998462,0.00008068737,0.00056195573,0.00027183935,0.0002398055,0.0003836852],"domain_scores_gemma":[0.98596764,0.013193189,0.00015890997,0.00022819835,0.00027451743,0.00017753034],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00084022584,0.00020019794,0.00042949384,0.00011689106,0.00009802336,0.000017303346,0.00014056826,0.00004672902,0.00027107383],"category_scores_gemma":[0.071296334,0.00015863751,0.000016397475,0.00035389396,0.00022347277,0.00003169899,0.000030049769,0.00014317675,0.000002936652],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022882533,0.00018108464,0.040745493,0.000680311,0.0000366244,0.0002128937,0.00038211653,0.00006362361,0.0057769804,0.9178453,0.0026543601,0.031192372],"study_design_scores_gemma":[0.00083024247,0.0001544039,0.010247276,0.0004049995,0.00008816043,0.000005957127,0.000088952176,0.21867587,0.000064789594,0.76919657,0.000085205196,0.00015760858],"about_ca_topic_score_codex":0.00011696633,"about_ca_topic_score_gemma":0.000014715071,"teacher_disagreement_score":0.21861224,"about_ca_system_score_codex":0.00005876792,"about_ca_system_score_gemma":0.000077244025,"threshold_uncertainty_score":0.93652654},"labels":[],"label_agreement":null},{"id":"W1991135418","doi":"10.1002/1097-0258(20001115)19:21<3017::aid-sim785>3.0.co;2-p","title":"M. D. deB. Edwardes, ‘The generalization of the odds ratio, risk ratio and risk difference tor ×k tables’.Statistics in Medicine 2000;19(14): 1901-1914","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital","funders":"","keywords":"Statistics; Generalization; Medical statistics; Odds ratio; Mathematics; Odds; Medicine; Logistic regression","score_opus":0.15515203872518482,"score_gpt":0.46718523153196945,"score_spread":0.31203319280678465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991135418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013863161,0.0008217635,0.977279,0.0012140737,0.0010062403,0.0014717013,0.0032810897,0.00003498664,0.001028006],"genre_scores_gemma":[0.0700213,0.014696521,0.910629,0.0010250442,0.00093127094,0.000153201,0.00014399571,0.000117555304,0.0022821513],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9913014,0.0035062365,0.002769048,0.0006391102,0.00122885,0.0005553284],"domain_scores_gemma":[0.9432147,0.054194752,0.00106234,0.0009762111,0.00033501018,0.00021698896],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007417223,0.00047855155,0.001478964,0.00018087102,0.00025783348,0.000026996353,0.00063087087,0.00026782398,0.002457183],"category_scores_gemma":[0.17916685,0.00028003892,0.000043811273,0.0009092234,0.0021128189,0.000053327087,0.00012575815,0.0010439393,0.000007248672],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076802383,0.00057553675,0.077991754,0.0010676393,0.00027771338,0.00007998557,0.008731477,0.001032115,0.0003694222,0.60669416,0.09827486,0.20413733],"study_design_scores_gemma":[0.004592647,0.00049375155,0.088467926,0.0007365143,0.0006160234,0.00001103854,0.00030007723,0.04321931,0.0000764363,0.859759,0.0013755604,0.00035172858],"about_ca_topic_score_codex":0.003156371,"about_ca_topic_score_gemma":0.0033491086,"teacher_disagreement_score":0.25306484,"about_ca_system_score_codex":0.00017944096,"about_ca_system_score_gemma":0.00023849355,"threshold_uncertainty_score":0.9999652},"labels":[],"label_agreement":null},{"id":"W1991362225","doi":"10.1002/sim.3383","title":"Sample size calculation for cluster randomized cross‐over trials","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Intraclass correlation; Sample size determination; Cluster (spacecraft); Statistics; Sample (material); Cluster analysis; Cross over; Randomized controlled trial; Computer science; Correlation; External validity; Econometrics; Mathematics; Medicine; Physics; Psychometrics; Internal medicine; Thermodynamics","score_opus":0.5602429666646603,"score_gpt":0.6200809675466604,"score_spread":0.059838000882000086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991362225","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002595501,0.000052218355,0.9899044,0.0005880314,0.0016712932,0.0032499065,0.0012534115,0.00005954346,0.0006256667],"genre_scores_gemma":[0.011169032,0.00013178252,0.9854928,0.00077805965,0.0012004991,0.00037505367,0.000036353085,0.00006006219,0.0007563297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9910928,0.0035442056,0.0036851359,0.0004889049,0.0007398458,0.00044909737],"domain_scores_gemma":[0.40547365,0.59304374,0.0006987997,0.00036741738,0.00028098366,0.00013539201],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033032194,0.0003020635,0.0032205132,0.00012725894,0.00013244676,0.000017041599,0.00022841588,0.00024724784,0.0017541766],"category_scores_gemma":[0.9313619,0.00021217267,0.00021651118,0.00023800677,0.0011385877,0.000050006154,0.000054444037,0.00032072267,0.000009504874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06691938,0.00023881436,0.0009717276,0.00048501298,0.00024652487,0.000036055222,0.0009053029,0.000042389678,0.00007141245,0.81520253,0.10850077,0.0063800546],"study_design_scores_gemma":[0.1902551,0.00015476887,0.0007434044,0.00011875367,0.00024190018,0.0000044177864,0.000013771387,0.008017958,0.000032314118,0.7995901,0.00063926855,0.0001882212],"about_ca_topic_score_codex":0.00012448699,"about_ca_topic_score_gemma":0.000022807622,"teacher_disagreement_score":0.89832973,"about_ca_system_score_codex":0.0001013035,"about_ca_system_score_gemma":0.00009427287,"threshold_uncertainty_score":0.9991584},"labels":[],"label_agreement":null},{"id":"W1992221362","doi":"10.1002/sim.3316","title":"Archimedean copula model selection under dependent truncation","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Copula (linguistics); Mathematics; Truncation (statistics); Multivariate statistics; Statistics; Econometrics; Applied mathematics","score_opus":0.15964420102335394,"score_gpt":0.431878468074725,"score_spread":0.2722342670513711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992221362","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015898606,0.000023198536,0.97979724,0.0002587328,0.00016332728,0.00019770127,0.000053779284,0.000043114116,0.0035643163],"genre_scores_gemma":[0.42188388,0.000065728265,0.57719713,0.00017080262,0.00008309881,0.000017684311,0.000022698674,0.000017528611,0.0005414153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984186,0.0001440009,0.0004893308,0.00024431525,0.00045118856,0.00025254238],"domain_scores_gemma":[0.99795365,0.0015055813,0.00011692075,0.00018536708,0.00013286472,0.0001056019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061674224,0.00015145354,0.00031783115,0.00013569539,0.000098425946,0.000004767413,0.00011284224,0.000066826105,0.00030204176],"category_scores_gemma":[0.0037279062,0.00012557964,0.000013146044,0.00019808309,0.0002111361,0.000029535573,0.000024017181,0.00028173163,0.000013213974],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030113695,0.00008865328,0.0007846153,0.00005891065,0.000011283875,0.00001900475,0.0009929923,0.00042743643,0.00041242386,0.98305815,0.005244797,0.008871637],"study_design_scores_gemma":[0.0005965067,0.00012811042,0.0055110673,0.000057467612,0.000024398403,0.000029223356,0.0001148307,0.1933247,0.00009602469,0.79997784,0.000022161583,0.00011768408],"about_ca_topic_score_codex":0.00020566321,"about_ca_topic_score_gemma":0.00024648334,"teacher_disagreement_score":0.40598527,"about_ca_system_score_codex":0.00011415709,"about_ca_system_score_gemma":0.00009270855,"threshold_uncertainty_score":0.5120989},"labels":[],"label_agreement":null},{"id":"W1992435907","doi":"10.1002/1097-0258(20010130)20:2<249::aid-sim641>3.0.co;2-l","title":"Statistical inferences for a twin correlation with multinomial outcomes","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multinomial distribution; Sample size determination; Statistics; Point estimation; Goodness of fit; Statistical inference; Confidence interval; Interval estimation; Computer science; Econometrics; Inference; Sample (material); Monte Carlo method; Mathematics; Artificial intelligence","score_opus":0.4665853261819578,"score_gpt":0.5871577886326694,"score_spread":0.12057246245071163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992435907","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043217707,0.000012079754,0.9905111,0.00072603044,0.00072363234,0.0010550194,0.00064839085,0.00006536082,0.0019366235],"genre_scores_gemma":[0.07072932,0.00002659812,0.9279713,0.00027762185,0.00033100674,0.00015440561,0.00005212433,0.000043699238,0.0004139162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996759,0.00041646435,0.0013064542,0.00045605307,0.00059828267,0.00046375836],"domain_scores_gemma":[0.8881183,0.11085883,0.00030936353,0.0003079979,0.00023396318,0.0001715277],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028720312,0.00029252082,0.0010614758,0.00016447126,0.00008274689,0.000020512043,0.00022073403,0.00015851611,0.00089905673],"category_scores_gemma":[0.17254163,0.00019702657,0.000032182026,0.0002686697,0.00059568067,0.000050908744,0.00003907174,0.00038006573,0.000015453428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083358865,0.00022851197,0.083039105,0.00015495662,0.00006894886,0.000100843434,0.00040354527,0.000023801662,0.000008897266,0.8698447,0.009395882,0.035897236],"study_design_scores_gemma":[0.0058472627,0.0010483094,0.04438588,0.00019588448,0.00017130566,0.000012148351,0.00023058703,0.008039498,0.000004375553,0.93888336,0.0009186331,0.0002627245],"about_ca_topic_score_codex":0.00010287356,"about_ca_topic_score_gemma":0.0003428773,"teacher_disagreement_score":0.1696696,"about_ca_system_score_codex":0.000085797285,"about_ca_system_score_gemma":0.00010218245,"threshold_uncertainty_score":0.9844041},"labels":[],"label_agreement":null},{"id":"W1993310646","doi":"10.1002/sim.857","title":"Evaluation of an adjusted chi‐square statistic as applied to observational studies involving clustered binary data","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Statistics; Statistic; Chi-square test; Binary data; Test statistic; Observational study; Ancillary statistic; Mathematics; Binary number; Square (algebra); Statistical hypothesis testing; Pearson's chi-squared test; Econometrics; PRESS statistic; F-test; Arithmetic","score_opus":0.547003564024309,"score_gpt":0.5393908008446755,"score_spread":0.007612763179633553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993310646","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036646187,0.0002855924,0.9585429,0.00037544264,0.00036694002,0.0011254853,0.0013844434,0.000042521086,0.0012304789],"genre_scores_gemma":[0.147338,0.000103984734,0.85117644,0.0002738956,0.00016286604,0.000044753477,0.0008347228,0.000033821325,0.000031486685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955751,0.0006830964,0.0011162045,0.000558499,0.0017341364,0.000332986],"domain_scores_gemma":[0.99195296,0.005427284,0.00033850168,0.0009089286,0.0011979492,0.00017436272],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0061335624,0.00026221565,0.0007474922,0.0002799571,0.000090035566,0.000013709467,0.0005096419,0.00008128748,0.0006944641],"category_scores_gemma":[0.049992125,0.00022420118,0.000010963122,0.00066786725,0.00027391536,0.0001230953,0.00024076004,0.00023161952,0.000011075146],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001974057,0.00027546016,0.0010503028,0.00052961253,0.00012355208,0.00006329815,0.0034234382,0.00011585639,0.00049706805,0.84499073,0.007656294,0.14107701],"study_design_scores_gemma":[0.0016323156,0.00053614116,0.031108927,0.0005943742,0.00039268404,0.000009150767,0.0032254239,0.09894494,0.00002078232,0.8632403,0.000063716405,0.00023126676],"about_ca_topic_score_codex":0.00016753252,"about_ca_topic_score_gemma":0.00086305017,"teacher_disagreement_score":0.14084575,"about_ca_system_score_codex":0.0001781243,"about_ca_system_score_gemma":0.0002787457,"threshold_uncertainty_score":0.9580102},"labels":[],"label_agreement":null},{"id":"W1993607274","doi":"10.1002/sim.1297","title":"The European regulatory experience","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hatch (Canada)","funders":"","keywords":"Clinical trial; Regulatory science; Margin (machine learning); Risk analysis (engineering); Work (physics); Medicine; Computer science; Management science; Economics","score_opus":0.5295102756246849,"score_gpt":0.563117157145275,"score_spread":0.033606881520590104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993607274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028269012,0.0006845947,0.7964706,0.0030764139,0.0031928166,0.0006964328,0.00009532592,0.00016078248,0.19279617],"genre_scores_gemma":[0.0859851,0.0004984218,0.90870404,0.00048939826,0.0009143717,0.00003098433,0.000001294829,0.000056473113,0.003319923],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961763,0.0015756856,0.0010270189,0.0002903407,0.0005762131,0.00035442106],"domain_scores_gemma":[0.9408338,0.058120772,0.00019897804,0.0006357632,0.000085878426,0.00012478506],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006179464,0.00015967092,0.00039274874,0.00004846235,0.00015212929,0.000017768334,0.00044474474,0.000049640625,0.0011400952],"category_scores_gemma":[0.18378642,0.00009751986,0.00002443544,0.00023380651,0.0010913853,0.000022778393,0.00008874618,0.00037443696,0.00009910193],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012736052,0.00005454196,0.0002974261,0.000032183318,0.000012046544,0.00012033792,0.0013974301,5.1737135e-7,0.000042208525,0.7311053,0.12360421,0.14332102],"study_design_scores_gemma":[0.00079946296,0.00010644284,0.0036098252,0.00011749074,0.000021903556,0.0000066508114,0.00037604722,0.0007400411,0.000017395085,0.98338336,0.010692265,0.0001291328],"about_ca_topic_score_codex":0.0000085137035,"about_ca_topic_score_gemma":0.000017264572,"teacher_disagreement_score":0.252278,"about_ca_system_score_codex":0.00004699483,"about_ca_system_score_gemma":0.0000073547094,"threshold_uncertainty_score":0.999773},"labels":[],"label_agreement":null},{"id":"W1993793629","doi":"10.1002/sim.3807","title":"Bootstrap‐based methods for estimating standard errors in Cox's regression analyses of clustered event times","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Statistics; Proportional hazards model; Regression; Event (particle physics); Regression analysis; Computer science; Standard error; Econometrics; Mathematics","score_opus":0.21099525133564637,"score_gpt":0.5786252017706595,"score_spread":0.3676299504350131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1993793629","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004002719,0.000042738902,0.9940588,0.00022587775,0.0004743065,0.00048337082,0.0003133261,0.00001810143,0.00038076434],"genre_scores_gemma":[0.07014676,0.0000055650617,0.9295908,0.000051648552,0.00006465179,0.000044025408,0.000034645655,0.000025777354,0.000036101123],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975407,0.00038578027,0.0011223108,0.00029159026,0.0003544656,0.00030513052],"domain_scores_gemma":[0.98510474,0.013768912,0.00042682124,0.00034390666,0.0002523381,0.000103303704],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037423323,0.00021782974,0.000862242,0.00028692387,0.000043229487,0.000007317055,0.00020215676,0.00012345139,0.00045454485],"category_scores_gemma":[0.042788595,0.00015735794,0.00004104121,0.00031029512,0.000336228,0.000027243515,0.000038336464,0.00041052888,4.246235e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00069306255,0.0003465527,0.0017753511,0.0025165814,0.00006745066,0.00003896944,0.0018970813,0.00031961146,0.03594655,0.5186726,0.0045404616,0.43318573],"study_design_scores_gemma":[0.0018179826,0.00044422105,0.00091887056,0.0008838833,0.00008093287,0.0000016558288,0.00024861182,0.39433718,0.0047345925,0.59631366,0.000068269364,0.00015013308],"about_ca_topic_score_codex":0.00014067485,"about_ca_topic_score_gemma":0.00017554367,"teacher_disagreement_score":0.43303558,"about_ca_system_score_codex":0.000046167825,"about_ca_system_score_gemma":0.0001306709,"threshold_uncertainty_score":0.9652744},"labels":[],"label_agreement":null},{"id":"W1994343730","doi":"10.1002/sim.1723","title":"Three validation metrics for automated probabilistic image segmentation of brain tumours","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Center for Research Resources; U.S. National Library of Medicine; National Cancer Institute; Agency for Healthcare Research and Quality; National Institutes of Health","keywords":"Segmentation; Computer science; Artificial intelligence; Markov random field; Metric (unit); Similarity (geometry); Pixel; Pattern recognition (psychology); Gold standard (test); Image segmentation; Image (mathematics); Mathematics; Statistics","score_opus":0.027769904315747322,"score_gpt":0.3596305153886217,"score_spread":0.33186061107287435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994343730","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008811906,0.000029982446,0.9960353,0.0015424445,0.00022018215,0.00089352403,0.000057578254,0.00025957433,0.000080272854],"genre_scores_gemma":[0.029939307,0.0000137503675,0.9693884,0.00031796467,0.000037205828,0.00009663254,0.00018312185,0.000012416726,0.00001115267],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99825937,0.00004889233,0.00064025685,0.00028374768,0.0005632891,0.00020444216],"domain_scores_gemma":[0.9980875,0.000911828,0.00028986722,0.00028450694,0.00034488065,0.00008141777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012266673,0.00012930755,0.00026501244,0.00040698203,0.00003938193,0.000022842263,0.0003824552,0.000050070714,0.000025699159],"category_scores_gemma":[0.0050761476,0.00011573169,0.000018367971,0.0008944515,0.00021700333,0.00023928132,0.000052412062,0.0001040133,0.000003156427],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008487922,0.0008168269,0.0013540104,0.0017881902,0.00006842419,0.00010267505,0.006617204,0.0018507957,0.16305736,0.53760445,0.07506582,0.21158937],"study_design_scores_gemma":[0.0058462657,0.0014938184,0.006550688,0.0004421081,0.00005873552,0.000013111318,0.00024977204,0.19803026,0.13669865,0.6502268,0.000029628436,0.0003601898],"about_ca_topic_score_codex":0.00013789615,"about_ca_topic_score_gemma":0.00004582826,"teacher_disagreement_score":0.21122918,"about_ca_system_score_codex":0.00019028907,"about_ca_system_score_gemma":0.00013326004,"threshold_uncertainty_score":0.607699},"labels":[],"label_agreement":null},{"id":"W1997239045","doi":"10.1002/sim.980","title":"A three‐stage clinical trial design for rare disorders","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Randomized controlled trial; Stage (stratigraphy); Clinical trial; Medicine; Sample size determination; Placebo; Research design; Clinical study design; N of 1 trial; Completely randomized design; Randomization; Physical therapy; Surgery; Internal medicine; Statistics; Alternative medicine; Mathematics; Pathology","score_opus":0.6420867572546721,"score_gpt":0.5536282516752941,"score_spread":0.08845850557937807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997239045","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051854323,0.0009665168,0.9652102,0.02140895,0.002267523,0.0024442142,0.0006801148,0.000033455257,0.001803571],"genre_scores_gemma":[0.16633676,0.005447415,0.76701206,0.040320154,0.009851282,0.0023875837,0.0010678255,0.00029946485,0.007277474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933873,0.0003125341,0.005185077,0.00055884087,0.00011125254,0.00044501887],"domain_scores_gemma":[0.98952323,0.008324906,0.0014578484,0.00044564926,0.000059839804,0.0001884945],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.030894674,0.0001877599,0.001247773,0.00029200438,0.00011475489,0.000021171134,0.0002733456,0.00016793031,0.0010333351],"category_scores_gemma":[0.03113914,0.00021202177,0.000072416355,0.00020459511,0.00021744012,0.00011718574,0.000026874031,0.00024974922,0.0002767148],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004635596,0.00032497488,0.047106206,0.0003171185,0.00008653534,0.000009789011,0.0011422259,0.00030720088,1.7144103e-7,0.5903208,0.34982225,0.0059270686],"study_design_scores_gemma":[0.06042956,0.00231756,0.014582432,0.00013602946,0.00001953333,0.0000022729623,0.0008887238,0.055018272,9.046396e-8,0.58223146,0.28394228,0.0004318032],"about_ca_topic_score_codex":0.00073790783,"about_ca_topic_score_gemma":0.0020003838,"teacher_disagreement_score":0.19819818,"about_ca_system_score_codex":0.00023360207,"about_ca_system_score_gemma":0.00015749912,"threshold_uncertainty_score":0.99987984},"labels":[],"label_agreement":null},{"id":"W1997256514","doi":"10.1002/sim.5572","title":"Comments on the FDA draft guidance on biosimilar products","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Biosimilars and Bioanalytical Methods","field":"Immunology and Microbiology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interchangeability; Biosimilar; Food and drug administration; Risk analysis (engineering); Computer science; Scientific evidence; Management science; Operations research; Business; Medicine; Engineering; Statistics","score_opus":0.051552394930830296,"score_gpt":0.3530185489860644,"score_spread":0.3014661540552341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997256514","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08312262,0.0266742,0.019589946,0.6809264,0.03233122,0.0049509103,0.0023119813,0.00033860747,0.14975417],"genre_scores_gemma":[0.9589822,0.0002848642,0.006378428,0.030342268,0.00039174155,0.000028770242,0.000073015515,0.000024961812,0.0034937442],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985976,0.00039937353,0.0002966531,0.00020799368,0.00008565185,0.000412683],"domain_scores_gemma":[0.9982163,0.0012347243,0.00008318775,0.00037881208,0.00005333646,0.00003364727],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013876302,0.00016735088,0.00026762873,0.00007071803,0.000110563684,0.0000036077179,0.00022175988,0.00012586782,0.0011132498],"category_scores_gemma":[0.0023133478,0.000088683315,0.000016045366,0.00020162467,0.0005309199,0.000016817006,0.00004628768,0.0004825779,0.00019287984],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017449782,0.00040640615,0.005972241,0.000036857327,0.00008801292,0.000009326332,0.0004753926,5.6212303e-7,0.013778676,0.16994135,0.7977748,0.011341886],"study_design_scores_gemma":[0.0021342032,0.001518454,0.07288233,0.00045510428,0.00010942255,0.000015266769,0.00036789503,0.00002228575,0.039740358,0.0073299897,0.87506235,0.0003623716],"about_ca_topic_score_codex":0.000019653464,"about_ca_topic_score_gemma":0.0000068059744,"teacher_disagreement_score":0.8758596,"about_ca_system_score_codex":0.000042796873,"about_ca_system_score_gemma":0.000015113326,"threshold_uncertainty_score":0.99979985},"labels":[],"label_agreement":null},{"id":"W1998669587","doi":"10.1002/sim.1227","title":"Assessing the gain in diagnostic performance when combining two diagnostic tests","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McMaster University","funders":"","keywords":"Statistics; Likelihood-ratio test; Test (biology); Sensitivity (control systems); Component (thermodynamics); Score test; Diagnostic test; Computer science; Econometrics; Mathematics; Medicine","score_opus":0.44492644498609113,"score_gpt":0.5605836017274896,"score_spread":0.11565715674139843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998669587","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14410478,0.0014546415,0.8170305,0.0070792916,0.004233128,0.003083987,0.00019574376,0.00023734917,0.022580601],"genre_scores_gemma":[0.543396,0.00046244063,0.45492533,0.0005803518,0.00035782464,0.000106733496,0.0000052144546,0.00004974436,0.00011635412],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944042,0.001576274,0.0019966539,0.0004991109,0.00082971563,0.00069405546],"domain_scores_gemma":[0.624348,0.37467924,0.00030629267,0.00046634642,0.00008713274,0.000113044196],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008071226,0.0003448961,0.001002642,0.00021246674,0.00014145717,0.00006395525,0.0005510407,0.00013155177,0.0014013628],"category_scores_gemma":[0.7061069,0.00024028435,0.000035373727,0.00058706506,0.0007942821,0.00012709621,0.00014985073,0.0011412353,0.000070759656],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044626926,0.0011764509,0.16963811,0.0010594354,0.000087133514,0.001585521,0.009117852,0.00055088056,0.00006458461,0.43639854,0.05583026,0.3244466],"study_design_scores_gemma":[0.0035716165,0.0003086621,0.033154186,0.002320473,0.00011375533,0.000020425583,0.00055722886,0.04526064,0.000018625971,0.914074,0.0002673892,0.00033300935],"about_ca_topic_score_codex":0.00012674455,"about_ca_topic_score_gemma":0.00013445382,"teacher_disagreement_score":0.69803566,"about_ca_system_score_codex":0.00012717418,"about_ca_system_score_gemma":0.000041373984,"threshold_uncertainty_score":0.9995115},"labels":[],"label_agreement":null},{"id":"W1999968123","doi":"10.1002/sim.6043","title":"A marginal structural model for multiple-outcome survival data:assessing the impact of injection drug use on several causes of death in the Canadian Co-infection Cohort","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Liver Disease Diagnosis and Treatment","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Marginal structural model; Inverse probability weighting; Confounding; Econometrics; Inverse probability; Estimator; Statistics; Weighting; Proportional hazards model; Outcome (game theory); Cohort; Medicine; Computer science; Mathematics; Bayesian probability","score_opus":0.09557594705627659,"score_gpt":0.41972797201469403,"score_spread":0.32415202495841744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999968123","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.995253,0.000023821858,0.0015367063,0.00028925267,0.00011969397,0.0013248784,0.0013803341,0.000004306181,0.00006800178],"genre_scores_gemma":[0.9976268,0.000029290102,0.00094894593,0.00011947009,0.00006982469,0.00007045132,0.0011008596,0.000013199777,0.000021204085],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987375,0.00012106309,0.000396538,0.00019083144,0.00033913317,0.00021493506],"domain_scores_gemma":[0.9980834,0.0011350256,0.00014688546,0.0003734322,0.0001653133,0.00009591703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005604289,0.00015021011,0.00035440116,0.00018463808,0.00008469432,0.000020907686,0.00010610913,0.00004172203,0.00003630021],"category_scores_gemma":[0.00082442886,0.00007541951,0.000037938164,0.00014476554,0.00013121992,0.00013681628,0.000013616738,0.00018149035,5.626555e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008768797,0.0001020619,0.99282265,0.0000705347,0.00010562708,0.000012378121,0.0009912653,0.0033283555,0.000010685985,0.00063674874,0.0015132709,0.00031871494],"study_design_scores_gemma":[0.0017169924,0.0002569725,0.77149975,0.00011765243,0.00016748499,0.000006979515,0.00021503854,0.22546522,0.0000052754244,0.0004963538,0.000002449058,0.000049830385],"about_ca_topic_score_codex":0.70926255,"about_ca_topic_score_gemma":0.3005941,"teacher_disagreement_score":0.4086685,"about_ca_system_score_codex":0.0004047836,"about_ca_system_score_gemma":0.00034890554,"threshold_uncertainty_score":0.7121683},"labels":[],"label_agreement":null},{"id":"W2001885105","doi":"10.1002/sim.6235","title":"The estimation of calibration equations for variables with heteroscedastic measurement errors","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"National Institutes of Health","keywords":"Heteroscedasticity; Calibration; Observational error; Transformation (genetics); Statistics; Computer science; Sample size determination; Set (abstract data type); Statistical hypothesis testing; Mathematics; Applied mathematics; Algorithm","score_opus":0.14812013680284633,"score_gpt":0.43135458447398406,"score_spread":0.2832344476711377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001885105","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000876427,0.000019785253,0.998775,0.00031778423,0.00011391511,0.00046754384,0.000058526377,0.000020381769,0.00013943428],"genre_scores_gemma":[0.2521213,0.000005475761,0.74767125,0.00002820833,0.000032391847,0.00008436105,0.00001676827,0.000018916495,0.00002136971],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99868274,0.00013731752,0.0004664659,0.00014137448,0.0004086009,0.00016348345],"domain_scores_gemma":[0.9910709,0.008214948,0.00021113799,0.00019772477,0.00026162452,0.000043612967],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018978959,0.00010452435,0.0002465579,0.000047179074,0.00009040077,0.000006853591,0.00008377887,0.00003043103,0.000005381778],"category_scores_gemma":[0.022193618,0.000061550105,0.000009920853,0.000105405394,0.00019504501,0.000037862075,0.000009910698,0.00007779032,1.2909368e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054121705,0.000030025147,0.000008515257,0.00015855653,0.00001240493,2.1781749e-7,0.00023923561,0.007995177,0.00019697352,0.9707856,0.00035316526,0.020166002],"study_design_scores_gemma":[0.00048301238,0.00026709403,0.000032414602,0.00012439543,0.000042336247,3.3335175e-7,0.00006258595,0.44261128,0.0000736478,0.5561857,0.000074738186,0.000042444422],"about_ca_topic_score_codex":0.000018996016,"about_ca_topic_score_gemma":0.00018374485,"teacher_disagreement_score":0.43461612,"about_ca_system_score_codex":0.00004770314,"about_ca_system_score_gemma":0.000042281652,"threshold_uncertainty_score":0.98604286},"labels":[],"label_agreement":null},{"id":"W2002271480","doi":"10.1002/sim.1477","title":"Misclassification in a matched case‐control study with variable matching ratio: application to a study of c‐erbB‐2 overexpression and breast cancer","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Odds ratio; Case-control study; Breast cancer; Risk factor; Statistics; Matching (statistics); Covariate; Medicine; Breast disease; Confidence interval; Oncology; Internal medicine; Mathematics; Computer science; Cancer","score_opus":0.15994251799571924,"score_gpt":0.5014059989025446,"score_spread":0.3414634809068253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002271480","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33943614,0.000012486019,0.6574149,0.00009898626,0.000056516692,0.0026740627,0.00020977837,0.000013467859,0.000083636674],"genre_scores_gemma":[0.6439562,0.000004000923,0.35563177,0.000042835458,0.000030918232,0.00030030086,0.0000010210604,0.000021864887,0.0000111180625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961388,0.0013614456,0.0012675974,0.00049554853,0.0005008704,0.00023571134],"domain_scores_gemma":[0.98494697,0.013885011,0.00040252524,0.00045169756,0.00019097238,0.00012284673],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0044198,0.00021674919,0.0008667533,0.00018785016,0.00005640762,0.000013199431,0.000119404765,0.00007647241,0.00015755143],"category_scores_gemma":[0.011428999,0.00016128109,0.0000074928876,0.00056338555,0.00008692434,0.000043909455,0.00003176389,0.0002864281,7.0696785e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053995186,0.018515164,0.31200728,0.0019433309,0.000692645,0.0011860533,0.07723285,0.0022030775,0.018195631,0.49786228,0.00067339855,0.06408876],"study_design_scores_gemma":[0.022524154,0.0028518597,0.17692031,0.0010861938,0.00052874396,0.000121902776,0.03169614,0.0048958915,0.000083632556,0.75885445,0.000005486837,0.00043121478],"about_ca_topic_score_codex":0.0014126706,"about_ca_topic_score_gemma":0.0013062591,"teacher_disagreement_score":0.30452004,"about_ca_system_score_codex":0.00009610699,"about_ca_system_score_gemma":0.00006321237,"threshold_uncertainty_score":0.9968982},"labels":[],"label_agreement":null},{"id":"W2004052735","doi":"10.1002/sim.1798","title":"Estimating episode lengths when some observations are probably censored","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Healthcare Policy and Management","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"National Institute on Drug Abuse","keywords":"Censoring (clinical trials); Estimator; Resampling; Statistics; Computer science; Econometrics; Monte Carlo method; Survival analysis; Mathematics","score_opus":0.08770789891825295,"score_gpt":0.3170221799295941,"score_spread":0.22931428101134113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004052735","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015849913,0.0016380688,0.86052734,0.10712155,0.0019958478,0.0010965016,0.001342791,0.00012875878,0.010299208],"genre_scores_gemma":[0.44054982,0.00028505773,0.5500821,0.0069510564,0.00072639243,0.00011514272,0.0001910425,0.00004633204,0.0010530467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984913,0.000016542017,0.0007776661,0.000297706,0.00006659135,0.00035018282],"domain_scores_gemma":[0.99915606,0.00011881706,0.0003070504,0.00027514936,0.000040162835,0.00010273445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006399688,0.0001337722,0.00038557596,0.00024042414,0.00009830106,0.000015730013,0.00016838053,0.00006116703,0.00011475212],"category_scores_gemma":[0.0016858339,0.00014648662,0.00001738859,0.00020030739,0.000094827665,0.00012194285,0.000043378797,0.00020874853,0.00012716018],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032550836,0.000044492903,0.005711975,0.00015965074,0.0000128179545,0.000022609796,0.0012678267,0.0019443375,0.0000013003119,0.98461705,0.0048307036,0.0013840056],"study_design_scores_gemma":[0.0010917648,0.000079438374,0.036565978,0.00019556361,0.0000055734195,0.00000146511,0.00016614921,0.0065804697,0.0000019520069,0.9372701,0.01788186,0.00015968698],"about_ca_topic_score_codex":0.008352361,"about_ca_topic_score_gemma":0.0020651736,"teacher_disagreement_score":0.4246999,"about_ca_system_score_codex":0.00024914436,"about_ca_system_score_gemma":0.000030423631,"threshold_uncertainty_score":0.9982511},"labels":[],"label_agreement":null},{"id":"W2004536301","doi":"10.1002/sim.3875","title":"On Bayesian shared component disease mapping and ecological regression with errors in covariates","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Child and Family Research Institute","keywords":"Multivariate statistics; Covariate; Bayesian probability; Context (archaeology); Computer science; Markov chain Monte Carlo; Bayesian inference; Prior probability; Bayesian hierarchical modeling; Autoregressive model; Econometrics; Statistics; Machine learning; Artificial intelligence; Geography; Mathematics","score_opus":0.046227544003509174,"score_gpt":0.3725131808067419,"score_spread":0.32628563680323275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004536301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07828535,0.000018185,0.91919667,0.0011381402,0.00019679942,0.00037573295,0.00015365587,0.000028288232,0.0006071687],"genre_scores_gemma":[0.41768065,0.000011881003,0.58205914,0.00014265624,0.000034019635,0.000021487154,0.000022340177,0.000011793753,0.000016038653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985378,0.00016560365,0.00040605973,0.00032289073,0.00029916744,0.0002684783],"domain_scores_gemma":[0.99501246,0.004389942,0.00011468758,0.00022274355,0.000045088374,0.0002150947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007130027,0.00019250653,0.00042412212,0.0001699026,0.000055860866,0.000015132421,0.0001154299,0.00007867494,0.00059382326],"category_scores_gemma":[0.007339366,0.000117921816,0.000007863749,0.00018431907,0.00034766318,0.000026421587,0.000044634533,0.0005470627,0.000001761258],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021899039,0.00021608567,0.017820042,0.00018355496,0.000006690805,0.0005866239,0.00057518494,0.0000015245548,0.00024305121,0.9722591,0.0010524187,0.006836717],"study_design_scores_gemma":[0.0011837059,0.00025468107,0.20072551,0.0007181142,0.00001650044,0.00000620342,0.00014333092,0.014135647,0.000005011275,0.782638,0.000031737945,0.00014154933],"about_ca_topic_score_codex":0.00005594579,"about_ca_topic_score_gemma":0.00032329292,"teacher_disagreement_score":0.3393953,"about_ca_system_score_codex":0.000031760726,"about_ca_system_score_gemma":0.000039718234,"threshold_uncertainty_score":0.8786437},"labels":[],"label_agreement":null},{"id":"W2004618413","doi":"10.1002/sim.1030","title":"A measure of continuity of care based on the multiplicative intensity model","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Healthcare Policy and Management","field":"Economics, Econometrics and Finance","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Heritage Foundation for Medical Research","keywords":"Multiplicative function; Measure (data warehouse); Continuity of care; Covariate; Computer science; Health care; Intensity (physics); Econometrics; Mathematics; Data mining; Machine learning; Economics","score_opus":0.09829028965133782,"score_gpt":0.30572034029172646,"score_spread":0.20743005064038864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2004618413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026380328,0.002130231,0.7643067,0.03284145,0.00042753827,0.0018877005,0.0048487433,0.00002891209,0.16714835],"genre_scores_gemma":[0.9954666,0.00008504661,0.0032642896,0.0010537003,0.00001811317,0.000014583554,0.000008979785,0.0000063028056,0.00008241591],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916995,0.000024705563,0.00047164134,0.00014867453,0.00006325395,0.00012180525],"domain_scores_gemma":[0.9990112,0.00027827278,0.00026497996,0.00029249638,0.00011987497,0.000033137636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005902246,0.00007408921,0.00036062242,0.00012558246,0.000022575596,0.0000012190812,0.00013495557,0.000036262365,0.00011809936],"category_scores_gemma":[0.0014475705,0.000058485868,0.000021016622,0.00014972177,0.00017264741,0.000010417571,0.000021978649,0.0001393325,0.000008428199],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037908183,0.00007694759,0.004850095,0.00020924884,0.000015023221,0.0000017001437,0.007537899,0.0009551861,0.000005122886,0.97869754,0.004423048,0.0031902778],"study_design_scores_gemma":[0.001772588,0.00049992383,0.023749731,0.00031800268,0.00001471695,1.9484133e-7,0.0017727164,0.87810576,0.00010058609,0.090208955,0.0032925596,0.00016428779],"about_ca_topic_score_codex":0.0016611121,"about_ca_topic_score_gemma":0.00042711475,"teacher_disagreement_score":0.9690862,"about_ca_system_score_codex":0.000060514474,"about_ca_system_score_gemma":0.0000091950615,"threshold_uncertainty_score":0.25111157},"labels":[],"label_agreement":null},{"id":"W2005293181","doi":"10.1002/sim.5606","title":"A generalized Jonckheere test against ordered alternatives for repeated measures in randomized blocks","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Null hypothesis; Null (SQL); Mathematics; Statistical hypothesis testing; Statistics; Randomized controlled trial; Applied mathematics; Null distribution; Block (permutation group theory); Computer science; Econometrics; Medicine; Test statistic; Data mining; Internal medicine; Combinatorics","score_opus":0.401823268684664,"score_gpt":0.5537626732144015,"score_spread":0.15193940452973753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005293181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012039201,0.0007511696,0.9768182,0.0009811185,0.0016887501,0.003685409,0.0007999207,0.00010472078,0.0031315007],"genre_scores_gemma":[0.07784748,0.0004874383,0.91919625,0.0004930768,0.00082077994,0.0005576632,0.000048464157,0.000077382894,0.00047147242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9933478,0.0020763217,0.0026458558,0.00046515276,0.00070364756,0.00076121825],"domain_scores_gemma":[0.81567925,0.18272279,0.00058091484,0.00046018665,0.0003180079,0.00023885502],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.018533079,0.0003939257,0.0026731018,0.00033149097,0.000060545422,0.000016880673,0.00033744244,0.00022198229,0.00035605178],"category_scores_gemma":[0.64158,0.00029128577,0.00011800267,0.00043790645,0.0007061819,0.000059802827,0.00007465557,0.000494086,0.0000053882527],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.031991526,0.0018584727,0.008075385,0.00092964986,0.0005039271,0.00013596183,0.0057386695,0.00003716706,0.0020143394,0.86003137,0.036258377,0.052425183],"study_design_scores_gemma":[0.15314813,0.0001842169,0.0004187265,0.0005775633,0.0002072462,0.0000035114126,0.00020933579,0.0047772364,0.0002856428,0.83924735,0.000615615,0.0003254382],"about_ca_topic_score_codex":0.00013022489,"about_ca_topic_score_gemma":0.0001438066,"teacher_disagreement_score":0.62304693,"about_ca_system_score_codex":0.00014566114,"about_ca_system_score_gemma":0.000081150596,"threshold_uncertainty_score":0.9999539},"labels":[],"label_agreement":null},{"id":"W2005628926","doi":"10.1002/sim.4182","title":"Estimation of reliability in a three‐factor model","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Intraclass correlation; Reliability (semiconductor); Statistics; Interval estimation; Point estimation; Confidence interval; Markov chain Monte Carlo; Markov chain; Variance (accounting); Monte Carlo method; Random effects model; Estimation; Econometrics; Computer science; Mathematics; Medicine; Psychometrics; Meta-analysis","score_opus":0.14374485287821784,"score_gpt":0.4220546455536928,"score_spread":0.27830979267547495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005628926","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020133266,0.000012746076,0.97651416,0.000038542632,0.0000764035,0.00021677412,0.00013938316,0.000012783389,0.0028559524],"genre_scores_gemma":[0.38809127,0.0000068144673,0.61185104,0.000014267681,0.0000073921997,0.000009729634,0.0000033914894,0.0000073285532,0.000008794609],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985947,0.000093515366,0.000683842,0.00018994646,0.00025739154,0.00018061415],"domain_scores_gemma":[0.9976226,0.0018072822,0.0001500497,0.00028036593,0.00008323151,0.000056488934],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008634716,0.00011808309,0.00041725443,0.00013267748,0.000011347634,0.0000015649495,0.00013086962,0.00006886981,0.000426434],"category_scores_gemma":[0.010983489,0.000092982336,0.000012012042,0.00021512991,0.0002527514,0.000036879424,0.00002877005,0.00020136291,0.0000024712892],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004864999,0.00014011576,0.005688446,0.00028293987,0.00000335079,0.000013424143,0.0021784503,0.00003377025,0.0000409587,0.9418617,0.00016796803,0.04954023],"study_design_scores_gemma":[0.00036988978,0.00010074631,0.023327889,0.00016607597,0.000010363844,6.590175e-7,0.00004086241,0.27854827,0.00007087308,0.6973021,5.330607e-7,0.00006173553],"about_ca_topic_score_codex":0.00036672235,"about_ca_topic_score_gemma":0.00033595206,"teacher_disagreement_score":0.367958,"about_ca_system_score_codex":0.000050233317,"about_ca_system_score_gemma":0.000055023476,"threshold_uncertainty_score":0.9973474},"labels":[],"label_agreement":null},{"id":"W2006136142","doi":"10.1002/sim.5673","title":"A<i>K</i>‐nearest neighbors survival probability prediction method","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institutes of Health","keywords":"Covariate; Proportional hazards model; Survival analysis; Statistics; Estimator; Nonparametric statistics; Metric (unit); Data set; Mathematics; Similarity (geometry); Computer science; Set (abstract data type); Artificial intelligence","score_opus":0.10052311971365267,"score_gpt":0.4154534579781773,"score_spread":0.3149303382645246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006136142","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039201756,0.000025517284,0.9829286,0.00060261216,0.00070093054,0.00065500516,0.00024317949,0.00007822517,0.010845805],"genre_scores_gemma":[0.03127299,0.00002417522,0.96783537,0.00016813962,0.00022871792,0.00012009939,0.00003387274,0.000028938828,0.0002876896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99732506,0.00057222275,0.0007895878,0.00039035926,0.000534851,0.00038793523],"domain_scores_gemma":[0.9917877,0.0071407226,0.00015395731,0.00042902384,0.00030077947,0.00018786205],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021965485,0.00022121042,0.0005431444,0.00010730909,0.000065868364,0.000021423095,0.00020451359,0.00011040914,0.0033853047],"category_scores_gemma":[0.021213202,0.00016714203,0.000022510356,0.00032846595,0.00030736506,0.00006955069,0.000062007304,0.00040976878,0.000054128526],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020250813,0.000118519594,0.006176223,0.0002121897,0.000016981834,0.000011372088,0.00055285956,0.0000044076337,0.00020946507,0.9333016,0.014100227,0.04527586],"study_design_scores_gemma":[0.0006371801,0.00031478843,0.04584705,0.00011418161,0.000036061454,0.000004476268,0.00024290555,0.015036169,0.000034096567,0.9371386,0.0004443262,0.0001501624],"about_ca_topic_score_codex":0.0008957154,"about_ca_topic_score_gemma":0.00013048993,"teacher_disagreement_score":0.045125697,"about_ca_system_score_codex":0.000097370175,"about_ca_system_score_gemma":0.00005863468,"threshold_uncertainty_score":0.99752575},"labels":[],"label_agreement":null},{"id":"W2007493872","doi":"10.1002/sim.2737","title":"Biased odds ratios from dichotomization of age","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":74,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; Columbia College","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Mental Health","keywords":"Odds; Odds ratio; Statistics; Demography; Medicine; Econometrics; Computer science; Logistic regression; Mathematics","score_opus":0.05253306517601675,"score_gpt":0.3872355764733088,"score_spread":0.33470251129729206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007493872","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004449223,0.00004254776,0.99003834,0.00009985629,0.0001806886,0.00020363837,0.0004791711,0.000022360822,0.0044841915],"genre_scores_gemma":[0.19031882,0.000014921415,0.80912936,0.000059222846,0.00015742744,0.000011562927,0.00019013949,0.00001581374,0.00010272764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984665,0.00016536622,0.0006848212,0.00018536816,0.00033546472,0.00016251067],"domain_scores_gemma":[0.9951679,0.004241405,0.00020620704,0.00023122146,0.00010779259,0.000045449255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047493598,0.0001291712,0.00043431477,0.000117210184,0.000024866706,0.0000068857094,0.00011637881,0.000067072855,0.00090538635],"category_scores_gemma":[0.0051887105,0.00010447455,0.000014356909,0.00024884977,0.00023736389,0.000025624226,0.00001811292,0.00013547775,0.0000043361265],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002912458,0.00009019744,0.0023490502,0.000087107874,0.0000091728025,0.000064941174,0.00025951225,0.0000034567054,0.0021847833,0.97668606,0.009199676,0.009036917],"study_design_scores_gemma":[0.0010568171,0.000094005016,0.018906191,0.0002011099,0.00004672505,7.030186e-7,0.00006169672,0.0041544656,0.0006008411,0.97464466,0.0001295366,0.000103265156],"about_ca_topic_score_codex":0.0011742292,"about_ca_topic_score_gemma":0.00046989066,"teacher_disagreement_score":0.1858696,"about_ca_system_score_codex":0.000031672047,"about_ca_system_score_gemma":0.00003368377,"threshold_uncertainty_score":0.99133456},"labels":[],"label_agreement":null},{"id":"W2011410147","doi":"10.1002/sim.6356","title":"A model for time to fracture with a shock stream superimposed on progressive degradation: the Study of Osteoporotic Fractures","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bone health and osteoporosis research","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Ottawa Hospital","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute on Aging; University of Maryland","keywords":"Hip fracture; Fracture (geology); Event (particle physics); Shock (circulatory); Computer science; Econometrics; Perspective (graphical); Statistics; Medicine; Osteoporosis; Mathematics; Artificial intelligence; Engineering; Internal medicine","score_opus":0.027479904661868674,"score_gpt":0.3744236494380615,"score_spread":0.34694374477619283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011410147","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9435462,0.00015434653,0.030432574,0.014421356,0.000064256084,0.010453083,0.00019622961,0.000033681765,0.00069832196],"genre_scores_gemma":[0.9862856,0.0000038916205,0.0091714095,0.0030843068,0.00014509776,0.0003803687,0.00015730652,0.000035177927,0.00073681585],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794966,0.00010672996,0.00046443776,0.00031558887,0.0008128635,0.00035074825],"domain_scores_gemma":[0.99768937,0.0010539838,0.0001359914,0.00047431677,0.0004013929,0.00024494328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006803942,0.00020043654,0.0005633432,0.00018987575,0.00010005356,0.000008167856,0.00015270711,0.00007522024,0.00018715968],"category_scores_gemma":[0.0016722599,0.00010271117,0.00001794952,0.00029002706,0.0001514947,0.00002166907,0.000023444136,0.00037955234,0.00000835709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07476513,0.016530585,0.059873916,0.0064605633,0.0010003228,0.0005157672,0.1297601,0.033240363,0.0045952434,0.0044740112,0.3453863,0.3233977],"study_design_scores_gemma":[0.049299322,0.1538455,0.2562922,0.0028648465,0.0008070925,0.000074262556,0.014603362,0.51213694,0.0007551992,0.0027262298,0.005832131,0.0007629154],"about_ca_topic_score_codex":0.00012113247,"about_ca_topic_score_gemma":0.00030583295,"teacher_disagreement_score":0.4788966,"about_ca_system_score_codex":0.00006303197,"about_ca_system_score_gemma":0.00026756377,"threshold_uncertainty_score":0.418844},"labels":[],"label_agreement":null},{"id":"W2011513835","doi":"10.1002/sim.5436","title":"Misspecification of Cox regression models with composite endpoints","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Econometrics; Estimator; Copula (linguistics); Censoring (clinical trials); Proportional hazards model; Multivariate statistics; Statistics; Context (archaeology); Regression; Mathematics","score_opus":0.530858385765817,"score_gpt":0.5711734862838657,"score_spread":0.04031510051804865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011513835","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045154816,0.00015213258,0.9876018,0.00023465086,0.00037670313,0.00037802075,0.00016020265,0.00002756399,0.006553455],"genre_scores_gemma":[0.20723338,0.000088726745,0.79224074,0.00006149019,0.00020434096,0.000014332645,0.000013724354,0.000026860416,0.000116409465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972573,0.0005369225,0.0010559361,0.00021675424,0.000629615,0.00030347361],"domain_scores_gemma":[0.97418743,0.024527626,0.0004717991,0.00044371298,0.00019912631,0.00017031771],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032145209,0.00018061214,0.00074545166,0.00012355353,0.00003161884,0.0000033246472,0.00018394312,0.00010201538,0.000378092],"category_scores_gemma":[0.020838123,0.00011789231,0.000019871844,0.00025949886,0.00045741737,0.00006683611,0.000039975286,0.0002809446,0.0000073831634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004045195,0.00034999265,0.0023391321,0.0003269452,0.000035513134,0.000013346134,0.0012188093,0.0000133735075,0.0013613979,0.97646743,0.0069710165,0.010498521],"study_design_scores_gemma":[0.0017955818,0.00026540467,0.0031855267,0.000838709,0.000102209524,0.000008341745,0.00020970691,0.0018798603,0.0013300934,0.99009055,0.000146489,0.0001475006],"about_ca_topic_score_codex":0.000020457092,"about_ca_topic_score_gemma":0.000005571487,"teacher_disagreement_score":0.2027179,"about_ca_system_score_codex":0.000053958298,"about_ca_system_score_gemma":0.000026571028,"threshold_uncertainty_score":0.9874098},"labels":[],"label_agreement":null},{"id":"W2012127814","doi":"10.1002/1097-0258(20001030)19:20<2775::aid-sim545>3.0.co;2-g","title":"Numerical methods for the evaluation of individual bioequivalence criteria","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SNC-Lavalin (Canada)","funders":"","keywords":"Restricted maximum likelihood; Resampling; Fortran; Variance (accounting); Statistics; Mathematics; Bioequivalence; Computer science; Covariate; Mixed model; Maximum likelihood; Algorithm; Applied mathematics","score_opus":0.7410054186035245,"score_gpt":0.7031661636645462,"score_spread":0.03783925493897833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012127814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00042085836,0.00031474073,0.99490213,0.00085633434,0.00071696687,0.0011580836,0.0003905081,0.000018066941,0.0012223044],"genre_scores_gemma":[0.01260198,0.00013023522,0.9863942,0.00024391632,0.00032800387,0.00018648659,0.000010975578,0.00002580794,0.00007837873],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9942953,0.00269244,0.0013942161,0.00031447728,0.0010119822,0.00029160045],"domain_scores_gemma":[0.8424781,0.1563723,0.00025589985,0.0004407403,0.00038239136,0.000070587965],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.034812354,0.00016944473,0.0007063858,0.00007762773,0.00006215399,0.000010407845,0.00046880732,0.000110434456,0.006999695],"category_scores_gemma":[0.28470063,0.00010697394,0.000049416718,0.00034520729,0.00064965605,0.000026716683,0.000035138193,0.00025174208,0.000005118223],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013996588,0.00009728367,0.000037265105,0.00014666893,0.000059756912,0.0000011011632,0.000592345,0.000020815916,0.00009708463,0.13755228,0.009634491,0.851621],"study_design_scores_gemma":[0.0020075322,0.00036898078,0.0021725236,0.00014370661,0.00064430246,0.0000025410905,0.00013246581,0.042574283,0.00020159301,0.95071757,0.00092365785,0.000110867695],"about_ca_topic_score_codex":0.000027703798,"about_ca_topic_score_gemma":0.0000035709738,"teacher_disagreement_score":0.85151005,"about_ca_system_score_codex":0.000048360667,"about_ca_system_score_gemma":0.00009661407,"threshold_uncertainty_score":0.99390805},"labels":[],"label_agreement":null},{"id":"W2013186997","doi":"10.1002/sim.1777","title":"Non‐parametric estimation of gap time survival functions for ordered multivariate failure time data","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; McMaster University","keywords":"Censoring (clinical trials); Estimator; Identifiability; Parametric statistics; Multivariate statistics; Statistics; Mathematics; Nonparametric statistics; Bivariate analysis; Applied mathematics","score_opus":0.13900848002663804,"score_gpt":0.4338596289471855,"score_spread":0.2948511489205474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013186997","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001162477,0.000021698137,0.9939779,0.00037546875,0.00023115499,0.00059561315,0.0028725786,0.000030530216,0.00073256175],"genre_scores_gemma":[0.039487243,0.0000081483995,0.95903575,0.000030352849,0.00009440955,0.000028822906,0.00088842807,0.000030753858,0.00039610104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99815655,0.000090351125,0.00075520464,0.00034576183,0.00038241874,0.00026973733],"domain_scores_gemma":[0.9922919,0.0064213495,0.0002761181,0.00064110715,0.00027485393,0.000094644616],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014665431,0.00019062337,0.0006098509,0.0002006539,0.00006222672,0.0000103977745,0.00032755182,0.00009994069,0.000503707],"category_scores_gemma":[0.03337645,0.00015777073,0.000019331677,0.0005879789,0.0002184029,0.000068246125,0.00009187055,0.00019545208,0.000051988736],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026488642,0.0007732492,0.000103479324,0.0011484526,0.00018488112,0.000023585684,0.0010074866,0.0016746444,0.004380322,0.9129697,0.032368477,0.045100804],"study_design_scores_gemma":[0.0027007891,0.0004269971,0.0008962961,0.00026798426,0.00016390742,0.000003081946,0.00011553689,0.3179006,0.00006866135,0.6771089,0.00017417208,0.00017310362],"about_ca_topic_score_codex":0.00025044635,"about_ca_topic_score_gemma":0.000046492853,"teacher_disagreement_score":0.31622595,"about_ca_system_score_codex":0.000074655014,"about_ca_system_score_gemma":0.00012784643,"threshold_uncertainty_score":0.97476584},"labels":[],"label_agreement":null},{"id":"W2013245256","doi":"10.1002/sim.3764","title":"A weighted Cox model for modelling time‐dependent exposures in the analysis of case–control studies","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"Canadian Institutes of Health Research; Health Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; McGill University","keywords":"Proportional hazards model; Computer science; Econometrics; Statistics; Mathematics","score_opus":0.14315108448926323,"score_gpt":0.4545637737110838,"score_spread":0.3114126892218206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013245256","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035001937,0.0001594189,0.96354365,0.000120534074,0.00003739513,0.0006075918,0.00039167333,0.000026925349,0.00011084135],"genre_scores_gemma":[0.61930096,0.000053643525,0.3803869,0.000046883382,0.000023145047,0.000114428956,0.00001718797,0.000011771878,0.000045069737],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984654,0.000094990195,0.00071051525,0.00019837593,0.000317538,0.00021314014],"domain_scores_gemma":[0.9932083,0.005870746,0.00024434263,0.0003785898,0.00026969577,0.000028359795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020510445,0.00016138592,0.0007176003,0.00039787692,0.00004113197,0.000004371869,0.00019976062,0.00007578805,0.000025172918],"category_scores_gemma":[0.0021338623,0.00010365402,0.0000389925,0.00039935327,0.00022651536,0.000039268405,0.000022655324,0.0003103905,2.7511703e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022108006,0.00036733525,0.00061325356,0.0005117057,0.0015516147,0.00048462293,0.034106843,0.08013266,0.00505751,0.8714249,0.002105624,0.0034228582],"study_design_scores_gemma":[0.00043382746,0.00006550817,0.000007789007,0.0000421697,0.00061247393,0.0000067648507,0.00095185195,0.55765045,0.00009070187,0.4400775,0.0000017167464,0.000059252612],"about_ca_topic_score_codex":0.00008278547,"about_ca_topic_score_gemma":0.0021590535,"teacher_disagreement_score":0.584299,"about_ca_system_score_codex":0.00003758319,"about_ca_system_score_gemma":0.000029915978,"threshold_uncertainty_score":0.42268884},"labels":[],"label_agreement":null},{"id":"W2013920814","doi":"10.1002/sim.4200","title":"Comparing paired vs non‐paired statistical methods of analyses when making inferences about absolute risk reductions in propensity‐score matched samples","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":325,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Statistics; Confidence interval; Confounding; Sample size determination; Selection bias; Observational study; Statistical significance; Statistical inference; Matching (statistics); Causal inference; Medicine; Mathematics","score_opus":0.6053372113795614,"score_gpt":0.5275261212026646,"score_spread":0.0778110901768968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013920814","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08581615,0.00010420826,0.9114445,0.000042413696,0.00015527585,0.0005861518,0.0001259834,0.00011683779,0.0016084836],"genre_scores_gemma":[0.46800825,0.00009729292,0.53173524,0.000016605589,0.000022380967,0.00004679545,0.000027806385,0.000024464181,0.000021185142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99641496,0.0006600106,0.001585777,0.00046752457,0.0004049093,0.00046682527],"domain_scores_gemma":[0.9953412,0.0029471603,0.0007358047,0.0005739904,0.0003085739,0.00009331571],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002377219,0.00034803335,0.0014254736,0.0006387852,0.00008582623,0.000014965807,0.0003881759,0.00014946693,0.00034684464],"category_scores_gemma":[0.009036527,0.00029271893,0.000038211205,0.0005980207,0.00096417224,0.00013995654,0.00017575081,0.00063786015,0.0000022637637],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005824228,0.0007308396,0.31245413,0.0014685509,0.000359229,0.00017041237,0.027554257,0.00010960089,0.006081633,0.61489916,0.003428724,0.032161053],"study_design_scores_gemma":[0.0005951396,0.00024546165,0.23654388,0.0012500089,0.00019832262,0.0000057135067,0.0015930324,0.004142211,0.0018935741,0.7532755,0.000015680382,0.00024148115],"about_ca_topic_score_codex":0.003637289,"about_ca_topic_score_gemma":0.0041072345,"teacher_disagreement_score":0.38219208,"about_ca_system_score_codex":0.00016392721,"about_ca_system_score_gemma":0.00013608554,"threshold_uncertainty_score":0.9999525},"labels":[],"label_agreement":null},{"id":"W2014084548","doi":"10.1002/sim.2523","title":"Predicting case numbers during infectious disease outbreaks when some cases are undiagnosed","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Outbreak; Infectious disease (medical specialty); Markov chain Monte Carlo; Basic reproduction number; Bayesian probability; Markov chain; Statistics; Disease; Computer science; Medicine; Mathematics; Virology; Environmental health; Pathology","score_opus":0.09159471013788364,"score_gpt":0.39795735505440083,"score_spread":0.3063626449165172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014084548","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9872575,0.0007020236,0.007859859,0.0016045362,0.0004412461,0.00062260014,0.00050183036,0.0002880948,0.0007223238],"genre_scores_gemma":[0.9934631,0.0001232648,0.0047667744,0.00046478747,0.0007457787,0.00009035683,0.00003736841,0.00003962183,0.00026896584],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976195,0.0002241712,0.0008476265,0.00044031258,0.0003620342,0.0005063429],"domain_scores_gemma":[0.98702097,0.011993081,0.00035806576,0.00034409208,0.00008945139,0.0001943153],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00074377534,0.00030290242,0.0006926901,0.00012408603,0.00026180226,0.000013963995,0.00012593048,0.00008669905,0.00018795629],"category_scores_gemma":[0.04169378,0.00024118398,0.000045966866,0.00019191607,0.00035680443,0.000070317525,0.00014440808,0.00036630503,0.0000112990765],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060545794,0.00021831735,0.9004285,0.0008104937,0.000050686365,0.04094511,0.0006006191,0.00025540302,0.00000951064,0.03532393,0.021016097,0.00028083878],"study_design_scores_gemma":[0.0023811585,0.00013966778,0.270284,0.0006290189,0.0002304097,0.00046888326,0.0010718104,0.0010987627,0.0000057112075,0.72291297,0.00039693338,0.00038064347],"about_ca_topic_score_codex":0.008363792,"about_ca_topic_score_gemma":0.012539907,"teacher_disagreement_score":0.68758905,"about_ca_system_score_codex":0.0003521458,"about_ca_system_score_gemma":0.000033720007,"threshold_uncertainty_score":0.9982396},"labels":[],"label_agreement":null},{"id":"W2014423310","doi":"10.1002/sim.5569","title":"On the interchangeability of biologic drug products","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Biosimilars and Bioanalytical Methods","field":"Immunology and Microbiology","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"","keywords":"Interchangeability; Bioequivalence; Drug; Risk analysis (engineering); Biosimilar; Tilmicosin; Medicine; Equivalence (formal languages); Pharmacology; Computer science; Mathematics; Chemistry; Pharmacokinetics","score_opus":0.06153093761929549,"score_gpt":0.3525918014453326,"score_spread":0.2910608638260371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014423310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.916323,0.009970704,0.010761071,0.04144058,0.0067320615,0.0014176762,0.00060099136,0.00005770966,0.012696181],"genre_scores_gemma":[0.9960617,0.000068994304,0.002546742,0.0007716276,0.000056748082,0.00000682694,0.000017326527,0.000003655133,0.00046640623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9989577,0.00043398576,0.00024350145,0.00011981185,0.00003254873,0.00021247579],"domain_scores_gemma":[0.9978645,0.0017677605,0.000069665206,0.00022920509,0.00005525791,0.000013636844],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001963177,0.00008494389,0.00022792016,0.00004726886,0.000027223905,5.975754e-7,0.00013874249,0.00007193337,0.0012850767],"category_scores_gemma":[0.00450298,0.00003942324,0.000012805708,0.00015082415,0.00084515975,0.000008955562,0.000044347787,0.00027173304,0.000024361716],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000305597,0.00063500553,0.049480923,0.0001584504,0.000114951,0.0000028220593,0.0028531405,2.467433e-7,0.0706361,0.68652594,0.16000395,0.0292829],"study_design_scores_gemma":[0.002990299,0.002810057,0.5509533,0.0005923295,0.00024994023,0.000029989164,0.003078138,0.000029265157,0.1475122,0.20836276,0.08280278,0.0005889315],"about_ca_topic_score_codex":0.000061362785,"about_ca_topic_score_gemma":0.000028349772,"teacher_disagreement_score":0.5014724,"about_ca_system_score_codex":0.000017647566,"about_ca_system_score_gemma":0.000009972572,"threshold_uncertainty_score":0.9996279},"labels":[],"label_agreement":null},{"id":"W2014828742","doi":"10.1002/sim.1720","title":"Two macroscopic and microscopic brain imaging studies of human hippocampus in early Alzheimer's disease and schizophrenia research","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Smiths Detection (Canada)","funders":"National Institute of Neurological Disorders and Stroke; National Institute of Mental Health; National Institutes of Health","keywords":"Neuroscience; Schizophrenia (object-oriented programming); Hippocampal formation; Hippocampus; Human brain; Functional magnetic resonance imaging; Disease; Brain Structure and Function; Psychology; Alzheimer's disease; Neuroimaging; Medicine; Psychiatry; Pathology","score_opus":0.08440019450687297,"score_gpt":0.42488422864518777,"score_spread":0.3404840341383148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014828742","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9854364,0.007161508,0.00010964839,0.00660678,0.00018494784,0.00035261436,0.00006193188,0.000013723387,0.00007248577],"genre_scores_gemma":[0.9973543,0.00044738094,0.0014324252,0.0006314319,0.000065089145,0.00003022,0.0000025113595,0.000016515884,0.00002009085],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980773,0.00026652595,0.00035923746,0.00051508425,0.0004426543,0.00033924344],"domain_scores_gemma":[0.9932691,0.006258686,0.00007387454,0.00019591853,0.00010293228,0.00009951972],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010239163,0.00015998472,0.00036888395,0.0004258793,0.00021602905,0.000017631051,0.0001199076,0.000019995725,0.0000049194664],"category_scores_gemma":[0.01679508,0.00014477907,0.000007601718,0.00045609768,0.0025150094,0.00009255856,0.00023270026,0.00036123255,0.000001531165],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057066546,0.00030694416,0.50085634,0.0008200578,0.00007903291,0.001220299,0.016138049,0.00005868311,0.2907857,0.1770221,0.002491153,0.00965097],"study_design_scores_gemma":[0.006661102,0.0005337976,0.46291313,0.0011567835,0.000037968348,0.000011070813,0.0015526357,0.00007677245,0.0044006705,0.5224192,0.000026094018,0.00021074782],"about_ca_topic_score_codex":0.0007405208,"about_ca_topic_score_gemma":0.0012438154,"teacher_disagreement_score":0.34539714,"about_ca_system_score_codex":0.000083764775,"about_ca_system_score_gemma":0.00007573373,"threshold_uncertainty_score":0.99148685},"labels":[],"label_agreement":null},{"id":"W2016649643","doi":"10.1002/sim.5581","title":"Regression with incomplete covariates and left‐truncated time‐to‐event data","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Statistics; Truncation (statistics); Proportional hazards model; Econometrics; Censoring (clinical trials); Medicine; Survival analysis; Event (particle physics); Clinical trial; Mathematics; Internal medicine","score_opus":0.12745610875890212,"score_gpt":0.4359655878327633,"score_spread":0.30850947907386117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016649643","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031736959,0.00016443798,0.99370575,0.0006408057,0.00012992602,0.00030451824,0.00054227235,0.000032663822,0.0013059052],"genre_scores_gemma":[0.07583197,0.000029965211,0.92318285,0.00027835375,0.00014275704,0.0000057676903,0.00015898985,0.000026806143,0.00034255415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99847734,0.00017816578,0.00039485094,0.00027020054,0.00034602452,0.00033341636],"domain_scores_gemma":[0.995929,0.0030978166,0.000115589464,0.000533408,0.000082512066,0.00024169253],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015324274,0.00018037726,0.0004221875,0.00009687184,0.000058114565,0.000010975369,0.00023279677,0.00004964821,0.0012937387],"category_scores_gemma":[0.0077261575,0.000111173635,0.0000035628364,0.00016845987,0.00020110839,0.00006292426,0.00022369476,0.00019903867,0.000034062097],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002810743,0.00029133202,0.0112835225,0.0005008386,0.00008257254,0.00007218167,0.0035286967,0.0000025556476,0.0013941646,0.7954316,0.105481975,0.08164949],"study_design_scores_gemma":[0.0031318592,0.0013185329,0.0606754,0.0023711736,0.0002952966,0.00010610524,0.0004703878,0.04764609,0.00014702899,0.8733899,0.009684653,0.0007635761],"about_ca_topic_score_codex":0.00007737482,"about_ca_topic_score_gemma":0.000029185816,"teacher_disagreement_score":0.09579732,"about_ca_system_score_codex":0.00003105016,"about_ca_system_score_gemma":0.000030027564,"threshold_uncertainty_score":0.9996192},"labels":[],"label_agreement":null},{"id":"W2016919144","doi":"10.1002/sim.2711","title":"Bayesian sensitivity analysis for unmeasured confounding in observational studies","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":184,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Confounding; Statistics; Markov chain Monte Carlo; Bayesian probability; Observational study; Econometrics; Logistic regression; Prior probability; Sample size determination; Sensitivity (control systems); Mathematics; Computer science","score_opus":0.2203225194206481,"score_gpt":0.47620137534415125,"score_spread":0.2558788559235031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016919144","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024742503,0.00008674066,0.9955192,0.00052258075,0.00018292991,0.00031799971,0.00031839704,0.000020047195,0.00055784726],"genre_scores_gemma":[0.3052233,0.000013119526,0.6943384,0.00008847916,0.00013010217,0.0000382837,0.000082087005,0.000011728392,0.00007450845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99797475,0.000286481,0.00075904216,0.00029801112,0.00037534253,0.00030635964],"domain_scores_gemma":[0.98395,0.01535692,0.00017676533,0.0001837016,0.00028516923,0.000047413425],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0029453596,0.00017683323,0.0008009552,0.00036287852,0.00006371525,0.000011712958,0.00007116511,0.00006606093,0.000067379464],"category_scores_gemma":[0.018057633,0.0001502257,0.00003818837,0.00082771847,0.0002536201,0.00003833509,0.000021523767,0.00016788692,8.42037e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003397561,0.00006637172,0.05800291,0.00018333529,0.00011404387,0.000059783968,0.0003161396,0.000075465796,0.00012500782,0.93625164,0.002197913,0.0025734066],"study_design_scores_gemma":[0.0008069526,0.000056783127,0.12075936,0.00013816546,0.00023241046,0.0000016632472,0.00030504243,0.032794774,0.000018236795,0.84468216,0.000063868014,0.00014057552],"about_ca_topic_score_codex":0.00036651365,"about_ca_topic_score_gemma":0.0058852825,"teacher_disagreement_score":0.30274904,"about_ca_system_score_codex":0.00016111675,"about_ca_system_score_gemma":0.00005240186,"threshold_uncertainty_score":0.9902137},"labels":[],"label_agreement":null},{"id":"W2017135200","doi":"10.1002/sim.5637","title":"Empirical likelihood‐based confidence intervals for length‐biased data","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"National Cancer Institute","keywords":"Statistics; Confidence interval; Event (particle physics); Poisson distribution; Econometrics; Population; Sampling bias; Sample size determination; Survival analysis; Sample (material); Margin (machine learning); Simple random sample; Mathematics; Computer science; Demography","score_opus":0.38984294806424596,"score_gpt":0.5328989883676382,"score_spread":0.1430560403033922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017135200","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008928865,0.00018667351,0.9939429,0.0010588906,0.0007130181,0.0004932154,0.0015787898,0.00004352276,0.0010900742],"genre_scores_gemma":[0.14532922,0.00002060035,0.85252476,0.0012786785,0.0004362896,0.00005746856,0.00023976176,0.0000336292,0.00007958287],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99755454,0.00027544997,0.00078125176,0.0003650369,0.00042212443,0.0006016072],"domain_scores_gemma":[0.98000395,0.018506441,0.0001858481,0.0008494443,0.00018333904,0.00027100276],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035950104,0.00022577173,0.0005964038,0.00011031646,0.000058606274,0.000014702568,0.0005583896,0.000103022176,0.0008793095],"category_scores_gemma":[0.054399047,0.0001747837,0.000022355405,0.00018827789,0.00032050267,0.000085951215,0.00012792616,0.00029330197,0.000019646739],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014030091,0.00040234384,0.005178461,0.0006721683,0.000039262763,0.000018500657,0.0013185885,6.079561e-7,0.00022959406,0.7386398,0.20933527,0.04402511],"study_design_scores_gemma":[0.0022988021,0.0005131184,0.005299248,0.00056812,0.00016818596,0.0000061798887,0.0004652394,0.040159777,0.00019543547,0.9413449,0.008625901,0.00035508067],"about_ca_topic_score_codex":0.000070473696,"about_ca_topic_score_gemma":0.00004809662,"teacher_disagreement_score":0.20270512,"about_ca_system_score_codex":0.000057424648,"about_ca_system_score_gemma":0.00010541539,"threshold_uncertainty_score":0.96278226},"labels":[],"label_agreement":null},{"id":"W2017258397","doi":"10.1002/sim.2895","title":"Tests of association under misclassification: Application to histological sampling in oncology","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Cancer Institute","keywords":"Feature (linguistics); Medicine; Oligodendroglioma; Outcome (game theory); Association (psychology); Sampling (signal processing); Radiology; Pathology; Computer science; Psychology; Glioma; Mathematics; Astrocytoma","score_opus":0.0552569513599816,"score_gpt":0.3907814980580758,"score_spread":0.33552454669809423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017258397","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044099577,0.0000486043,0.98953944,0.0035340644,0.00036916987,0.00020756244,0.0000028563222,0.000024263461,0.0018640785],"genre_scores_gemma":[0.7727816,0.000016160882,0.22665147,0.00039864928,0.000079182515,0.000021449088,0.0000067969904,0.0000038663125,0.000040829054],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987086,0.00006270175,0.0004899198,0.00024879907,0.00030598347,0.00018401728],"domain_scores_gemma":[0.99806994,0.0012693309,0.00024348915,0.00022373973,0.00014187073,0.000051633855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018243998,0.00006861143,0.00019747719,0.00026003603,0.000021967888,0.0000034734824,0.00024967457,0.00010522752,0.000010827517],"category_scores_gemma":[0.0010749236,0.00006657263,0.000006744054,0.0007377552,0.00004727037,0.000045997425,0.00003319079,0.0001813794,0.000007803386],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000560545,0.00018704013,0.04256163,0.00004383081,0.000009491265,0.000013361512,0.0028541044,0.0022823017,0.017755073,0.31175005,0.0028216983,0.6196653],"study_design_scores_gemma":[0.0008420759,0.0004733129,0.90078086,0.000061685285,0.000007400507,0.0000058994433,0.0002901273,0.011688714,0.0004885236,0.07659684,0.00862544,0.00013912785],"about_ca_topic_score_codex":0.00019252348,"about_ca_topic_score_gemma":0.0020101364,"teacher_disagreement_score":0.8582192,"about_ca_system_score_codex":0.0016342979,"about_ca_system_score_gemma":0.00007663128,"threshold_uncertainty_score":0.42736322},"labels":[],"label_agreement":null},{"id":"W2017498225","doi":"10.1002/sim.5791","title":"A comparison of Bayesian hierarchical modeling with group‐based exposure assessment in occupational epidemiology","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Occupational and environmental lung diseases","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Environmental Health Sciences","keywords":"Bayesian probability; Logistic regression; Computer science; Epidemiology; Bayesian hierarchical modeling; Hierarchical database model; Cohort; Statistics; Bayesian inference; Data mining; Econometrics; Medicine; Machine learning; Artificial intelligence; Mathematics; Pathology","score_opus":0.052482689336623825,"score_gpt":0.40254146372720645,"score_spread":0.35005877439058264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017498225","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4911474,0.00015986885,0.5059558,0.0016589344,0.000042908403,0.00043995483,0.00007262572,0.000009252127,0.00051325565],"genre_scores_gemma":[0.86867166,0.000009815086,0.12997587,0.00050211226,0.00005125075,0.00005985768,0.00070849835,0.000010158188,0.000010762843],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998471,0.00012168808,0.0006465713,0.00021422245,0.00035031416,0.00019618255],"domain_scores_gemma":[0.99884474,0.0007285055,0.00011008819,0.00014320225,0.000044364093,0.00012907678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000324919,0.00012771448,0.0005319185,0.0001803376,0.000019505575,0.0000011506049,0.000054863343,0.000058439255,0.0007461272],"category_scores_gemma":[0.00032110597,0.00009034351,0.00001760925,0.00014394737,0.00025626735,0.000031519794,0.000015851587,0.00027800017,0.000004521547],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003955067,0.0005255925,0.97451645,0.00014083959,0.000015832631,0.000016977947,0.00008581964,0.011069414,0.00012614985,0.010951129,0.00036050234,0.0017957825],"study_design_scores_gemma":[0.0017392664,0.00081247865,0.61817986,0.00023319645,0.000024322651,0.0000020967436,0.00013665324,0.3747771,0.0000020850962,0.0040328437,0.0000074542986,0.00005263173],"about_ca_topic_score_codex":0.0005729158,"about_ca_topic_score_gemma":0.00017760656,"teacher_disagreement_score":0.37752426,"about_ca_system_score_codex":0.00011268755,"about_ca_system_score_gemma":0.00010295903,"threshold_uncertainty_score":0.816957},"labels":[],"label_agreement":null},{"id":"W2020884741","doi":"10.1002/sim.4193","title":"Regression models, scan statistics and reappearance probabilities to detect regions of association between gene expression and copy number","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research; University Health Network","keywords":"Covariate; Statistic; Statistics; Breast cancer; Regression; Chromosome; Regression analysis; Biology; Mathematics; Cancer; Genetics; Gene","score_opus":0.030693225007564433,"score_gpt":0.3028105837693933,"score_spread":0.27211735876182885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2020884741","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38013434,0.000865954,0.61635935,0.00022248618,0.00015706463,0.000485403,0.0004918179,0.000012459558,0.0012711391],"genre_scores_gemma":[0.8795732,0.0013359934,0.11836183,0.000059930433,0.00007838064,0.000031124757,0.00012900795,0.000015540705,0.00041495182],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99892163,0.00010105257,0.00032119508,0.00029350698,0.00020815402,0.00015448572],"domain_scores_gemma":[0.99925965,0.000058859943,0.00019084862,0.00022800837,0.00015829546,0.00010435095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033780493,0.00012413548,0.00021826019,0.000062847124,0.000050474537,0.0000045423985,0.0000794187,0.00011509012,0.000017875165],"category_scores_gemma":[0.0004138093,0.000103234685,0.000007984345,0.000093893505,0.00012776138,0.0000058722385,0.00006680218,0.00008946202,6.141701e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060145237,0.00008494174,0.21871759,0.00043142465,0.000069084264,0.000005793973,0.005469991,0.000037579808,0.6772757,0.00993634,0.058018252,0.02935182],"study_design_scores_gemma":[0.0045040715,0.0018816296,0.278634,0.0017571029,0.00018401913,0.000014730745,0.0020758912,0.0006602958,0.5443396,0.15850343,0.006574915,0.0008702654],"about_ca_topic_score_codex":0.00010443717,"about_ca_topic_score_gemma":0.000067056586,"teacher_disagreement_score":0.4994389,"about_ca_system_score_codex":0.000030809504,"about_ca_system_score_gemma":0.000043314878,"threshold_uncertainty_score":0.4209788},"labels":[],"label_agreement":null},{"id":"W2021071948","doi":"10.1002/sim.1473","title":"Bias correction of two‐state latent Markov process parameter estimates under misclassification","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Alberta","funders":"","keywords":"Estimator; Unobservable; Statistics; Mathematics; Computer science; Maximum likelihood; Econometrics","score_opus":0.16662811501022856,"score_gpt":0.4631804032302823,"score_spread":0.29655228822005375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021071948","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024541786,0.00012649098,0.97131276,0.00013326971,0.0013974179,0.00022896448,0.00004795925,0.000024944595,0.0021864274],"genre_scores_gemma":[0.9046702,0.000028897786,0.09443282,0.000054425796,0.00003783763,0.000023374034,0.0000161159,0.00001951896,0.00071681436],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99641305,0.00022092837,0.001202657,0.0004923122,0.0013608332,0.00031023377],"domain_scores_gemma":[0.9876692,0.010594767,0.0005282213,0.00037054074,0.00070933736,0.00012792926],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002238481,0.00019619372,0.0004764101,0.00033689683,0.000076187716,0.00003127013,0.00028442175,0.000052357966,0.00030399504],"category_scores_gemma":[0.05786743,0.00014411013,0.000020520081,0.000978938,0.0004435278,0.00015675907,0.000023510007,0.00026828353,0.000026431615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045975082,0.0006677348,0.2598992,0.00043451638,0.000081321276,0.00012997852,0.00660377,0.10553062,0.004812735,0.1905619,0.010128533,0.4206899],"study_design_scores_gemma":[0.00095384725,0.0001700887,0.023043122,0.00014109942,0.000025467107,0.000008281732,0.0011597307,0.078499585,0.0028675892,0.8927914,0.00016096847,0.00017885256],"about_ca_topic_score_codex":0.00005099528,"about_ca_topic_score_gemma":0.000062204235,"teacher_disagreement_score":0.8801284,"about_ca_system_score_codex":0.000096707816,"about_ca_system_score_gemma":0.00008991058,"threshold_uncertainty_score":0.95006853},"labels":[],"label_agreement":null},{"id":"W2021281962","doi":"10.1002/sim.6455","title":"Estimating survival probabilities by exposure levels: utilizing vital statistics and complex survey data with mortality follow‐up","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Statistics; Estimator; Jackknife resampling; Categorical variable; Survey sampling; Variance (accounting); Econometrics; Hazard ratio; Hazard; Survey data collection; Mathematics; Computer science; Medicine; Population; Confidence interval; Economics","score_opus":0.3310131340846792,"score_gpt":0.46000764865395993,"score_spread":0.12899451456928074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021281962","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26663092,0.0018746639,0.6599745,0.0044382955,0.005952931,0.0022736604,0.04924727,0.0002223762,0.00938535],"genre_scores_gemma":[0.8682783,0.00008408514,0.12779534,0.0005712234,0.0002890166,0.000013939433,0.0024409308,0.00003057525,0.0004965672],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99674004,0.0007466549,0.000574579,0.0004022326,0.0009695522,0.0005669214],"domain_scores_gemma":[0.9959207,0.0028009804,0.00017269576,0.00039270663,0.0003141131,0.00039880635],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0063483724,0.00019351307,0.00052410114,0.00004974815,0.0003126771,0.00007111479,0.00035664585,0.00007680041,0.000099763376],"category_scores_gemma":[0.012852452,0.00015908972,0.000005175923,0.00022516135,0.001143074,0.00019928512,0.00014232121,0.00024869526,0.0000016496135],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054261338,0.000041669984,0.8613684,0.00036436532,0.000032248205,0.00003178827,0.01808787,0.000011616686,5.723983e-7,0.04521217,0.07020323,0.004591781],"study_design_scores_gemma":[0.00320618,0.00036260742,0.88839614,0.00033632206,0.00007084974,0.0000033102542,0.068465315,0.008838132,3.1592035e-7,0.02285623,0.006977761,0.00048684643],"about_ca_topic_score_codex":0.09315734,"about_ca_topic_score_gemma":0.22553395,"teacher_disagreement_score":0.6016474,"about_ca_system_score_codex":0.00013993577,"about_ca_system_score_gemma":0.000653879,"threshold_uncertainty_score":0.9954627},"labels":[],"label_agreement":null},{"id":"W2023282380","doi":"10.1002/sim.2968","title":"A comparison of bootstrap methods and an adjusted bootstrap approach for estimating the prediction error in microarray classification","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Bootstrap aggregating; Computer science; Statistics; Sample size determination; Set (abstract data type); Sample (material); Data mining; Mathematics","score_opus":0.12683376374931365,"score_gpt":0.46886889527667613,"score_spread":0.3420351315273625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023282380","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08492563,0.00037802468,0.91375285,0.000099587196,0.00013477408,0.00039991277,0.000037332848,0.0000045546867,0.0002673284],"genre_scores_gemma":[0.6622813,0.000019426872,0.33713236,0.000034008623,0.00010441744,0.000038986655,0.00035720298,0.0000085144275,0.000023782857],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988416,0.00012764843,0.0004972114,0.0002691354,0.00011620502,0.00014819491],"domain_scores_gemma":[0.99932283,0.00010280855,0.00020963307,0.00022809858,0.000089356676,0.000047276848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014491385,0.00010004088,0.00018389372,0.00010258784,0.000046200315,0.0000050077047,0.00010882522,0.00011019139,0.0000033247557],"category_scores_gemma":[0.00038107517,0.000076106255,0.000012075015,0.00014876194,0.00019017898,0.0000040192635,0.000014420342,0.00011921818,3.3771418e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020708423,0.00012414479,0.016168559,0.00011916016,0.0000107054975,1.7218272e-7,0.0012585315,0.00053227495,0.9076259,0.0011734684,0.0011307282,0.07164925],"study_design_scores_gemma":[0.0031506002,0.0011702252,0.3728892,0.0001419509,0.000072310075,0.000007224765,0.014185022,0.5044837,0.100129865,0.001476872,0.002050989,0.00024204822],"about_ca_topic_score_codex":0.000031643365,"about_ca_topic_score_gemma":0.000098152086,"teacher_disagreement_score":0.8074961,"about_ca_system_score_codex":0.000021042244,"about_ca_system_score_gemma":0.00003847951,"threshold_uncertainty_score":0.3103523},"labels":[],"label_agreement":null},{"id":"W2023939511","doi":"10.1002/sim.2521","title":"Some design issues of strata‐matched non‐randomized studies with survival outcomes","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Barrie Urology Group","funders":"National Cancer Institute; National Institutes of Natural Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Randomized controlled trial; Sample size determination; Statistics; Covariate; Mathematics; Test (biology); Completely randomized design; Log-rank test; Research design; Intervention (counseling); Medicine; Survival analysis; Surgery","score_opus":0.13716863590134443,"score_gpt":0.45099642339759155,"score_spread":0.3138277874962471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023939511","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055916626,0.00069813704,0.9914515,0.0005088713,0.00026855592,0.0006145494,0.0001192856,0.000029623101,0.00071778725],"genre_scores_gemma":[0.07731516,0.00032777237,0.92156535,0.000051755105,0.00014822619,0.00004943596,0.00001298735,0.000027953807,0.00050137826],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973735,0.00051528285,0.0010013417,0.00024730165,0.0005771477,0.00028541565],"domain_scores_gemma":[0.9790363,0.020007256,0.000323793,0.00029202673,0.0002860007,0.000054658758],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0027498375,0.00026314173,0.0019711645,0.00013019778,0.000037336173,0.0000070214523,0.00016873746,0.000059491515,0.00011047367],"category_scores_gemma":[0.011997331,0.00015303475,0.00003057783,0.00019409254,0.0012823913,0.000042014908,0.000035316512,0.00018851594,0.000002768279],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018933233,0.00012994892,0.0010896088,0.00041055758,0.00016119686,0.00006053161,0.0013366924,0.000022948048,0.00012752702,0.99081653,0.0033292419,0.00062191865],"study_design_scores_gemma":[0.027469635,0.00035156097,0.0025251778,0.00036734846,0.0002147545,0.0000017534401,0.0016327659,0.0013625895,0.00031841558,0.96556664,0.000008812259,0.00018056718],"about_ca_topic_score_codex":0.0005682917,"about_ca_topic_score_gemma":0.00014517798,"teacher_disagreement_score":0.0717235,"about_ca_system_score_codex":0.000031939886,"about_ca_system_score_gemma":0.000055668068,"threshold_uncertainty_score":0.996325},"labels":[],"label_agreement":null},{"id":"W2025797841","doi":"10.1002/sim.2178","title":"Estimation of age‐specific sensitivity and sojourn time in breast cancer screening studies","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; National Institutes of Health","keywords":"Estimator; Breast cancer; Sensitivity (control systems); Statistics; Selection (genetic algorithm); Model selection; Computer science; Econometrics; Breast cancer screening; Cancer; Mathematics; Medicine; Machine learning; Mammography; Internal medicine","score_opus":0.07831978169133007,"score_gpt":0.40168126907008117,"score_spread":0.3233614873787511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025797841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.945646,0.010269297,0.0316054,0.01087881,0.00015718775,0.00046972986,0.00019445589,0.000030315685,0.0007488444],"genre_scores_gemma":[0.95867985,0.0020661664,0.038559306,0.00038023017,0.00020091906,0.0000059653144,0.000022890303,0.0000102469685,0.00007443759],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987755,0.000060567916,0.00042365803,0.00019035595,0.00035134825,0.00019857546],"domain_scores_gemma":[0.9992634,0.00030204875,0.000116450996,0.000115696705,0.00012915365,0.000073251715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082972506,0.00012387929,0.000502145,0.00019578516,0.000028985824,0.0000035556668,0.00002934854,0.00004591136,0.00008704972],"category_scores_gemma":[0.0003299065,0.00010312864,0.000011521344,0.00025977715,0.0002897071,0.000077725876,0.00003034884,0.0002215831,0.0000025709387],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073230645,0.00009316675,0.1603831,0.00041526512,0.00010591178,0.0011701218,0.006201866,0.0067771384,0.0051109404,0.0014648078,0.014534291,0.80301106],"study_design_scores_gemma":[0.0041402425,0.00025773502,0.8969847,0.0048687076,0.0001169178,0.00029154014,0.0024627137,0.08890301,0.000249883,0.0011205021,0.0003974603,0.00020656871],"about_ca_topic_score_codex":0.00066906563,"about_ca_topic_score_gemma":0.0011824947,"teacher_disagreement_score":0.8028045,"about_ca_system_score_codex":0.00014722881,"about_ca_system_score_gemma":0.000043689895,"threshold_uncertainty_score":0.42054638},"labels":[],"label_agreement":null},{"id":"W2027702724","doi":"10.1002/sim.2392","title":"Comparison of Cox's and relative survival models when estimating the effects of prognostic factors on disease‐specific mortality: a simulation study under proportional excess hazards","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal General Hospital","funders":"","keywords":"Proportional hazards model; Relative survival; Medicine; Population; Survival analysis; Disease; Demography; Statistics; Mortality rate; Regression analysis; Relative risk; Cause of death; Oncology; Cancer registry; Internal medicine; Mathematics; Confidence interval; Environmental health","score_opus":0.08855982869920223,"score_gpt":0.40453573870942483,"score_spread":0.3159759100102226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027702724","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74018544,0.00025015016,0.25827116,0.000104269595,0.00015825285,0.0009087013,0.000022941022,0.000014184364,0.0000849092],"genre_scores_gemma":[0.99626786,0.000005838465,0.0034797376,0.000015428459,0.000119381846,0.000030975898,0.000048521437,0.000013734239,0.000018531724],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982359,0.0001524427,0.0005346023,0.00022221949,0.00073380646,0.00012103463],"domain_scores_gemma":[0.99722105,0.0020505635,0.0002838656,0.0001726579,0.00019463601,0.00007721625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047247185,0.00014260114,0.0004557013,0.00012632862,0.000063902466,0.0000047671674,0.00004614831,0.000038270646,0.000014327071],"category_scores_gemma":[0.0013928886,0.000093432325,0.000020045756,0.00018165717,0.00025490986,0.00005860034,0.000023885174,0.0002413302,1.9071375e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002463069,0.0010188207,0.7700175,0.00068758155,0.00019731467,0.000014875026,0.013330827,0.19341561,0.000059531558,0.006039032,0.00007696528,0.012678887],"study_design_scores_gemma":[0.001328961,0.0027450095,0.5697686,0.0004452912,0.00020358023,4.2046267e-7,0.0010433219,0.41791576,0.000029901572,0.0064619128,0.0000019580357,0.00005525769],"about_ca_topic_score_codex":0.00016536015,"about_ca_topic_score_gemma":0.00015606146,"teacher_disagreement_score":0.25608242,"about_ca_system_score_codex":0.00008670111,"about_ca_system_score_gemma":0.000071496535,"threshold_uncertainty_score":0.38100597},"labels":[],"label_agreement":null},{"id":"W2029359551","doi":"10.1002/sim.781","title":"Testing for the presence of cured patients: a simulation study","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada; National Research Council Canada; Alberta Heritage Foundation for Medical Research","keywords":"Censoring (clinical trials); Weibull distribution; Statistics; Likelihood-ratio test; Mathematics; Hazard ratio; Score test; Null distribution; Null hypothesis; Null (SQL); Maximum likelihood; Asymptotic distribution; Sample size determination; Applied mathematics; Statistical hypothesis testing; Econometrics; Test statistic; Confidence interval; Computer science","score_opus":0.058367907964955994,"score_gpt":0.38105411797635275,"score_spread":0.32268621001139675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029359551","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002509654,0.00006251787,0.99616224,0.00017306708,0.00024231526,0.00063485,0.000008111172,0.000011600427,0.00019567042],"genre_scores_gemma":[0.5376808,0.00000288159,0.46217945,0.000054404274,0.000038781418,0.000017392287,0.0000014384143,0.0000030460108,0.000021820313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990759,0.00009717941,0.00028976772,0.00016607942,0.00024339625,0.0001277163],"domain_scores_gemma":[0.9951166,0.004185748,0.00012061621,0.00028923023,0.00026233378,0.000025492382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094564434,0.000068902686,0.00015020464,0.00005619522,0.00005258796,0.0000082684355,0.00034011086,0.000017666436,0.0000035394473],"category_scores_gemma":[0.004125593,0.000042642212,0.0000075370235,0.00036343408,0.000058224072,0.000061829065,0.0000544474,0.000074363335,2.2004866e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036911748,0.00035906018,0.055562306,0.00004419687,0.000018412218,0.000009006506,0.007135235,0.0044825138,0.00006216497,0.0789133,0.0010132807,0.8523636],"study_design_scores_gemma":[0.001108118,0.00068490754,0.07407087,0.000050295566,0.000015368576,4.7019694e-7,0.00008801268,0.8349212,0.0000035624503,0.08880323,0.00019891631,0.000055086224],"about_ca_topic_score_codex":0.00007691734,"about_ca_topic_score_gemma":0.00002817902,"teacher_disagreement_score":0.8523085,"about_ca_system_score_codex":0.000012582045,"about_ca_system_score_gemma":0.000022363804,"threshold_uncertainty_score":0.49390182},"labels":[],"label_agreement":null},{"id":"W2030157325","doi":"10.1002/sim.4018","title":"A Bayesian approach to simultaneously adjusting for verification and reference standard bias in diagnostic test studies","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Covariate; Statistics; Bayesian probability; Test (biology); Independence (probability theory); Sensitivity (control systems); Conditional independence; Selection bias; Computer science; Econometrics; Mathematics","score_opus":0.5507579548728604,"score_gpt":0.5716683765821122,"score_spread":0.020910421709251836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030157325","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009851074,0.00009754871,0.98576,0.00060612924,0.00049057166,0.001675938,0.0007573266,0.00004364061,0.00071781094],"genre_scores_gemma":[0.21622568,0.00014652635,0.7829665,0.00014584092,0.00020510837,0.00022636709,0.00001273928,0.00003082268,0.00004043553],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971097,0.00027323523,0.0013300031,0.00052613975,0.00039152932,0.0003694081],"domain_scores_gemma":[0.63449806,0.36443228,0.000244703,0.00034329423,0.00032038617,0.00016129701],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006316659,0.00023420919,0.00091415684,0.00019030618,0.00006961088,0.00001801057,0.00019933506,0.00014664681,0.00002457684],"category_scores_gemma":[0.8895271,0.00018981945,0.00001412243,0.0003579237,0.00041346328,0.000027634813,0.00007629684,0.0005589609,0.0000019221359],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005341268,0.0005714521,0.009367628,0.0030516277,0.000066072054,0.00010689942,0.0070179044,0.000115487106,0.0012052758,0.7913573,0.0071904617,0.17941579],"study_design_scores_gemma":[0.0023257649,0.00080150145,0.002258011,0.0006641737,0.000102321115,0.000008042478,0.0015313167,0.010791085,0.00005538273,0.9806556,0.0005401146,0.00026669767],"about_ca_topic_score_codex":0.000043683303,"about_ca_topic_score_gemma":0.00047265273,"teacher_disagreement_score":0.8832104,"about_ca_system_score_codex":0.0000751409,"about_ca_system_score_gemma":0.00006189044,"threshold_uncertainty_score":0.77406126},"labels":[],"label_agreement":null},{"id":"W2030381164","doi":"10.1002/sim.1106","title":"Prediction trees with soft nodes for binary outcomes","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical and Computational Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Heart Institute; McGill University","funders":"","keywords":"Computer science; Event (particle physics); Novelty; Tree (set theory); Data mining; Data set; Set (abstract data type); Node (physics); Algorithm; Statistics; Artificial intelligence; Mathematics","score_opus":0.04925586001394029,"score_gpt":0.2959766245404736,"score_spread":0.2467207645265333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030381164","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00083002617,0.00010885828,0.99607694,0.0020404407,0.0002362318,0.0001658013,0.000096111675,0.00006600656,0.0003795868],"genre_scores_gemma":[0.41293287,0.000017128505,0.5861564,0.00047662685,0.00008132039,0.00004203841,0.000030074712,0.000008457889,0.00025503227],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891084,0.00002349811,0.00027227358,0.00026467102,0.00032834616,0.00020038038],"domain_scores_gemma":[0.9984643,0.0011264074,0.00005587038,0.00016320351,0.00012188274,0.00006836975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015761875,0.00011849554,0.00020448108,0.00011797945,0.00007792567,0.000020369875,0.0002283018,0.00002762916,0.000046862977],"category_scores_gemma":[0.00031995855,0.00008183411,0.000011749742,0.00020493468,0.00009988023,0.00010332303,0.00003246995,0.000090337664,0.000008163869],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000339397,0.0001625066,0.011421115,0.00007226567,0.00003724507,0.00007130125,0.0014860645,0.016104681,0.000029963274,0.8376168,0.013059288,0.119904846],"study_design_scores_gemma":[0.00094167184,0.0003895937,0.023456441,0.00005747445,0.000011057644,0.0000068766417,0.00004398668,0.85482365,0.000001657752,0.119902745,0.0002758002,0.000089071145],"about_ca_topic_score_codex":0.000026030337,"about_ca_topic_score_gemma":0.000021843392,"teacher_disagreement_score":0.83871895,"about_ca_system_score_codex":0.000030038815,"about_ca_system_score_gemma":0.000015843685,"threshold_uncertainty_score":0.3337098},"labels":[],"label_agreement":null},{"id":"W2032526975","doi":"10.1002/sim.2002","title":"The utility of prior information and stratification for parameter estimation with two screening tests but no gold standard","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Gold standard (test); Prior information; Estimation; Statistics; Computer science; Stratification (seeds); Econometrics; Risk stratification; Mathematics; Medicine; Artificial intelligence; Internal medicine; Biology; Economics","score_opus":0.05101232799794388,"score_gpt":0.398043093680317,"score_spread":0.3470307656823731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032526975","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034453126,0.00001854231,0.994993,0.0002448753,0.00005159083,0.0006242917,0.00030801666,0.000012987568,0.0003013974],"genre_scores_gemma":[0.17038229,0.00001544036,0.8294689,0.000025200754,0.000018275925,0.000040397365,0.00003647748,0.000006211202,0.000006785253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99880826,0.000057854322,0.0005676253,0.000118828066,0.00029635974,0.0001510933],"domain_scores_gemma":[0.99413645,0.0049540424,0.0002888292,0.00019431523,0.0003782596,0.000048101592],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011967095,0.000111293215,0.00024596258,0.000053469834,0.00008273509,0.000028056185,0.00007849773,0.00003691896,0.000013054539],"category_scores_gemma":[0.012694777,0.00006760764,0.000007978279,0.00011766733,0.00034999795,0.00011992236,0.000012627839,0.0001184515,5.059138e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024029377,0.000016647684,0.00036627383,0.00028083342,0.000011629606,7.4200983e-7,0.00047695474,0.000009143951,0.00004058472,0.6326803,0.0002648297,0.36561176],"study_design_scores_gemma":[0.0017694774,0.0005615117,0.0089127915,0.00031620046,0.00004981548,0.0000036597064,0.0002770733,0.048124555,0.0001848634,0.9396584,0.000057622354,0.00008403878],"about_ca_topic_score_codex":0.000090242655,"about_ca_topic_score_gemma":0.00014418593,"teacher_disagreement_score":0.36552772,"about_ca_system_score_codex":0.000027097669,"about_ca_system_score_gemma":0.00007629653,"threshold_uncertainty_score":0.99562174},"labels":[],"label_agreement":null},{"id":"W2033533453","doi":"10.1002/sim.2608","title":"‘A memorandum on the Present Position and Prospects of Medical Statistics and Epidemiology’ by Major Greenwood","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Cambridge; London School of Hygiene and Tropical Medicine","keywords":"Memorandum; Staffing; Medical statistics; Quarter (Canadian coin); Position (finance); Summary statistics; Mathematical statistics; History; Statistics; Political science; Law; Economics; Mathematics; Archaeology","score_opus":0.011391141148016391,"score_gpt":0.28886839334842546,"score_spread":0.2774772522004091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2033533453","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66302395,0.002708361,0.25397763,0.06667808,0.00023231063,0.0009376084,0.0009730872,0.000029111261,0.0114398515],"genre_scores_gemma":[0.99346143,0.000327656,0.004927408,0.0008523384,0.00006354206,0.000010934781,0.000102628444,0.000006428635,0.0002476505],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99867034,0.00022376893,0.00035328887,0.00021275324,0.00036368228,0.00017617748],"domain_scores_gemma":[0.99811673,0.0015597643,0.000112105336,0.00013174127,0.000008033225,0.00007159713],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014177513,0.0001006989,0.0002783838,0.00003223639,0.00007040269,0.0000020440887,0.00010404928,0.00009241188,0.0011237153],"category_scores_gemma":[0.0008953398,0.00006152385,0.0000068474037,0.00011549355,0.0013196308,0.000019148387,0.000064943124,0.0002025698,0.0000070627],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011650741,0.00021502239,0.4352422,0.00006281955,0.000050776587,0.00011577608,0.0004695519,0.00012858344,0.00046074492,0.19893616,0.35778633,0.0064155],"study_design_scores_gemma":[0.0025299944,0.0009323553,0.45353985,0.00011240935,0.00020493197,0.000040481264,0.00013642658,0.055376574,0.0002510273,0.48411605,0.0025173756,0.00024249748],"about_ca_topic_score_codex":0.0028103753,"about_ca_topic_score_gemma":0.001256202,"teacher_disagreement_score":0.35526896,"about_ca_system_score_codex":0.000023958306,"about_ca_system_score_gemma":0.0000064486453,"threshold_uncertainty_score":0.9997894},"labels":[],"label_agreement":null},{"id":"W2034925381","doi":"10.1002/sim.1670","title":"Estimating the incidence of subclinical infections with<i>Legionella Pneumonia</i>using data augmentation: analysis of an outbreak in The Netherlands","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Legionella and Acanthamoeba research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Subclinical infection; Outbreak; Legionella; Incidence (geometry); Epidemiology; Pneumonia; Cluster (spacecraft); Legionnaires' disease; Medicine; Population; Immunology; Biology; Virology; Environmental health; Internal medicine; Legionella pneumophila; Bacteria","score_opus":0.0533357147632414,"score_gpt":0.4054226833367912,"score_spread":0.3520869685735498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034925381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9275407,0.000112839865,0.071709834,0.00016810674,0.000047447145,0.00014698971,0.00007563472,0.000001101586,0.00019733107],"genre_scores_gemma":[0.99143267,0.00007319574,0.008049624,0.0001038798,0.00005659392,0.0000053076596,0.00026557618,0.000006198875,0.000006953435],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986869,0.0003114611,0.00038573972,0.00020711204,0.00027910716,0.00012964738],"domain_scores_gemma":[0.99878705,0.0003476257,0.00015377808,0.0005873342,0.00009695911,0.000027241742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017096052,0.00007916529,0.0002047665,0.00010637662,0.00005422209,0.0000064536493,0.00034643174,0.00004501882,0.000010642053],"category_scores_gemma":[0.00083850976,0.0000439338,0.000015096151,0.0007276725,0.00035331462,0.0000061206697,0.000055543365,0.00015355983,1.09917245e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021930126,0.0005858343,0.86971444,0.00012479523,0.00050875795,0.00006290683,0.0038674513,0.07902716,0.039798543,0.0031283575,0.00047428664,0.002488147],"study_design_scores_gemma":[0.004748201,0.0029789067,0.3668076,0.00037775162,0.0015466884,0.00012202875,0.009375893,0.6057876,0.00381626,0.0033174371,0.0006484951,0.00047314106],"about_ca_topic_score_codex":0.0007276158,"about_ca_topic_score_gemma":0.0048714248,"teacher_disagreement_score":0.5267604,"about_ca_system_score_codex":0.0000088730385,"about_ca_system_score_gemma":0.00011281109,"threshold_uncertainty_score":0.27183694},"labels":[],"label_agreement":null},{"id":"W2035743530","doi":"10.1002/sim.2816","title":"HIV viral dynamic models with dropouts and missing covariates","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Covariate; Missing data; Dropout (neural networks); Human immunodeficiency virus (HIV); Drop out; Viral load; Medicine; Set (abstract data type); Econometrics; Statistics; Computer science; Immunology; Mathematics; Machine learning","score_opus":0.012216009390193109,"score_gpt":0.3083770029980744,"score_spread":0.2961609936078813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2035743530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.116311416,0.004415089,0.872159,0.0010679003,0.00016200145,0.00031527368,0.00030347693,0.000036093083,0.005229734],"genre_scores_gemma":[0.98290336,0.00016471204,0.015279154,0.00007119509,0.000010873472,0.0000036226086,0.00041090208,0.000009721029,0.0011464858],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99926156,0.000048319707,0.00016858731,0.0001653974,0.00004954561,0.00030657844],"domain_scores_gemma":[0.9994608,0.0003248504,0.00003427341,0.000103017854,0.000037617912,0.00003940744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034339976,0.000101843136,0.0001905832,0.0001154621,0.00007575847,0.0000041827566,0.000051769548,0.00005967535,0.00015864611],"category_scores_gemma":[0.00008976446,0.00006751006,0.0000043344758,0.000070721915,0.00043853745,0.00002749247,0.000021341082,0.0001940822,0.000044182874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00522624,0.0010449586,0.112399936,0.00047072882,0.0012179151,0.0055833557,0.01566024,0.0001615066,0.10020734,0.41173834,0.01763737,0.32865208],"study_design_scores_gemma":[0.083935946,0.0124382125,0.35594735,0.0020985256,0.00070831063,0.0018514203,0.008569046,0.014523635,0.0053537707,0.49868035,0.01391129,0.0019821606],"about_ca_topic_score_codex":0.00023890706,"about_ca_topic_score_gemma":0.00031081683,"teacher_disagreement_score":0.86659193,"about_ca_system_score_codex":0.00004841026,"about_ca_system_score_gemma":0.000038348266,"threshold_uncertainty_score":0.27529803},"labels":[],"label_agreement":null},{"id":"W2036036016","doi":"10.1002/sim.1014","title":"Selection effects in randomized trials with count data","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Count data; Selection (genetic algorithm); Selection bias; Sample size determination; Statistics; Clinical trial; Econometrics; Computer science; Population; Sample (material); Medicine; Mathematics; Internal medicine; Artificial intelligence","score_opus":0.6251665613778234,"score_gpt":0.5981809771304896,"score_spread":0.026985584247333883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036036016","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005186047,0.00023849783,0.9926437,0.00072282756,0.0007685649,0.0023248324,0.0002517779,0.000055545333,0.002475659],"genre_scores_gemma":[0.014258414,0.00041615652,0.9841069,0.00030574124,0.00047278637,0.00014705375,0.000029502713,0.00004593853,0.00021751174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98802036,0.0074006743,0.0027237472,0.0006073599,0.0008318195,0.00041601597],"domain_scores_gemma":[0.6571437,0.34149277,0.0005499589,0.0006012167,0.00010843151,0.000103905746],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.041726157,0.00027750028,0.0036837123,0.000266453,0.000036113852,0.000017572598,0.00041212022,0.00015794403,0.0014893584],"category_scores_gemma":[0.7270354,0.00017499819,0.00003871095,0.0006091167,0.0005596824,0.00006388569,0.00008490997,0.00059063465,0.000022472615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02747482,0.00075230363,0.00092980504,0.0012073928,0.000329548,0.00047527402,0.0009689398,0.000017950226,0.0000717389,0.80526096,0.098663345,0.063847944],"study_design_scores_gemma":[0.14344306,0.00034521078,0.00020589025,0.0008189803,0.00038395938,0.000009296461,0.000037869268,0.0325002,0.000018100636,0.82179517,0.00025109897,0.00019115927],"about_ca_topic_score_codex":0.00013200431,"about_ca_topic_score_gemma":0.00029371673,"teacher_disagreement_score":0.68530923,"about_ca_system_score_codex":0.00011263498,"about_ca_system_score_gemma":0.000040564093,"threshold_uncertainty_score":0.99942344},"labels":[],"label_agreement":null},{"id":"W2036916777","doi":"10.1002/sim.3102","title":"Analysis of a nonsusceptible fraction with current status data","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Waterloo","funders":"","keywords":"Covariate; Statistics; Nonparametric statistics; Censoring (clinical trials); Estimator; Parametric statistics; Event (particle physics); Econometrics; Confidence interval; Population; Event data; Survival analysis; Mathematics; Medicine; Environmental health","score_opus":0.13284856464219846,"score_gpt":0.4801103101450883,"score_spread":0.34726174550288985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036916777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034009991,0.00005370806,0.99198073,0.000093178896,0.000047900005,0.00018056206,0.0028663455,0.000022625354,0.0013539288],"genre_scores_gemma":[0.75434065,0.000085363296,0.24125715,0.000035780802,0.000039500475,0.000010654511,0.0041841073,0.000011935516,0.000034872995],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9985564,0.00003183485,0.0005599868,0.000225576,0.0004157948,0.0002104245],"domain_scores_gemma":[0.9970449,0.0018480069,0.00023960839,0.00053462846,0.00022414245,0.000108700435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079135085,0.00010094054,0.00034618645,0.00035835672,0.00003882924,0.0000045025226,0.00016221938,0.00003059401,0.0007690018],"category_scores_gemma":[0.0023922992,0.000078854784,0.000011242178,0.001484924,0.00021845914,0.00004677659,0.000035763594,0.00015897909,0.0000064187943],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006111147,0.00030974793,0.01419079,0.00010891103,0.000172222,0.0000066059056,0.00023315198,0.000042570064,0.00006867507,0.93967825,0.009006083,0.036121868],"study_design_scores_gemma":[0.0026594542,0.0003180313,0.62947506,0.00029113988,0.0033264053,0.0000037660736,0.0016745935,0.15752,0.00007220969,0.19240542,0.011853891,0.0004000561],"about_ca_topic_score_codex":0.00014141404,"about_ca_topic_score_gemma":0.000977896,"teacher_disagreement_score":0.75093967,"about_ca_system_score_codex":0.00007577579,"about_ca_system_score_gemma":0.000054695774,"threshold_uncertainty_score":0.84200305},"labels":[],"label_agreement":null},{"id":"W2037113505","doi":"10.1002/sim.1347","title":"Incremental net benefit in randomized clinical trials with quality‐adjusted survival","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Waterloo; University of Toronto","funders":"","keywords":"Censoring (clinical trials); Statistics; Survival analysis; Analysis of covariance; Covariance; Quality-adjusted life year; Mathematics; Econometrics; Cost effectiveness","score_opus":0.6064299540665855,"score_gpt":0.5651836531183877,"score_spread":0.04124630094819781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037113505","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46747297,0.009237907,0.3962112,0.04419573,0.008849906,0.010935022,0.0033186926,0.00014130768,0.059637256],"genre_scores_gemma":[0.92892283,0.0015654082,0.05533878,0.011255195,0.00090758095,0.00039175808,0.00044220017,0.00009604767,0.0010801972],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9685223,0.011930252,0.017808998,0.0008201797,0.00030743572,0.000610826],"domain_scores_gemma":[0.9525344,0.042468518,0.004131596,0.00052138604,0.00009564714,0.00024847206],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.32541326,0.0002756673,0.005465286,0.0005651335,0.00006424731,0.000026530599,0.00022675873,0.00019895947,0.0016517558],"category_scores_gemma":[0.18110973,0.00025910707,0.000105040715,0.00039317438,0.00042788862,0.00013973215,0.000026154306,0.00047517993,0.00020835428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029102575,0.00016291329,0.15474369,0.0001830517,0.00011073386,0.000011416045,0.001101545,0.000110036985,5.5032984e-7,0.83476526,0.0055024754,0.00039810856],"study_design_scores_gemma":[0.45664775,0.0006508848,0.17466444,0.0008006005,0.00008994142,0.000010616631,0.007366362,0.008012934,0.00000228926,0.3359761,0.01470648,0.0010716107],"about_ca_topic_score_codex":0.005545612,"about_ca_topic_score_gemma":0.0067555667,"teacher_disagreement_score":0.49878913,"about_ca_system_score_codex":0.0004377266,"about_ca_system_score_gemma":0.00021536234,"threshold_uncertainty_score":0.9999861},"labels":[],"label_agreement":null},{"id":"W2037652844","doi":"10.1002/sim.2352","title":"Modelling the transmission dynamics of acute haemorrhagic conjunctivitis: application to the 2003 outbreak in Mexico","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Outbreak; Transmission (telecommunications); Coronavirus disease 2019 (COVID-19); Virology; Disease transmission; Medicine; Computer science; Disease; Internal medicine; Telecommunications; Infectious disease (medical specialty)","score_opus":0.08694857396430807,"score_gpt":0.3994271032886009,"score_spread":0.3124785293242929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037652844","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028668037,0.00027398017,0.96924174,0.025932416,0.0000668774,0.000844769,0.00011407732,0.000018984085,0.0006403386],"genre_scores_gemma":[0.8448687,0.0006848753,0.15136907,0.0025143577,0.0001280418,0.00017662381,0.00004350334,0.000025050802,0.0001897866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822295,0.00020703151,0.0007282728,0.00025331622,0.00032933208,0.0002591152],"domain_scores_gemma":[0.99566716,0.0036106498,0.00018113563,0.00036190992,0.00012714368,0.00005199374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020266087,0.00016930651,0.0004918093,0.00008050467,0.00007781097,0.00000353914,0.00030564461,0.000070039816,0.000039370676],"category_scores_gemma":[0.0022687197,0.00008570334,0.00002185974,0.0005569656,0.00022970627,0.000023725112,0.00006431452,0.00032937992,0.0000066063676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019494885,0.00027331387,0.002578988,0.00024589172,0.000100829326,0.000018861767,0.011037421,0.25658095,0.000071530456,0.5857521,0.019999027,0.12314612],"study_design_scores_gemma":[0.00044059943,0.000084993815,0.00064312085,0.0001231568,0.00007026701,0.0000022652443,0.00051333255,0.79522777,0.000014110159,0.19984585,0.0029479302,0.000086574226],"about_ca_topic_score_codex":0.00064985955,"about_ca_topic_score_gemma":0.0016834231,"teacher_disagreement_score":0.8420019,"about_ca_system_score_codex":0.00019997076,"about_ca_system_score_gemma":0.0000344076,"threshold_uncertainty_score":0.34948808},"labels":[],"label_agreement":null},{"id":"W2037889113","doi":"10.1002/sim.5530","title":"Efficient analysis of case‐control studies with sample weights","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital","funders":"","keywords":"Estimator; Covariate; Statistics; Sample (material); Population; Sample size determination; Mathematics; Bootstrapping (finance); Robustness (evolution); Econometrics; Computer science","score_opus":0.1146731685975503,"score_gpt":0.4553308516164282,"score_spread":0.3406576830188779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037889113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.073625505,0.0006331108,0.92476493,0.000051071962,0.000055662316,0.00024070924,0.00029229603,0.000044764456,0.0002919405],"genre_scores_gemma":[0.62646806,0.000029843231,0.37338576,0.000030868072,0.000033323548,0.000019792202,0.000008479999,0.000009888209,0.000014008466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987212,0.00008348097,0.0004721508,0.0001379143,0.00032016882,0.0002650915],"domain_scores_gemma":[0.9936838,0.0054709013,0.00023652031,0.00030442947,0.00023266538,0.00007169324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008312558,0.00015113881,0.0007353694,0.0003953418,0.00003386749,0.0000014031141,0.00007808117,0.000036994654,0.00012809975],"category_scores_gemma":[0.003564691,0.00009571629,0.000022060904,0.00070084084,0.0003347388,0.000022878463,0.000024073071,0.00013165787,7.45479e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052161235,0.0002024613,0.018330678,0.00020099647,0.0015954719,0.00019981293,0.0060876263,0.0003581073,0.0001061831,0.9705385,0.00070331077,0.0016246813],"study_design_scores_gemma":[0.003211778,0.0013564331,0.011302361,0.0007633663,0.013844886,0.00015778029,0.011188621,0.028327258,0.0008380226,0.9280299,0.000270478,0.00070910715],"about_ca_topic_score_codex":0.00011993587,"about_ca_topic_score_gemma":0.0004528627,"teacher_disagreement_score":0.55284256,"about_ca_system_score_codex":0.0000828697,"about_ca_system_score_gemma":0.000015156161,"threshold_uncertainty_score":0.42675254},"labels":[],"label_agreement":null},{"id":"W2038189661","doi":"10.1002/sim.2800","title":"Sampling an unknown universe: problems of researching mass casualty incidents (a history of ECRU's field research)","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Disaster Response and Management","field":"Health Professions","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Sampling (signal processing); Operations research; Disaster research; Field (mathematics); Library science; History; Sociology; Computer science; Telecommunications; Meteorology; Engineering; Geography; Mathematics","score_opus":0.3175418562933978,"score_gpt":0.5628297905198613,"score_spread":0.24528793422646344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038189661","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23178259,0.00081080844,0.4278656,0.000852599,0.0019575087,0.00249777,0.00011400685,0.000049537717,0.33406958],"genre_scores_gemma":[0.95831674,0.00042446255,0.019715635,0.00039433804,0.00023088901,0.000023489332,0.00008771089,0.000044565488,0.020762155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.996657,0.00089968875,0.00079180166,0.00022482395,0.0008911601,0.0005355366],"domain_scores_gemma":[0.9954484,0.0033488108,0.00023034013,0.00040390764,0.00040741588,0.00016113647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011243194,0.000096340285,0.00031679595,0.00075467344,0.00010943152,0.0000011945884,0.00031652424,0.000093487055,0.0005410687],"category_scores_gemma":[0.0033508488,0.000085830274,0.000012872693,0.00032949058,0.00032575283,0.00007565598,0.0002602764,0.0008574122,0.000009946141],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023879125,0.00048839493,0.019359618,0.0066900477,0.0001010961,0.00046998207,0.26204625,0.000112084424,0.011208783,0.4489828,0.17916936,0.06898368],"study_design_scores_gemma":[0.00841504,0.004784775,0.038115542,0.011669712,0.000094354284,0.000002625957,0.2414857,0.0014729599,0.00019963234,0.13768518,0.555546,0.0005285129],"about_ca_topic_score_codex":0.006689243,"about_ca_topic_score_gemma":0.0061001577,"teacher_disagreement_score":0.7265342,"about_ca_system_score_codex":0.0006458402,"about_ca_system_score_gemma":0.0004023854,"threshold_uncertainty_score":0.9999253},"labels":[],"label_agreement":null},{"id":"W2040330324","doi":"10.1002/sim.4486","title":"Optimal allocation of participants for the estimation of selection, preference and treatment effects in the two‐stage randomised trial design","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Preference; Selection (genetic algorithm); Randomized controlled trial; Sample size determination; Treatment and control groups; Treatment effect; Clinical trial; Medicine; Statistics; Mathematics; Computer science; Internal medicine","score_opus":0.5865424133203638,"score_gpt":0.5720278292840314,"score_spread":0.014514584036332434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040330324","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03763472,0.00008524211,0.9579216,0.000116560484,0.00023583903,0.003935093,0.00004319194,0.0000049659834,0.000022756383],"genre_scores_gemma":[0.4581502,0.000044460154,0.5412119,0.000014423988,0.00008657244,0.00047294187,0.000002854277,0.000007089656,0.000009575392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99680823,0.0015626447,0.0009899647,0.00013451205,0.00028388025,0.00022078096],"domain_scores_gemma":[0.8314808,0.16788512,0.00034855903,0.00016828746,0.00008031556,0.000036900557],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009890106,0.00012560815,0.00057597883,0.00006179747,0.0000379469,0.00000456682,0.00011089456,0.0000566418,0.000025938441],"category_scores_gemma":[0.13589546,0.000064290354,0.000023181476,0.00018259569,0.000268288,0.000031418003,0.000011513077,0.00010261707,2.2864388e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.11418138,0.0020275158,0.0013873052,0.00133985,0.00030846937,0.0000024989067,0.015573524,0.0070446953,0.00090591353,0.7264287,0.0009496802,0.12985048],"study_design_scores_gemma":[0.2100211,0.0045614676,0.0051896833,0.00033917656,0.00083748624,0.0000012778122,0.0004941357,0.21611862,0.002813692,0.5594702,0.000013111306,0.00014004913],"about_ca_topic_score_codex":0.00006949833,"about_ca_topic_score_gemma":0.000030920874,"teacher_disagreement_score":0.42051548,"about_ca_system_score_codex":0.000043931865,"about_ca_system_score_gemma":0.000051853447,"threshold_uncertainty_score":0.87138325},"labels":[],"label_agreement":null},{"id":"W2040984821","doi":"10.1002/sim.2507","title":"An innovative application of Bayesian disease mapping methods to patient safety research: a Canadian adverse medical event study","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria; Children’s Health Research Institute; University of British Columbia","funders":"Canadian Institutes of Health Research; Ministry of Health, British Columbia","keywords":"Adverse effect; Event (particle physics); Bayesian probability; Computer science; Adverse Event Reporting System; Patient safety; Medicine; Statistics; Artificial intelligence; Internal medicine; Mathematics; Health care","score_opus":0.3067687218428774,"score_gpt":0.5485006337421326,"score_spread":0.24173191189925525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2040984821","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062431086,0.0002720563,0.9090946,0.021632953,0.0003584791,0.0028553836,0.0013460078,0.00001806215,0.0019913977],"genre_scores_gemma":[0.92907566,0.00001210367,0.06710942,0.0029278162,0.00024220893,0.00028906588,0.00027688363,0.000026558953,0.000040283947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99272114,0.0015260981,0.0042730807,0.00057990005,0.00041181358,0.000487961],"domain_scores_gemma":[0.9955744,0.0018418292,0.00084127043,0.0006223593,0.00038931685,0.0007308331],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.043735422,0.00015780136,0.00080686563,0.0014887913,0.00015639598,0.000008633762,0.00033936222,0.0000871468,0.00045792418],"category_scores_gemma":[0.01736407,0.00018381611,0.000018672636,0.0013094343,0.00019104415,0.0001013128,0.00005154636,0.00032674716,0.00007552778],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011587295,0.0012082547,0.36432698,0.00036347716,0.00006536403,0.00004689233,0.03161609,0.0017843882,0.000006768928,0.56139076,0.018348178,0.020726962],"study_design_scores_gemma":[0.0019488966,0.0010015921,0.7938238,0.00032677152,0.0000087579065,0.0000013494532,0.019578412,0.06206104,0.0000015847135,0.078703865,0.042151336,0.0003926067],"about_ca_topic_score_codex":0.27560976,"about_ca_topic_score_gemma":0.16716118,"teacher_disagreement_score":0.86664456,"about_ca_system_score_codex":0.0013572518,"about_ca_system_score_gemma":0.0007908417,"threshold_uncertainty_score":0.9909131},"labels":[],"label_agreement":null},{"id":"W2041326463","doi":"10.1002/sim.5640","title":"Doubly robust estimation, optimally truncated inverse‐intensity weighting and increment‐based methods for the analysis of irregularly observed longitudinal data","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto; St. Joseph’s Healthcare Hamilton","funders":"","keywords":"Estimator; Weighting; Truncation (statistics); Applied mathematics; Inverse; Mathematics; Computer science; Mean squared error; Statistics; Algorithm; Medicine","score_opus":0.41399082421169303,"score_gpt":0.48337734009618,"score_spread":0.06938651588448697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041326463","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003971544,0.00019084496,0.99415684,0.00037313384,0.00018248087,0.00042659606,0.0006264219,0.000017540744,0.000054571174],"genre_scores_gemma":[0.07001008,0.000018552408,0.9293598,0.00011594856,0.000056219764,0.000023484119,0.00038222954,0.000017141638,0.000016543749],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99781805,0.00035506106,0.00085006456,0.00031562327,0.00033110537,0.00033008552],"domain_scores_gemma":[0.98195314,0.016256997,0.00042064203,0.0007351633,0.0005091104,0.00012494525],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007386923,0.0002038267,0.0007903853,0.00023005415,0.00012153634,0.000019956633,0.0003846419,0.00007426714,0.00015987993],"category_scores_gemma":[0.032709803,0.00013500138,0.000030448047,0.0008199378,0.00045701166,0.00011033432,0.00016413108,0.00020251266,2.9840416e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006981739,0.0004993993,0.07495562,0.0014112346,0.0028942013,0.000009188679,0.0027300548,0.0019405142,0.0013735208,0.792255,0.009933192,0.11129994],"study_design_scores_gemma":[0.00092201045,0.00010484303,0.08669712,0.000104409446,0.0028487185,0.0000014903693,0.0002738133,0.8682814,0.000083145846,0.040490463,0.000056424535,0.00013616295],"about_ca_topic_score_codex":0.0004282366,"about_ca_topic_score_gemma":0.00017876644,"teacher_disagreement_score":0.8663409,"about_ca_system_score_codex":0.00004555147,"about_ca_system_score_gemma":0.00006441867,"threshold_uncertainty_score":0.9754381},"labels":[],"label_agreement":null},{"id":"W2041490883","doi":"10.1002/sim.6484","title":"A flexible mixed‐effect negative binomial regression model for detecting unusual increases in MRI lesion counts in individual multiple sclerosis patients","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Multiple Sclerosis Society of Canada","keywords":"Negative binomial distribution; Random effects model; Dirichlet process; Dirichlet distribution; Statistics; Bayesian probability; Parametric statistics; Mixed model; Conditional probability distribution; Mathematics; Computer science; Medicine; Poisson distribution; Meta-analysis; Pathology","score_opus":0.11343398538156718,"score_gpt":0.35615538315047834,"score_spread":0.24272139776891116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041490883","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09827162,0.000076048615,0.9006887,0.00003911779,0.0002981946,0.00042417384,0.00007529229,0.000020372923,0.00010646221],"genre_scores_gemma":[0.57252824,0.000011971264,0.4272592,0.00006604986,0.00004447322,0.0000381948,0.00002564891,0.0000095750265,0.000016644964],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983608,0.00028110924,0.00037254975,0.00034034072,0.0003639426,0.0002812246],"domain_scores_gemma":[0.99829787,0.0011781014,0.0001272211,0.00018899333,0.00010178293,0.00010601457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017399917,0.0001630962,0.00032996834,0.00033485083,0.000045231645,0.000020370286,0.0002850321,0.000097497345,0.0000016786661],"category_scores_gemma":[0.0029454418,0.00012693871,0.000015203359,0.00042199623,0.000071832284,0.00014090024,0.00013778865,0.00022647897,0.0000018350428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063179404,0.00043077354,0.052922674,0.00018204289,0.000016285356,0.00003947632,0.010406561,0.002518954,0.00031895968,0.011119076,0.011227428,0.910186],"study_design_scores_gemma":[0.006337611,0.00057219446,0.014179558,0.0006762967,0.000009864847,0.000001016699,0.00006955556,0.9315945,0.0007032327,0.04564896,0.000019410087,0.00018782188],"about_ca_topic_score_codex":0.00043152313,"about_ca_topic_score_gemma":0.00040452016,"teacher_disagreement_score":0.92907554,"about_ca_system_score_codex":0.000151165,"about_ca_system_score_gemma":0.000116946605,"threshold_uncertainty_score":0.51764107},"labels":[],"label_agreement":null},{"id":"W2042643721","doi":"10.1002/sim.2254","title":"Application of reliability coefficients in cDNA microarray data analysis","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research","keywords":"Normalization (sociology); Computer science; Data mining; Microarray analysis techniques; Gene chip analysis; Reliability (semiconductor); Microarray; Statistics; Computational biology; Bioinformatics; Mathematics; Biology; Gene expression; Gene; Genetics","score_opus":0.016859038281986833,"score_gpt":0.33940636258979473,"score_spread":0.3225473243078079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042643721","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13183858,0.00044448866,0.8661831,0.0005731503,0.000062069026,0.00019610897,0.00022941106,0.0000032204805,0.00046985273],"genre_scores_gemma":[0.98454374,0.00017844194,0.013141874,0.000101078076,0.00006264283,0.000011619336,0.0018590911,0.000004975571,0.00009655885],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990462,0.00005473178,0.0003381199,0.00032682033,0.00013984894,0.0000942429],"domain_scores_gemma":[0.9990145,0.000023296023,0.00010857004,0.00075709494,0.000065313565,0.000031237487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005230614,0.00006507604,0.00015667891,0.00013613515,0.0000106766465,0.0000015195312,0.00025134312,0.000057769386,0.000032477095],"category_scores_gemma":[0.00031928893,0.00005795041,0.0000104770215,0.0004266929,0.000102294725,0.0000019678776,0.000063036125,0.000060442377,0.0000017063725],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001406114,0.0003633937,0.18736398,0.00006402941,0.00005423491,7.8811667e-7,0.00031874896,0.005738035,0.7148976,0.0007495558,0.013865981,0.07644306],"study_design_scores_gemma":[0.0036162066,0.00028037222,0.6726446,0.00007449519,0.0002549571,0.0000013839993,0.0006412918,0.111570664,0.057072658,0.00084630185,0.1526022,0.00039486174],"about_ca_topic_score_codex":0.00012394642,"about_ca_topic_score_gemma":0.0006322449,"teacher_disagreement_score":0.85304123,"about_ca_system_score_codex":0.0000231487,"about_ca_system_score_gemma":0.000035102996,"threshold_uncertainty_score":0.23631491},"labels":[],"label_agreement":null},{"id":"W2045286429","doi":"10.1002/sim.3751","title":"Assessment of risks by predicting counterfactuals","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Risk and Safety Analysis","field":"Decision Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Counterfactual conditional; Econometrics; Computer science; Statistics; Mathematics; Psychology; Counterfactual thinking","score_opus":0.11143002454222618,"score_gpt":0.49855336493011776,"score_spread":0.3871233403878916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045286429","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0707476,0.00049673376,0.90596795,0.002978371,0.0002835712,0.0001478785,0.0004015312,0.000014980169,0.01896138],"genre_scores_gemma":[0.98004454,0.0004630749,0.018702567,0.0002691494,0.000053239957,0.0000012725629,0.000027340304,0.0000035860492,0.00043523504],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99668074,0.0001776853,0.0010558132,0.00026729365,0.0016388507,0.00017963466],"domain_scores_gemma":[0.9964852,0.0024377697,0.00037119104,0.00036668062,0.00026145292,0.00007774794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042338204,0.00010198234,0.00049812294,0.00024787188,0.000050506973,0.00001596319,0.00038101056,0.000047391175,0.0009003496],"category_scores_gemma":[0.005238116,0.00006824893,0.000027172477,0.0006346471,0.00016851247,0.00006713012,0.00002436956,0.00018599145,0.0000096520735],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049837352,0.0002748305,0.36262086,0.000015577521,0.00006560879,0.00005188305,0.0030426325,0.0020887314,0.0034778193,0.032678142,0.19817689,0.3974572],"study_design_scores_gemma":[0.001200767,0.000714592,0.6572418,0.000105860716,0.00007167426,0.0000027534672,0.0028200857,0.056495003,0.00018073381,0.27559957,0.0054087006,0.00015847174],"about_ca_topic_score_codex":0.00026531165,"about_ca_topic_score_gemma":0.0000762804,"teacher_disagreement_score":0.90929693,"about_ca_system_score_codex":0.000040262068,"about_ca_system_score_gemma":0.00005110184,"threshold_uncertainty_score":0.9858197},"labels":[],"label_agreement":null},{"id":"W2045335212","doi":"10.1002/sim.776","title":"Power comparison of robust approximate and non‐parametric tests for the analysis of cross‐over trials","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Parametric statistics; Sample size determination; Mathematics; Ordinary least squares; Statistics; Robustness (evolution); Covariance; Applied mathematics; Statistical hypothesis testing","score_opus":0.3388194152568817,"score_gpt":0.5831102429260211,"score_spread":0.2442908276691394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045335212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14095023,0.0012432645,0.8559732,0.00007931126,0.00024001402,0.0005383845,0.00024515393,0.0000034554696,0.0007270189],"genre_scores_gemma":[0.7541279,0.00007101443,0.24557047,0.00004005836,0.000020116384,0.000015575768,0.000008811474,0.000007239758,0.00013881916],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99602103,0.00045880827,0.001887849,0.00032304338,0.001117831,0.00019145553],"domain_scores_gemma":[0.9556472,0.042484693,0.00091301196,0.0004679781,0.00042116744,0.00006596321],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01672762,0.00013864477,0.0014726241,0.0009799831,0.000054911776,0.000036074765,0.0004295249,0.000065127264,0.0006275351],"category_scores_gemma":[0.05933647,0.00007515881,0.00008708382,0.003695165,0.0007779125,0.00006681922,0.00007515302,0.00010993737,9.319462e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002279402,0.0006946144,0.81154805,0.00008253077,0.0011563926,0.000014068542,0.007040475,0.045477495,0.012404747,0.017062126,0.017407928,0.08483219],"study_design_scores_gemma":[0.0025876942,0.00066646485,0.44556972,0.000035181092,0.00061509985,0.0000012696075,0.002179885,0.53395236,0.001094863,0.012777186,0.00039213974,0.00012816722],"about_ca_topic_score_codex":0.0001499516,"about_ca_topic_score_gemma":0.000040254326,"teacher_disagreement_score":0.61317766,"about_ca_system_score_codex":0.000025373647,"about_ca_system_score_gemma":0.000030224153,"threshold_uncertainty_score":0.9485871},"labels":[],"label_agreement":null},{"id":"W2045862988","doi":"10.1002/sim.1696","title":"A non‐parametric procedure for evaluating treatment effect in the meta‐analysis of survival data","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Statistics; Hazard ratio; Censoring (clinical trials); Mathematics; Logarithm; Confidence interval; Multiplicative function; Contrast (vision); Econometrics; Computer science; Artificial intelligence","score_opus":0.769066250341494,"score_gpt":0.6656981586317418,"score_spread":0.10336809170975225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045862988","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011205524,0.00043968236,0.98048705,0.0008943176,0.0003030289,0.003483579,0.0028379848,0.000016885286,0.00033195835],"genre_scores_gemma":[0.115227275,0.00006571983,0.88393414,0.00011444846,0.000103703685,0.0003691786,0.00013705407,0.000026704438,0.000021774162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953143,0.0012736177,0.0016348986,0.00054940296,0.0008856151,0.0003421747],"domain_scores_gemma":[0.805255,0.19303441,0.00045510606,0.0010552924,0.00014198381,0.000058233003],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022447215,0.00027967826,0.0027024325,0.00054288196,0.000041322244,0.000010853579,0.0007069028,0.00011142962,0.00011111567],"category_scores_gemma":[0.29689956,0.00014565741,0.00018290001,0.0024960542,0.00026553264,0.000028982082,0.00008202344,0.00024584902,0.0000012673871],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022965893,0.004457432,0.007822698,0.005075217,0.13001418,0.00023780981,0.009437209,0.005695797,0.0002126406,0.7853789,0.0027168395,0.046654686],"study_design_scores_gemma":[0.005449199,0.0026298556,0.002443835,0.0000870026,0.12284311,0.0000010434693,0.0003071697,0.022927364,0.0000475516,0.843097,0.000011011437,0.00015585449],"about_ca_topic_score_codex":0.00037311311,"about_ca_topic_score_gemma":0.0009161824,"teacher_disagreement_score":0.27445236,"about_ca_system_score_codex":0.00011985253,"about_ca_system_score_gemma":0.00014202985,"threshold_uncertainty_score":0.7779802},"labels":[],"label_agreement":null},{"id":"W2046459096","doi":"10.1002/sim.6167","title":"Bootstrap confidence intervals for loess-based calibration curves","year":2014,"lang":"en","type":"letter","venue":"Statistics in Medicine","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Erasmus+; Library science; Citation; Confidence interval; Sociology; Operations research; Psychology; History; Computer science; Statistics; Mathematics; Art history","score_opus":0.04343705579199119,"score_gpt":0.3279541332850265,"score_spread":0.2845170774930353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046459096","genre_codex":"methods","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004563109,0.00014495222,0.78495604,0.21107551,0.00064362865,0.0006299558,0.00066202576,0.000025927771,0.0018574056],"genre_scores_gemma":[0.0017788572,0.00023359769,0.0363046,0.95291746,0.0014236461,0.00023001182,0.0050108377,0.000077538236,0.0020234648],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99769413,0.00012255105,0.0006440012,0.00051093503,0.000606535,0.00042183185],"domain_scores_gemma":[0.99742645,0.0017615547,0.00033132744,0.00036835848,0.00003952385,0.00007279351],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00074932247,0.00030664654,0.00054685574,0.00009746789,0.00006442004,0.000021945403,0.0003571628,0.00025794553,0.0021869524],"category_scores_gemma":[0.0015320233,0.00027247058,0.000034989844,0.00013954983,0.00053764204,0.000044827513,0.00005340061,0.0006606201,0.00004182898],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000826684,0.000009321137,0.00029639777,0.00086255436,0.000008356256,0.0000779075,0.00006463637,0.00013776738,0.000025897181,0.0009784742,0.99575806,0.001772354],"study_design_scores_gemma":[0.0010903223,0.00041815406,0.00092008564,0.0027317363,0.00011927639,0.0000067850538,0.000019646608,0.05311648,0.000030301337,0.049003232,0.8920234,0.000520621],"about_ca_topic_score_codex":0.0009672191,"about_ca_topic_score_gemma":0.00034383533,"teacher_disagreement_score":0.74865144,"about_ca_system_score_codex":0.00013516762,"about_ca_system_score_gemma":0.000044082433,"threshold_uncertainty_score":0.99997276},"labels":[],"label_agreement":null},{"id":"W2047326606","doi":"10.1002/sim.2519","title":"Joint estimation of time‐dependent and non‐linear effects of continuous covariates on survival","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Covariate; Mathematics; Generalization; Statistics; Applied mathematics; Parametric statistics; Maximum likelihood; Contrast (vision); Proportional hazards model; Regression; Linear regression; Regression analysis; Econometrics; Computer science; Mathematical analysis","score_opus":0.02742268541216722,"score_gpt":0.35343593669833295,"score_spread":0.32601325128616576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047326606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06432628,0.000037505055,0.9334464,0.000044961776,0.0001594762,0.0002757655,0.00012285645,0.000009127328,0.0015775925],"genre_scores_gemma":[0.5221412,0.000017008686,0.47766966,0.000013372204,0.000039408482,0.0000056334056,0.00001742279,0.000011099212,0.000085206266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99861825,0.00014442034,0.000609855,0.00015271218,0.00033853675,0.00013622007],"domain_scores_gemma":[0.9930196,0.006402758,0.00025400287,0.00016103266,0.00012366225,0.00003897815],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00088612066,0.00012716668,0.00059131125,0.000104008905,0.000016123464,0.0000025947434,0.00005877559,0.000055690973,0.000083972205],"category_scores_gemma":[0.008720471,0.00009783931,0.000011523866,0.00009986409,0.0002297662,0.000012132304,0.00002498713,0.00012322089,0.000002835591],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088512505,0.000290406,0.00077342946,0.0015812076,0.000028497394,0.000042909596,0.00044016272,0.00016764822,0.009559726,0.97116107,0.0011633707,0.014703091],"study_design_scores_gemma":[0.002063227,0.0012342554,0.023539396,0.00092834735,0.00009947733,0.0000027119358,0.000058385012,0.0674347,0.00944903,0.8950532,0.000003561841,0.00013368034],"about_ca_topic_score_codex":0.00044938648,"about_ca_topic_score_gemma":0.000017901937,"teacher_disagreement_score":0.45781493,"about_ca_system_score_codex":0.000018526645,"about_ca_system_score_gemma":0.000021265963,"threshold_uncertainty_score":0.9996295},"labels":[],"label_agreement":null},{"id":"W2047363455","doi":"10.1002/sim.2890","title":"Mapping disability‐adjusted life years: a Bayesian hierarchical model framework for burden of disease and injury assessment","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Michael Smith Health Research BC; Child and Family Research Institute","keywords":"Bayesian probability; Burden of disease; Computer science; Hierarchical database model; Disease; Statistics; Econometrics; Medicine; Artificial intelligence; Data mining; Mathematics; Internal medicine","score_opus":0.2060665600718926,"score_gpt":0.47105916337036907,"score_spread":0.26499260329847646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047363455","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07526104,0.0004961306,0.9079675,0.013702813,0.00023824704,0.000791343,0.0013426611,0.000014492531,0.00018576629],"genre_scores_gemma":[0.69453937,0.000093067116,0.30284464,0.0019660662,0.0003637125,0.00005338031,0.00008128947,0.000022671675,0.00003579876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99589187,0.00011812878,0.003084598,0.000423105,0.00013623823,0.00034607665],"domain_scores_gemma":[0.9942848,0.0040461095,0.0008631095,0.0003733515,0.0000560184,0.0003765807],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013409913,0.00014754862,0.0008778683,0.0002786603,0.00005663765,0.000011987165,0.00015623902,0.000117582815,0.00010209803],"category_scores_gemma":[0.015781483,0.00017690961,0.000034597473,0.00018652633,0.0003679667,0.000081352475,0.000048341884,0.00026270503,0.0000051827415],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011002144,0.000099036784,0.060883094,0.0012151676,0.000045323228,0.0000019031438,0.004568179,0.0005606521,0.0000027686172,0.92793876,0.0027434577,0.0018316611],"study_design_scores_gemma":[0.00091519835,0.0001366358,0.14312936,0.00033645533,0.000011717283,2.714946e-7,0.001556504,0.24840358,1.9163774e-7,0.6046661,0.0006727136,0.00017123892],"about_ca_topic_score_codex":0.00036226062,"about_ca_topic_score_gemma":0.00006655284,"teacher_disagreement_score":0.6192783,"about_ca_system_score_codex":0.0002954792,"about_ca_system_score_gemma":0.00016760857,"threshold_uncertainty_score":0.992509},"labels":[],"label_agreement":null},{"id":"W2048605164","doi":"10.1002/1097-0258(20000915/30)19:17/18<2421::aid-sim579>3.0.co;2-c","title":"Parametric bootstrap and penalized quasi-likelihood inference in conditional autoregressive models","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"BC Research (Canada); Simon Fraser University; British Columbia Centre of Excellence for Women's Health","funders":"","keywords":"Autoregressive model; Inference; Econometrics; Parametric statistics; Computer science; Parametric model; Statistics; Maximum likelihood; Mathematics; Artificial intelligence","score_opus":0.11185539004052535,"score_gpt":0.43240643843448806,"score_spread":0.3205510483939627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048605164","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043479938,0.0002808548,0.9488088,0.00030497136,0.000100923105,0.00038924094,0.00048946304,0.000034132354,0.00611166],"genre_scores_gemma":[0.6543342,0.000313285,0.3448744,0.0001812001,0.00004811341,0.00004273478,0.00004977994,0.000016417769,0.00013987489],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978747,0.00025154083,0.0007033557,0.0003457509,0.00044905988,0.0003756366],"domain_scores_gemma":[0.9906087,0.008789413,0.00012485523,0.00020957923,0.00010415679,0.0001632937],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00083523267,0.00022129982,0.00058659987,0.00028668655,0.000045216235,0.000017935528,0.00015073112,0.000105681785,0.0030691763],"category_scores_gemma":[0.008309751,0.00017973714,0.000014233888,0.00038078878,0.0004451529,0.00007333208,0.000027342998,0.00040491586,0.0000115875155],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006257019,0.0001619926,0.0011156733,0.00011769308,0.000012379593,0.00013693635,0.0008718945,0.000055227734,0.00001037955,0.9436687,0.0009022594,0.052884243],"study_design_scores_gemma":[0.0017826858,0.00026109256,0.012032698,0.00030593536,0.000025459607,0.000009828171,0.00015172987,0.08695799,0.0000054576267,0.8982112,0.000075297365,0.00018065925],"about_ca_topic_score_codex":0.00036530138,"about_ca_topic_score_gemma":0.00013975032,"teacher_disagreement_score":0.61085427,"about_ca_system_score_codex":0.00006174616,"about_ca_system_score_gemma":0.0000922674,"threshold_uncertainty_score":0.99784213},"labels":[],"label_agreement":null},{"id":"W2049450020","doi":"10.1002/sim.3804","title":"Analysis of interval‐censored disease progression data via multi‐state models under a nonignorable inspection process","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Process (computing); Interval (graph theory); Counting process; Estimation; Statistics; Expectation–maximization algorithm; Econometrics; Data mining; Maximum likelihood; Mathematics; Engineering","score_opus":0.13466788280961697,"score_gpt":0.47681463888454273,"score_spread":0.34214675607492573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049450020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02799586,0.00003750128,0.96998596,0.00010733692,0.00022680206,0.00032809828,0.0010439585,0.000046356818,0.00022810127],"genre_scores_gemma":[0.5565707,0.000025526559,0.44306052,0.00003393053,0.000029076193,0.000019179013,0.0002075119,0.000017980095,0.000035602545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978194,0.00015254514,0.0007830856,0.00045193467,0.00052774936,0.00026524728],"domain_scores_gemma":[0.99687845,0.0013605369,0.00033768502,0.00085953233,0.00036708836,0.00019673069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011771889,0.00019889395,0.0006551854,0.00037583712,0.00005873652,0.00001360441,0.0004243015,0.00006817425,0.00025225378],"category_scores_gemma":[0.006177893,0.00014937892,0.000027327427,0.00090205536,0.00041125447,0.00012099393,0.0001294547,0.000412791,0.0000017469457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010095992,0.0031028667,0.024869252,0.0027751105,0.0012976625,0.00019623397,0.009117639,0.0037331763,0.0038782156,0.81488013,0.001961773,0.13317834],"study_design_scores_gemma":[0.00050263264,0.00007001985,0.0061940122,0.00015672103,0.00047479183,6.8380194e-7,0.00018886167,0.5857286,0.00003787399,0.40653676,0.0000042218358,0.00010487775],"about_ca_topic_score_codex":0.00024140696,"about_ca_topic_score_gemma":0.00096579426,"teacher_disagreement_score":0.58199537,"about_ca_system_score_codex":0.000030511792,"about_ca_system_score_gemma":0.000088917244,"threshold_uncertainty_score":0.7395961},"labels":[],"label_agreement":null},{"id":"W2050134213","doi":"10.1002/sim.4132","title":"Estimating and testing for center effects in competing risks","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Medical College of Wisconsin","keywords":"Covariate; Statistics; Proportional hazards model; Random effects model; Context (archaeology); Computer science; Monte Carlo method; Econometrics; Mathematics; Medicine; Meta-analysis","score_opus":0.5113882250710012,"score_gpt":0.4856096886464182,"score_spread":0.025778536424583054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050134213","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3100955,0.0015397344,0.6723218,0.0029185654,0.0015836944,0.0019651912,0.00044378304,0.000050068666,0.009081686],"genre_scores_gemma":[0.47460505,0.00000896338,0.5234193,0.0016129545,0.00020087241,0.00008352514,0.000027303628,0.000021185559,0.000020817602],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99691594,0.0001415783,0.0022458748,0.00033356732,0.000047133773,0.00031591946],"domain_scores_gemma":[0.9932374,0.005636156,0.0008418757,0.00015821455,0.000040011077,0.00008633826],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011712336,0.0001265194,0.00069761433,0.00029253872,0.00007272517,0.00001100867,0.000099826946,0.000061368555,0.00005217235],"category_scores_gemma":[0.031563587,0.00015019123,0.000010878528,0.00013642389,0.000096861615,0.00009207162,0.000031835283,0.00016508947,0.00002658297],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011790163,0.0000490227,0.86270154,0.0013063987,0.0000106555535,0.000006764261,0.0072442642,0.00006872596,0.0000023958207,0.12464954,0.0012435963,0.002705302],"study_design_scores_gemma":[0.003380485,0.00029512253,0.49723437,0.0012300268,0.00000643161,0.0000068599256,0.0011557059,0.2768624,0.0000016924373,0.2191963,0.00036885202,0.00026173485],"about_ca_topic_score_codex":0.0022852828,"about_ca_topic_score_gemma":0.0004185944,"teacher_disagreement_score":0.36546716,"about_ca_system_score_codex":0.00015846938,"about_ca_system_score_gemma":0.000028332757,"threshold_uncertainty_score":0.976594},"labels":[],"label_agreement":null},{"id":"W2050464345","doi":"10.1002/sim.4501","title":"Ratio of geometric means to analyze continuous outcomes in meta‐analysis: comparison to mean differences and ratio of arithmetic means using empiric data and simulation","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Institute for Clinical Evaluative Sciences; Population Health Research Institute; Public Health Ontario; Hospital for Sick Children; Health Sciences Centre; Sunnybrook Health Science Centre; SickKids Foundation; University of Toronto; St. Michael's Hospital","funders":"Canadian Institutes of Health Research","keywords":"Pooling; Statistics; Standard deviation; Post-hoc analysis; Meta-analysis; Post hoc; Computer science; Confidence interval; Geometric mean; Econometrics; Mathematics; Medicine; Artificial intelligence; Internal medicine","score_opus":0.7130185644199137,"score_gpt":0.5692878424835579,"score_spread":0.14373072193635583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050464345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27898496,0.0027904394,0.7169733,0.00022367518,0.00006794069,0.00057008397,0.000355423,0.0000012930209,0.000032859472],"genre_scores_gemma":[0.915945,0.000034818884,0.0837694,0.00008671301,0.000022544462,0.000006304332,0.000059469014,0.0000069199377,0.00006884013],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98468566,0.0035905947,0.0074833687,0.00082752324,0.0031418044,0.00027102674],"domain_scores_gemma":[0.9808412,0.012976938,0.0026541355,0.0026127587,0.00068711577,0.0002278209],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05489317,0.00028579778,0.007081279,0.0033613911,0.00004686125,0.00008866113,0.0011205587,0.000058505677,0.0005125733],"category_scores_gemma":[0.053896617,0.0001488091,0.00015559753,0.0065056216,0.00014441214,0.00023424414,0.0003621296,0.00012545343,0.000004847887],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010065766,0.00009954131,0.96711934,0.00009048065,0.0051545715,0.0000013665216,0.0059888023,0.018119134,0.000028666758,0.0005009419,0.00031604318,0.0025710494],"study_design_scores_gemma":[0.00026221402,0.00008212163,0.36382598,0.000028155748,0.023276364,5.834974e-7,0.0036607943,0.60800606,0.0000035255132,0.0006599007,0.00007035046,0.00012391176],"about_ca_topic_score_codex":0.0008690143,"about_ca_topic_score_gemma":0.0052788067,"teacher_disagreement_score":0.63696,"about_ca_system_score_codex":0.000023608816,"about_ca_system_score_gemma":0.000036351124,"threshold_uncertainty_score":0.9731864},"labels":[],"label_agreement":null},{"id":"W2052429290","doi":"10.1002/sim.4319","title":"On the association between variables with lower detection limits","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Copula (linguistics); Estimator; Nonparametric statistics; Statistics; Mathematics; Random variable; Censoring (clinical trials); Applied mathematics; Econometrics","score_opus":0.08501645329480319,"score_gpt":0.3461242279515183,"score_spread":0.26110777465671514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052429290","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060023363,0.0000023175646,0.97376186,0.00058906636,0.00008095753,0.00028299572,0.00022833927,0.000046204914,0.019005954],"genre_scores_gemma":[0.9760748,0.0000052033397,0.023075258,0.00022230839,0.0000711702,0.000075833086,0.00006132914,0.0000144097,0.00039968622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893415,0.00009083867,0.0002993239,0.00015068373,0.0003571773,0.0001678488],"domain_scores_gemma":[0.9958499,0.003554184,0.00017599952,0.00020164294,0.00016274932,0.000055498516],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00062119385,0.000108680775,0.00017304318,0.000057955545,0.00010991284,0.000008581111,0.00010432713,0.000060419523,0.0010391256],"category_scores_gemma":[0.005426595,0.000065895256,0.000009228786,0.000296327,0.0001001914,0.00002532517,0.000008089239,0.00022041914,0.00006216789],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021311605,0.00006751419,0.0010793247,0.000013235856,0.000023887513,0.0000025964775,0.00025135177,0.0000013240412,0.000014684756,0.9893164,0.0078105056,0.0013978631],"study_design_scores_gemma":[0.0005728699,0.00027498498,0.050012704,0.000091085574,0.0000999966,0.0000011990631,0.00013954283,0.0011930258,0.00018969827,0.9467801,0.00053318765,0.00011160485],"about_ca_topic_score_codex":0.000046428184,"about_ca_topic_score_gemma":0.00008546702,"teacher_disagreement_score":0.97007245,"about_ca_system_score_codex":0.00013934403,"about_ca_system_score_gemma":0.000022258733,"threshold_uncertainty_score":0.99987406},"labels":[],"label_agreement":null},{"id":"W2054140640","doi":"10.1002/sim.2210","title":"An appraisal of methods for the analysis of longitudinal categorical data with MAR drop‐outs","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Waterloo","funders":"","keywords":"Categorical variable; Statistics; Generalized estimating equation; Marginal model; Mathematics; Gee; Missing data; Econometrics; Contingency table; Applied mathematics; Regression analysis","score_opus":0.1568631137230554,"score_gpt":0.5382222258091557,"score_spread":0.3813591120861003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054140640","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024330948,0.00011631243,0.9979982,0.00027372342,0.00007853755,0.00024922192,0.0008519477,0.000008531681,0.0001802575],"genre_scores_gemma":[0.067691796,0.000030470263,0.93195945,0.00002570177,0.00010335739,0.00001693533,0.00013980907,0.000016010095,0.000016460339],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980971,0.00031659717,0.0007368238,0.00031476302,0.00031494146,0.00021972653],"domain_scores_gemma":[0.9759599,0.022458747,0.00031374887,0.0009409995,0.00024554235,0.00008105533],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030979025,0.00015579176,0.0008166905,0.00019691202,0.000040226783,0.00000627687,0.0005836041,0.00005769257,0.00034105338],"category_scores_gemma":[0.0097678,0.000086710046,0.000027583332,0.0007594385,0.0005606483,0.000049580558,0.00006750893,0.00017799655,3.1894734e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016224248,0.00020143315,0.0035431713,0.00017687908,0.0005152456,0.0000043336777,0.000557,0.000035989295,0.00015656467,0.7336606,0.0018480425,0.25913855],"study_design_scores_gemma":[0.0011018196,0.00075445557,0.028055638,0.000069732756,0.0042761085,0.0000058396236,0.00057297945,0.6305364,0.000102727616,0.33370593,0.0006352384,0.00018314803],"about_ca_topic_score_codex":0.00023644908,"about_ca_topic_score_gemma":0.00047378457,"teacher_disagreement_score":0.6305004,"about_ca_system_score_codex":0.000021237569,"about_ca_system_score_gemma":0.00006845393,"threshold_uncertainty_score":0.99857336},"labels":[],"label_agreement":null},{"id":"W2054344391","doi":"10.1002/sim.3504","title":"Age‐ and size‐related reference ranges: A case study of spirometry through childhood and adulthood","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":165,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"Medical Research Council; National Institute for Health and Care Research","keywords":"Skewness; Kurtosis; Statistics; Spirometry; Mathematics; Generalized additive model; Linear regression; Medicine; Internal medicine","score_opus":0.017518818533129855,"score_gpt":0.28501926695840435,"score_spread":0.2675004484252745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054344391","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99744624,0.00025750438,0.0004995455,0.00006872196,0.000024615107,0.0001734752,0.000015744903,0.000008266806,0.0015058987],"genre_scores_gemma":[0.9955213,0.00050289894,0.0037642804,0.000109142115,0.000009760242,0.0000054211278,0.0000062770473,0.000006376947,0.00007451944],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99892217,0.00011325113,0.00033087484,0.00027393154,0.00020909176,0.00015067693],"domain_scores_gemma":[0.9992803,0.0003744899,0.00009492858,0.00017674836,0.000007780954,0.00006579891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027459336,0.00011758648,0.0003395978,0.000041623294,0.00009883197,0.0000015338452,0.00006887259,0.000068672525,0.0006635091],"category_scores_gemma":[0.00037048783,0.00009223189,0.000006372407,0.00037355113,0.0007309882,0.000052453717,0.000082406674,0.00020965203,0.0000056349854],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060679395,0.0009564372,0.8184949,0.000041181043,0.00013183923,0.023487294,0.14946611,0.00007442326,0.0003394989,0.00032437145,0.0008279659,0.0057953126],"study_design_scores_gemma":[0.004955043,0.0016253787,0.9700427,0.00004081815,0.00020955341,0.0020973394,0.014489072,0.00046793625,0.000015546044,0.0057949442,0.00006326279,0.0001983877],"about_ca_topic_score_codex":0.0044125486,"about_ca_topic_score_gemma":0.0028984363,"teacher_disagreement_score":0.15154783,"about_ca_system_score_codex":0.000016331429,"about_ca_system_score_gemma":0.000005259558,"threshold_uncertainty_score":0.726496},"labels":[],"label_agreement":null},{"id":"W2054584201","doi":"10.1002/sim.3547","title":"Bayesian multivariate disease mapping and ecological regression with errors in covariates: Bayesian estimation of DALYs and ‘preventable’ DALYs","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Child and Family Research Institute; University of British Columbia","funders":"Canadian Institutes of Health Research; University of British Columbia; Ministry of Health, British Columbia","keywords":"Multivariate statistics; Covariate; Bayesian probability; Estimation; Disease; Bayesian inference; Multivariate analysis; Regression analysis; Statistics; Geography; Computer science; Environmental health; Medicine; Machine learning; Engineering; Mathematics","score_opus":0.03902389800503935,"score_gpt":0.3799327395614607,"score_spread":0.3409088415564213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054584201","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012982562,0.00009179365,0.98557854,0.0005165921,0.00004062256,0.00040595932,0.0000816508,0.000018478228,0.00028379494],"genre_scores_gemma":[0.47972363,0.000042235828,0.520122,0.000054254,0.000012807038,0.000008325472,0.000018903347,0.000007913424,0.000009949846],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979766,0.00032446856,0.00071956095,0.00038136446,0.00031186594,0.00028615576],"domain_scores_gemma":[0.9969703,0.002267042,0.00026985764,0.00022726445,0.00006036098,0.00020518572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001066976,0.00024051101,0.00067296036,0.0002551167,0.000058988553,0.000014405543,0.00010043661,0.000093807015,0.00009790025],"category_scores_gemma":[0.005242457,0.00016297196,0.000011005401,0.000353343,0.0003167569,0.00007877463,0.000040333947,0.0002724415,1.6870271e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050982315,0.00054273,0.034615908,0.00096585683,0.000036520873,0.0004960088,0.0033121947,0.000106653475,0.0003141872,0.85495055,0.00023601388,0.10391359],"study_design_scores_gemma":[0.0013467731,0.00031911864,0.12862106,0.0011551405,0.000058053272,0.0000068228214,0.00027384883,0.27436665,0.000008157821,0.5937066,0.0000021242074,0.0001356244],"about_ca_topic_score_codex":0.000120473356,"about_ca_topic_score_gemma":0.00008820121,"teacher_disagreement_score":0.46674109,"about_ca_system_score_codex":0.000050201263,"about_ca_system_score_gemma":0.00005562466,"threshold_uncertainty_score":0.6645804},"labels":[],"label_agreement":null},{"id":"W2054826081","doi":"10.1002/sim.3036","title":"Use of instrumental variables in the analysis of generalized linear models in the presence of unmeasured confounding with applications to epidemiological research","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Toronto; St. Paul's Hospital; University of British Columbia","funders":"Canadian Institutes of Health Research; Michael Smith Health Research BC","keywords":"Confounding; Generalized linear model; Instrumental variable; Epidemiology; Poisson distribution; Econometrics; Poisson regression; Linear model; Statistics; Logistic regression; Medicine; Computer science; Mathematics; Population; Environmental health; Internal medicine","score_opus":0.4857623800456914,"score_gpt":0.5493356677123323,"score_spread":0.06357328766664094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054826081","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18486494,0.000020090147,0.8138846,0.00015186194,0.000004152489,0.0007751886,0.000070248294,0.0000048205816,0.00022408832],"genre_scores_gemma":[0.62936425,0.000047993566,0.37044644,0.00004078486,0.0000070860942,0.000069207505,0.00001682031,0.0000040806553,0.0000033283986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973165,0.0006899157,0.00090667955,0.00017247275,0.0006860294,0.00022842066],"domain_scores_gemma":[0.9836292,0.015388818,0.00023999992,0.0004445317,0.0002691509,0.000028253786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011111337,0.00009676557,0.00055440626,0.00057201006,0.000023381172,0.0000026259693,0.00039989466,0.00006144163,0.000012855481],"category_scores_gemma":[0.0078057987,0.00005076166,0.000017123248,0.0024230038,0.0005956807,0.000047660495,0.000051483392,0.00033439917,6.377226e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001371149,0.00018064323,0.014631403,0.00007702376,0.0000465273,0.000007272327,0.004636482,0.0063631986,0.0027990453,0.97033715,0.000099631725,0.00068450975],"study_design_scores_gemma":[0.0005830284,0.0004546605,0.01702068,0.00040232515,0.00014345351,0.0000025185973,0.006075015,0.043363858,0.0012314704,0.9305879,0.000032737065,0.00010233857],"about_ca_topic_score_codex":0.0013984608,"about_ca_topic_score_gemma":0.0022614794,"teacher_disagreement_score":0.4444993,"about_ca_system_score_codex":0.000065370616,"about_ca_system_score_gemma":0.000044196924,"threshold_uncertainty_score":0.9344834},"labels":[],"label_agreement":null},{"id":"W2054869597","doi":"10.1002/sim.3808","title":"Threshold regression for survival data with time‐varying covariates","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Eye Institute; National Heart, Lung, and Blood Institute; National Institute for Occupational Safety and Health; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Covariate; Proportional hazards model; Statistics; Econometrics; Markov chain; Regression analysis; Event (particle physics); Computer science; Inference; Accelerated failure time model; Regression; Markov model; Mathematics; Artificial intelligence","score_opus":0.13762832443698783,"score_gpt":0.4428136105549579,"score_spread":0.30518528611797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054869597","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002226627,0.000022244209,0.9910602,0.00045064942,0.0005559884,0.00039938345,0.001021888,0.000040410756,0.004222585],"genre_scores_gemma":[0.01833498,0.000013651311,0.980556,0.00009667797,0.0002977133,0.000023400378,0.00029564893,0.000035268517,0.00034666716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99850374,0.00006232791,0.00041388435,0.0003678615,0.00036119667,0.00029097428],"domain_scores_gemma":[0.990957,0.007866903,0.00014824371,0.00075902074,0.00016218386,0.00010664099],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018524313,0.00018231163,0.00045510608,0.00007466625,0.000081964485,0.00001712526,0.00042557,0.00008455293,0.00069429114],"category_scores_gemma":[0.013111371,0.00011262205,0.000007793378,0.00015135428,0.0002792028,0.000051824125,0.000116658695,0.00039419168,0.0000075694948],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001505823,0.00007249724,0.00066833437,0.0001933707,0.000022343555,0.000031765947,0.00030400595,8.0453106e-7,0.0023339875,0.96721154,0.01605293,0.012957813],"study_design_scores_gemma":[0.0018792247,0.00036702486,0.00079828,0.00041172965,0.00009391518,0.000009951301,0.00009184326,0.057393886,0.00013972282,0.936948,0.0016400443,0.00022635309],"about_ca_topic_score_codex":0.000059516897,"about_ca_topic_score_gemma":0.0001398218,"teacher_disagreement_score":0.05739308,"about_ca_system_score_codex":0.000012512697,"about_ca_system_score_gemma":0.00006803036,"threshold_uncertainty_score":0.9952016},"labels":[],"label_agreement":null},{"id":"W2055260064","doi":"10.1002/sim.1442","title":"A comparison of several regression models for analysing cost of CABG surgery","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":143,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Health Sciences Centre; Institute for Clinical Evaluative Sciences; University of Calgary; Sunnybrook Health Science Centre; Women's College Hospital; University of Toronto","funders":"","keywords":"Linear regression; Statistics; Poisson regression; Generalized linear model; Regression analysis; Regression; Proportional hazards model; Medicine; Linear model; Negative binomial distribution; Mathematics; Poisson distribution; Econometrics; Population","score_opus":0.5450433319250734,"score_gpt":0.5321256663837163,"score_spread":0.012917665541357093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055260064","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029485742,0.0021642973,0.96314216,0.0015968365,0.00052953657,0.00061302236,0.00087318046,0.0000069232824,0.0015882752],"genre_scores_gemma":[0.94120467,0.00012637775,0.0578457,0.00044871122,0.000068161055,0.000034712815,0.00012881303,0.0000180797,0.00012478321],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948333,0.0002333881,0.0043388708,0.000256362,0.00010902385,0.00022906894],"domain_scores_gemma":[0.9926246,0.0043660807,0.0025141207,0.00028006782,0.00013569769,0.00007945779],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0136245405,0.00011832129,0.0016290854,0.00047729138,0.000045966117,0.000004054012,0.0000970144,0.00008169579,0.00015087904],"category_scores_gemma":[0.011872816,0.00012868206,0.000054353135,0.00023788668,0.00013140576,0.00009767392,0.000010281963,0.00010418377,0.000005745246],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063334635,0.00020358151,0.18864857,0.0018589925,0.000085114516,0.0000011642535,0.0054863584,0.02052904,0.000012253927,0.7018703,0.08047863,0.0007626469],"study_design_scores_gemma":[0.002440492,0.00019736613,0.011833042,0.0011294298,0.00003854051,0.000002122513,0.0035631428,0.69950837,0.000066427056,0.2753469,0.0055524153,0.00032171505],"about_ca_topic_score_codex":0.0006645215,"about_ca_topic_score_gemma":0.00020180705,"teacher_disagreement_score":0.9117189,"about_ca_system_score_codex":0.0001895245,"about_ca_system_score_gemma":0.00013561327,"threshold_uncertainty_score":0.9964506},"labels":[],"label_agreement":null},{"id":"W2055353237","doi":"10.1002/sim.3092","title":"Comparison of algorithms to generate event times conditional on time‐dependent covariates","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"","keywords":"Covariate; Computer science; Toolbox; Event (particle physics); Algorithm; Stability (learning theory); Calibration; Flexibility (engineering); Binomial (polynomial); Statistics; Data mining; Mathematics; Machine learning","score_opus":0.37609532417178737,"score_gpt":0.6061969173828708,"score_spread":0.23010159321108348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055353237","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023088462,0.000029898327,0.9920363,0.00046939123,0.00074903213,0.00054728065,0.00096840074,0.000030086025,0.0028607962],"genre_scores_gemma":[0.08163392,0.000008102229,0.91669124,0.00043670804,0.00045748812,0.00001766764,0.000061763916,0.000032866283,0.000660266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958531,0.00043587622,0.0019268948,0.0003735875,0.0010326328,0.0003778712],"domain_scores_gemma":[0.94478315,0.05398894,0.00040216744,0.00033731494,0.00026338192,0.00022503694],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007309828,0.00023217253,0.0010957808,0.00025021122,0.00004527417,0.0000066412276,0.00025289145,0.00013317312,0.0029549648],"category_scores_gemma":[0.07066413,0.00018861954,0.00003846339,0.0002952687,0.0002831786,0.00001503604,0.00007042045,0.00036152283,0.00013238045],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045749277,0.0008084173,0.0007088476,0.00014672297,0.00010716976,0.00009986819,0.0006677555,0.00040644585,0.0015913906,0.91365886,0.06272773,0.018619291],"study_design_scores_gemma":[0.0018955471,0.0013489425,0.0028321932,0.00029903016,0.00009155739,0.000003126577,0.00015546294,0.0051121674,0.0052539497,0.98247975,0.0003168366,0.00021144167],"about_ca_topic_score_codex":0.000030827177,"about_ca_topic_score_gemma":0.000017232782,"teacher_disagreement_score":0.07932507,"about_ca_system_score_codex":0.00011767205,"about_ca_system_score_gemma":0.00005673924,"threshold_uncertainty_score":0.99795645},"labels":[],"label_agreement":null},{"id":"W2055628766","doi":"10.1002/sim.4208","title":"Flexible modeling of the effects of continuous prognostic factors in relative survival","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Proportional hazards model; Statistics; Hazard ratio; Survival analysis; Relative survival; Hazard; Mathematics; Linear regression; Econometrics; Relative risk; Parametric statistics; Regression analysis; Medicine; Confidence interval; Internal medicine; Cancer; Biology; Cancer registry","score_opus":0.12102041667364608,"score_gpt":0.3824141029771552,"score_spread":0.2613936863035091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055628766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21849358,0.000063427186,0.7768274,0.000010884314,0.00037229984,0.00043066766,0.0000527704,0.000008302485,0.00374068],"genre_scores_gemma":[0.8236697,0.000016677954,0.17623226,0.0000067861824,0.000011081328,0.000009288101,0.0000018939322,0.000012240175,0.00004007719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983705,0.00030655743,0.00067078747,0.0001501939,0.00031130508,0.0001906038],"domain_scores_gemma":[0.9907467,0.0086082835,0.00023067482,0.00022993839,0.0001440995,0.00004029945],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00077572785,0.00013270494,0.00055972004,0.000101820006,0.000015980671,0.000001058302,0.00018600172,0.00006495114,0.00007524668],"category_scores_gemma":[0.038378693,0.000081164355,0.000021474894,0.00029726184,0.00031444212,0.000022145945,0.00005543958,0.0002664572,4.1756255e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034758443,0.0001515482,0.07069423,0.0007190636,0.000021020145,0.000011587563,0.008688561,0.000008910022,0.00030532066,0.9180607,0.00003708469,0.0012672081],"study_design_scores_gemma":[0.00079899665,0.00039263416,0.059594087,0.0013011941,0.00006480248,5.2748146e-7,0.0008774816,0.009063758,0.0013447362,0.92647076,7.725512e-7,0.000090258174],"about_ca_topic_score_codex":0.0006989667,"about_ca_topic_score_gemma":0.00011831904,"teacher_disagreement_score":0.6051761,"about_ca_system_score_codex":0.00002630404,"about_ca_system_score_gemma":0.000047778674,"threshold_uncertainty_score":0.96972144},"labels":[],"label_agreement":null},{"id":"W2055909840","doi":"10.1002/sim.4343","title":"Comparison of alternative models for linking drug exposure with adverse effects","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":80,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal; McGill University Health Centre","funders":"Canadian Institutes of Health Research; Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"A priori and a posteriori; Model selection; Metric (unit); Computer science; Information Criteria; Statistics; Econometrics; Mathematics; Data mining; Machine learning","score_opus":0.5145667783424172,"score_gpt":0.5664642533495956,"score_spread":0.05189747500717845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055909840","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064186803,0.000059746948,0.9894896,0.000035352212,0.000528353,0.0010566687,0.00016298762,0.000027446524,0.0022211398],"genre_scores_gemma":[0.32332817,0.000013139314,0.6763416,0.000044308115,0.00012252128,0.000065672335,0.0000066784064,0.000030951356,0.00004696628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99724793,0.00042668567,0.0012101821,0.00032705755,0.0004949597,0.0002932072],"domain_scores_gemma":[0.940815,0.05783952,0.0005848808,0.00034861016,0.00030438742,0.00010763063],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025840928,0.00022322581,0.0012145886,0.00013136123,0.0000359152,0.0000022003533,0.0002717034,0.00009424423,0.00008520339],"category_scores_gemma":[0.036003172,0.00015899523,0.000038608603,0.0001843048,0.00047716804,0.00004326682,0.00005014659,0.0003233407,0.000001406381],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008559056,0.00042682103,0.0046961783,0.0016144397,0.00014417448,0.000043907843,0.01107642,0.00012822692,0.000056152185,0.96955305,0.0015730277,0.0098316865],"study_design_scores_gemma":[0.004051947,0.0015449272,0.0005953895,0.0013371558,0.00024240941,0.0000011286527,0.00071098015,0.019121679,0.0017405746,0.9704746,0.000010994001,0.00016821022],"about_ca_topic_score_codex":0.00006603195,"about_ca_topic_score_gemma":0.00007456,"teacher_disagreement_score":0.31690946,"about_ca_system_score_codex":0.00004316368,"about_ca_system_score_gemma":0.000046046614,"threshold_uncertainty_score":0.972117},"labels":[],"label_agreement":null},{"id":"W2056285559","doi":"10.1002/sim.5402","title":"Improving the reporting of randomised trials: the CONSORT Statement and beyond","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Medical Research Council","keywords":"Consolidated Standards of Reporting Trials; Context (archaeology); Alternative medicine; Systematic review; Clinical trial; Medicine; Medical research; Reliability (semiconductor); MEDLINE; Family medicine; Medical education; Political science","score_opus":0.7374228889944674,"score_gpt":0.5840386606266567,"score_spread":0.15338422836781074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056285559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.118508935,0.018545706,0.83675784,0.0064327084,0.0018951515,0.005068006,0.000117466734,0.0000044066533,0.012669773],"genre_scores_gemma":[0.98095495,0.00014107235,0.016913487,0.0004489596,0.00020124529,0.000056550136,0.0000066123275,0.0000072103608,0.0012699073],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.93998045,0.017647924,0.036987375,0.00044115816,0.004617096,0.00032599393],"domain_scores_gemma":[0.87927634,0.08067937,0.036895987,0.0022289322,0.0007957093,0.00012366386],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.603489,0.00014474147,0.0032672372,0.0001220341,0.00010735097,0.00007255467,0.00048516624,0.000025989139,0.0022537494],"category_scores_gemma":[0.6088646,0.00004008858,0.00019390367,0.00043838107,0.0003154161,0.00005633149,0.000078177465,0.00014908706,0.0000146885095],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028359256,0.00009619535,0.13097048,0.0003478982,0.0007381363,0.00001932868,0.028509634,0.000043425844,0.0013372783,0.08913092,0.3765777,0.3719454],"study_design_scores_gemma":[0.042689577,0.000672723,0.18170254,0.00077376707,0.008427151,0.00018480467,0.18094307,0.07817345,0.0005387732,0.23885798,0.2659638,0.0010723438],"about_ca_topic_score_codex":0.00007225492,"about_ca_topic_score_gemma":0.00003357511,"teacher_disagreement_score":0.862446,"about_ca_system_score_codex":0.000014165412,"about_ca_system_score_gemma":0.000048221813,"threshold_uncertainty_score":0.9986583},"labels":[],"label_agreement":null},{"id":"W2056730537","doi":"10.1002/sim.4305","title":"Monitoring binary outcomes using risk‐adjusted charts: a comparative study","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Windsor; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"CUSUM; Computer science; Control chart; Statistics; Statistical process control; Context (archaeology); Type I and type II errors; Shewhart individuals control chart; Binary number; Chart; Mathematics; EWMA chart; Process (computing)","score_opus":0.4789125639840743,"score_gpt":0.5315657088707874,"score_spread":0.05265314488671308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2056730537","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5618087,0.00022084656,0.43400002,0.000022304836,0.0018866296,0.00055615365,0.000119280645,0.0000562122,0.0013298652],"genre_scores_gemma":[0.87473834,0.000020353727,0.124823354,0.00001540253,0.00018934705,0.000024741441,0.0000022049405,0.000022580482,0.00016369553],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99494636,0.0005210157,0.0014282339,0.0007292984,0.0018793147,0.0004957633],"domain_scores_gemma":[0.9930072,0.005008648,0.00056639436,0.0006317517,0.00055451464,0.00023150325],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026901022,0.00032571238,0.000973792,0.00056433096,0.0002542398,0.00003567194,0.0006974645,0.00006375945,0.00035907608],"category_scores_gemma":[0.01370341,0.00023247571,0.000028478147,0.0011794664,0.00043961164,0.00028604493,0.00020934832,0.0005848753,0.00007247284],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010252968,0.0003136694,0.9611856,0.000010827837,0.000041345997,0.0003433467,0.024087304,0.0003292309,0.00007589444,0.0014360576,0.00017885734,0.01189539],"study_design_scores_gemma":[0.0017508225,0.00068953756,0.85234827,0.0001302098,0.000077005556,0.0000043416544,0.051009618,0.0096561825,0.00008082038,0.083919846,0.000035724654,0.00029759706],"about_ca_topic_score_codex":0.00084152835,"about_ca_topic_score_gemma":0.00011649738,"teacher_disagreement_score":0.31292963,"about_ca_system_score_codex":0.00015684274,"about_ca_system_score_gemma":0.000060007264,"threshold_uncertainty_score":0.9946046},"labels":[],"label_agreement":null},{"id":"W2057909673","doi":"10.1002/sim.3758","title":"Estimation of prediction error for survival models","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Waterloo","funders":"","keywords":"Estimator; Statistics; Confidence interval; Point estimation; Regression analysis; Regression; Prediction interval; Computer science; Standard error; Econometrics; Estimation; Mean squared error; Model selection; Mathematics","score_opus":0.15834846963960886,"score_gpt":0.45548541308610574,"score_spread":0.2971369434464969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057909673","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015180446,0.00002279571,0.9948997,0.00023681828,0.00024411776,0.0003202814,0.0005406384,0.000021370459,0.0021962142],"genre_scores_gemma":[0.31522816,0.000011579714,0.68455166,0.00003985529,0.00005684681,0.000012074225,0.00004407764,0.000007026889,0.000048734986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99883354,0.000065924425,0.0005375765,0.0001456403,0.00026392634,0.00015339683],"domain_scores_gemma":[0.9969713,0.0025290193,0.00014493523,0.00015941338,0.00014574567,0.000049567963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009326416,0.00009949253,0.0003425171,0.0000909712,0.000024700477,0.0000028135821,0.00008176683,0.00005534724,0.00006180226],"category_scores_gemma":[0.0074289977,0.00008112574,0.000014589972,0.00012939272,0.000096874595,0.00003711559,0.000006892425,0.00009472366,5.386642e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044545974,0.000060122293,0.000021791697,0.000122192,0.0000051955085,0.000001296569,0.00042594312,0.000395555,0.000112533955,0.91827434,0.0024434153,0.078093074],"study_design_scores_gemma":[0.0004982083,0.00038519278,0.0009548151,0.00010243391,0.000025892125,6.2035406e-7,0.00007573817,0.39464176,0.000051713683,0.6032112,0.00001173975,0.000040640844],"about_ca_topic_score_codex":0.00002146587,"about_ca_topic_score_gemma":0.000008977078,"teacher_disagreement_score":0.3942462,"about_ca_system_score_codex":0.00003055781,"about_ca_system_score_gemma":0.000028897495,"threshold_uncertainty_score":0.889374},"labels":[],"label_agreement":null},{"id":"W2058899694","doi":"10.1002/sim.4011","title":"Nonparametric sequential monitoring of longitudinal trials","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Nonparametric statistics; Computer science; Simple (philosophy); Applied mathematics; Monte Carlo method; Statistics; Longitudinal data; Mathematics; Algorithm; Data mining","score_opus":0.6279650322204489,"score_gpt":0.6259249707736588,"score_spread":0.0020400614467900313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058899694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09149694,0.00007097444,0.89728796,0.00022116398,0.0078091957,0.0007223982,0.00037240898,0.000051608153,0.0019673656],"genre_scores_gemma":[0.23108704,0.000053142387,0.7674971,0.000012879345,0.0012211035,0.000021049806,0.0000033112535,0.000028077064,0.000076263714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945468,0.0010595358,0.0027829893,0.0003816373,0.00086000393,0.00036906105],"domain_scores_gemma":[0.85187846,0.14629577,0.00082718325,0.000538111,0.00029147335,0.00016896652],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018957302,0.00023076803,0.0018333473,0.0003933041,0.000037968657,0.000010713697,0.00036244636,0.00022262176,0.0015764185],"category_scores_gemma":[0.60937965,0.00017713635,0.00008446279,0.00071622955,0.00066150626,0.000035367746,0.00008439827,0.00090399454,0.000011852615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031698062,0.0003654207,0.05156487,0.0005261687,0.00014718957,0.00012259875,0.00029711096,0.0000035351313,0.01038496,0.87594384,0.005015174,0.05531215],"study_design_scores_gemma":[0.002374745,0.00029698334,0.018906489,0.00023091205,0.00022771386,0.000007303632,0.000075695694,0.0001803968,0.0025795747,0.9748288,0.0001234328,0.00016794597],"about_ca_topic_score_codex":0.000088633664,"about_ca_topic_score_gemma":0.000027451773,"teacher_disagreement_score":0.59042233,"about_ca_system_score_codex":0.00003822436,"about_ca_system_score_gemma":0.000086619926,"threshold_uncertainty_score":0.9993363},"labels":[],"label_agreement":null},{"id":"W2059447605","doi":"10.1002/sim.1973","title":"Concomitant information in bioassay and semi-parametric estimation","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St. Joseph's Hospital; St. Joseph’s Healthcare Hamilton; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Interval estimation; Parametric statistics; Point estimation; Bioassay; Smoothing; Semiparametric model; Statistics; Confidence interval; Computer science; Estimation; Mathematics; Concomitant; Econometrics; Applied mathematics; Engineering","score_opus":0.04963630052769486,"score_gpt":0.38964238202597695,"score_spread":0.3400060814982821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059447605","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023488589,0.000057544756,0.9733616,0.00037278314,0.0001377961,0.0002482556,0.00006852089,0.000019596395,0.0022452776],"genre_scores_gemma":[0.46833137,0.000063742824,0.5314184,0.00012919401,0.000014725669,0.0000116439705,0.000018561504,0.000005184005,0.0000071984414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987557,0.000075690055,0.000601337,0.00012258741,0.0002565006,0.00018818273],"domain_scores_gemma":[0.99701995,0.0025708363,0.00013231958,0.00013285942,0.0000724055,0.00007164248],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010236974,0.00012065913,0.00030933894,0.0003636571,0.000025554278,0.0000151909235,0.00006939551,0.00007026666,0.000064797685],"category_scores_gemma":[0.018778149,0.00009796813,0.000005660809,0.0004923703,0.00018377477,0.00011026616,0.00002584843,0.00022023963,0.0000090214435],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017566943,0.000036505622,0.001118414,0.00017062694,0.000003830884,0.000019277368,0.0016554211,0.000136601,0.000018078863,0.9439531,0.00041338318,0.05245719],"study_design_scores_gemma":[0.0017604786,0.00018601542,0.015423104,0.00029153543,0.000014156647,0.000009233956,0.00048253097,0.03632242,0.000030613563,0.94529635,0.000069304784,0.00011427729],"about_ca_topic_score_codex":0.0003370343,"about_ca_topic_score_gemma":0.000078631776,"teacher_disagreement_score":0.4448428,"about_ca_system_score_codex":0.00012298641,"about_ca_system_score_gemma":0.000048799586,"threshold_uncertainty_score":0.9894871},"labels":[],"label_agreement":null},{"id":"W2059629136","doi":"10.1002/sim.3766","title":"Optimal two‐stage reliability studies","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Hemodynamic Monitoring and Therapy","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Intraclass correlation; Reliability (semiconductor); Measure (data warehouse); Stage (stratigraphy); Mathematics; Statistics; Limit (mathematics); Correlation; Correlation coefficient; Computer science; Reproducibility; Data mining; Power (physics); Physics; Biology","score_opus":0.03542734917062795,"score_gpt":0.41329293431337893,"score_spread":0.377865585142751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059629136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9322468,0.0025374044,0.043604445,0.009385756,0.0014597191,0.0006663613,0.000062265026,0.00017157428,0.009865685],"genre_scores_gemma":[0.93505824,0.00090667675,0.059779517,0.0008806647,0.0006020142,0.000008618289,0.000037239533,0.000015252827,0.002711808],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986155,0.000056506768,0.00041368845,0.0002730377,0.00036094835,0.0002802926],"domain_scores_gemma":[0.99898237,0.00030815424,0.00006349652,0.00036057635,0.00015475067,0.0001306504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007746085,0.00016111185,0.0005130679,0.00012065747,0.000045089753,0.0000031955833,0.00007384141,0.00004973984,0.00012432178],"category_scores_gemma":[0.0013248984,0.00011928489,0.000021687927,0.00020752258,0.00023574753,0.000024063622,0.0000128888705,0.00033261624,0.000013846235],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003416931,0.0024663843,0.14937563,0.0017637184,0.0006225661,0.0065700854,0.02883421,0.0037981542,0.012329237,0.17634903,0.07149193,0.5429821],"study_design_scores_gemma":[0.053329714,0.017740315,0.6412748,0.005224326,0.00069675123,0.0003218993,0.011475343,0.054082863,0.0021253233,0.1285098,0.083376445,0.0018424054],"about_ca_topic_score_codex":0.00007645858,"about_ca_topic_score_gemma":0.000009257105,"teacher_disagreement_score":0.5411397,"about_ca_system_score_codex":0.00016890395,"about_ca_system_score_gemma":0.00006131073,"threshold_uncertainty_score":0.48642966},"labels":[],"label_agreement":null},{"id":"W2059794838","doi":"10.1002/(sici)1097-0258(20000315)19:5<743::aid-sim338>3.0.co;2-f","title":"Retrospective estimation of the birth prevalence for delayed onset disorders: application to cystic fibrosis in Nova Scotia","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Cystic Fibrosis Research Advances","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Dalhousie University; University of British Columbia","funders":"Cystic Fibrosis Foundation","keywords":"Nova scotia; Medicine; Cystic fibrosis; Pediatrics; Maximum likelihood; Estimation; Demography; Statistics; Internal medicine; Geography","score_opus":0.01023350576769561,"score_gpt":0.34114217346828263,"score_spread":0.330908667700587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059794838","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4239843,0.00032918248,0.56677717,0.0024745686,0.00014412656,0.0044931937,0.0012989964,0.000026129715,0.00047235182],"genre_scores_gemma":[0.9133893,0.00007482912,0.08590946,0.00011413803,0.0000419276,0.00012655914,0.00008553883,0.000019435767,0.00023877589],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99821204,0.00006787315,0.0005375046,0.0003187329,0.00058805745,0.00027577486],"domain_scores_gemma":[0.9985434,0.0007026011,0.00010431859,0.00039978753,0.00016415246,0.000085771244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005900434,0.00014083613,0.00035967748,0.00020423539,0.000032583914,0.0000046499977,0.00017858799,0.00005424784,0.0003713228],"category_scores_gemma":[0.004114676,0.00010317321,0.000024070718,0.00087146467,0.00028727963,0.0000496498,0.000027583645,0.0002111836,0.000018915915],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01148946,0.0013500785,0.4382211,0.007692311,0.00012822986,0.000017164406,0.007288705,0.036868773,0.022733733,0.012563283,0.014155503,0.44749168],"study_design_scores_gemma":[0.0030237043,0.0018247024,0.90705585,0.0016013219,0.000062926425,0.00000829612,0.00018425124,0.0686036,0.0005323161,0.016489545,0.00047239073,0.0001410982],"about_ca_topic_score_codex":0.001036912,"about_ca_topic_score_gemma":0.003738839,"teacher_disagreement_score":0.48940504,"about_ca_system_score_codex":0.00024471263,"about_ca_system_score_gemma":0.00011240845,"threshold_uncertainty_score":0.49259484},"labels":[],"label_agreement":null},{"id":"W2060230329","doi":"10.1002/sim.2197","title":"Bias-corrected maximum likelihood estimator of the intraclass correlation parameter for binary data","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Intraclass correlation; Mathematics; Estimator; Maximum likelihood; Binary data; Restricted maximum likelihood; Estimation theory; Score test; Binary number","score_opus":0.12125405863141317,"score_gpt":0.4067263800309504,"score_spread":0.28547232139953727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060230329","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017575696,0.0000277856,0.9891601,0.0036911136,0.00025315065,0.0007243421,0.0040225144,0.00003702396,0.00032640682],"genre_scores_gemma":[0.32055447,0.000013266479,0.67651564,0.000267409,0.00012939629,0.000106120104,0.002255328,0.00002572127,0.00013263673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841684,0.000074186406,0.00073274603,0.0002510535,0.00031971102,0.00020547147],"domain_scores_gemma":[0.99410796,0.004575935,0.00031411456,0.0006969708,0.00023450909,0.00007051879],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006121076,0.0001394802,0.00028789774,0.0000753614,0.0000929157,0.000008537261,0.0004003407,0.00007658746,0.00024744315],"category_scores_gemma":[0.016100956,0.00009940372,0.00002120519,0.00036381077,0.0002788569,0.00006804915,0.00009198857,0.00018765508,0.000012292592],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000364543,0.00024236781,0.000572234,0.00014227655,0.000020393374,8.1692474e-7,0.00019063207,0.00015081368,0.00014729604,0.8163247,0.1426197,0.039552324],"study_design_scores_gemma":[0.0009550979,0.000059521906,0.007966896,0.00013649896,0.00009721816,0.0000039148385,0.0001039727,0.5400381,0.000059108523,0.4480099,0.0024671103,0.00010265374],"about_ca_topic_score_codex":0.000021554435,"about_ca_topic_score_gemma":0.000084000574,"teacher_disagreement_score":0.53988725,"about_ca_system_score_codex":0.000069368405,"about_ca_system_score_gemma":0.000085650594,"threshold_uncertainty_score":0.99218684},"labels":[],"label_agreement":null},{"id":"W2061407842","doi":"10.1002/sim.2618","title":"Conditioning on the propensity score can result in biased estimation of common measures of treatment effect: a Monte Carlo study","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":227,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Propensity score matching; Statistics; Covariate; Hazard ratio; Observational study; Mathematics; Econometrics; Confidence interval","score_opus":0.20389167045157128,"score_gpt":0.42466937770647534,"score_spread":0.22077770725490406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061407842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98644376,0.000016436728,0.011403142,0.00009518329,0.000023732038,0.0015523476,0.00012248525,0.000026145033,0.0003167688],"genre_scores_gemma":[0.99206644,0.000005251086,0.007735792,0.000012896182,0.0000121343,0.000106856576,0.000031102885,0.000012885799,0.000016646774],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99848163,0.0003205381,0.0005981983,0.00014335285,0.00033257555,0.0001236802],"domain_scores_gemma":[0.996643,0.00259557,0.00032214238,0.00030249936,0.00011926027,0.000017503582],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010144653,0.00014991396,0.0005247193,0.00015780743,0.000032651307,0.0000030410758,0.000095340736,0.000037233327,0.000007700153],"category_scores_gemma":[0.002681419,0.000088262015,0.00001303845,0.00022553538,0.00020149321,0.000021215968,0.000016648059,0.00015174689,1.8903305e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016231446,0.005766741,0.42524713,0.0012766479,0.00022153764,0.00044568407,0.028328497,0.032605913,0.010711916,0.46100995,0.0038631156,0.02889972],"study_design_scores_gemma":[0.007982511,0.017106254,0.26197192,0.004273138,0.00030751948,0.000005993682,0.0022034978,0.017809616,0.051758155,0.6361921,0.000004717701,0.00038459868],"about_ca_topic_score_codex":0.008497692,"about_ca_topic_score_gemma":0.01650867,"teacher_disagreement_score":0.17518212,"about_ca_system_score_codex":0.00024425043,"about_ca_system_score_gemma":0.00004269863,"threshold_uncertainty_score":0.9981048},"labels":[],"label_agreement":null},{"id":"W2061691003","doi":"10.1002/sim.3200","title":"Impact of mis‐specification of the treatment model on estimates from a marginal structural model","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Estimator; Marginal structural model; Confounding; Inverse probability; Context (archaeology); Computer science; Econometrics; Specification; Mean squared error; Average treatment effect; Statistics; Sample size determination; Mathematics; Bayesian probability","score_opus":0.1925234186916368,"score_gpt":0.4631170529289025,"score_spread":0.2705936342372657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061691003","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49542767,0.000028162987,0.50355285,0.00002247739,0.00001813244,0.00020281393,0.00040346687,0.00001697841,0.00032742883],"genre_scores_gemma":[0.62819445,0.00007210279,0.3716346,0.0000061398077,0.000013533147,0.0000073346214,0.000027138547,0.00001079035,0.00003388441],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989405,0.000022936947,0.00044799887,0.00014206709,0.00030947337,0.00013699701],"domain_scores_gemma":[0.9984182,0.0007552904,0.00028002268,0.00038629406,0.00012438293,0.00003578318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000103016806,0.00015616648,0.00036067632,0.000084616666,0.000029277131,9.4193564e-7,0.000154721,0.00005256547,0.000045627698],"category_scores_gemma":[0.00054841355,0.000088505476,0.000036858313,0.00011231729,0.00032288543,0.000027344215,0.000012426073,0.00011829466,3.576693e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008612474,0.0008506037,0.028461697,0.00017107493,0.00021302098,0.000030605668,0.01878209,0.11291463,0.0476409,0.7757717,0.004274994,0.010027436],"study_design_scores_gemma":[0.0004228677,0.00038896562,0.009656379,0.000113755195,0.00002872555,0.0000018160734,0.000042651758,0.3936989,0.0047344225,0.5908553,3.0145145e-7,0.00005588481],"about_ca_topic_score_codex":0.0002644936,"about_ca_topic_score_gemma":0.000036448047,"teacher_disagreement_score":0.28078428,"about_ca_system_score_codex":0.00022955639,"about_ca_system_score_gemma":0.00007285726,"threshold_uncertainty_score":0.36091486},"labels":[],"label_agreement":null},{"id":"W2063846874","doi":"10.1002/sim.3460","title":"Bayesian propensity score analysis for observational data","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":117,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto; University of British Columbia; Simon Fraser University","funders":"","keywords":"Propensity score matching; Observational study; Statistics; Confounding; Confidence interval; Bayesian probability; Markov chain Monte Carlo; Credible interval; Econometrics; Odds ratio; Outcome (game theory); Medicine; Mathematics","score_opus":0.5909869107336676,"score_gpt":0.490360892353943,"score_spread":0.10062601837972462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063846874","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071757687,0.000025279489,0.9907711,0.00036532583,0.000051773877,0.00045672624,0.0007191345,0.000075833574,0.00035904223],"genre_scores_gemma":[0.17815456,0.000057404304,0.8194624,0.00022163137,0.000108741406,0.000043708857,0.0016039438,0.000018487573,0.0003290916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99865234,0.000041949195,0.00045978415,0.00031188375,0.00033302282,0.00020101304],"domain_scores_gemma":[0.9973747,0.0014261405,0.0001632981,0.0007299104,0.000244806,0.000061133884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072613114,0.00013333406,0.0004612968,0.00018623346,0.000081700244,0.0000037509863,0.00037503158,0.000054855784,0.00016674025],"category_scores_gemma":[0.0065129953,0.00010897227,0.000017746725,0.000521474,0.00024722805,0.000115028,0.00010788451,0.00015497366,0.0000013451569],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000753707,0.00015083198,0.22463904,0.00020173882,0.000235417,0.0001035622,0.0006362728,0.000054900058,0.00020968939,0.680292,0.09114838,0.0022527738],"study_design_scores_gemma":[0.0005780605,0.00014320135,0.062243514,0.00007867767,0.00027348418,0.000008611961,0.000039494505,0.021770526,0.00008835609,0.9137309,0.0008612667,0.00018387655],"about_ca_topic_score_codex":0.00007261337,"about_ca_topic_score_gemma":0.00056183664,"teacher_disagreement_score":0.23343891,"about_ca_system_score_codex":0.00006198909,"about_ca_system_score_gemma":0.000083043094,"threshold_uncertainty_score":0.7797134},"labels":[],"label_agreement":null},{"id":"W2064530264","doi":"10.1002/sim.1060","title":"Longitudinal profiles of health care providers","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Healthcare Policy and Management","field":"Economics, Econometrics and Finance","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Harvard University","keywords":"Mahalanobis distance; Univariate; Health care; Computer science; Profiling (computer programming); Baseline (sea); Longitudinal data; Statistics; Data mining; Multivariate statistics; Econometrics; Actuarial science; Machine learning; Artificial intelligence; Business; Mathematics","score_opus":0.09542272310886057,"score_gpt":0.3368681650707985,"score_spread":0.2414454419619379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064530264","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02058241,0.12736927,0.37721473,0.20474797,0.0040553915,0.0048901965,0.004754199,0.00016989627,0.25621593],"genre_scores_gemma":[0.98946667,0.0010782585,0.007958016,0.0009115657,0.0000829111,0.000022663378,0.000037330254,0.000011939442,0.00043066803],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987248,0.000024698364,0.00075508363,0.00020210478,0.000052161424,0.00024112551],"domain_scores_gemma":[0.99936604,0.00006644782,0.00028935313,0.00018796223,0.000029352088,0.000060842744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005160736,0.000083673134,0.0003974992,0.00024106575,0.000037498998,0.0000035854584,0.00010160633,0.000030504903,0.00054181204],"category_scores_gemma":[0.0003575499,0.00008646825,0.000013755122,0.0001891287,0.0001089824,0.000034324035,0.000023342738,0.000107916574,0.00005030162],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038558187,0.000043390406,0.027353186,0.00082429865,0.000013723788,0.000008116267,0.007043887,0.00001286151,2.1528689e-7,0.9033857,0.035290815,0.02601997],"study_design_scores_gemma":[0.004882968,0.0025428191,0.25208881,0.00084234716,0.000018261357,0.0000068958075,0.009393469,0.0058551403,0.00001484705,0.21569498,0.50791126,0.0007481587],"about_ca_topic_score_codex":0.0076567335,"about_ca_topic_score_gemma":0.0006996508,"teacher_disagreement_score":0.9688842,"about_ca_system_score_codex":0.00012467073,"about_ca_system_score_gemma":0.000017676339,"threshold_uncertainty_score":0.9989514},"labels":[],"label_agreement":null},{"id":"W2064554092","doi":"10.1002/sim.2885","title":"Non‐inferiority trial design for recurrent events","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sample size determination; Statistics; Poisson distribution; Robustness (evolution); Null hypothesis; Econometrics; Computer science; Event (particle physics); Marginal distribution; Random effects model; Mathematics; Medicine; Random variable; Meta-analysis; Internal medicine","score_opus":0.6391600063244661,"score_gpt":0.6329558923146955,"score_spread":0.0062041140097706116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064554092","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012426054,0.00003050844,0.9901071,0.00024801758,0.0044067125,0.0029069025,0.00023217413,0.000042923635,0.00078303553],"genre_scores_gemma":[0.0072534876,0.00004580872,0.99058247,0.00017666181,0.0015599917,0.00013405686,0.000013782363,0.000045839442,0.00018793004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959036,0.00044847128,0.0019376162,0.0004486806,0.0006713061,0.000590301],"domain_scores_gemma":[0.8821255,0.11661376,0.00038170177,0.00041027536,0.0002425019,0.00022624018],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021215882,0.00026284775,0.0010528488,0.00016942945,0.00007271914,0.0000074837876,0.00030308543,0.00020917895,0.00033912572],"category_scores_gemma":[0.28007862,0.00021283118,0.00006554313,0.00029095248,0.00025434198,0.000027162552,0.000056209945,0.00044723577,0.00001328087],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.09075569,0.0011360234,0.0003486436,0.0007057457,0.000124186,0.000111442445,0.0006665135,0.000003843292,0.00012247308,0.65088826,0.07853328,0.17660388],"study_design_scores_gemma":[0.04351987,0.003831127,0.0006546496,0.00025472778,0.00013038218,0.0000018072157,0.00006892767,0.0007737258,0.00011776167,0.94948685,0.00094577746,0.00021438194],"about_ca_topic_score_codex":0.000015889567,"about_ca_topic_score_gemma":0.000051372488,"teacher_disagreement_score":0.2985986,"about_ca_system_score_codex":0.00015831909,"about_ca_system_score_gemma":0.000103322694,"threshold_uncertainty_score":0.8679003},"labels":[],"label_agreement":null},{"id":"W2064608069","doi":"10.1002/sim.4126","title":"Assessment of joint symmetry in arthritis","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Medical Research Council; University of Toronto","keywords":"Joint (building); Symmetry (geometry); Psoriatic arthritis; Arthritis; Consistency (knowledge bases); Joint disease; Contingency table; Disease; Medicine; Table (database); Goodness of fit; Econometrics; Mathematics; Computer science; Statistics; Artificial intelligence; Data mining; Pathology; Internal medicine; Alternative medicine; Structural engineering","score_opus":0.04119543443743018,"score_gpt":0.3491132775485651,"score_spread":0.3079178431111349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064608069","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8644083,0.014504569,0.018657248,0.00080810266,0.0004913271,0.0011018752,0.00014781416,0.00004274475,0.09983798],"genre_scores_gemma":[0.94130623,0.023066934,0.035347622,0.00010566119,0.000033271775,0.00002097959,0.000032352735,0.000015022037,0.00007190717],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99840873,0.00008028874,0.0005960695,0.00017885468,0.00045499063,0.0002810378],"domain_scores_gemma":[0.9993072,0.00013995549,0.0000824275,0.00023372791,0.000107836815,0.00012884293],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007642372,0.000111737114,0.00053656544,0.00045225653,0.000014562458,0.0000019294764,0.00007132524,0.000049554474,0.0014953801],"category_scores_gemma":[0.00067941495,0.00009232103,0.000020463767,0.0003133015,0.00035834318,0.000034239947,0.00003125576,0.00032419513,0.000007119876],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015945453,0.0006568685,0.6438494,0.00028839076,0.000060928138,0.0015440611,0.0030447915,7.497367e-7,0.003313869,0.20765725,0.0026963924,0.13672784],"study_design_scores_gemma":[0.00518125,0.0012402224,0.9635228,0.0022679477,0.0000029636433,0.000054148644,0.0010025239,0.00034979364,0.0004987909,0.025414351,0.00037464907,0.00009059139],"about_ca_topic_score_codex":0.0009958126,"about_ca_topic_score_gemma":0.0006147424,"teacher_disagreement_score":0.31967336,"about_ca_system_score_codex":0.000060894254,"about_ca_system_score_gemma":0.0001372765,"threshold_uncertainty_score":0.99941736},"labels":[],"label_agreement":null},{"id":"W2066581144","doi":"10.1002/sim.2546","title":"Bivariate models for co‐aggregation of dichotomous traits in twins","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Bivariate analysis; Twin study; Correlation; Dizygotic twin; Trait; Statistics; Similarity (geometry); Econometrics; Dizygotic twins; Population; Genetic correlation; Monozygotic twin; Psychology; Heritability; Mathematics; Demography; Biology; Computer science; Medicine; Genetics; Genetic variation; Artificial intelligence","score_opus":0.13561655662648225,"score_gpt":0.4075748772475037,"score_spread":0.27195832062102143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066581144","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0881031,0.00017530676,0.9042212,0.00091677427,0.00030357583,0.00085080456,0.00030774964,0.000008954804,0.005112575],"genre_scores_gemma":[0.973384,0.000028297507,0.026034232,0.000107079926,0.00008822525,0.000038080725,0.0000407643,0.000006873981,0.00027243872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99671274,0.00015391165,0.0012349961,0.00030926662,0.0013761822,0.00021287706],"domain_scores_gemma":[0.9971119,0.0020295207,0.00026116497,0.00023512103,0.00032304556,0.000039259867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059015867,0.000110227855,0.00039024235,0.0003613638,0.00003236062,0.000014377702,0.0003020841,0.0000576423,0.00013502706],"category_scores_gemma":[0.003534555,0.00007959294,0.000025640458,0.00053958583,0.00018013161,0.00009454748,0.000016353048,0.00010749289,0.000004674424],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005130135,0.0011612097,0.051407054,0.00029538808,0.000024102086,0.000037313293,0.00537659,0.10094725,0.0072144847,0.6232868,0.06809132,0.14164545],"study_design_scores_gemma":[0.0020020313,0.00024621657,0.042255007,0.00013743789,0.000009625846,5.408459e-7,0.0003220523,0.072430216,0.00031861739,0.88112575,0.0010645853,0.00008791293],"about_ca_topic_score_codex":0.0005883636,"about_ca_topic_score_gemma":0.0013530137,"teacher_disagreement_score":0.8852809,"about_ca_system_score_codex":0.00007305351,"about_ca_system_score_gemma":0.000059116064,"threshold_uncertainty_score":0.4231448},"labels":[],"label_agreement":null},{"id":"W2066948187","doi":"10.1002/sim.3953","title":"A binning method for analyzing mixed longitudinal data measured at distinct time points","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Poisson distribution; Mixed model; Smoothing; Poisson regression; Generalized linear mixed model; Longitudinal data; Computer science; Statistics; Preprocessor; Event (particle physics); Generalized linear model; Econometrics; Mathematics; Data mining; Artificial intelligence; Medicine","score_opus":0.14269810999708532,"score_gpt":0.45700158563559795,"score_spread":0.31430347563851263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066948187","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009092354,0.000034290293,0.99506694,0.0004494633,0.0005824414,0.0004260813,0.0017735794,0.000052214134,0.0007057474],"genre_scores_gemma":[0.007058195,0.0000048272327,0.9918356,0.00006115072,0.0003407514,0.00003562402,0.00040758992,0.000049369388,0.00020689824],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99723977,0.00028683819,0.0008253687,0.00065471936,0.00049341307,0.0004998728],"domain_scores_gemma":[0.9842233,0.014039928,0.00029044467,0.0009908777,0.00025085144,0.00020458987],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005408072,0.00028635346,0.0007951874,0.00018685598,0.0001675316,0.000027807986,0.0006136114,0.00012704139,0.0010745222],"category_scores_gemma":[0.059367858,0.00022807813,0.000030766783,0.00032805046,0.00029110935,0.00006808062,0.00038356465,0.0004911332,0.000022452423],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002516128,0.00016757325,0.00869847,0.0005995033,0.00014312788,0.00014213737,0.00050207146,4.3063133e-7,0.009080294,0.733032,0.056603495,0.1907793],"study_design_scores_gemma":[0.0015034297,0.00016943007,0.0093587795,0.0002560076,0.00026935514,0.000034501234,0.00003571454,0.06206119,0.00016935529,0.9247841,0.0010478199,0.00031027896],"about_ca_topic_score_codex":0.00007932526,"about_ca_topic_score_gemma":0.00067913556,"teacher_disagreement_score":0.19175215,"about_ca_system_score_codex":0.00006600333,"about_ca_system_score_gemma":0.00007491931,"threshold_uncertainty_score":0.99983865},"labels":[],"label_agreement":null},{"id":"W2068528322","doi":"10.1002/sim.2093","title":"Extending logistic regression to model diffuse interactions","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; St. Paul's Hospital; University of British Columbia","funders":"","keywords":"Logistic regression; Pairwise comparison; Outcome (game theory); Econometrics; Observational study; Computer science; Regression analysis; Ordered logit; Statistics; Extension (predicate logic); Additive model; Mathematics; Mathematical economics","score_opus":0.22472706457083738,"score_gpt":0.5077382236377517,"score_spread":0.2830111590669143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068528322","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023049684,0.00003196747,0.9901716,0.0016022776,0.00029014496,0.00019872446,0.00011395204,0.000046841316,0.005239484],"genre_scores_gemma":[0.1945535,0.00003392137,0.80321413,0.00050261023,0.00020816868,0.000028385906,0.0000097697675,0.000021907526,0.0014275893],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984599,0.000098523626,0.00055074634,0.00027709073,0.00030724434,0.00030654206],"domain_scores_gemma":[0.99597067,0.003305608,0.00010493665,0.00031461538,0.000108585366,0.00019560677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00060750725,0.00017806537,0.00037328634,0.00020818891,0.00007262249,0.000012587117,0.00017503806,0.000046605026,0.0006714842],"category_scores_gemma":[0.017144747,0.00013065226,0.000015551104,0.0002245763,0.00012587057,0.00004290282,0.00007269873,0.00032397162,0.000051308663],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003269298,0.00014418736,0.000080257734,0.000058700894,0.000006657694,0.000027600861,0.0011367677,0.0002625288,0.0006885849,0.8780938,0.032209344,0.08725888],"study_design_scores_gemma":[0.00058266486,0.00011132866,0.00040901467,0.0004923436,0.000032591663,0.000008251034,0.0001997717,0.26433906,0.00005639938,0.7322826,0.0013229363,0.0001630711],"about_ca_topic_score_codex":0.00003870533,"about_ca_topic_score_gemma":0.00013559776,"teacher_disagreement_score":0.26407653,"about_ca_system_score_codex":0.00014041118,"about_ca_system_score_gemma":0.000030796404,"threshold_uncertainty_score":0.9911343},"labels":[],"label_agreement":null},{"id":"W2068953434","doi":"10.1002/sim.2053","title":"The use of the propensity score for estimating treatment effects: administrative versus clinical data","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":225,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; Women's College Hospital; University of Toronto","funders":"","keywords":"Propensity score matching; Statistics; Econometrics; Medicine; Mathematics","score_opus":0.7319400186447765,"score_gpt":0.5861486378777672,"score_spread":0.14579138076700937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068953434","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01549587,0.000066865,0.9797662,0.00111236,0.00055776286,0.002327585,0.0004949808,0.0000497405,0.00012862856],"genre_scores_gemma":[0.049235564,0.0000871212,0.95013106,0.0000664967,0.00021719802,0.00008160062,0.00004991374,0.00001829628,0.00011275917],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984651,0.00024001612,0.0006567328,0.00022616086,0.00022753466,0.00018442783],"domain_scores_gemma":[0.9709049,0.027620975,0.00036920857,0.0009219985,0.00014228605,0.000040650393],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012477124,0.00014548094,0.00038003482,0.000017948552,0.00013485868,0.000010693555,0.00040691943,0.000053559303,0.000005410871],"category_scores_gemma":[0.045166507,0.00006860535,0.000023411896,0.00009262591,0.00062374223,0.00008210537,0.00014739438,0.0002233639,5.8874974e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011321597,0.00057269965,0.0037579779,0.00039070396,0.00022029711,0.000019440316,0.0016079505,0.000068844325,0.00012872266,0.44610476,0.044826068,0.5011704],"study_design_scores_gemma":[0.012847803,0.011549864,0.006923924,0.002944713,0.001094058,0.000014677775,0.00072465214,0.18848853,0.004366419,0.7459511,0.024433661,0.0006605966],"about_ca_topic_score_codex":0.000033034023,"about_ca_topic_score_gemma":0.0010106215,"teacher_disagreement_score":0.5005098,"about_ca_system_score_codex":0.000101741316,"about_ca_system_score_gemma":0.00012353768,"threshold_uncertainty_score":0.96287644},"labels":[],"label_agreement":null},{"id":"W2069688121","doi":"10.1002/1097-0258(20001030)19:20<2867::aid-sim551>3.0.co;2-j","title":"Properties of the estimated variance component for subject-by-formulation interaction in studies of individual bioequivalence","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Variance (accounting); Statistics; Restricted maximum likelihood; Econometrics; Variance components; Component (thermodynamics); Mathematics; Maximum likelihood; Medicine; Economics; Pharmacology","score_opus":0.6061784706403508,"score_gpt":0.5724391072053919,"score_spread":0.03373936343495887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069688121","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6958108,0.000833666,0.29697153,0.00093517493,0.001187613,0.0026889418,0.0012922158,0.000030688163,0.000249405],"genre_scores_gemma":[0.660035,0.00018762989,0.3395981,0.00003806207,0.000035059995,0.000045526092,0.000006542782,0.000011741438,0.00004233425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973805,0.0004332048,0.0014039138,0.00018841194,0.0004251602,0.00016880539],"domain_scores_gemma":[0.97946477,0.01963897,0.0004416491,0.00023400107,0.00019615966,0.000024477009],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031785327,0.00013251431,0.0006823751,0.00008271094,0.000029852792,0.0000032106373,0.00022925284,0.00006934507,0.00009011101],"category_scores_gemma":[0.06627908,0.00008317119,0.000026759773,0.00029317688,0.0005024502,0.00004159514,0.000043884193,0.00018736444,6.0879034e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053853644,0.0025929983,0.016151229,0.0128018465,0.0007124398,0.000013204174,0.026038488,0.001285325,0.06082845,0.57486355,0.018436365,0.2808907],"study_design_scores_gemma":[0.0031177776,0.00055048417,0.012524598,0.003888399,0.00017460417,0.0000019792742,0.0007476367,0.01014641,0.0111889,0.9574587,0.000046320103,0.00015419134],"about_ca_topic_score_codex":0.00007161493,"about_ca_topic_score_gemma":0.000044809738,"teacher_disagreement_score":0.38259512,"about_ca_system_score_codex":0.00006619347,"about_ca_system_score_gemma":0.000035123958,"threshold_uncertainty_score":0.941586},"labels":[],"label_agreement":null},{"id":"W2071109714","doi":"10.1002/sim.2655","title":"Analysing and interpreting competing risk data","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":184,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Hazard; Computer science; Event (particle physics); Population; Interpretation (philosophy); Econometrics; Statistics; Risk analysis (engineering); Mathematics; Medicine; Environmental health","score_opus":0.11141470997664706,"score_gpt":0.46070952155919104,"score_spread":0.349294811582544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071109714","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02219973,0.00017477889,0.9734604,0.000110090885,0.000046209727,0.00011179183,0.00012349345,0.00009792814,0.0036755856],"genre_scores_gemma":[0.3950902,0.00006674259,0.6045966,0.000034998287,0.000078959456,0.0000022677893,0.000089525165,0.0000145163085,0.000026169986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877965,0.00010779264,0.00046884132,0.00026024715,0.0001938509,0.00018958464],"domain_scores_gemma":[0.9967938,0.0024529926,0.0002305615,0.0004346174,0.000055170512,0.000032855314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014048404,0.00012328548,0.00030590044,0.0001291136,0.000060112277,0.000013126376,0.00020773798,0.0000382111,0.00004983817],"category_scores_gemma":[0.0062879394,0.0001053035,0.000004862316,0.00016935471,0.00021576707,0.00008150197,0.00021454564,0.00028777466,0.000001007496],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029510476,0.00008964951,0.10078013,0.00033956114,0.00004453839,0.00017514717,0.0018995893,0.00004696964,0.0024909542,0.7953867,0.016463082,0.08225418],"study_design_scores_gemma":[0.0002839835,0.000050364244,0.0019861339,0.0004991248,0.00006505438,0.000009054184,0.0006647958,0.042242214,0.000100934005,0.9536461,0.00031445315,0.00013774981],"about_ca_topic_score_codex":0.00058121904,"about_ca_topic_score_gemma":0.0006890958,"teacher_disagreement_score":0.37289047,"about_ca_system_score_codex":0.000041200336,"about_ca_system_score_gemma":0.00001136297,"threshold_uncertainty_score":0.7527705},"labels":[],"label_agreement":null},{"id":"W2071379517","doi":"10.1002/sim.2770","title":"A comparison of regression trees, logistic regression, generalized additive models, and multivariate adaptive regression splines for predicting AMI mortality","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Logistic regression; Multivariate adaptive regression splines; Statistics; Receiver operating characteristic; Multivariate statistics; Regression; Regression analysis; Logistic model tree; Predictive modelling; Mathematics; Bayesian multivariate linear regression; Medicine","score_opus":0.11830730882407893,"score_gpt":0.4368427016114135,"score_spread":0.31853539278733456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071379517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023495195,0.0014926434,0.9725293,0.0005538188,0.0004906713,0.0007758264,0.00038974202,0.000095149124,0.00017763974],"genre_scores_gemma":[0.6914147,0.000088109584,0.30782345,0.000048388145,0.00021111495,0.000058616264,0.0002551503,0.000021207532,0.00007927445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965249,0.0004805751,0.0011811844,0.00072714133,0.00066249596,0.0004237032],"domain_scores_gemma":[0.9957686,0.0020386837,0.0009922608,0.0005557586,0.0005058893,0.0001388096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011198479,0.00034830376,0.0009147302,0.0002614695,0.00022088137,0.000020087393,0.00043159688,0.00017294506,0.000010549716],"category_scores_gemma":[0.0022243008,0.00023870509,0.000035600446,0.0003781928,0.00034772663,0.0001707715,0.00024893953,0.00046580634,3.3591581e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011268217,0.00065767614,0.26029286,0.0015372881,0.00010279361,0.00017043231,0.011265648,0.040934462,0.0016012337,0.56156665,0.026106708,0.094637446],"study_design_scores_gemma":[0.001997193,0.00047768385,0.06557643,0.0019195426,0.000037117155,0.0000052032383,0.00026818144,0.8458922,0.00011995299,0.08342929,0.000083491475,0.00019371422],"about_ca_topic_score_codex":0.0056043933,"about_ca_topic_score_gemma":0.0011815074,"teacher_disagreement_score":0.80495775,"about_ca_system_score_codex":0.00010202752,"about_ca_system_score_gemma":0.00011479703,"threshold_uncertainty_score":0.97341114},"labels":[],"label_agreement":null},{"id":"W2071834496","doi":"10.1002/sim.5536","title":"Estimation methods for marginal and association parameters for longitudinal binary data with nonignorable missing observations","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Covariate; Pairwise comparison; Computer science; Statistics; Robustness (evolution); Econometrics; Binary data; Data mining; Binary number; Mathematics; Machine learning","score_opus":0.26870786049482126,"score_gpt":0.5006180560725655,"score_spread":0.23191019557774423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071834496","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006820816,0.00012640255,0.9967537,0.0008780433,0.00019828991,0.0006454537,0.00063417305,0.000019562725,0.00006231818],"genre_scores_gemma":[0.0028432743,0.000018141263,0.996364,0.00008256817,0.00010100187,0.00010865488,0.00039718355,0.000023495913,0.000061664214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99862176,0.00017814967,0.00040265953,0.00025724017,0.00019479988,0.0003453609],"domain_scores_gemma":[0.98115027,0.018043237,0.0002534398,0.0002785163,0.00016856834,0.000105985644],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004004835,0.00014860297,0.00037519235,0.00009096401,0.00014391648,0.000029284567,0.00012890021,0.00007323329,0.000017442277],"category_scores_gemma":[0.02304518,0.00011697401,0.000009085549,0.00017253234,0.000107326385,0.00020872329,0.000037901624,0.00013036856,2.936192e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001648396,0.00013329473,0.024047323,0.00083836436,0.00007787249,0.0000019688755,0.0005854716,0.000010874204,0.00015495424,0.68804705,0.010481043,0.27545696],"study_design_scores_gemma":[0.001125179,0.00033414637,0.016957637,0.00024974498,0.00029514078,0.0000056703325,0.00015382202,0.26186934,0.000029277933,0.71825284,0.0005655165,0.00016165993],"about_ca_topic_score_codex":0.00004981665,"about_ca_topic_score_gemma":0.000028830473,"teacher_disagreement_score":0.2752953,"about_ca_system_score_codex":0.00010577915,"about_ca_system_score_gemma":0.000056401997,"threshold_uncertainty_score":0.98518413},"labels":[],"label_agreement":null},{"id":"W2072082323","doi":"10.1002/sim.4374","title":"A Bayesian approach to risk‐adjusted outcome monitoring in healthcare","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Pacific Northwest National Laboratory; University of Waterloo; Virginia Polytechnic Institute and State University","keywords":"Computer science; Bayes' theorem; Bayesian probability; Outcome (game theory); Prior probability; Health care; Bayes factor; Data mining; Set (abstract data type); Bayesian inference; Machine learning; Artificial intelligence; Mathematics","score_opus":0.2882576065015896,"score_gpt":0.4814126593832788,"score_spread":0.19315505288168922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072082323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006248045,0.00017926443,0.9863316,0.00030465072,0.0011550004,0.00043767027,0.00012303679,0.000042761254,0.005178019],"genre_scores_gemma":[0.6576922,0.000020039151,0.3418053,0.00009070573,0.00016534673,0.00004385624,0.0000044296685,0.000022151951,0.00015598026],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9948619,0.00035244235,0.0016866558,0.0008122754,0.0016275882,0.0006591122],"domain_scores_gemma":[0.99572396,0.0025532385,0.00030563868,0.0006460762,0.0003358106,0.0004353013],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035739748,0.00026541442,0.00074830133,0.00084950076,0.00010286019,0.000025707559,0.0007983602,0.00010648758,0.000083326406],"category_scores_gemma":[0.031197244,0.00020802268,0.000021191183,0.0019885786,0.00019938311,0.00015389147,0.00016373875,0.0007733954,0.00006752864],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009294679,0.00009424082,0.89099354,0.00005599636,0.000004321073,0.00013470724,0.006164165,0.00040585658,0.000010430743,0.022794621,0.00035096606,0.07889821],"study_design_scores_gemma":[0.0009882151,0.00023802053,0.6741858,0.00015176312,0.000010732187,0.000005417254,0.004840743,0.0060971146,0.000026987638,0.31298342,0.00018833096,0.00028344773],"about_ca_topic_score_codex":0.0027299996,"about_ca_topic_score_gemma":0.0005363618,"teacher_disagreement_score":0.65144414,"about_ca_system_score_codex":0.0002446257,"about_ca_system_score_gemma":0.000061083614,"threshold_uncertainty_score":0.9769634},"labels":[],"label_agreement":null},{"id":"W2072845842","doi":"10.1002/sim.5852","title":"Concordance measures in shared frailty models: application to clustered data in cancer prognosis","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Frailty in Older Adults","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Cancer Research; Institut National Du Cancer; Association pour la Recherche sur le Cancer","keywords":"Concordance; Censoring (clinical trials); Frailty Index; Nonparametric statistics; Statistics; Index (typography); Covariate; Medicine; Econometrics; Computer science; Internal medicine; Mathematics","score_opus":0.11797337068013256,"score_gpt":0.3889841790892407,"score_spread":0.2710108084091082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072845842","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17338055,0.0040717567,0.7348347,0.06432498,0.0010171956,0.014664469,0.0028550522,0.00020636198,0.0046449816],"genre_scores_gemma":[0.9567818,0.00041574767,0.037848487,0.002278945,0.00019661293,0.0013905293,0.0007712465,0.000044943976,0.00027170774],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.997326,0.0000851006,0.00083380064,0.000672634,0.0006434069,0.0004390702],"domain_scores_gemma":[0.99814403,0.00032534054,0.00012587984,0.00095120916,0.00024407289,0.00020945205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063239055,0.00023462359,0.0006140302,0.00037480917,0.000020139127,0.000013370627,0.0004723763,0.000114224866,0.00029714665],"category_scores_gemma":[0.0018968743,0.00020846214,0.000009659663,0.0007795456,0.00014930226,0.00021015272,0.00017720037,0.0004486981,0.00004625255],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048501388,0.0007483643,0.3569827,0.0010967007,0.00006571428,0.00017112648,0.010181906,0.0033580079,0.0034391629,0.0013408925,0.172968,0.44916242],"study_design_scores_gemma":[0.008260275,0.00042819075,0.5745596,0.0033831738,0.00005865737,0.0000117231,0.0010726834,0.39816564,0.0001065711,0.009643321,0.0038938157,0.00041630055],"about_ca_topic_score_codex":0.029897353,"about_ca_topic_score_gemma":0.052647527,"teacher_disagreement_score":0.78340125,"about_ca_system_score_codex":0.00039707837,"about_ca_system_score_gemma":0.00018263356,"threshold_uncertainty_score":0.9765626},"labels":[],"label_agreement":null},{"id":"W2072863153","doi":"10.1002/sim.2108","title":"Application of hidden Markov models to multiple sclerosis lesion count data","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Actua; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Markov chain; Markov model; Multiple sclerosis; Perspective (graphical); Count data; Clinical trial; Artificial intelligence; Machine learning; Hidden Markov model; Data mining; Medicine; Statistics; Mathematics; Pathology","score_opus":0.10554507787332336,"score_gpt":0.3455094780797473,"score_spread":0.23996440020642396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072863153","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024975868,0.00020087154,0.99671113,0.00168972,0.000114557595,0.00028411797,0.00014256421,0.000024582794,0.000582692],"genre_scores_gemma":[0.23923203,0.00010374556,0.7599942,0.00047881212,0.00007803779,0.00001282195,0.000052789706,0.00000751415,0.00004004745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985204,0.00007945218,0.00040622495,0.00041804535,0.00038711756,0.00018876068],"domain_scores_gemma":[0.9981852,0.00033193847,0.00010937668,0.0011582045,0.00011160078,0.0001036813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011711325,0.000112936876,0.00025755464,0.00014017698,0.00003290945,0.0000107710075,0.0010780597,0.000049917577,0.000009975435],"category_scores_gemma":[0.0002209106,0.00009546077,0.000007978349,0.00033882758,0.000060048213,0.00020712159,0.000350991,0.00011538669,0.00000700995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011061543,0.00004298527,0.00007729342,0.000025220836,0.0000038872636,0.0000015595216,0.0008104415,0.00022745662,0.0024008155,0.13349232,0.009375954,0.853531],"study_design_scores_gemma":[0.0005128515,0.00006812921,0.0017300224,0.00010167681,0.000008902905,0.0000016723345,0.00001684528,0.9361797,0.00021605015,0.05931197,0.0017462615,0.00010591461],"about_ca_topic_score_codex":0.00034855728,"about_ca_topic_score_gemma":0.00026452617,"teacher_disagreement_score":0.93595225,"about_ca_system_score_codex":0.00005151103,"about_ca_system_score_gemma":0.000043665157,"threshold_uncertainty_score":0.38927773},"labels":[],"label_agreement":null},{"id":"W2075167302","doi":"10.1002/sim.3642","title":"A geometric confidence ellipse approach to the estimation of the ratio of two variables. <i>Statistics in Medicine</i> 2008; <b>27</b>:5956–5974.","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Ellipse; Term (time); Medical statistics; Applied mathematics; Statistics; Carry (investment); Mathematics; Confidence interval; Calculus (dental); Computer science; Geometry; Medicine; Physics","score_opus":0.16376878348943286,"score_gpt":0.42243540449526507,"score_spread":0.2586666210058322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075167302","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027613048,0.00031784514,0.9860238,0.0033034675,0.0011705688,0.0010139804,0.00013203059,0.000006779694,0.0052702636],"genre_scores_gemma":[0.93976855,0.000053181982,0.058003493,0.0008685841,0.00013492696,0.000019387287,0.00006612441,0.000009455214,0.0010763061],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9916931,0.0007588753,0.002037035,0.0005118307,0.004675222,0.00032393655],"domain_scores_gemma":[0.99194366,0.004866289,0.00087702065,0.00096760964,0.0012430697,0.00010237542],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021191444,0.00020642873,0.0006440313,0.0009522053,0.00010883819,0.000035370093,0.0012298173,0.000064608044,0.00038093346],"category_scores_gemma":[0.05637901,0.00010747283,0.00002909378,0.006249573,0.00064209406,0.000113803646,0.00006703169,0.00028612654,0.000018264976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015035762,0.00031335576,0.004982415,0.00006511859,0.000018802235,0.0000049047153,0.012439573,0.195577,0.002325367,0.24874341,0.4525155,0.08286419],"study_design_scores_gemma":[0.0029355453,0.0004876301,0.03930828,0.00046441535,0.00010939347,0.0000063086322,0.0027792226,0.56219286,0.0005624787,0.3894634,0.0014611811,0.00022926662],"about_ca_topic_score_codex":0.0008436908,"about_ca_topic_score_gemma":0.00082996796,"teacher_disagreement_score":0.93700725,"about_ca_system_score_codex":0.00011639541,"about_ca_system_score_gemma":0.00030489513,"threshold_uncertainty_score":0.9515695},"labels":[],"label_agreement":null},{"id":"W2075875797","doi":"10.1002/sim.6198","title":"Small sample GEE estimation of regression parameters for longitudinal data","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Generalized estimating equation; Estimator; Mathematics; Marginal model; Sample size determination; Estimating equations; Regression; Regression analysis; Gee; Confidence interval; Standard error; Econometrics","score_opus":0.2614241119052628,"score_gpt":0.46521650086800426,"score_spread":0.20379238896274143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075875797","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009664784,0.000021206599,0.9971121,0.00018374246,0.0002093813,0.00028711092,0.001014637,0.000015001577,0.00019034906],"genre_scores_gemma":[0.026604865,0.000014815194,0.9728868,0.000045545705,0.00006463599,0.000017346085,0.00033582657,0.000016362517,0.000013778119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985456,0.0001406396,0.00057960115,0.00029105536,0.00024186786,0.00020124218],"domain_scores_gemma":[0.98171276,0.017245162,0.0002493762,0.0006093832,0.00011496739,0.00006837936],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018189527,0.0001348335,0.00045575455,0.000097258846,0.000038237198,0.00000671235,0.00030672882,0.00006015628,0.00007976838],"category_scores_gemma":[0.059819296,0.00009848618,0.000012672582,0.00012756757,0.00022399153,0.000035012206,0.00007628603,0.00012277967,0.0000010989612],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005382543,0.000048882222,0.0007458795,0.0005115875,0.000011411558,0.0000019643057,0.0001405757,0.000010603334,0.000039950577,0.74817,0.00564047,0.24462485],"study_design_scores_gemma":[0.0006681675,0.00028146122,0.0018166068,0.0004155113,0.00006649289,0.0000016992541,0.0000369308,0.19727439,0.00008261072,0.79913926,0.00013050313,0.00008635206],"about_ca_topic_score_codex":0.00017263199,"about_ca_topic_score_gemma":0.000110951056,"teacher_disagreement_score":0.2445385,"about_ca_system_score_codex":0.000021439684,"about_ca_system_score_gemma":0.000029342622,"threshold_uncertainty_score":0.94810027},"labels":[],"label_agreement":null},{"id":"W2078983319","doi":"10.1002/sim.6226","title":"A random set approach to confidence regions with applications to the effective dose with combinations of agents","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Engineering and Physical Sciences Research Council; York University","keywords":"Set (abstract data type); Computer science; Confidence interval; Mathematics; Statistics","score_opus":0.08333612306527494,"score_gpt":0.434442795328112,"score_spread":0.35110667226283704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078983319","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013918841,0.000009352348,0.99240094,0.0009218848,0.000023410266,0.0024459301,0.00020075496,0.000017408373,0.003841126],"genre_scores_gemma":[0.2169066,0.000005737124,0.7814183,0.00034106735,0.000030444931,0.0010963499,0.000024354582,0.000019662231,0.00015743652],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99857676,0.00024684137,0.0003269681,0.00026972417,0.0003787697,0.0002009266],"domain_scores_gemma":[0.9934767,0.005496076,0.00013295231,0.0004568535,0.0002909929,0.00014645397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009448458,0.00015153611,0.00042101886,0.00010688106,0.000102143626,0.000006341062,0.00021387098,0.00002907135,0.000008549551],"category_scores_gemma":[0.0031064968,0.000083271996,0.000010293748,0.00049694406,0.0002919722,0.000021761904,0.000037510967,0.00017932725,0.0000031896334],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015870485,0.00017136245,0.000021267033,0.00009517017,0.00002515151,0.000001647633,0.0026547199,0.0012187836,0.000013882855,0.98806995,0.002734549,0.0048348196],"study_design_scores_gemma":[0.0045093014,0.0010267838,0.00080610014,0.00032692833,0.0001451434,0.000010743626,0.0010363766,0.012703153,0.000023204697,0.97624683,0.0029935786,0.00017182979],"about_ca_topic_score_codex":0.00006410219,"about_ca_topic_score_gemma":0.00017598603,"teacher_disagreement_score":0.21676742,"about_ca_system_score_codex":0.000036011166,"about_ca_system_score_gemma":0.00003221603,"threshold_uncertainty_score":0.3718991},"labels":[],"label_agreement":null},{"id":"W2079160353","doi":"10.1002/sim.1432","title":"Estimating the distribution of lag in the effect of short‐term exposures and interventions: adaptation of a non‐parametric regression spline model","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University; Montreal General Hospital; Institut National de la Recherche Scientifique","funders":"","keywords":"Statistics; Lag; Econometrics; Parametric statistics; Covariate; Regression analysis; Framingham Heart Study; Mathematics; Computer science; Medicine; Framingham Risk Score; Disease; Internal medicine","score_opus":0.25325483171826113,"score_gpt":0.4727333543971716,"score_spread":0.2194785226789105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079160353","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61215365,0.0017130447,0.38482255,0.0004046274,0.00009302122,0.00047050693,0.00024357802,0.0000015293856,0.000097497636],"genre_scores_gemma":[0.9837206,0.00010147477,0.015973315,0.000042456817,0.000020836542,0.00004303443,0.000084171275,0.000006568916,0.000007532656],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99627274,0.00051809475,0.0027965182,0.00016989387,0.00012145253,0.000121322155],"domain_scores_gemma":[0.99474144,0.0035881416,0.0013438764,0.0002464631,0.000056890924,0.000023188775],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019210014,0.00009719289,0.0006491959,0.00025985905,0.00003906343,0.0000047597837,0.00013063259,0.000054677806,0.000015678012],"category_scores_gemma":[0.016900362,0.000068235415,0.00003409159,0.0003572665,0.00018104014,0.00006777018,0.000016307917,0.0001388477,8.612802e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012074022,0.00026316478,0.70848227,0.0075173574,0.000068178844,0.000002851793,0.014318682,0.08544227,0.00004029177,0.17391993,0.0018731927,0.0079510845],"study_design_scores_gemma":[0.0011901441,0.0005490366,0.14505,0.0014468264,0.000023900999,0.0000033508284,0.001342696,0.82852936,0.000025261734,0.021753738,0.000010051681,0.00007565625],"about_ca_topic_score_codex":0.0004910806,"about_ca_topic_score_gemma":0.00014292821,"teacher_disagreement_score":0.74308705,"about_ca_system_score_codex":0.000074146716,"about_ca_system_score_gemma":0.000030958574,"threshold_uncertainty_score":0.9913807},"labels":[],"label_agreement":null},{"id":"W2079566573","doi":"10.1002/sim.2814","title":"Semi‐parametric regression models for cost‐effectiveness analysis: improving the efficiency of estimation from censored data","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; University of Toronto; University of Waterloo","funders":"","keywords":"Estimator; Statistics; Weighting; Covariate; Inverse probability weighting; Contrast (vision); Parametric statistics; Regression; Linear regression; Regression analysis; Mathematics; Variance (accounting); Econometrics; Computer science; Medicine; Artificial intelligence","score_opus":0.3306744055215149,"score_gpt":0.49142923597086385,"score_spread":0.16075483044934896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079566573","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056693356,0.0017884186,0.93585676,0.0006707608,0.00038755545,0.0011564029,0.0033110327,0.000012753575,0.00012292835],"genre_scores_gemma":[0.9168417,0.00007339407,0.08105535,0.00040621657,0.00014282676,0.00005164796,0.001389534,0.00001892392,0.000020422582],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99551535,0.00028161932,0.0031762978,0.0005446553,0.00017689391,0.0003051602],"domain_scores_gemma":[0.98254913,0.014142003,0.0021390836,0.0009459053,0.0001403871,0.00008346119],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037129268,0.00015414179,0.0010427502,0.00081031886,0.00011655466,0.000017981385,0.00050154375,0.00010559031,0.000048786325],"category_scores_gemma":[0.025263488,0.00013294506,0.000041762498,0.0010559643,0.00013485324,0.00021397289,0.00007785528,0.00016595496,0.000010273883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006961842,0.0006947692,0.09297677,0.0032466373,0.0012397884,0.0000087455,0.016038252,0.28003833,0.00011987358,0.5467682,0.01556987,0.04260261],"study_design_scores_gemma":[0.0010907357,0.0000748924,0.035789333,0.00015794951,0.000101824255,3.2038415e-7,0.0010994043,0.8982298,0.000016512955,0.0631902,0.00012609687,0.0001229842],"about_ca_topic_score_codex":0.0036379735,"about_ca_topic_score_gemma":0.00067839806,"teacher_disagreement_score":0.8601483,"about_ca_system_score_codex":0.0003165697,"about_ca_system_score_gemma":0.00008120933,"threshold_uncertainty_score":0.991478},"labels":[],"label_agreement":null},{"id":"W2080813654","doi":"10.1002/sim.1173","title":"Number needed to treat (NNT): estimation of a measure of clinical benefit","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; McMaster University Medical Centre","funders":"","keywords":"Number needed to treat; Estimator; Context (archaeology); Event (particle physics); Medicine; Randomized controlled trial; Statistics; Absolute risk reduction; Clinical trial; Confidence interval; Econometrics; Computer science; Relative risk; Mathematics; Surgery; Internal medicine","score_opus":0.5337564789862494,"score_gpt":0.6268482031556304,"score_spread":0.09309172416938094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080813654","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06820636,0.000021188838,0.9210532,0.00080205913,0.0006724323,0.00065457314,0.00030631034,0.000028865916,0.008255048],"genre_scores_gemma":[0.12834954,0.00006515127,0.8707464,0.00023955504,0.00024316323,0.000020547426,0.000009351901,0.000032849523,0.00029349502],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944819,0.0006243607,0.0033712965,0.00035987096,0.00087302265,0.00028950477],"domain_scores_gemma":[0.93778205,0.060258504,0.0007058089,0.0005626336,0.00046456093,0.00022644973],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0074099563,0.00021892549,0.0017384215,0.00015265544,0.00002111141,0.000003589773,0.0002843479,0.0002194473,0.0013720412],"category_scores_gemma":[0.32151693,0.00017308877,0.00008068218,0.0006172201,0.00043984657,0.000029779203,0.00007016233,0.00034605057,0.000025170832],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013664386,0.00082867086,0.011011326,0.0007196868,0.00009719249,0.00008179738,0.0009967112,0.0001443285,0.00020684033,0.671365,0.02851841,0.28466356],"study_design_scores_gemma":[0.0034352574,0.00073754723,0.006223049,0.00079359947,0.00022560105,0.000008316575,0.00024339609,0.0025485596,0.00027404493,0.9852033,0.00014241395,0.00016486985],"about_ca_topic_score_codex":0.0002703744,"about_ca_topic_score_gemma":0.00007236811,"teacher_disagreement_score":0.31410697,"about_ca_system_score_codex":0.000043140764,"about_ca_system_score_gemma":0.000074960626,"threshold_uncertainty_score":0.99954087},"labels":[],"label_agreement":null},{"id":"W2082625612","doi":"10.1002/sim.4037","title":"Bayesian sample size for diagnostic test studies in the absence of a gold standard: Comparing identifiable with non‐identifiable models","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Royal Victoria Regional Health Centre; McGill University; Royal Victoria Hospital","funders":"","keywords":"Sample size determination; Statistics; Sample (material); Bayesian probability; Conditional independence; Imperfect; Statistical hypothesis testing; Computer science; Gold standard (test); Econometrics; Independence (probability theory); Mathematics","score_opus":0.08947318568387154,"score_gpt":0.4160162086473315,"score_spread":0.32654302296346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082625612","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007194413,0.00007757562,0.9899122,0.0001525723,0.00031740646,0.0009278474,0.0006919765,0.000014633104,0.0007113433],"genre_scores_gemma":[0.40484506,0.00005594873,0.5947817,0.000043435175,0.00005675932,0.00013736896,0.000008135098,0.000019883204,0.00005169783],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99765474,0.00010845049,0.00087165996,0.00035061644,0.00058483746,0.00042971462],"domain_scores_gemma":[0.88420665,0.114569336,0.00028634642,0.00048653435,0.00037873074,0.00007241495],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028030653,0.00024390522,0.00086640095,0.00012973872,0.000086188746,0.000032850206,0.00040911202,0.00006729601,0.00007802477],"category_scores_gemma":[0.10215003,0.00015469322,0.000023312628,0.00045045276,0.00079446594,0.00009486767,0.00006151438,0.0004399586,7.8173923e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001528205,0.00033371925,0.020323161,0.0025491938,0.00006943479,0.00010647025,0.00771284,0.00015312611,0.00067433895,0.95182693,0.012613129,0.0034848512],"study_design_scores_gemma":[0.0015238149,0.00041728292,0.00223842,0.0012100028,0.000086967695,0.000009847289,0.0027231742,0.029576097,0.00012594946,0.9618559,0.00004733671,0.00018523836],"about_ca_topic_score_codex":0.0007066618,"about_ca_topic_score_gemma":0.0047057644,"teacher_disagreement_score":0.39765063,"about_ca_system_score_codex":0.00004703674,"about_ca_system_score_gemma":0.00009833584,"threshold_uncertainty_score":0.9054129},"labels":[],"label_agreement":null},{"id":"W2083675429","doi":"10.1002/1097-0258(20000730)19:14<1952::aid-sim474>3.0.co;2-k","title":"The theory of dispersion models. Bent J�rgensen, Chapman and Hall, 1997. No. of pages: 237. Price: �39.95. ISBN 0-412-99718-8","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Citation; Library science; Mathematical economics; Statistics; Computer science; Mathematics","score_opus":0.04923718532831025,"score_gpt":0.3494584815210401,"score_spread":0.30022129619272986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083675429","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006046193,0.0018407686,0.98061275,0.00046176114,0.00022867024,0.00048645056,0.0004871906,0.000020227035,0.009815981],"genre_scores_gemma":[0.18026401,0.015508408,0.80270135,0.00016944247,0.00017212372,0.00002045207,0.000041033443,0.000055034063,0.0010681184],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997753,0.00032530777,0.000819206,0.00027211604,0.00051735353,0.00031300413],"domain_scores_gemma":[0.9927993,0.0061982777,0.00025333208,0.00042809764,0.0002037208,0.0001173141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018021935,0.000215669,0.000576971,0.000067290624,0.000097950666,0.000008865804,0.00024655685,0.00009114301,0.00072587805],"category_scores_gemma":[0.0035554026,0.00013265024,0.000028882385,0.0001919099,0.00089353486,0.00004139881,0.000064362495,0.00026758513,0.000005516183],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015755027,0.00010580794,0.00009985165,0.0004017091,0.000033480163,0.000015448075,0.0017506614,0.0000030674637,0.00018635622,0.8632504,0.0071303295,0.12686534],"study_design_scores_gemma":[0.00078584417,0.00043544962,0.0012291681,0.0004948842,0.00008615968,0.000006001167,0.0007595501,0.014961974,0.0000870322,0.980174,0.0008353006,0.0001446278],"about_ca_topic_score_codex":0.00007663918,"about_ca_topic_score_gemma":0.00003554625,"teacher_disagreement_score":0.17791139,"about_ca_system_score_codex":0.000029451337,"about_ca_system_score_gemma":0.000042050724,"threshold_uncertainty_score":0.79478556},"labels":[],"label_agreement":null},{"id":"W2084292194","doi":"10.1002/sim.2731","title":"Developments in cluster randomized trials and <i>Statistics in Medicine</i>","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":248,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Royal Society","keywords":"Sample size determination; Medical statistics; Statistics; Cluster (spacecraft); Cluster analysis; Randomized controlled trial; Computer science; Population; Psychological intervention; Research design; Medicine; Econometrics; Data science; Mathematics; Surgery","score_opus":0.08618382227126765,"score_gpt":0.4329159356107219,"score_spread":0.34673211333945425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2084292194","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008020336,0.0004212901,0.98914313,0.000768577,0.00043565067,0.0012108859,0.00024155476,0.000022127515,0.006954772],"genre_scores_gemma":[0.024283325,0.00045872948,0.9740484,0.0005040952,0.00020709845,0.00012812296,0.00009529198,0.000039754614,0.00023517887],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99309736,0.0021539142,0.0030739282,0.00048602698,0.0006442686,0.0005445118],"domain_scores_gemma":[0.9511223,0.04789391,0.00048181874,0.0002482797,0.00013028666,0.00012341773],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.013721334,0.00038075968,0.0030015411,0.0005611365,0.000041908068,0.000018693812,0.00019403426,0.00016986503,0.00035048212],"category_scores_gemma":[0.07601936,0.00027142747,0.000025042618,0.000527877,0.00090227264,0.000051694973,0.00007354252,0.000502421,0.000005772247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028097432,0.00011369965,0.0033227974,0.00035149354,0.000022046182,0.0003077955,0.0010012491,0.000001884221,0.000044213273,0.94585544,0.019915145,0.026254522],"study_design_scores_gemma":[0.08762998,0.000093529314,0.0062975483,0.0010184787,0.00009503439,0.000012472359,0.0002116868,0.002544212,0.000010938461,0.901451,0.00036814148,0.0002669675],"about_ca_topic_score_codex":0.0016576516,"about_ca_topic_score_gemma":0.0026428448,"teacher_disagreement_score":0.08482024,"about_ca_system_score_codex":0.0001355855,"about_ca_system_score_gemma":0.00010388676,"threshold_uncertainty_score":0.9999738},"labels":[],"label_agreement":null},{"id":"W2085249160","doi":"10.1002/sim.3448","title":"Statistical issues in the design and analysis of expertise‐based randomized clinical trials","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Hip disorders and treatments","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Randomized controlled trial; Research design; Confounding; Medicine; Clinical study design; Medical physics; Intervention (counseling); Completely randomized design; Computer science; Randomized experiment; Clinical trial; Physical therapy; Statistics; Surgery; Mathematics; Nursing","score_opus":0.17718784971561388,"score_gpt":0.5005786867762901,"score_spread":0.3233908370606763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085249160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.065931745,0.0032258662,0.9257994,0.0025256253,0.000101867445,0.001912555,0.00014165224,0.000010655737,0.0003506033],"genre_scores_gemma":[0.9174888,0.0028877018,0.07850777,0.0007052438,0.000044434582,0.00007893395,0.00022092443,0.000010907701,0.00005524329],"study_design_codex":"observational","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99386185,0.003652664,0.0016097162,0.00024406896,0.0004530073,0.00017868339],"domain_scores_gemma":[0.97639704,0.022955913,0.00023137381,0.00024792025,0.0000757207,0.000092063674],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011201701,0.00015324863,0.002501603,0.00040747374,0.000031579126,0.0000028153756,0.00007017681,0.00008124916,0.0003238473],"category_scores_gemma":[0.024431748,0.00008022321,0.000092036906,0.00057639607,0.001036557,0.000013211439,0.000009285702,0.0001981821,0.0000016497548],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.13789207,0.0041905874,0.7187226,0.0002949485,0.005145303,0.004917753,0.020200003,0.0002860804,0.00007247384,0.022638671,0.026176753,0.059462767],"study_design_scores_gemma":[0.41955775,0.0018675628,0.41177425,0.00030059033,0.008205886,0.000023668772,0.0011980408,0.14984065,0.000021440406,0.0067619784,0.00023037604,0.00021782066],"about_ca_topic_score_codex":0.0005622379,"about_ca_topic_score_gemma":0.00008151278,"teacher_disagreement_score":0.8515571,"about_ca_system_score_codex":0.000022135382,"about_ca_system_score_gemma":0.000099699486,"threshold_uncertainty_score":0.98378587},"labels":[],"label_agreement":null},{"id":"W2087047720","doi":"10.1002/(sici)1097-0258(20000315)19:5<715::aid-sim342>3.0.co;2-t","title":"GEE Analysis of negatively correlated binary responses: a caution","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Royal Victoria Hospital","funders":"National Cancer Institute","keywords":"Generalized estimating equation; Bounding overwatch; Binary number; Independence (probability theory); Statistics; Correlation; Binary data; Gee; Mathematics; Binomial (polynomial); Negative binomial distribution; Applied mathematics; Econometrics; Computer science","score_opus":0.05795689346548086,"score_gpt":0.41620766905050866,"score_spread":0.3582507755850278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087047720","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045852005,0.00006383541,0.9487332,0.00021549367,0.00009130411,0.00019238547,0.00062366755,0.000028174607,0.0041998993],"genre_scores_gemma":[0.22254165,0.0001384819,0.7761842,0.0001179568,0.00003582619,0.0000136219915,0.00007672604,0.000016698403,0.0008748381],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99802554,0.00041783132,0.0007406859,0.00023470128,0.0003653963,0.00021585246],"domain_scores_gemma":[0.993623,0.005694549,0.00017983429,0.00027754344,0.00014258116,0.00008247302],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010203222,0.00015128784,0.0006829585,0.00047676236,0.000039747698,0.0000044178696,0.00013613584,0.00008703453,0.0061176256],"category_scores_gemma":[0.006635668,0.00012099672,0.000036452828,0.0015914803,0.0003987502,0.000029706473,0.000016374433,0.00022802917,0.000010732108],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060199253,0.00024466257,0.0039056628,0.00015599577,0.00049272995,0.00020588895,0.0034101047,0.000045126508,0.00055079587,0.8989071,0.008567459,0.082912475],"study_design_scores_gemma":[0.0010175993,0.00050592766,0.08856768,0.00027399955,0.0012333182,0.000004854685,0.00028244845,0.056109536,0.000040084346,0.85154694,0.00023137254,0.00018621507],"about_ca_topic_score_codex":0.00029403108,"about_ca_topic_score_gemma":0.00010547603,"teacher_disagreement_score":0.17668964,"about_ca_system_score_codex":0.000056341305,"about_ca_system_score_gemma":0.000061509454,"threshold_uncertainty_score":0.9947909},"labels":[],"label_agreement":null},{"id":"W2087811140","doi":"10.1002/sim.3830","title":"A copula‐based mixed Poisson model for bivariate recurrent events under event‐dependent censoring","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; GlaxoSmithKline","keywords":"Bivariate analysis; Copula (linguistics); Censoring (clinical trials); Estimator; Econometrics; Poisson distribution; Statistics; Marginal model; Random effects model; Marginal distribution; Negative binomial distribution; Parametric statistics; Mathematics; Regression analysis; Random variable; Medicine; Internal medicine; Meta-analysis","score_opus":0.1449655822639636,"score_gpt":0.4545331163864958,"score_spread":0.3095675341225322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087811140","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009290518,0.000021139995,0.986948,0.0005632183,0.0015469497,0.00064934854,0.0006986135,0.000042685522,0.000239504],"genre_scores_gemma":[0.34314948,0.000010786496,0.65614676,0.00014941796,0.00013738322,0.00009017874,0.000058263093,0.000037518235,0.00022020037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976195,0.00013697699,0.00080059,0.00041002,0.0005469306,0.00048596243],"domain_scores_gemma":[0.99531674,0.0035752056,0.00024672085,0.0004183635,0.00024227038,0.00020068424],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016732046,0.00027168158,0.00055462617,0.00016692978,0.00009007124,0.00001251844,0.0002561322,0.00013614603,0.0002710623],"category_scores_gemma":[0.010403291,0.00022413726,0.000040738392,0.00016346798,0.00011830964,0.000029901465,0.000051401676,0.0005314773,0.000006771878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014070555,0.00024828414,0.0002187638,0.0003411558,0.00002551729,0.000010972602,0.00037803838,0.00029818222,0.0016535091,0.97835624,0.0023579728,0.01597065],"study_design_scores_gemma":[0.0015967966,0.00016350152,0.0008933373,0.00019262217,0.000059727507,0.0000017009323,0.00006131391,0.4086372,0.00011866016,0.5880549,0.000058259982,0.00016198016],"about_ca_topic_score_codex":0.00008007144,"about_ca_topic_score_gemma":0.00035378578,"teacher_disagreement_score":0.40833902,"about_ca_system_score_codex":0.00009266226,"about_ca_system_score_gemma":0.00011214096,"threshold_uncertainty_score":0.9979325},"labels":[],"label_agreement":null},{"id":"W2089365578","doi":"10.1002/sim.3295","title":"The power of testing a semi‐parametric shared gamma frailty parameter in failure time data","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Estimator; Nonparametric statistics; Statistics; Parametric statistics; Mathematics; Hazard; Power (physics); Parametric model; Function (biology); Econometrics; Computer science; Physics","score_opus":0.08350817376501589,"score_gpt":0.3597535548972013,"score_spread":0.2762453811321854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089365578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8778318,0.0031457543,0.0140637485,0.0059075356,0.0019332558,0.003837418,0.0020282187,0.00018407748,0.09106815],"genre_scores_gemma":[0.9787295,0.00033553664,0.020051816,0.00016386561,0.000104722436,0.000018829405,0.00008940621,0.000015956719,0.0004903524],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99721044,0.0003530704,0.00065222365,0.0003600688,0.00096581026,0.00045839386],"domain_scores_gemma":[0.99520475,0.0035429979,0.00025541338,0.0007377979,0.00017965713,0.00007940835],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030566377,0.0001500875,0.00035838134,0.00033977468,0.00025381596,0.000021213331,0.0009496171,0.000081927166,0.00024213865],"category_scores_gemma":[0.015714891,0.0001132352,0.00001887644,0.0022354617,0.0013103363,0.00012585457,0.00018888348,0.00033508305,0.000020596728],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056025663,0.00024479153,0.8111066,0.00009915279,0.00007881761,0.00039606087,0.016524693,0.000095883406,0.000037804297,0.01620408,0.1379776,0.017178454],"study_design_scores_gemma":[0.0015949043,0.00025693947,0.928954,0.00029699787,0.000059584916,0.000004905181,0.0060746097,0.0072141257,0.0000034566567,0.020417053,0.03474712,0.0003762716],"about_ca_topic_score_codex":0.0059862533,"about_ca_topic_score_gemma":0.007903607,"teacher_disagreement_score":0.11784739,"about_ca_system_score_codex":0.00008862866,"about_ca_system_score_gemma":0.00012928122,"threshold_uncertainty_score":0.9925762},"labels":[],"label_agreement":null},{"id":"W2089415104","doi":"10.1002/sim.1687","title":"Inflation of the type I error rate when a continuous confounding variable is categorized in logistic regression analyses","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":248,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Confounding; Statistics; Categorical variable; Type I and type II errors; Logistic regression; Mathematics; Inflation (cosmology); Sample size determination; Econometrics; Variable (mathematics); Regression analysis","score_opus":0.5624346742081207,"score_gpt":0.6001798666323802,"score_spread":0.037745192424259555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089415104","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029097944,0.00013634084,0.96289057,0.0012509488,0.0020454063,0.0011871739,0.00019653847,0.000039158545,0.0031559404],"genre_scores_gemma":[0.32353976,0.000047576654,0.67574507,0.0002629384,0.00012399018,0.000015802114,0.00000951733,0.000026209096,0.00022912295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99638414,0.0009272852,0.0015951133,0.00030818328,0.0004924686,0.0002928249],"domain_scores_gemma":[0.97070897,0.027735071,0.00070214516,0.000486944,0.00029503801,0.000071861425],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0047478164,0.00020883449,0.0010236447,0.00018084003,0.000049782313,0.000010818799,0.00029685095,0.00016430931,0.0005797995],"category_scores_gemma":[0.22493549,0.00012903995,0.000034233548,0.0007293968,0.0005066833,0.000038071492,0.00008817995,0.0004530701,0.0000058590203],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00060708635,0.00026026522,0.004528323,0.00062082143,0.00009215776,0.000075152064,0.0036297007,0.00042334676,0.008536065,0.975642,0.0033447503,0.0022403342],"study_design_scores_gemma":[0.0037563362,0.00020834288,0.003439062,0.0012531028,0.00015880747,0.0000025250936,0.00036992726,0.0017775685,0.00053911353,0.9882916,0.00007056141,0.00013301738],"about_ca_topic_score_codex":0.0006772228,"about_ca_topic_score_gemma":0.00013842386,"teacher_disagreement_score":0.29444182,"about_ca_system_score_codex":0.00017446566,"about_ca_system_score_gemma":0.00019862801,"threshold_uncertainty_score":0.7815932},"labels":[],"label_agreement":null},{"id":"W2090906954","doi":"10.1002/sim.2791","title":"A likelihood approach to estimating sensitivity and specificity for binocular data: application in ophthalmology","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Alexandra Hospital; University of Alberta; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; University of Calgary","keywords":"Sensitivity (control systems); Extension (predicate logic); Maximum likelihood; Computer science; Statistics; Binary data; Optometry; Mathematics; Artificial intelligence; Binary number; Medicine","score_opus":0.11626529237192867,"score_gpt":0.4428071937723671,"score_spread":0.32654190140043843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090906954","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061218906,0.000027718306,0.9915502,0.00013248155,0.000112310394,0.0008316587,0.00030278848,0.000015440688,0.0009055294],"genre_scores_gemma":[0.10846519,0.000003327132,0.89114636,0.000070533235,0.00015938022,0.000036015044,0.00009757347,0.000016814485,0.0000048272914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982457,0.00013978878,0.00056497107,0.00048722123,0.00020071508,0.00036160304],"domain_scores_gemma":[0.9927882,0.006465942,0.0001129837,0.00041825869,0.000087384076,0.0001272498],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005429704,0.00015499309,0.0004623924,0.00018218701,0.00004498831,0.000009819403,0.00014252731,0.00008688147,0.000007288594],"category_scores_gemma":[0.012196035,0.00013738772,0.000006705839,0.00029566264,0.00015404532,0.00003691409,0.00011328039,0.00021389748,0.0000014170321],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009686784,0.00022183885,0.005303003,0.0005238875,0.00001040308,0.00011579834,0.00082001154,0.000006453326,0.00069277734,0.8167497,0.00075481663,0.17470442],"study_design_scores_gemma":[0.00076951727,0.00014825836,0.018887784,0.00011746241,0.000026733562,0.00007352378,0.00032444228,0.15970267,0.000035550453,0.819668,0.000080065634,0.00016597066],"about_ca_topic_score_codex":0.00025780813,"about_ca_topic_score_gemma":0.00025610765,"teacher_disagreement_score":0.17453845,"about_ca_system_score_codex":0.00005682944,"about_ca_system_score_gemma":0.00002681041,"threshold_uncertainty_score":0.9961247},"labels":[],"label_agreement":null},{"id":"W2091019309","doi":"10.1002/sim.5466","title":"Sample size formulas for estimating intraclass correlation coefficients with precision and assurance","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":467,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Intraclass correlation; Confidence interval; Reliability (semiconductor); Sample size determination; Statistics; Interval (graph theory); Mathematics; Coverage probability; Limit (mathematics); Interval estimation; Sample (material); Correlation coefficient; Correlation; Computer science; Reproducibility; Power (physics); Mathematical analysis; Combinatorics; Physics","score_opus":0.0854428886232476,"score_gpt":0.3958068923931848,"score_spread":0.31036400376993717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091019309","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03243521,0.00010128357,0.9651323,0.00061456853,0.00073737855,0.00061404746,0.00008665168,0.000010270444,0.00026826697],"genre_scores_gemma":[0.5394728,0.000008728366,0.46020034,0.00008952562,0.00010990037,0.00002323863,0.00001157251,0.000005826205,0.000078045574],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727046,0.000117423035,0.00066958315,0.00029017255,0.0013546677,0.00029768917],"domain_scores_gemma":[0.97717905,0.021839257,0.00025683033,0.00025805025,0.000351443,0.00011536452],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00701403,0.00012944343,0.00029271565,0.000097374934,0.0001445583,0.00004037315,0.0001777118,0.000048677823,0.00011377545],"category_scores_gemma":[0.058951147,0.00007927259,0.000011404964,0.00031914256,0.00018170373,0.00019465249,0.00003749401,0.000128265,0.000007101997],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049228786,0.00032291983,0.44257334,0.00016265754,0.000023073188,0.0000023071145,0.005014019,0.020674469,0.000284349,0.026756644,0.020592978,0.48310095],"study_design_scores_gemma":[0.003485309,0.00095118873,0.21504311,0.0005213569,0.000050617444,0.000006225203,0.0012084448,0.5956204,0.00005170642,0.17636253,0.0064261793,0.00027295997],"about_ca_topic_score_codex":0.00003909961,"about_ca_topic_score_gemma":0.000076827804,"teacher_disagreement_score":0.5749459,"about_ca_system_score_codex":0.000064033564,"about_ca_system_score_gemma":0.000031253658,"threshold_uncertainty_score":0.9489757},"labels":[],"label_agreement":null},{"id":"W2091501852","doi":"10.1002/sim.3289","title":"Interval estimation of risk difference for data sampled from clusters","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Statistics; Confidence interval; Mathematics; Cluster (spacecraft); Variance (accounting); Cluster sampling; Sample size determination; Coverage probability; Interval estimation; Sampling (signal processing); Computer science; Econometrics; Population; Demography","score_opus":0.16970249555560965,"score_gpt":0.4414141727607394,"score_spread":0.2717116772051298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091501852","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010094245,0.000039210845,0.9826541,0.000077208584,0.00025711954,0.00028063424,0.006487615,0.000017088963,0.00009277255],"genre_scores_gemma":[0.1294167,0.0000755455,0.8697831,0.00003804291,0.00007690081,0.000013566185,0.00056844275,0.000014915598,0.000012787071],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99837226,0.0001643196,0.0006917291,0.00029596596,0.00028991315,0.00018584022],"domain_scores_gemma":[0.9826092,0.01633315,0.00029935798,0.00057950773,0.00011000951,0.00006876553],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00071155804,0.0001447792,0.0005360255,0.00008555921,0.000051574,0.000004012985,0.00038717507,0.00005982725,0.00019084543],"category_scores_gemma":[0.03650795,0.000113748974,0.000015142871,0.00012409917,0.0003632413,0.000038992017,0.0001054483,0.00017460439,0.0000017168628],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032472223,0.00022847053,0.007379448,0.00045719833,0.00008124366,0.000030979205,0.0048231487,0.00001051513,0.00013753529,0.57492274,0.01699463,0.3946094],"study_design_scores_gemma":[0.0010380936,0.0001461364,0.017322343,0.00022799766,0.000082004975,0.0000022381782,0.00012612226,0.21312651,0.000029867651,0.767779,0.000025312256,0.00009436348],"about_ca_topic_score_codex":0.00090428116,"about_ca_topic_score_gemma":0.00026593346,"teacher_disagreement_score":0.39451504,"about_ca_system_score_codex":0.000027984035,"about_ca_system_score_gemma":0.00004888844,"threshold_uncertainty_score":0.971608},"labels":[],"label_agreement":null},{"id":"W2092848201","doi":"10.1002/sim.2680","title":"Modelling smoking history using a comprehensive smoking index: application to lung cancer","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Smoking Behavior and Cessation","field":"Medicine","cited_by":139,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Montreal General Hospital; Université de Montréal; McGill University; Queen's University","funders":"","keywords":"Lung cancer; Statistics; Smoking history; Covariate; Econometrics; Regression analysis; Medicine; Index (typography); Demography; Computer science; Mathematics; Oncology; Internal medicine","score_opus":0.05194383189967641,"score_gpt":0.3575085325930135,"score_spread":0.3055647006933371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092848201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38447538,0.0006874887,0.61333394,0.00015178489,0.00045472066,0.00041562997,0.000017351758,0.000042659707,0.00042100676],"genre_scores_gemma":[0.99091876,0.000046391368,0.0074810158,0.0005932321,0.00057306915,0.000075645235,0.00015037255,0.000044389504,0.00011714098],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998184,0.000037426773,0.00050536764,0.0003623012,0.0006049979,0.0003058597],"domain_scores_gemma":[0.9990836,0.00011751579,0.00016696731,0.00026008597,0.00026962068,0.000102247504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002585605,0.00019504389,0.00039217676,0.00040677813,0.00007306112,0.000006624313,0.00008125422,0.00011643086,0.00015782211],"category_scores_gemma":[0.00004734908,0.00019311877,0.000023011424,0.00034237147,0.00009925691,0.000050559724,0.000027531441,0.00035730144,5.7075044e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013525004,0.000108947446,0.72648215,0.0003381424,0.000040792784,0.00009986271,0.0019818062,0.24734867,0.0058022663,0.0040655322,0.0059941006,0.0076024556],"study_design_scores_gemma":[0.002738719,0.00009747292,0.2137201,0.0013582535,0.0004986178,0.000030280396,0.00042495114,0.7748002,0.00016932424,0.0013393029,0.0044734497,0.0003493694],"about_ca_topic_score_codex":0.013966669,"about_ca_topic_score_gemma":0.00016866592,"teacher_disagreement_score":0.60644335,"about_ca_system_score_codex":0.0018760195,"about_ca_system_score_gemma":0.00015014617,"threshold_uncertainty_score":0.9925994},"labels":[],"label_agreement":null},{"id":"W2095752327","doi":"10.1002/(sici)1097-0258(20000315)19:5<723::aid-sim379>3.0.co;2-a","title":"Interval estimation for Cohen's kappa as a measure of agreement","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":217,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Confidence interval; Statistics; Mathematics; Measure (data warehouse); Kappa; Statistic; Variance (accounting); Delta method; Coverage probability; Asymptotic analysis; Computation; Asymptotic distribution; Cohen's kappa; Applied mathematics; Computer science; Algorithm","score_opus":0.11948518704376823,"score_gpt":0.4260948892710158,"score_spread":0.3066097022272476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095752327","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09164632,0.00033246726,0.87748086,0.0059719835,0.0009288197,0.0017594662,0.00026011167,0.000020903772,0.021599073],"genre_scores_gemma":[0.934467,0.000054860157,0.062390182,0.0004828379,0.0001126822,0.00006699333,0.00004351584,0.00000935096,0.0023725657],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958637,0.00018771716,0.0012035646,0.0003503025,0.0021770194,0.00021769441],"domain_scores_gemma":[0.9970811,0.001633237,0.00023951916,0.00044417116,0.0005190375,0.00008291486],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007252351,0.00013812908,0.00043697792,0.00018062303,0.00005625889,0.0000204042,0.00043934936,0.000052849133,0.006227912],"category_scores_gemma":[0.008945916,0.000094976735,0.00004560084,0.00037748177,0.00024921555,0.000073867865,0.000025884367,0.000116392934,0.00011006977],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004506093,0.0003054597,0.0033102415,0.000110227964,0.000039016802,0.00000870051,0.0032759362,0.004834862,0.00050358963,0.027285425,0.09017988,0.869696],"study_design_scores_gemma":[0.0042837616,0.002271252,0.015318377,0.0006632088,0.00008327864,0.000004389221,0.0020945803,0.08427042,0.00056159747,0.8536577,0.03650804,0.00028335804],"about_ca_topic_score_codex":0.00014507158,"about_ca_topic_score_gemma":0.0001421121,"teacher_disagreement_score":0.8694127,"about_ca_system_score_codex":0.00007963402,"about_ca_system_score_gemma":0.00007118362,"threshold_uncertainty_score":0.99940217},"labels":[],"label_agreement":null},{"id":"W2095973044","doi":"10.1002/(sici)1097-0258(20000415)19:7<975::aid-sim381>3.0.co;2-9","title":"A robust mixed linear model analysis for longitudinal data","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Okanagan University College; Okanagan College","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; McMaster University","keywords":"Random effects model; Mixed model; Generalized linear mixed model; Autocorrelation; Bayesian probability; Longitudinal data; Computer science; Statistics; Linear model; Econometrics; Linear regression; Robust regression; Subject (documents); Mathematics; Data mining; Medicine","score_opus":0.3914669943620445,"score_gpt":0.473223682916968,"score_spread":0.08175668855492346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095973044","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014269665,0.000049778075,0.9933729,0.00027132503,0.00008241545,0.00026309644,0.0030366248,0.000028200022,0.0014686739],"genre_scores_gemma":[0.024275161,0.000082478924,0.97386557,0.000121523204,0.00015389803,0.00002894076,0.0005435876,0.000023261557,0.0009055947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981184,0.00009116212,0.0006371672,0.00047635922,0.00034742386,0.0003295139],"domain_scores_gemma":[0.9948667,0.003909335,0.00010042399,0.0008587729,0.00013982113,0.0001249279],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014833233,0.00018403147,0.0006511802,0.00017371571,0.00006494428,0.000010973531,0.00044898028,0.000073116935,0.0019477345],"category_scores_gemma":[0.00834349,0.00014573132,0.00003087441,0.00053771713,0.00020513327,0.00004321222,0.00006303677,0.00019812096,0.000009502471],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020343688,0.000263595,0.0024541516,0.00032557355,0.00045289198,0.000051493775,0.00055998453,0.00926734,0.000016283317,0.8687808,0.046586987,0.07103747],"study_design_scores_gemma":[0.000544034,0.00008664198,0.0011872472,0.000040144114,0.0005037255,0.0000012258831,0.000038479448,0.63212305,0.0000020887312,0.36512688,0.00023793949,0.000108542656],"about_ca_topic_score_codex":0.00012221346,"about_ca_topic_score_gemma":0.00039411095,"teacher_disagreement_score":0.6228557,"about_ca_system_score_codex":0.000033847347,"about_ca_system_score_gemma":0.000055445922,"threshold_uncertainty_score":0.9989646},"labels":[],"label_agreement":null},{"id":"W2096521417","doi":"10.1002/sim.5317","title":"A simulation study of finite‐sample properties of marginal structural Cox proportional hazards models","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Center for Research Resources; National Institute of Allergy and Infectious Diseases; National Institute on Alcohol Abuse and Alcoholism; National Institutes of Health","keywords":"Statistics; Confidence interval; Hazard ratio; Proportional hazards model; Mathematics; Estimator; Standard error; Confounding; Mean squared error; Sample size determination; Marginal structural model; Range (aeronautics); Nominal level; Econometrics; Coverage probability","score_opus":0.21699590011067962,"score_gpt":0.45071684087391395,"score_spread":0.23372094076323432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096521417","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4085655,0.000049099646,0.59065837,0.000012418085,0.000055276607,0.00047961037,0.00008834166,0.000024905958,0.00006650207],"genre_scores_gemma":[0.82216924,0.000004252023,0.17768885,0.000007164631,0.000049037928,0.000027010004,0.000022690641,0.000014106466,0.000017648052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99833757,0.00008501991,0.000710599,0.000116992174,0.00055032305,0.00019951613],"domain_scores_gemma":[0.9975891,0.0014382387,0.0003585074,0.00021311564,0.0003545136,0.00004650373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059786544,0.00013547846,0.0004070235,0.00014951994,0.000025686386,0.000001797671,0.00010668556,0.000046646637,0.000112233756],"category_scores_gemma":[0.0051361076,0.0000993599,0.000012077731,0.00016152894,0.00022588122,0.00015154984,0.00004409122,0.00015177645,2.6655553e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005281237,0.001576764,0.050929185,0.0015612482,0.00012122496,0.000009911147,0.034704532,0.074315846,0.0033268405,0.8270581,0.00029434153,0.0055739232],"study_design_scores_gemma":[0.0009514368,0.0008623108,0.0033882866,0.000276641,0.000067369925,0.0000013370537,0.002478516,0.2209786,0.0009929349,0.7698551,0.000005691521,0.00014180924],"about_ca_topic_score_codex":0.00018932018,"about_ca_topic_score_gemma":0.000065829765,"teacher_disagreement_score":0.41360372,"about_ca_system_score_codex":0.00005561445,"about_ca_system_score_gemma":0.00005091401,"threshold_uncertainty_score":0.61487716},"labels":[],"label_agreement":null},{"id":"W2096649070","doi":"10.1002/sim.3387","title":"Bivariate modeling of interobserver agreement coefficients","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bivariate analysis; Anxiety; Outcome (game theory); Trait; Psychology; Statistics; Depression (economics); Clinical psychology; Medicine; Psychiatry; Mathematics; Computer science","score_opus":0.2636804934739743,"score_gpt":0.41067999707973896,"score_spread":0.14699950360576464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096649070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2562768,0.00014396648,0.7381275,0.00053375424,0.00079823186,0.00026093132,0.00004384974,0.000007953743,0.003807012],"genre_scores_gemma":[0.98481953,0.00010700493,0.014295311,0.00020606845,0.000055735276,0.000006116722,0.000010557031,0.0000060429,0.0004936606],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951486,0.00022310561,0.0014185057,0.0003845095,0.0025781605,0.0002471381],"domain_scores_gemma":[0.99780047,0.00072645344,0.00025080977,0.00056390726,0.0005689121,0.00008946227],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0053847698,0.0001389238,0.00044916346,0.00029184166,0.00007451432,0.000008749466,0.00059224485,0.000044746106,0.0012153013],"category_scores_gemma":[0.005526881,0.00009320396,0.00003546298,0.0006102101,0.00030098358,0.00006446388,0.00012241516,0.00016654002,0.00007196934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005473346,0.0021188394,0.28653452,0.00023853712,0.0001483354,0.00029726865,0.026290126,0.459126,0.0035042919,0.059830327,0.112770505,0.04859392],"study_design_scores_gemma":[0.0036221629,0.0008715349,0.04007524,0.00049408793,0.000036468948,0.000008516381,0.0024116375,0.80993825,0.0001914076,0.13907543,0.0029443402,0.00033094067],"about_ca_topic_score_codex":0.00030912846,"about_ca_topic_score_gemma":0.00010183453,"teacher_disagreement_score":0.7285427,"about_ca_system_score_codex":0.00007322352,"about_ca_system_score_gemma":0.00005767747,"threshold_uncertainty_score":0.99969774},"labels":[],"label_agreement":null},{"id":"W2096726864","doi":"10.1002/sim.1028","title":"Regression models for allele sharing: analysis of accumulating data in affected sib pair studies","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill Genome Centre; McGill University Health Centre; Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Genetics; Allele; Biology; Microsatellite; Genotype; Genetic marker; Genetic association; Disease; Gene; Single-nucleotide polymorphism; Medicine","score_opus":0.17005254369451553,"score_gpt":0.4320606346360941,"score_spread":0.2620080909415786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096726864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7012646,0.0057401047,0.29058933,0.0007946179,0.0001398223,0.00046183486,0.0006585579,0.000008207585,0.00034293797],"genre_scores_gemma":[0.95699805,0.0010619634,0.039756116,0.000087684835,0.000059015172,0.000018578827,0.0018405416,0.000009204925,0.00016886188],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988231,0.00008544479,0.0004747481,0.00033308243,0.0000976307,0.0001859721],"domain_scores_gemma":[0.9988917,0.00031551791,0.0002007473,0.00045009388,0.000114110466,0.000027806293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009331416,0.000102026264,0.00045332854,0.00016801103,0.000028986362,0.0000014440105,0.00022090896,0.00009346808,0.000021026137],"category_scores_gemma":[0.004186458,0.00008233244,0.000023845734,0.00030586883,0.00008152551,0.000002663721,0.00017271705,0.00006749999,1.8844507e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015988597,0.00049508055,0.71117526,0.0004508901,0.0030521178,0.000017011493,0.0040468215,0.13235189,0.022746393,0.004180728,0.097025566,0.024298366],"study_design_scores_gemma":[0.0010637469,0.00022527797,0.050510954,0.00006458744,0.00025716083,3.7299566e-7,0.00079236535,0.94257647,0.000060473507,0.0040641506,0.0002723205,0.000112106456],"about_ca_topic_score_codex":0.00008190111,"about_ca_topic_score_gemma":0.0009478076,"teacher_disagreement_score":0.8102246,"about_ca_system_score_codex":0.000019610652,"about_ca_system_score_gemma":0.000009490809,"threshold_uncertainty_score":0.50118834},"labels":[],"label_agreement":null},{"id":"W2096911929","doi":"10.1002/sim.1290","title":"Clinical research and trials in developing countries","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Blood Pressure and Hypertension Studies","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Developing country; Clinical trial; Medicine; Economic growth; Economics; Pathology","score_opus":0.47626321956660006,"score_gpt":0.5355790470014814,"score_spread":0.05931582743488134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096911929","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2858917,0.26159602,0.007952946,0.37759942,0.003265278,0.004771828,0.00024991785,0.00016603517,0.05850682],"genre_scores_gemma":[0.7560509,0.16712148,0.052286524,0.019437985,0.0015797581,0.00006646876,0.000038416016,0.000046957273,0.0033715074],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975369,0.00046425758,0.0010137046,0.00025579234,0.00045850157,0.00027082078],"domain_scores_gemma":[0.9915065,0.007891692,0.000074180774,0.00016493714,0.00027551092,0.000087188],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009507467,0.00009954712,0.0012285588,0.00032355788,0.0000612623,0.000006979091,0.000048577145,0.00009531165,0.00028835968],"category_scores_gemma":[0.0119866235,0.00006885809,0.0000132063215,0.00029795954,0.0006773123,0.000021991758,0.00006248441,0.00048931054,0.0000206579],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030219453,0.00017901999,0.35737455,0.00038104685,0.00014912378,0.0013610306,0.0031947212,1.3018258e-7,0.00002142572,0.05077048,0.5558615,0.030404834],"study_design_scores_gemma":[0.009447336,0.0011077108,0.32156068,0.0018564383,0.00022676271,0.000076852055,0.001597492,0.0003554222,0.000017072316,0.015298825,0.6482764,0.00017904521],"about_ca_topic_score_codex":0.00012321818,"about_ca_topic_score_gemma":0.00026079634,"teacher_disagreement_score":0.47015917,"about_ca_system_score_codex":0.000019248479,"about_ca_system_score_gemma":0.00004664187,"threshold_uncertainty_score":0.9963358},"labels":[],"label_agreement":null},{"id":"W2097027506","doi":"10.1002/1097-0258(20000730)19:14<1849::aid-sim506>3.0.co;2-1","title":"Estimating treatment effects in randomized clinical trials in the presence of non-compliance","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":159,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Universiteit Leiden","keywords":"Confounding; Randomization; Randomized controlled trial; Outcome (game theory); Clinical trial; Medicine; Placebo; Estimator; Statistics; Instrumental variable; Causal inference; Econometrics; Internal medicine; Mathematics","score_opus":0.28974091353382553,"score_gpt":0.5720931192616544,"score_spread":0.2823522057278289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097027506","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06532778,0.00021742121,0.9277225,0.00035107107,0.0001810141,0.0036778743,0.00002769681,0.00003456976,0.0024600537],"genre_scores_gemma":[0.38336784,0.0003487446,0.6156754,0.00008453342,0.00008428524,0.00035036614,0.000008801272,0.000013921755,0.00006613875],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9925598,0.00402531,0.0025681623,0.00025249846,0.00033910314,0.0002551406],"domain_scores_gemma":[0.89139515,0.10769333,0.00047100225,0.0003656458,0.000040971056,0.000033877826],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0237718,0.000185358,0.002218789,0.00013153783,0.000015921349,0.000004809496,0.0002545853,0.00008334205,0.000117637195],"category_scores_gemma":[0.096706964,0.000105053674,0.000062355786,0.00029815236,0.0004613751,0.000041956853,0.000016597212,0.00031846878,0.0000030807055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01638176,0.0018500695,0.0058648996,0.0016065361,0.000106682295,0.0006734867,0.018114759,0.001065722,0.0004275819,0.20661384,0.0028811505,0.7444135],"study_design_scores_gemma":[0.05925073,0.00052266585,0.0015449094,0.0026452292,0.00006761331,0.0000040119867,0.00016165253,0.07916347,0.00015210787,0.8563522,0.000015315793,0.000120095734],"about_ca_topic_score_codex":0.00030281502,"about_ca_topic_score_gemma":0.00022892322,"teacher_disagreement_score":0.7442934,"about_ca_system_score_codex":0.000076813856,"about_ca_system_score_gemma":0.00005067522,"threshold_uncertainty_score":0.91090184},"labels":[],"label_agreement":null},{"id":"W2097223884","doi":"10.1002/sim.2813","title":"A comparison of the statistical power of different methods for the analysis of cluster randomization trials with binary outcomes","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Statistics; Wilcoxon signed-rank test; Statistical power; Mathematics; Generalized estimating equation; Cluster randomised controlled trial; Statistical hypothesis testing; Randomization; Intraclass correlation; Type I and type II errors; Restricted randomization; Randomized controlled trial; Sample size determination; Resampling; Random effects model; Meta-analysis; Medicine; Mann–Whitney U test","score_opus":0.13128335709531094,"score_gpt":0.5424346180488774,"score_spread":0.41115126095356647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097223884","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036584667,0.000077856195,0.9942207,0.00021599726,0.0001806081,0.000992495,0.0005586271,0.000003907923,0.00009138059],"genre_scores_gemma":[0.33486307,0.0000085532165,0.66502875,0.00003027031,0.00001103361,0.000019073566,0.000015563319,0.0000103446055,0.000013342092],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99580926,0.0012766373,0.0020451895,0.00017599532,0.0004937976,0.00019910505],"domain_scores_gemma":[0.875364,0.12285835,0.0010419608,0.00037408606,0.00031938194,0.000042212047],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009532663,0.0001782448,0.0022097477,0.00024400039,0.000042607924,0.0000035629616,0.00024642202,0.00006989539,0.00021058554],"category_scores_gemma":[0.047183793,0.00007183058,0.00011734759,0.00067203405,0.0007066498,0.0000122261845,0.00004664155,0.00016439875,4.0639854e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028072416,0.00040411623,0.042944115,0.00043289337,0.0014826688,9.740611e-7,0.0028578488,0.00006721041,0.0004812746,0.9092354,0.0007110773,0.038575135],"study_design_scores_gemma":[0.008917226,0.0009017993,0.3045618,0.00031251687,0.008211224,6.994255e-7,0.0018244336,0.06178827,0.0015393567,0.61174864,0.000026838445,0.00016718676],"about_ca_topic_score_codex":0.000052048214,"about_ca_topic_score_gemma":0.00014979902,"teacher_disagreement_score":0.3312046,"about_ca_system_score_codex":0.000026447375,"about_ca_system_score_gemma":0.000041207222,"threshold_uncertainty_score":0.9608422},"labels":[],"label_agreement":null},{"id":"W2098062766","doi":"10.1002/sim.822","title":"Simultaneous modelling of operative mortality and long‐term survival after coronary artery bypass surgery","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Simon Fraser University; University of Alberta","funders":"Division of Mathematical Sciences; Heart and Stroke Foundation of Canada","keywords":"Covariate; Poisson regression; Coronary artery bypass surgery; Proportional hazards model; Medicine; Survival analysis; Bypass surgery; Accelerated failure time model; Artery; Poisson distribution; Regression analysis; Term (time); Surgery; Cardiology; Internal medicine; Statistics; Mathematics; Population","score_opus":0.05708445331418451,"score_gpt":0.3571871711612406,"score_spread":0.3001027178470561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098062766","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9316966,0.0006443003,0.06363841,0.0001888245,0.00071369205,0.0003146134,0.00013333382,0.000025517418,0.0026446912],"genre_scores_gemma":[0.9946089,0.0036378372,0.0010961279,0.00013713456,0.0002116472,0.000021339229,0.000040719493,0.000015769141,0.00023057296],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99754655,0.0003765399,0.0006024066,0.00033214843,0.0007549229,0.00038745103],"domain_scores_gemma":[0.99784374,0.0014330067,0.00015669336,0.00024031916,0.00019841126,0.00012781774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001840415,0.00018252042,0.00050871633,0.00019339038,0.00013715237,0.000020729722,0.00014775946,0.00008142521,0.00021800368],"category_scores_gemma":[0.00043046416,0.00016935945,0.00003389168,0.00036057003,0.0012297973,0.00011333295,0.000050441307,0.00019306746,0.0000026325038],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000100649915,0.00010250884,0.9807883,0.000084329076,0.00009122435,0.0014582858,0.005903666,0.001138125,0.0000033417634,0.004482243,0.00013380355,0.0057135043],"study_design_scores_gemma":[0.0005859006,0.00008404817,0.98604333,0.00019854597,0.00010693055,0.000005279531,0.0023886417,0.0049001058,0.0000014809984,0.005113437,0.00030510954,0.00026719397],"about_ca_topic_score_codex":0.0039510163,"about_ca_topic_score_gemma":0.01950405,"teacher_disagreement_score":0.06291224,"about_ca_system_score_codex":0.00006886684,"about_ca_system_score_gemma":0.00007768479,"threshold_uncertainty_score":0.99838746},"labels":[],"label_agreement":null},{"id":"W2098196266","doi":"10.1002/sim.6115","title":"Statistics for quantifying heterogeneity in univariate and bivariate meta-analyses of binary data: The case of meta-analyses of diagnostic accuracy","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":215,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Bivariate analysis; Univariate; Statistics; Variance (accounting); Estimator; Meta-analysis; Econometrics; Statistic; Bivariate data; Mathematics; Multivariate statistics; Medicine","score_opus":0.9168580576152456,"score_gpt":0.6467614652057476,"score_spread":0.270096592409498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098196266","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049791288,0.00907913,0.93265855,0.00047775882,0.0001765743,0.0012508209,0.006493161,0.0000020698699,0.00007063737],"genre_scores_gemma":[0.8665233,0.0004098222,0.13271177,0.000076067736,0.000028702945,0.00004137409,0.00014123356,0.000017064904,0.00005063182],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.96788365,0.013408246,0.014232006,0.0010835591,0.0030641838,0.00032833824],"domain_scores_gemma":[0.7858435,0.19661538,0.010305275,0.0048943944,0.0022135098,0.00012791113],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1378905,0.0004463421,0.009631727,0.0008970557,0.0000858192,0.00006853336,0.0018105315,0.00008298119,0.0010655449],"category_scores_gemma":[0.4882441,0.00017949533,0.0007193278,0.0018127477,0.0006133188,0.00018297066,0.00040159683,0.00020980019,0.000004235756],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005044369,0.0018732554,0.033326402,0.010739221,0.21120693,0.0012684208,0.009073657,0.04128237,0.019828811,0.5558249,0.07409772,0.040973876],"study_design_scores_gemma":[0.0026276761,0.0008722253,0.018664937,0.00021816987,0.30935898,0.00011186938,0.0033992971,0.5032345,0.0011382501,0.15761335,0.002134763,0.00062596693],"about_ca_topic_score_codex":0.0035702896,"about_ca_topic_score_gemma":0.0039756405,"teacher_disagreement_score":0.81673205,"about_ca_system_score_codex":0.00001913236,"about_ca_system_score_gemma":0.000110131485,"threshold_uncertainty_score":0.9998476},"labels":[],"label_agreement":null},{"id":"W2098373960","doi":"10.1002/sim.1858","title":"Methods for modelling change in cluster randomization trials","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Cancer Care Ontario","funders":"National Institute on Drug Abuse","keywords":"Cluster randomised controlled trial; Sample size determination; Cluster (spacecraft); Randomization; Analysis of covariance; Intervention (counseling); Computer science; Statistics; Covariance; Statistical power; Outcome (game theory); Random effects model; Econometrics; Randomized controlled trial; Medicine; Mathematics; Meta-analysis","score_opus":0.3197844407598542,"score_gpt":0.5497557916040277,"score_spread":0.22997135084417347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098373960","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000067947774,0.00016742406,0.99676716,0.0007582914,0.00039747026,0.0014651144,0.000098899596,0.000019345116,0.0002583233],"genre_scores_gemma":[0.0031111138,0.0001381836,0.9957172,0.00033355167,0.0002783325,0.00034033,0.00003541561,0.000027428556,0.000018433619],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972575,0.0008464537,0.0011596866,0.00026041208,0.00018538859,0.00029056464],"domain_scores_gemma":[0.9789744,0.020423906,0.00023979665,0.00017891351,0.000113050795,0.00006991411],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010845973,0.00017052295,0.0010209507,0.00024240931,0.000034498476,0.000011431083,0.00011464695,0.0001056287,0.00011096327],"category_scores_gemma":[0.037812788,0.0001285549,0.000034312357,0.00026768382,0.00009939432,0.000051674233,0.000020479978,0.00018768688,0.0000014765101],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036162147,0.000057928293,0.000026808671,0.00022237905,0.000010451193,0.00000643543,0.0017580995,0.0002547012,0.000035912577,0.85569376,0.00018269545,0.14138922],"study_design_scores_gemma":[0.011621508,0.00012478055,0.00003997965,0.00038510008,0.000058202313,0.0000017220265,0.000076407625,0.14024028,0.00005800718,0.84713054,0.00014273198,0.0001207171],"about_ca_topic_score_codex":0.00021179704,"about_ca_topic_score_gemma":0.00013841566,"teacher_disagreement_score":0.1412685,"about_ca_system_score_codex":0.00010254955,"about_ca_system_score_gemma":0.000045041623,"threshold_uncertainty_score":0.97029215},"labels":[],"label_agreement":null},{"id":"W2098378469","doi":"10.1002/sim.6740","title":"Flexible estimation of survival curves conditional on non‐linear and time‐dependent predictor effects","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; McGill University","funders":"","keywords":"Covariate; Statistics; Proportional hazards model; Mathematics; Survival analysis; Accelerated failure time model; Survival function; Hazard ratio; Econometrics; Confidence interval","score_opus":0.2149952634266843,"score_gpt":0.4461013914400345,"score_spread":0.23110612801335023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098378469","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10952218,0.0060109263,0.8298492,0.024648113,0.0029011415,0.0027891009,0.0063774628,0.00008713029,0.017814787],"genre_scores_gemma":[0.95238715,0.0005559453,0.03586989,0.00680848,0.0007243004,0.00013100491,0.0016484879,0.000056672005,0.0018180767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972673,0.00020547227,0.0018602173,0.00028072344,0.0002062288,0.00018007081],"domain_scores_gemma":[0.99630916,0.0023889234,0.0008387526,0.00020965561,0.000089703215,0.00016380555],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010034309,0.00012898908,0.0007880572,0.0002675736,0.000034596273,0.0000059871168,0.00010026195,0.00007043835,0.00022128495],"category_scores_gemma":[0.012143025,0.00014332218,0.000013916307,0.00011297304,0.00016548531,0.00010672465,0.00002429399,0.00013610387,0.00027118163],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014957505,0.000346487,0.041994963,0.0050850776,0.00012825368,0.000014705833,0.0036715625,0.008527716,0.00001491987,0.6595326,0.27980906,0.00072510174],"study_design_scores_gemma":[0.0096084885,0.0022624407,0.15146595,0.003051531,0.000047030266,0.000010715196,0.00063900196,0.38695583,0.000065183296,0.4427225,0.002592171,0.00057917234],"about_ca_topic_score_codex":0.0003294998,"about_ca_topic_score_gemma":0.00002242604,"teacher_disagreement_score":0.842865,"about_ca_system_score_codex":0.00019454146,"about_ca_system_score_gemma":0.00011379071,"threshold_uncertainty_score":0.9961781},"labels":[],"label_agreement":null},{"id":"W2098998213","doi":"10.1002/sim.4228","title":"A flexible genome‐wide bootstrap method that accounts for rankingand threshold‐selection bias in GWAS interpretation and replication study design","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Public Health Ontario; University of Toronto; Mount Sinai Hospital","funders":"Canadian Institutes of Health Research; Wellcome Trust","keywords":"Replication (statistics); Genome-wide association study; Selection (genetic algorithm); Computer science; Interpretation (philosophy); Selection bias; Computational biology; Biology; Statistics; Genetics; Artificial intelligence; Mathematics; Single-nucleotide polymorphism; Gene","score_opus":0.14032837438079812,"score_gpt":0.39995353483916085,"score_spread":0.2596251604583627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098998213","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2465147,0.00022774123,0.75220907,0.00007119876,0.00007201604,0.000734855,0.00001670529,0.000005591952,0.00014811417],"genre_scores_gemma":[0.8920942,0.00019898405,0.10705405,0.00018690008,0.000052716336,0.0001789619,0.00013687911,0.00001490772,0.00008240726],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99866945,0.00023710073,0.00038793348,0.00041557636,0.00009087236,0.0001990813],"domain_scores_gemma":[0.99919003,0.00027435194,0.00018133568,0.00021706677,0.000099836296,0.000037376507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026446795,0.0001281628,0.00025113949,0.00014374066,0.000053012413,0.0000063063376,0.00009065998,0.000115947536,0.000015698635],"category_scores_gemma":[0.0015475602,0.00011695485,0.00001406869,0.00011173549,0.00005763403,0.000004975343,0.000028164066,0.00009797721,6.845599e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008156194,0.00026139896,0.9565502,0.000055498534,0.00010525178,0.0000032864325,0.0051760534,0.00089384295,0.013503368,0.0005536443,0.0016103396,0.020471524],"study_design_scores_gemma":[0.002519289,0.0017690506,0.9630062,0.000029039164,0.000069981914,0.000006998324,0.0012684828,0.010523781,0.001975328,0.018376125,0.00027226357,0.00018347564],"about_ca_topic_score_codex":0.00022612126,"about_ca_topic_score_gemma":0.0006854901,"teacher_disagreement_score":0.6455795,"about_ca_system_score_codex":0.0000380116,"about_ca_system_score_gemma":0.00004269288,"threshold_uncertainty_score":0.47692803},"labels":[],"label_agreement":null},{"id":"W2099320460","doi":"10.1002/sim.6523","title":"Adaptive sampling in two‐phase designs: a biomarker study for progression in arthritis","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Estimator; Computer science; Sampling (signal processing); Exploit; Adaptive sampling; Optimal design; Sample size determination; Phase (matter); Biomarker; Resource allocation; Statistics; Data mining; Machine learning; Mathematics; Monte Carlo method","score_opus":0.5332255921247048,"score_gpt":0.6223730082861888,"score_spread":0.08914741616148403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099320460","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10435087,0.001606732,0.8900298,0.00014574482,0.0005935245,0.0025681832,0.00008724842,0.00001852951,0.00059936923],"genre_scores_gemma":[0.54259527,0.000013570113,0.45702443,0.000056036955,0.000041821706,0.00021196465,0.000009784405,0.000015157138,0.000031960946],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99500746,0.0011788368,0.0013589697,0.00065969955,0.001375219,0.00041979586],"domain_scores_gemma":[0.9933094,0.005585012,0.00024665028,0.0003700105,0.00029061647,0.00019830574],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016815467,0.00021898646,0.0006904062,0.000936709,0.00004038219,0.000045620338,0.00041571507,0.000057154262,0.00009064612],"category_scores_gemma":[0.02275156,0.00016454009,0.000020632138,0.0014458012,0.00025596944,0.00017887207,0.00011397751,0.00023512641,0.000013437149],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003311131,0.0021822636,0.052194852,0.00001034054,0.000014028209,0.0007217414,0.019721461,0.0004948592,0.0029379453,0.0040778834,0.0036327867,0.9107007],"study_design_scores_gemma":[0.08519574,0.015920449,0.049154263,0.001959624,0.000028867158,0.00003102818,0.11763887,0.25054425,0.00072109804,0.47708663,0.00081121945,0.00090797787],"about_ca_topic_score_codex":0.00042048443,"about_ca_topic_score_gemma":0.0013707507,"teacher_disagreement_score":0.9097927,"about_ca_system_score_codex":0.00024398451,"about_ca_system_score_gemma":0.00016733735,"threshold_uncertainty_score":0.9854802},"labels":[],"label_agreement":null},{"id":"W2099844674","doi":"10.1002/sim.1115","title":"Current and future challenges in the design and analysis of cluster randomization trials","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":172,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Cancer Care Ontario","funders":"","keywords":"Randomization; Cluster (spacecraft); Cluster randomised controlled trial; Restricted randomization; Psychological intervention; Randomized controlled trial; Research design; Computer science; Medicine; Statistics; Mathematics; Psychiatry","score_opus":0.6291099124678506,"score_gpt":0.5903951121051839,"score_spread":0.038714800362666724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099844674","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001715755,0.0048192185,0.98924136,0.0027831167,0.00028096745,0.00091041316,0.000069839945,0.0000061125875,0.00017320535],"genre_scores_gemma":[0.01685627,0.075076796,0.9073563,0.00014925827,0.00046258228,0.00006380152,0.000012682366,0.000016031265,0.0000062487443],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9924769,0.0052543897,0.0014894587,0.00024871886,0.0003760933,0.00015448678],"domain_scores_gemma":[0.84550714,0.1538071,0.00035681235,0.00021193716,0.00007410357,0.000042870775],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02845252,0.00014075421,0.0014874549,0.0003282651,0.000022015072,0.000007754959,0.00011448592,0.000090219415,0.00010397249],"category_scores_gemma":[0.13853988,0.00007918111,0.00003325487,0.0005794817,0.0002655987,0.000020496891,0.000028493756,0.00023035564,1.9453749e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017293831,0.000215166,0.002131017,0.00038500706,0.0003363965,0.000025227242,0.0054616905,0.000047135538,0.00000878353,0.48034698,0.0015453998,0.50776786],"study_design_scores_gemma":[0.008749942,0.00018901021,0.012706195,0.00017069658,0.0015746111,0.000003125225,0.0008593666,0.012628359,0.000002147579,0.9624972,0.000521298,0.00009805933],"about_ca_topic_score_codex":0.00000854579,"about_ca_topic_score_gemma":0.000056519228,"teacher_disagreement_score":0.50766975,"about_ca_system_score_codex":0.000014787286,"about_ca_system_score_gemma":0.000015508514,"threshold_uncertainty_score":0.9861132},"labels":[],"label_agreement":null},{"id":"W2100071619","doi":"10.1002/sim.1021","title":"Spatio‐temporal modelling of rates for the construction of disease maps","year":2002,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University; University of British Columbia; Providence Health Care","funders":"","keywords":"Popularity; Generalized linear mixed model; Geography; Disease; Computer science; Econometrics; Statistics; Regional science; Medicine; Mathematics","score_opus":0.09536913431964626,"score_gpt":0.3928062166486516,"score_spread":0.29743708232900534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100071619","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000002519011,0.85559136,0.13081707,0.000082995786,0.00036341598,0.0015828778,0.0114297345,0.000012900302,0.000117153235],"genre_scores_gemma":[0.00016157264,0.9638061,0.029282678,0.000026440555,0.00025941388,0.00010642853,0.0061825803,0.000047650065,0.00012715427],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976101,0.00011953893,0.0013033235,0.0003043784,0.0004585958,0.00020407584],"domain_scores_gemma":[0.99630046,0.0017569888,0.0008714436,0.0006078178,0.00032205088,0.00014123837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058314233,0.00029244207,0.001985451,0.00024713087,0.000030280928,0.0000028140107,0.00019586053,0.0000966375,0.00018983059],"category_scores_gemma":[0.0014871926,0.00018395594,0.0001501465,0.0003369954,0.0006813498,0.000022624494,0.00003584917,0.00026161852,0.0000033047252],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003530454,0.00015805181,0.0009806433,0.1011754,0.00041946396,0.00004763827,0.00011542641,0.00020175998,1.1277476e-7,0.011084989,0.017899433,0.867564],"study_design_scores_gemma":[0.0024897954,0.00040207515,0.00012026421,0.04631603,0.005077187,0.000017841934,0.00011876797,0.028825555,5.267665e-7,0.005943966,0.9103649,0.00032308834],"about_ca_topic_score_codex":0.00008645314,"about_ca_topic_score_gemma":0.00001699813,"teacher_disagreement_score":0.8924655,"about_ca_system_score_codex":0.00007199892,"about_ca_system_score_gemma":0.00033350248,"threshold_uncertainty_score":0.75015056},"labels":[],"label_agreement":null},{"id":"W2101735855","doi":"10.1002/sim.1285","title":"The Cochrane Collaboration – how is it progressing?","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Medical Research Council Canada","keywords":"Cochrane collaboration; Systematic review; Quality (philosophy); Randomized controlled trial; Medicine; MEDLINE; Alternative medicine; Cochrane Library; Family medicine; Political science; Pathology","score_opus":0.5756978853050545,"score_gpt":0.5595249099652397,"score_spread":0.016172975339814766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101735855","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004525839,0.040903103,0.3450976,0.5035198,0.0038385363,0.003221303,0.00030404676,0.000017430773,0.09857239],"genre_scores_gemma":[0.68060964,0.0026398322,0.058273945,0.005542054,0.0007890726,0.00013538453,0.00003993632,0.00003281822,0.2519373],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9863735,0.003291046,0.004167105,0.00048956857,0.0054526236,0.00022617687],"domain_scores_gemma":[0.9864541,0.008081336,0.0021623983,0.0018129232,0.0013958493,0.00009335051],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.050224505,0.00017096939,0.0014999202,0.0001765216,0.00022237205,0.0006196614,0.000878208,0.000048271133,0.014839599],"category_scores_gemma":[0.10002017,0.00006343795,0.00010394225,0.0016616827,0.0002924931,0.00008607969,0.00003737058,0.00015159712,0.0009658227],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017817699,0.000013609222,0.0017062572,0.000020151661,0.000023848532,0.000012600888,0.0024433176,0.000003032779,0.000009301756,0.008750588,0.9399793,0.047036216],"study_design_scores_gemma":[0.00047344476,0.00011740423,0.0019781322,0.00016692505,0.00012111444,0.000009057351,0.0076724915,0.07997772,0.0000071821546,0.02762693,0.8817141,0.00013548104],"about_ca_topic_score_codex":0.0000054180173,"about_ca_topic_score_gemma":0.00017963389,"teacher_disagreement_score":0.6760838,"about_ca_system_score_codex":0.000031442865,"about_ca_system_score_gemma":0.000025724232,"threshold_uncertainty_score":0.99981207},"labels":[],"label_agreement":null},{"id":"W2102520493","doi":"10.1002/sim.2328","title":"A comparison of propensity score methods: a case‐study estimating the effectiveness of post‐AMI statin use","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":565,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Propensity score matching; Statin; Statistics; Medicine; Internal medicine; Computer science; Mathematics","score_opus":0.31956570844757465,"score_gpt":0.5520056064708857,"score_spread":0.23243989802331105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102520493","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4748936,0.000026012112,0.52401406,0.000015214917,0.000033422373,0.0009111875,0.000037801175,0.00002742925,0.000041279665],"genre_scores_gemma":[0.5095511,0.0000012235154,0.49036577,0.0000098497285,0.000015830014,0.000033794102,0.0000050743997,0.000014145979,0.00000318943],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99658763,0.0015816797,0.001004126,0.00023062705,0.00038807982,0.00020784079],"domain_scores_gemma":[0.98058593,0.017776186,0.00057873625,0.0004905913,0.0005275191,0.000041008945],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0051970277,0.000201513,0.0009233155,0.0001338412,0.000058902573,0.0000065934564,0.00020664772,0.00005223488,0.000023291732],"category_scores_gemma":[0.018450016,0.00012941612,0.000021288355,0.00032394603,0.0004314344,0.00009708928,0.000118625045,0.0003791928,4.534697e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012093899,0.0048260028,0.397978,0.0062288884,0.00040315502,0.001375217,0.08864853,0.0029462287,0.040537503,0.27528113,0.0009364065,0.17962953],"study_design_scores_gemma":[0.006051955,0.009193189,0.09257529,0.006477603,0.00093342393,0.00070211745,0.040456716,0.11658138,0.055133637,0.67089397,0.000028782011,0.0009719493],"about_ca_topic_score_codex":0.0011934737,"about_ca_topic_score_gemma":0.00083077396,"teacher_disagreement_score":0.39561284,"about_ca_system_score_codex":0.00008125761,"about_ca_system_score_gemma":0.000059068592,"threshold_uncertainty_score":0.989818},"labels":[],"label_agreement":null},{"id":"W2102524079","doi":"10.1002/sim.4056","title":"The analysis of case cohort design in the presence of competing risks with application to estimate the risk of delayed cardiac toxicity among Hodgkin Lymphoma survivors","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Centre for Advancing Health Outcomes; Public Health Ontario; University of Toronto; University Health Network","funders":"Canadian Institutes of Health Research","keywords":"Jackknife resampling; Statistics; Medicine; Cohort; Econometrics; Disease; Proportional hazards model; Hazard ratio; Lymphoma; Mathematics; Risk analysis (engineering); Internal medicine; Confidence interval","score_opus":0.04083622230011155,"score_gpt":0.40275318208260447,"score_spread":0.36191695978249294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102524079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45393494,0.000014011077,0.54518795,0.000030517074,0.000029799205,0.00052373623,0.00019928148,0.0000027399617,0.00007705538],"genre_scores_gemma":[0.71592313,0.000027555445,0.2839484,0.0000074073573,0.000011138629,0.00006766122,0.0000053213494,0.000007861505,0.0000015437917],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971018,0.0011055254,0.00083492324,0.00020416913,0.0005515274,0.0002020539],"domain_scores_gemma":[0.96064574,0.037684873,0.0006239546,0.0006836319,0.0003142583,0.000047570546],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009901582,0.00014742748,0.00062668876,0.0001288174,0.00010174088,0.00000780324,0.0004049205,0.00005436083,0.0000112952275],"category_scores_gemma":[0.019032253,0.00006745614,0.00003418438,0.0011884377,0.0009093542,0.000015616515,0.000053448795,0.00027660475,1.574964e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003149236,0.00021660473,0.63796717,0.00016973278,0.00080382463,0.000049522067,0.011905304,0.006303156,0.0011942226,0.29900298,0.0001534378,0.041919135],"study_design_scores_gemma":[0.00036827222,0.00027950163,0.6628288,0.00009561019,0.0015109122,0.0000070296555,0.0030090655,0.2620003,0.0006124169,0.06917114,0.0000038985995,0.000113044116],"about_ca_topic_score_codex":0.016701095,"about_ca_topic_score_gemma":0.021262672,"teacher_disagreement_score":0.26198816,"about_ca_system_score_codex":0.0000189978,"about_ca_system_score_gemma":0.00004963904,"threshold_uncertainty_score":0.99659675},"labels":[],"label_agreement":null},{"id":"W2103338349","doi":"10.1002/sim.5683","title":"Ties between event times and jump times in the Cox model","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Event (particle physics); Computer science; Proportional hazards model; Software; Jump; Statistics; Binary data; Event data; Econometrics; Binary number; Mathematics; Machine learning","score_opus":0.09058773425645432,"score_gpt":0.42891557197893215,"score_spread":0.3383278377224778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103338349","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004188388,0.00036873153,0.98783493,0.00082453893,0.000092213224,0.0002452779,0.00017078423,0.000013928294,0.0062612016],"genre_scores_gemma":[0.42264152,0.00008012343,0.5766795,0.00017252592,0.00015359688,0.00001984065,0.00001365307,0.0000131387615,0.00022605764],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854565,0.00024857544,0.00042668346,0.00014132803,0.00032171878,0.00031607584],"domain_scores_gemma":[0.99398607,0.005604436,0.0000841099,0.00020591865,0.000034515575,0.000084949905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019353833,0.00014906796,0.00037425943,0.00009655299,0.000045381934,0.00001100822,0.00015007795,0.000063681844,0.00023188296],"category_scores_gemma":[0.0035217982,0.00009114695,0.000010043234,0.0001435226,0.00029843432,0.000045697434,0.000044704717,0.000284029,0.000007752044],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000080511,0.000049576913,0.011019009,0.0001189421,0.00000943049,0.000007943273,0.004379278,0.0000011245488,0.000007592772,0.95453304,0.01365558,0.016210401],"study_design_scores_gemma":[0.00039889466,0.00008171226,0.020157948,0.00015072103,0.000052992193,0.000004744928,0.00072915794,0.0075883237,0.000009774515,0.97047275,0.00023863056,0.0001143506],"about_ca_topic_score_codex":0.000063664695,"about_ca_topic_score_gemma":0.000024810632,"teacher_disagreement_score":0.41845313,"about_ca_system_score_codex":0.000026673499,"about_ca_system_score_gemma":0.000024957446,"threshold_uncertainty_score":0.4216176},"labels":[],"label_agreement":null},{"id":"W2103371988","doi":"10.1002/sim.5705","title":"The performance of different propensity score methods for estimating marginal hazard ratios","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":995,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Odds ratio; Estimator; Matching (statistics); Medicine; Mathematics","score_opus":0.22020753118718697,"score_gpt":0.4904911441960751,"score_spread":0.27028361300888815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103371988","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06839165,0.000094207935,0.93017393,0.00012031017,0.00026562027,0.0007133104,0.000016702863,0.00003677284,0.00018749823],"genre_scores_gemma":[0.19177236,0.00004180599,0.80780804,0.000025422712,0.00012501192,0.00011226327,0.000010578186,0.000017596733,0.00008695062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99867797,0.00013657245,0.0005378662,0.00011770506,0.00021526488,0.00031464512],"domain_scores_gemma":[0.9950841,0.0040758783,0.00029939413,0.00028894373,0.00019292721,0.000058766407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002238949,0.00015149084,0.00039684807,0.00005268499,0.0001149006,0.000005728927,0.00018131392,0.00004535697,0.000023089584],"category_scores_gemma":[0.0065260795,0.00008779509,0.00001731552,0.000096663905,0.00029962012,0.00008154345,0.00006211945,0.0002099996,5.209366e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014150966,0.00013102194,0.026839644,0.001189853,0.00003550294,0.0000011662486,0.0017837703,0.000014164555,0.005966098,0.7812556,0.0034087494,0.17923293],"study_design_scores_gemma":[0.0009979375,0.0009844513,0.012969004,0.00101758,0.00012811605,0.000013738967,0.00029301192,0.088986054,0.02950362,0.86437964,0.0004199635,0.00030689983],"about_ca_topic_score_codex":0.0000051866728,"about_ca_topic_score_gemma":0.000018884162,"teacher_disagreement_score":0.17892604,"about_ca_system_score_codex":0.00007045359,"about_ca_system_score_gemma":0.000028404293,"threshold_uncertainty_score":0.7812798},"labels":[],"label_agreement":null},{"id":"W2104787905","doi":"10.1002/sim.3447","title":"Empirical study of the dependence of the results of multivariable flexible survival analyses on model selection strategy","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Covariate; Parametric statistics; Proportional hazards model; Econometrics; Statistics; Selection (genetic algorithm); Model selection; Log-linear model; Semiparametric model; Parametric model; Computer science; Mathematics; Linear model; Artificial intelligence","score_opus":0.1659354445021612,"score_gpt":0.43033108846376195,"score_spread":0.26439564396160076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104787905","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98305565,0.000034443292,0.014015426,0.00009825984,0.00018045881,0.0003947523,0.000047159825,0.00000960353,0.0021642356],"genre_scores_gemma":[0.9985875,0.000019168514,0.0009591301,0.000023650919,0.00004410556,0.000006429902,0.0000034646157,0.00000751369,0.00034905365],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99830365,0.0001709293,0.0005440927,0.00017800037,0.0006920208,0.00011129281],"domain_scores_gemma":[0.99869096,0.00042117215,0.00028577467,0.00029402174,0.00027628106,0.00003179527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005038085,0.00009709503,0.00037317522,0.00010928801,0.00006042879,7.334258e-7,0.00011546793,0.000053322743,0.0000113096785],"category_scores_gemma":[0.001553163,0.00005225796,0.00003116391,0.0007895536,0.00021942341,0.000015717618,0.000033897857,0.00028868119,1.4019992e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02675662,0.003026038,0.43770418,0.0003661522,0.00032076755,0.000021103513,0.012588907,0.4724375,0.03784987,0.00068144506,0.00461603,0.0036313904],"study_design_scores_gemma":[0.0070581813,0.010693597,0.77727044,0.00043239444,0.00023851327,0.000020880729,0.002306795,0.17162913,0.029337939,0.00091013365,0.000009067313,0.00009295784],"about_ca_topic_score_codex":0.004487752,"about_ca_topic_score_gemma":0.0016227359,"teacher_disagreement_score":0.33956623,"about_ca_system_score_codex":0.00006460042,"about_ca_system_score_gemma":0.00021714163,"threshold_uncertainty_score":0.67841685},"labels":[],"label_agreement":null},{"id":"W2105005539","doi":"10.1002/sim.2341","title":"Curious phenomena in Bayesian adjustment for exposure misclassification","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Intuition; Bayesian probability; Confounding; Econometrics; Bayes' theorem; Computer science; Statistics; Psychology; Artificial intelligence; Mathematics","score_opus":0.06258520134647907,"score_gpt":0.3989627422616326,"score_spread":0.3363775409151535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105005539","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022496888,0.00027164718,0.99359256,0.001637164,0.00022815568,0.0006563796,0.00018153242,0.000026337062,0.0031812699],"genre_scores_gemma":[0.038130853,0.00010336262,0.9603236,0.00033040834,0.00058364007,0.00018766859,0.00005239326,0.00002812365,0.00026000643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981966,0.00012420205,0.0007379137,0.00031105246,0.0002792788,0.00035092724],"domain_scores_gemma":[0.996606,0.0027669468,0.00015313661,0.0002792682,0.00009048526,0.00010418246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094154355,0.00018480097,0.00043289497,0.00018459964,0.000036895137,0.000008809696,0.00016326673,0.000082638675,0.00036965116],"category_scores_gemma":[0.0038019924,0.00015420878,0.000017875309,0.00021750074,0.00013777,0.000039490675,0.00001900811,0.00020736152,0.0000072657967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003529886,0.00013736694,0.00029033553,0.00015089395,0.000006474354,0.0000069000075,0.0009364151,0.0000029974003,0.00008922932,0.6817504,0.0064654816,0.31012818],"study_design_scores_gemma":[0.0021436708,0.0003288439,0.0070272814,0.00023553272,0.000034480672,0.0000032644632,0.0003703629,0.015407732,0.00003372636,0.96941274,0.004810571,0.000191786],"about_ca_topic_score_codex":0.000039842056,"about_ca_topic_score_gemma":0.0004438247,"teacher_disagreement_score":0.30993637,"about_ca_system_score_codex":0.00019002672,"about_ca_system_score_gemma":0.000054626616,"threshold_uncertainty_score":0.62884516},"labels":[],"label_agreement":null},{"id":"W2105385152","doi":"10.1002/sim.5676","title":"Comparing diagnostic tests: trials in people with discordant test results","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"National Institutes of Health; Universiteit van Amsterdam; National Institute for Health and Care Research","keywords":"Statistics; Test (biology); Gold standard (test); Statistical hypothesis testing; Computer science; Medicine; Econometrics; Mathematics","score_opus":0.5460293344991152,"score_gpt":0.5771006422312617,"score_spread":0.031071307732146503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105385152","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05335245,0.00047517204,0.9246786,0.0024349159,0.0027283723,0.0034719699,0.0024230136,0.00016990713,0.0102655515],"genre_scores_gemma":[0.41672453,0.00011775302,0.5822122,0.00011183883,0.0005787688,0.00010093059,0.000029400904,0.000044483782,0.00008006794],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9922604,0.0021849554,0.0034885614,0.00046131163,0.0007960029,0.00080879213],"domain_scores_gemma":[0.4581117,0.54017943,0.0007510307,0.000562416,0.000107404885,0.00028800964],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027723521,0.00036161082,0.00262076,0.00027598976,0.000052698048,0.000020740355,0.00032048547,0.00008895268,0.00022653842],"category_scores_gemma":[0.8694941,0.00024038667,0.000042491738,0.0007573203,0.0004475876,0.00008929633,0.00011117981,0.0007275244,0.000027799917],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090958626,0.0016010888,0.6677448,0.00058655447,0.00006898374,0.0003968465,0.002384065,0.00002426902,0.000079941645,0.30176768,0.018645423,0.005790741],"study_design_scores_gemma":[0.009878109,0.00082708214,0.33791915,0.00217841,0.00025236479,0.000032084696,0.0007287342,0.0006097908,0.000053093267,0.6468367,0.00026331606,0.00042117716],"about_ca_topic_score_codex":0.00031214007,"about_ca_topic_score_gemma":0.0019345573,"teacher_disagreement_score":0.8417706,"about_ca_system_score_codex":0.00019589758,"about_ca_system_score_gemma":0.00008509805,"threshold_uncertainty_score":0.9802684},"labels":[],"label_agreement":null},{"id":"W2105409485","doi":"10.1002/sim.5592","title":"Generalization of Youden index for multiple‐class classification problems applied to the assessment of externally validated cognition in Parkinson disease screening","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Generalization; Youden's J statistic; Cognition; Dementia; Class (philosophy); Index (typography); Disease; Medicine; Psychology; Artificial intelligence; Computer science; Mathematics; Machine learning; Psychiatry; Pathology; Receiver operating characteristic","score_opus":0.05750702138733923,"score_gpt":0.35622437236500176,"score_spread":0.29871735097766255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105409485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18647575,0.00012991254,0.81026787,0.00034797617,0.000120243916,0.0020611482,0.00043260705,0.000010987056,0.00015352061],"genre_scores_gemma":[0.9640716,0.00006968884,0.033735815,0.00015776952,0.000103418315,0.00041954932,0.0014008697,0.000022405327,0.00001891651],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99848926,0.00007446476,0.00055555115,0.00020494121,0.00045276713,0.0002229867],"domain_scores_gemma":[0.99897027,0.00019129449,0.00027713733,0.00021685996,0.00017511526,0.00016931504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066796184,0.00014276963,0.00033280405,0.00024731958,0.000031737847,0.000003954941,0.00007831744,0.000050001076,0.000027048423],"category_scores_gemma":[0.00032814904,0.00010409431,0.000024100007,0.000288646,0.000057164543,0.000042038057,0.00002182078,0.00008669282,7.314168e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011342949,0.0012048283,0.9342301,0.00073283125,0.00013101079,0.000008147644,0.0011096979,0.002031814,0.026900832,0.010815003,0.00043225655,0.021269208],"study_design_scores_gemma":[0.0051379623,0.00022010882,0.92873335,0.0005459478,0.0002629614,8.36133e-7,0.00031409232,0.06195133,0.00061601656,0.0010627755,0.001065752,0.00008885175],"about_ca_topic_score_codex":0.0001168995,"about_ca_topic_score_gemma":0.00012679546,"teacher_disagreement_score":0.7775958,"about_ca_system_score_codex":0.000100170844,"about_ca_system_score_gemma":0.0000779757,"threshold_uncertainty_score":0.42448428},"labels":[],"label_agreement":null},{"id":"W2105683190","doi":"10.1002/sim.1936","title":"Statistical methods for multivariate interval‐censored recurrent events","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Marginal model; Statistics; Multivariate statistics; Inference; Covariance; Event (particle physics); Econometrics; Computer science; Regression; Regression analysis; Mathematics; Artificial intelligence","score_opus":0.151138328609492,"score_gpt":0.5335458073367135,"score_spread":0.38240747872722153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105683190","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034433842,0.00009074661,0.99554414,0.00058213406,0.001100783,0.0007914243,0.00088943366,0.000053436124,0.00060354633],"genre_scores_gemma":[0.0112045035,0.0000450757,0.98795253,0.00021619987,0.00018261597,0.00015051856,0.000097389384,0.00005046443,0.00010068262],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99705476,0.00048863614,0.0010613934,0.0004918393,0.00034886473,0.0005545358],"domain_scores_gemma":[0.98704356,0.011863511,0.00022526762,0.00036983704,0.0002617575,0.00023605725],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026380986,0.00031114125,0.0008206225,0.00017037246,0.00007984547,0.000012073983,0.00027738584,0.00011994238,0.0005237389],"category_scores_gemma":[0.047336515,0.000246147,0.000041620846,0.00023569752,0.00029144212,0.00003539478,0.000077365854,0.00039365937,0.000014032526],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014758,0.00019120792,0.000049440845,0.00025101527,0.000032693904,0.000017609682,0.0008216644,0.000004400232,0.00023360127,0.8305102,0.0017373108,0.16600327],"study_design_scores_gemma":[0.0036450715,0.0008669733,0.0029537294,0.0005059281,0.000103944105,0.000007814073,0.0002178965,0.0059200716,0.00014960184,0.98416525,0.0011912289,0.00027250536],"about_ca_topic_score_codex":0.00016855345,"about_ca_topic_score_gemma":0.000054167016,"teacher_disagreement_score":0.16573077,"about_ca_system_score_codex":0.0002113837,"about_ca_system_score_gemma":0.000099291814,"threshold_uncertainty_score":0.9999991},"labels":[],"label_agreement":null},{"id":"W2105829241","doi":"10.1002/sim.2157","title":"Variance estimation for clustered recurrent event data with a small number of clusters","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"McMaster University","keywords":"Jackknife resampling; Estimator; Statistics; Variance (accounting); Mathematics; Parametric statistics; Econometrics; Computer science","score_opus":0.14738161384038687,"score_gpt":0.4531564777925362,"score_spread":0.30577486395214937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105829241","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006320183,0.00003362534,0.996539,0.00064160564,0.00015697135,0.00053645705,0.00086241786,0.000013937995,0.000583994],"genre_scores_gemma":[0.025658067,0.000025506088,0.97374195,0.00011606599,0.00010740385,0.000040652667,0.0001875533,0.000020655934,0.000102168924],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844754,0.00010258693,0.0006587324,0.00028997945,0.0002811253,0.00022003944],"domain_scores_gemma":[0.9952498,0.0036772224,0.00028234575,0.000539022,0.00017700475,0.000074622236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011917276,0.00015139721,0.00042212007,0.000054384065,0.000029024935,0.0000060509997,0.0002894512,0.000049287883,0.00018268808],"category_scores_gemma":[0.007466398,0.00011098634,0.000009952351,0.00014509157,0.00017283435,0.000045350316,0.0000737226,0.0001415164,0.0000026024957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035934002,0.00023615532,0.00021185694,0.00093154324,0.00004418074,0.000006293154,0.0010720555,0.00023973141,0.000017946528,0.6164604,0.009824767,0.37059572],"study_design_scores_gemma":[0.0023581483,0.00044466933,0.0005361223,0.0008874279,0.00012845172,0.000011699188,0.0001547792,0.62558085,0.00002254872,0.36877537,0.0009335348,0.00016639101],"about_ca_topic_score_codex":0.00004966888,"about_ca_topic_score_gemma":0.0002963915,"teacher_disagreement_score":0.6253411,"about_ca_system_score_codex":0.000056853318,"about_ca_system_score_gemma":0.00006940786,"threshold_uncertainty_score":0.8938516},"labels":[],"label_agreement":null},{"id":"W2105884242","doi":"10.1002/sim.5687","title":"A semiparametric marginal mixture cure model for clustered survival data","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Semiparametric regression; Expectation–maximization algorithm; Proportional hazards model; Mathematics; Estimating equations; Regression; Marginal model; Generalized estimating equation; Mixture model; Econometrics; Maximization; Semiparametric model; Data set; Regression analysis; Computer science; Applied mathematics; Mathematical optimization; Nonparametric statistics; Estimator; Maximum likelihood","score_opus":0.2795852382993958,"score_gpt":0.4776737204319478,"score_spread":0.19808848213255198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105884242","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036028598,0.0003128332,0.9933151,0.00043424938,0.00067582086,0.0004601288,0.0031199604,0.000029849203,0.001291757],"genre_scores_gemma":[0.046346616,0.00007732416,0.95180815,0.00022496872,0.0004961284,0.00003898651,0.00036558489,0.000038549897,0.0006037093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99790806,0.00015839053,0.0005816526,0.00033475657,0.00045351847,0.0005636524],"domain_scores_gemma":[0.9909072,0.0078002415,0.00016554081,0.0007528498,0.00015661815,0.00021757034],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002623215,0.00022691385,0.00057613826,0.00016713206,0.0000610889,0.000012464147,0.0004928671,0.00012792299,0.00023504402],"category_scores_gemma":[0.02410941,0.00017486702,0.000018057053,0.000353515,0.00018002836,0.00008758022,0.0001706727,0.0003487588,0.000006605082],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087517416,0.00016329475,0.0010639471,0.0004640217,0.000029707244,0.000006436675,0.0008902973,0.000013088227,0.000030383031,0.87175936,0.109353304,0.016138626],"study_design_scores_gemma":[0.001059377,0.00010113236,0.0006761666,0.00011523862,0.00010836899,0.000005862147,0.00017312683,0.46140045,0.000003535999,0.5344792,0.0016960854,0.00018145588],"about_ca_topic_score_codex":0.000033696633,"about_ca_topic_score_gemma":0.000049933493,"teacher_disagreement_score":0.46138737,"about_ca_system_score_codex":0.000054530523,"about_ca_system_score_gemma":0.00006766081,"threshold_uncertainty_score":0.98411095},"labels":[],"label_agreement":null},{"id":"W2106169817","doi":"10.1002/sim.4394","title":"A longitudinal model for magnetic resonance imaging lesion count data in multiple sclerosis patients","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Multiple Sclerosis Research Studies","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Magnetic resonance imaging; Nonparametric statistics; Computer science; Parametric statistics; Statistical power; Markov chain; Statistics; Data mining; Medical physics; Artificial intelligence; Pattern recognition (psychology); Machine learning; Medicine; Mathematics; Radiology","score_opus":0.2889380930924304,"score_gpt":0.3821583364372672,"score_spread":0.0932202433448368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106169817","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39353597,0.022314707,0.5500027,0.0034943079,0.001426614,0.013016418,0.012390435,0.00023358391,0.00358527],"genre_scores_gemma":[0.8916699,0.001855172,0.105156556,0.00022375231,0.00009181939,0.00016800224,0.00061017775,0.000043417578,0.00018118751],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972868,0.000058442954,0.0006710692,0.0006501778,0.0007433855,0.00059010426],"domain_scores_gemma":[0.99794143,0.0006412365,0.000102552614,0.0007939855,0.0003604101,0.00016035324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010612231,0.00023722385,0.00056454923,0.00033112685,0.000090294525,0.0000074263176,0.00036197004,0.00005473195,0.00008343032],"category_scores_gemma":[0.0069230925,0.0001967761,0.000019720002,0.00030935978,0.00043505518,0.000119289994,0.00032459357,0.00032107483,0.00000638513],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000974882,0.00050735084,0.8923091,0.00031572575,0.000009447709,0.000040915504,0.002115479,0.000013914428,0.00033991714,0.00023729817,0.020186115,0.08294982],"study_design_scores_gemma":[0.006924229,0.0002974057,0.61335367,0.00088266336,0.000029663377,9.847059e-7,0.00017177999,0.37740362,0.000014199183,0.00047640462,0.00032912006,0.00011625161],"about_ca_topic_score_codex":0.0012069918,"about_ca_topic_score_gemma":0.0025755537,"teacher_disagreement_score":0.49813396,"about_ca_system_score_codex":0.0002230345,"about_ca_system_score_gemma":0.00011129993,"threshold_uncertainty_score":0.82880884},"labels":[],"label_agreement":null},{"id":"W2107476951","doi":"10.1002/sim.1764","title":"Test of treatment effect in pre‐drug and post‐drug count data with zero‐inflation","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"National Cancer Institute","keywords":"Likelihood-ratio test; Score test; Statistics; Statistic; Mathematics; Test statistic; Null hypothesis; Medicine; Statistical hypothesis testing","score_opus":0.21690093327361057,"score_gpt":0.5248629691353153,"score_spread":0.3079620358617047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107476951","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4138276,0.0004003686,0.5757674,0.0016222588,0.00046750557,0.0031158584,0.0039255396,0.00006142483,0.00081206777],"genre_scores_gemma":[0.31588,0.00017516587,0.6836015,0.00006322498,0.00007947956,0.000029725556,0.00008222092,0.000029161487,0.000059506197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99748105,0.00039469253,0.0010284242,0.00042566223,0.00043203405,0.00023814937],"domain_scores_gemma":[0.93555546,0.063270144,0.000309123,0.000661437,0.00010638445,0.00009746221],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0036756399,0.000242421,0.0009596188,0.00014218217,0.000024669587,0.000008041184,0.00022188328,0.000069743255,0.00006033714],"category_scores_gemma":[0.07483487,0.00015326287,0.000011118272,0.0002516783,0.00045858775,0.000057310986,0.00008580708,0.00023213992,0.000002122412],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0041930894,0.0032216785,0.26063713,0.0054499945,0.00044596748,0.0009757462,0.0145900715,0.00050879404,0.0022407887,0.5616491,0.0066793486,0.13940834],"study_design_scores_gemma":[0.011533423,0.0033749787,0.05567244,0.0015427782,0.00028372786,0.000009884228,0.00012226435,0.0014066505,0.0003703838,0.92541295,0.000050951774,0.00021955933],"about_ca_topic_score_codex":0.0014387171,"about_ca_topic_score_gemma":0.0019025955,"teacher_disagreement_score":0.3637639,"about_ca_system_score_codex":0.00020951648,"about_ca_system_score_gemma":0.00011719677,"threshold_uncertainty_score":0.9329582},"labels":[],"label_agreement":null},{"id":"W2107724629","doi":"10.1002/sim.1095","title":"Detecting and eliminating erroneous gestational ages: a normal mixture model","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Birth, Development, and Health","field":"Medicine","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada; Dalhousie University; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Gestational age; Birth weight; Medicine; Obstetrics; Population; Small for gestational age; Gestation; Pregnancy","score_opus":0.030349878838301425,"score_gpt":0.3359374601667724,"score_spread":0.30558758132847097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107724629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.56921756,0.0013366902,0.40060154,0.007202766,0.00040049432,0.00080012024,0.00008233287,0.00011720776,0.02024131],"genre_scores_gemma":[0.80748445,0.009424203,0.18031666,0.0021468105,0.00024208124,0.00001513962,0.00011332322,0.000026425463,0.00023090045],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985098,0.00003351017,0.00045180286,0.00025729192,0.00039621044,0.00035137916],"domain_scores_gemma":[0.9991211,0.0003098229,0.00011684357,0.000119105636,0.00013798533,0.00019508413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005865045,0.000159152,0.00033013694,0.00020067787,0.00013029315,0.0000069105927,0.000047848258,0.00009307286,0.00011200192],"category_scores_gemma":[0.0010128749,0.00013646882,0.000009897368,0.00019313715,0.00015038454,0.000040127834,0.000027625732,0.00046070054,0.0000045436573],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001283577,0.00049251056,0.2233402,0.0037207033,0.00017316092,0.0057557593,0.058431517,0.0012031452,0.0052185794,0.28332996,0.02015166,0.39689922],"study_design_scores_gemma":[0.010811411,0.0014750583,0.32594407,0.0020786345,0.00021142827,0.002465842,0.005821019,0.49190545,0.0000833613,0.15768808,0.0008560518,0.0006596049],"about_ca_topic_score_codex":0.00015235574,"about_ca_topic_score_gemma":0.00045131004,"teacher_disagreement_score":0.4907023,"about_ca_system_score_codex":0.00010706848,"about_ca_system_score_gemma":0.00019137311,"threshold_uncertainty_score":0.5565037},"labels":[],"label_agreement":null},{"id":"W2108268423","doi":"10.1002/sim.745","title":"Logistic discrimination of mixtures of M. tuberculosis and non‐specific tuberculin reactions","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"International Union Against Tuberculosis and Lung Disease","keywords":"Homogeneity (statistics); Tuberculin; Tuberculosis; Logistic regression; Goodness of fit; Tuberculin test; Medicine; Statistics; Mathematics; Pathology","score_opus":0.03422861188760234,"score_gpt":0.32867853000775166,"score_spread":0.2944499181201493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108268423","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035715336,0.0006472949,0.9922944,0.0007387587,0.00021239126,0.00011769442,0.00002010359,0.000009461635,0.0023884056],"genre_scores_gemma":[0.519528,0.0013950352,0.4789219,0.00004137913,0.00003621572,0.000004187847,0.000008232653,0.0000046413697,0.00006047926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886024,0.00009479763,0.00044516046,0.00022312716,0.00023995448,0.00013670446],"domain_scores_gemma":[0.9988678,0.00050111226,0.00014213288,0.00030050654,0.00013104203,0.000057389636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006108692,0.00010440136,0.0002958765,0.00021375193,0.000028665067,0.000006400819,0.00019823121,0.000054943874,0.000024742149],"category_scores_gemma":[0.00038106224,0.00008337008,0.0000148887075,0.0003680145,0.00025175526,0.0000802758,0.000051570256,0.00013128662,5.980343e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001884958,0.00010902512,0.0007810204,0.00021777512,0.000018091465,0.000037043897,0.002463696,0.000035645826,0.011649377,0.7325504,0.0020267835,0.2500923],"study_design_scores_gemma":[0.0015717119,0.00059593935,0.07634159,0.0007348145,0.00007774016,0.00008248766,0.000254053,0.061673354,0.0030199103,0.8540999,0.0012389922,0.0003094956],"about_ca_topic_score_codex":0.00026516055,"about_ca_topic_score_gemma":0.00006611496,"teacher_disagreement_score":0.5159564,"about_ca_system_score_codex":0.000021022162,"about_ca_system_score_gemma":0.000019115996,"threshold_uncertainty_score":0.33997336},"labels":[],"label_agreement":null},{"id":"W2108304037","doi":"10.1002/sim.3335","title":"Nonparametric statistical inference method for partial areas under receiver operating characteristic curves, with application to genomic studies","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Receiver operating characteristic; Nonparametric statistics; Confidence interval; Statistics; Statistical inference; Inference; Statistical hypothesis testing; Asymptotic distribution; Statistic; False positive paradox; Sample size determination; Mathematics; Computer science; Normality; Artificial intelligence; Estimator","score_opus":0.03394799462728353,"score_gpt":0.3616748351351232,"score_spread":0.3277268405078397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108304037","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037239347,0.0008704804,0.96035916,0.00028250285,0.00013274897,0.0007497571,0.0002757129,0.0000083562,0.000081953935],"genre_scores_gemma":[0.35977843,0.00045547736,0.63749063,0.0010657113,0.00025551414,0.000261639,0.00050283136,0.00002460099,0.00016520079],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9986005,0.00009329664,0.00038151056,0.00045250158,0.00019223776,0.00027998738],"domain_scores_gemma":[0.998799,0.00046870776,0.00010011665,0.00027044644,0.00023628175,0.00012543879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003478542,0.0001974778,0.00034294676,0.00007661461,0.00010687638,0.0000049857676,0.00015741115,0.000068408204,0.000024599416],"category_scores_gemma":[0.0014976438,0.00015917835,0.00001235357,0.00018642115,0.00022969641,0.000002644787,0.000053330426,0.000118956166,0.0000058420324],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004216128,0.0014952804,0.078394376,0.004079205,0.0017580366,0.00008260619,0.009144658,0.061614197,0.16520394,0.34525695,0.13198227,0.19677235],"study_design_scores_gemma":[0.006055614,0.0091181155,0.9392802,0.00079008006,0.00042059703,0.00014516061,0.0010255113,0.0064698895,0.0028790317,0.01897104,0.01339757,0.0014471879],"about_ca_topic_score_codex":0.00005722387,"about_ca_topic_score_gemma":0.00007623038,"teacher_disagreement_score":0.8608858,"about_ca_system_score_codex":0.00003763585,"about_ca_system_score_gemma":0.00013292898,"threshold_uncertainty_score":0.64911044},"labels":[],"label_agreement":null},{"id":"W2108885350","doi":"10.1002/sim.1107","title":"A new approach to training back‐propagation artificial neural networks: empirical evaluation on ten data sets from clinical studies","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Initialization; Artificial neural network; Backpropagation; Computer science; Logistic regression; Artificial intelligence; Deviance (statistics); Training set; Machine learning; Regularization (linguistics); Data mining; Statistics; Mathematics","score_opus":0.5224149863755513,"score_gpt":0.4928430757635104,"score_spread":0.029571910612040897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108885350","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017666984,0.00024188595,0.98668027,0.009007512,0.0008112557,0.0005791266,0.00004481032,0.00004501844,0.0008233982],"genre_scores_gemma":[0.4882162,0.00018199376,0.50244385,0.005153988,0.0030766202,0.00007096641,0.0006783872,0.00002551893,0.00015249991],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997281,0.00031261423,0.0007163044,0.00079194823,0.00061545894,0.0002826778],"domain_scores_gemma":[0.9972776,0.0013387806,0.0001498067,0.00092803896,0.00011525236,0.00019052165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015235372,0.00016866314,0.00036537007,0.000088279405,0.00010526102,0.00005146938,0.00083418406,0.000068091605,0.00007318546],"category_scores_gemma":[0.001219463,0.00013363753,0.000016962562,0.00062611344,0.00009525492,0.0001467631,0.0002560029,0.00035634,0.000063003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012084365,0.00008586709,0.0002163219,0.0000032191438,0.000018204195,0.0000053645076,0.0014950406,0.014911683,0.0000029778696,0.005553774,0.29325017,0.68444526],"study_design_scores_gemma":[0.0005154275,0.00017245593,0.0042047687,0.000053657695,0.000032838954,0.0000021622093,0.00017817004,0.9810816,4.369673e-7,0.012436409,0.0011873181,0.00013472907],"about_ca_topic_score_codex":0.000042654392,"about_ca_topic_score_gemma":0.000089787485,"teacher_disagreement_score":0.96616995,"about_ca_system_score_codex":0.00005404768,"about_ca_system_score_gemma":0.00003663471,"threshold_uncertainty_score":0.54495806},"labels":[],"label_agreement":null},{"id":"W2109920122","doi":"10.1002/sim.1261","title":"Exact unconditional tests for testing non‐inferiority in matched‐pairs design","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"Nuisance parameter; Exact statistics; Mathematics; Confidence interval; Sample size determination; Statistics; Monotonic function; Statistical hypothesis testing; Nominal level; Exact test; Score test; Applied mathematics; Estimator; Mathematical analysis","score_opus":0.6511081763640518,"score_gpt":0.5669361148639607,"score_spread":0.08417206150009116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109920122","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00142505,0.00003587284,0.9933546,0.0005647678,0.00065429596,0.0012156707,0.00062797137,0.00006034517,0.0020613924],"genre_scores_gemma":[0.038291145,0.00002145011,0.9604501,0.0002799008,0.00049217744,0.00020474446,0.000021490632,0.000052173087,0.000186805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962431,0.0005451982,0.00161147,0.00048476004,0.00057099084,0.00054448616],"domain_scores_gemma":[0.82954144,0.16943027,0.0003108117,0.00033175093,0.00022839097,0.00015732613],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0064164153,0.00029005684,0.0010468299,0.0002273588,0.00006979025,0.00001648989,0.00027065456,0.00019545652,0.0013028666],"category_scores_gemma":[0.38962734,0.00025521012,0.000038587008,0.00055607484,0.0003877556,0.000054325148,0.000053595675,0.0005347592,0.0000284546],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004352017,0.0020735364,0.03580517,0.0026440239,0.00014876368,0.00091517426,0.0024333186,0.00039061913,0.001125337,0.5949416,0.24572814,0.1133591],"study_design_scores_gemma":[0.003559438,0.0005802412,0.014334956,0.0005976014,0.000061620245,0.000009306306,0.00010621621,0.031259082,0.00004305964,0.9490823,0.00010932995,0.00025685458],"about_ca_topic_score_codex":0.00006255198,"about_ca_topic_score_gemma":0.00006927885,"teacher_disagreement_score":0.38321093,"about_ca_system_score_codex":0.00019755,"about_ca_system_score_gemma":0.00007454694,"threshold_uncertainty_score":0.99999},"labels":[],"label_agreement":null},{"id":"W2110136166","doi":"10.1002/sim.6563","title":"Testing for treatment‐biomarker interaction based on local partial‐likelihood","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Biomarker; Computer science; Statistics; Econometrics; Mathematics; Biology; Genetics","score_opus":0.2507980355314263,"score_gpt":0.46878566211708883,"score_spread":0.2179876265856625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110136166","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010507654,0.000012481719,0.99225587,0.00031701353,0.00052043254,0.00038125305,0.00016609406,0.00003879095,0.005257274],"genre_scores_gemma":[0.30615476,0.000001146225,0.6932356,0.00023438921,0.00015578263,0.000093247174,0.0000445948,0.000024083132,0.00005643583],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985776,0.00015487296,0.0004571428,0.00025147956,0.0002718054,0.0002871299],"domain_scores_gemma":[0.9886957,0.01055829,0.00013101262,0.00021824396,0.00022068855,0.00017608116],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009591362,0.00018072323,0.0003772322,0.0001096935,0.00004036109,0.000011089166,0.00007831896,0.000062208186,0.000117814976],"category_scores_gemma":[0.025052128,0.00013116804,0.000018121815,0.00017387947,0.00014352694,0.000023010996,0.000011170056,0.0000912564,0.000011487724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058582466,0.00049775926,0.0016316257,0.00016868183,0.000031493895,0.00006515262,0.0006821154,0.000093712035,0.00019709833,0.2777996,0.01779222,0.7004547],"study_design_scores_gemma":[0.0032183644,0.0029947853,0.0010055884,0.0002975368,0.000075553486,0.0000035434368,0.00050505693,0.43494365,0.0001621022,0.55515397,0.0014838611,0.00015601015],"about_ca_topic_score_codex":0.00017554681,"about_ca_topic_score_gemma":0.000061529325,"teacher_disagreement_score":0.70029867,"about_ca_system_score_codex":0.00026412026,"about_ca_system_score_gemma":0.0001085118,"threshold_uncertainty_score":0.98316026},"labels":[],"label_agreement":null},{"id":"W2110147390","doi":"10.1002/sim.1266","title":"Binary partitioning for continuous longitudinal data: categorizing a prognostic variable","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Population Health Research Institute; University of Toronto","funders":"","keywords":"Permutation (music); Statistics; Confidence interval; Statistic; Binary data; Binary number; Continuous variable; Variable (mathematics); Test statistic; Mathematics; Interval (graph theory); Set (abstract data type); Computer science; Data set; Statistical hypothesis testing; Combinatorics","score_opus":0.0849101194140717,"score_gpt":0.3404597345364128,"score_spread":0.2555496151223411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110147390","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005455721,0.000948204,0.9958007,0.00088131044,0.0006520023,0.00033322274,0.00007634285,0.000054506396,0.0011991718],"genre_scores_gemma":[0.037132137,0.0000756321,0.96175843,0.0002644472,0.00027541808,0.00005241839,0.000086580025,0.000012769863,0.00034214082],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849415,0.00008687391,0.00035835354,0.00047656026,0.00022076849,0.00036326595],"domain_scores_gemma":[0.99815977,0.00091595,0.000103980434,0.00061857066,0.000108600834,0.00009315326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011577393,0.00013745941,0.00030249008,0.00011160656,0.00011738224,0.000050511706,0.00064858526,0.000052080646,0.00005945861],"category_scores_gemma":[0.0013226453,0.00011826371,0.00000980732,0.00034517588,0.00009195604,0.00025034344,0.00017372017,0.0001818083,0.0000064210217],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007142792,0.000095530326,0.0015785452,0.00012613121,0.000020668393,0.00015278278,0.0007918238,0.00004198825,0.00015182419,0.8819156,0.044143844,0.070974104],"study_design_scores_gemma":[0.0010447362,0.00036136227,0.00094436074,0.00021379974,0.00004133334,0.00004069153,0.000027592505,0.7072869,0.000010371285,0.28209287,0.0077368123,0.00019915737],"about_ca_topic_score_codex":0.000059541304,"about_ca_topic_score_gemma":0.000020267678,"teacher_disagreement_score":0.70724493,"about_ca_system_score_codex":0.000031623436,"about_ca_system_score_gemma":0.000034937377,"threshold_uncertainty_score":0.4822654},"labels":[],"label_agreement":null},{"id":"W2110182275","doi":"10.1002/sim.4087","title":"Copula‐based regression models for a bivariate mixed discrete and continuous outcome","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":132,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Copula (linguistics); Bivariate analysis; Covariate; Econometrics; Joint probability distribution; Marginal distribution; Marginal model; Regression; Mathematics; Statistics; Regression analysis; Computer science; Random variable","score_opus":0.08217114540050523,"score_gpt":0.43601078137216187,"score_spread":0.35383963597165663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110182275","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024209893,0.000025523475,0.9946989,0.00064386433,0.00058751885,0.00050434266,0.00055675296,0.000035624736,0.0005264869],"genre_scores_gemma":[0.15722646,0.000007842497,0.8422791,0.00015992114,0.000102616745,0.00005620605,0.0000387331,0.000027801243,0.00010136156],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99837446,0.00010910606,0.00063149683,0.0003110906,0.00026484695,0.0003089983],"domain_scores_gemma":[0.9935064,0.005701514,0.0001941159,0.0003031654,0.0001389172,0.00015591999],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012233175,0.00021167326,0.000621008,0.00011855524,0.00007883861,0.000020086049,0.00013992543,0.000121165824,0.00009797138],"category_scores_gemma":[0.011116195,0.00014374862,0.000021464104,0.00011375393,0.00031897504,0.000038478727,0.00003840659,0.00035428553,6.7778103e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087625805,0.000038109607,0.0010207144,0.00029523374,0.0000085681495,0.000026864975,0.00020078498,8.4712457e-7,0.0007056268,0.96988976,0.0026502889,0.025075551],"study_design_scores_gemma":[0.00195865,0.00021887943,0.0012498975,0.00022384801,0.00006667654,0.00000492887,0.000072403156,0.09910513,0.00006683332,0.8966753,0.00018809362,0.00016936168],"about_ca_topic_score_codex":0.000082408274,"about_ca_topic_score_gemma":0.00016519627,"teacher_disagreement_score":0.15480547,"about_ca_system_score_codex":0.000015822308,"about_ca_system_score_gemma":0.000031458192,"threshold_uncertainty_score":0.9972136},"labels":[],"label_agreement":null},{"id":"W2110786877","doi":"10.1002/sim.3444","title":"A Bayesian multilevel model for estimating the diet/disease relationship in a multicenter study with exposures measured with error: The EPIC study","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute","keywords":"European Prospective Investigation into Cancer and Nutrition; Breast cancer; Medicine; Gibbs sampling; Statistics; Multilevel model; Cancer; Incidence (geometry); Prospective cohort study; Disease; Bayesian probability; Demography; Oncology; Internal medicine; Mathematics","score_opus":0.0986514510617566,"score_gpt":0.3617802300035223,"score_spread":0.2631287789417657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110786877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.645324,0.0004480753,0.34010723,0.0048128283,0.00010934807,0.008847056,0.00017137526,0.00003898792,0.0001410989],"genre_scores_gemma":[0.95445234,0.000008405949,0.043858055,0.00037402514,0.0001215925,0.0010110816,0.000035304463,0.00003198043,0.000107194195],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99798906,0.00015357946,0.0004988815,0.0003361092,0.00072423177,0.00029815553],"domain_scores_gemma":[0.99769604,0.0014265326,0.0001329504,0.00036795347,0.000262166,0.000114351315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000856437,0.00023011601,0.00041709762,0.000103297774,0.00041522572,0.000007707365,0.0001332364,0.000024507639,0.000010245729],"category_scores_gemma":[0.0019873164,0.000105686246,0.000021542168,0.00024788978,0.00035849478,0.00003643471,0.000035583438,0.00034896587,8.1408746e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004773806,0.002071788,0.96293676,0.000102739556,0.00011908111,0.00030608053,0.019660736,0.008315524,8.7245047e-7,0.00026310107,0.0012625381,0.00018698424],"study_design_scores_gemma":[0.012151116,0.0027053386,0.6488253,0.00029573758,0.00024209874,0.00000728823,0.01210874,0.32274207,7.561617e-8,0.0008193106,0.0000066309567,0.000096294076],"about_ca_topic_score_codex":0.0003759519,"about_ca_topic_score_gemma":0.0048146327,"teacher_disagreement_score":0.31442654,"about_ca_system_score_codex":0.00009384578,"about_ca_system_score_gemma":0.0001285886,"threshold_uncertainty_score":0.430976},"labels":[],"label_agreement":null},{"id":"W2110818436","doi":"10.1002/sim.6607","title":"Moving towards best practice when using inverse probability of treatment weighting (IPTW) using the propensity score to estimate causal treatment effects in observational studies","year":2015,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4309,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; National Institute of Mental Health; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Inverse probability weighting; Observational study; Inverse probability; Weighting; Average treatment effect; Statistics; Treatment and control groups; Econometrics; Sample size determination; Baseline (sea); Mathematics; Selection bias; Computer science; Posterior probability; Medicine; Bayesian probability","score_opus":0.6765608631638398,"score_gpt":0.5702584500397571,"score_spread":0.10630241312408273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110818436","genre_codex":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011806213,0.798593,0.1680657,0.0002591576,0.000776616,0.019474735,0.0005742618,0.00017279174,0.00027753433],"genre_scores_gemma":[0.0000461117,0.22818658,0.7710488,0.000028378035,0.00013268158,0.00038503396,0.000067938774,0.00007215919,0.00003233563],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956156,0.0009921558,0.0016808601,0.00060616253,0.0006564941,0.00044872993],"domain_scores_gemma":[0.9908638,0.00617586,0.001314674,0.0006982357,0.0008240381,0.00012338949],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026964298,0.0007237854,0.0031906613,0.00029772744,0.00010944421,0.0000176138,0.0002717285,0.00018826159,0.000006667016],"category_scores_gemma":[0.023051841,0.00041989377,0.000078120356,0.00056975946,0.00041745664,0.00017842643,0.0002624058,0.0004139525,0.0000011613803],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020542304,0.0020609275,0.0015475958,0.07049702,0.0014108038,0.0009908285,0.027532509,0.0016593756,0.000060217648,0.061163206,0.00041195707,0.83246017],"study_design_scores_gemma":[0.003798125,0.00917749,0.00008317934,0.23041928,0.012964728,0.000320958,0.0029605366,0.013449472,0.00011405706,0.69563556,0.028882224,0.002194393],"about_ca_topic_score_codex":0.0021494594,"about_ca_topic_score_gemma":0.001972817,"teacher_disagreement_score":0.83026576,"about_ca_system_score_codex":0.0070568663,"about_ca_system_score_gemma":0.0015856574,"threshold_uncertainty_score":0.9998253},"labels":[],"label_agreement":null},{"id":"W2110863526","doi":"10.1002/sim.2375","title":"Generalized gamma frailty model","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Frailty in Older Adults","field":"Medicine","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Weibull distribution; Angina; Isosorbide dinitrate; Mathematics; Monte Carlo method; Generalization; Computer science; Statistics; Applied mathematics; Medicine; Cardiology; Myocardial infarction","score_opus":0.04814974984037414,"score_gpt":0.3575446066813403,"score_spread":0.3093948568409662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110863526","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16028695,0.0025337746,0.68896633,0.06534814,0.0012106184,0.001977755,0.00052138406,0.00043944156,0.07871563],"genre_scores_gemma":[0.5013626,0.00050586736,0.46802765,0.0073104654,0.0012021156,0.000047390655,0.00035621217,0.00007255351,0.021115135],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798584,0.000041589366,0.0005969582,0.00034638034,0.00060777296,0.0004214468],"domain_scores_gemma":[0.9988192,0.00019263245,0.00008994411,0.00048430107,0.0001590906,0.0002548314],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003729016,0.00022890113,0.000546436,0.0002275765,0.00004009456,0.0000056613294,0.00014368667,0.00011844938,0.001391834],"category_scores_gemma":[0.0011422926,0.00018892188,0.000030613544,0.00025395543,0.00027012514,0.00005559035,0.000041710042,0.00042395238,0.00014160956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005263486,0.00049980904,0.0068472824,0.00037333497,0.00011852818,0.0006378603,0.0045603635,0.0058440687,0.0071919067,0.07833672,0.7226636,0.17240019],"study_design_scores_gemma":[0.022090515,0.0008624969,0.018853063,0.00089780183,0.00027981156,0.00024179462,0.0002808665,0.8277188,0.0010272433,0.029960878,0.0971559,0.0006308421],"about_ca_topic_score_codex":0.00014840752,"about_ca_topic_score_gemma":0.00039667223,"teacher_disagreement_score":0.82187474,"about_ca_system_score_codex":0.0002014925,"about_ca_system_score_gemma":0.00013418807,"threshold_uncertainty_score":0.999521},"labels":[],"label_agreement":null},{"id":"W2111018099","doi":"10.1002/sim.1851","title":"The use of quantile regression in health care research: a case study examining gender differences in the timeliness of thrombolytic therapy","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; Institute for Clinical Evaluative Sciences; Women's College Hospital; Toronto General Hospital; University of Toronto","funders":"","keywords":"Quantile regression; Quantile; Thrombolysis; Medicine; Regression analysis; Statistics; Regression; Linear regression; Econometrics; Proportional hazards model; Myocardial infarction; Mathematics; Internal medicine","score_opus":0.8464695569015244,"score_gpt":0.5826981290513751,"score_spread":0.2637714278501493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111018099","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9865441,0.0058901473,0.0016118655,0.0041806083,0.00019596286,0.0013800679,0.00013901106,0.0000034452416,0.000054840133],"genre_scores_gemma":[0.99628884,0.0012358874,0.0017999621,0.0005056427,0.00005821021,0.000074446354,0.00001281199,0.0000135893915,0.000010618983],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99346364,0.0018524618,0.0037299371,0.00032168924,0.00028263283,0.00034964026],"domain_scores_gemma":[0.98959297,0.008500353,0.0012137748,0.00051877927,0.00012465173,0.00004949338],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.032061394,0.00012836332,0.00091116165,0.00051261176,0.00014608735,0.000018518458,0.00030930762,0.000057424237,0.000027652786],"category_scores_gemma":[0.008210455,0.00008575466,0.000015361826,0.0006007687,0.00033745324,0.00008979698,0.000041067047,0.00038894374,0.0000044983926],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007889662,0.00057228294,0.5584932,0.0007421633,0.00003207785,0.00012709037,0.38351884,0.0007639165,0.0000018684947,0.051583566,0.0015940433,0.0024920846],"study_design_scores_gemma":[0.004190955,0.0012823803,0.5038645,0.0009514555,0.0000028782501,0.000020589201,0.465622,0.0035591628,0.0000010537121,0.020010427,0.0003402207,0.00015430857],"about_ca_topic_score_codex":0.03980307,"about_ca_topic_score_gemma":0.022360258,"teacher_disagreement_score":0.082103185,"about_ca_system_score_codex":0.00033738368,"about_ca_system_score_gemma":0.00031523188,"threshold_uncertainty_score":0.9966965},"labels":[],"label_agreement":null},{"id":"W2111584093","doi":"10.1002/sim.4444","title":"Effect of dependent errors in the assessment of diagnostic or screening test accuracy when the reference standard is imperfect","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Hemodynamic Monitoring and Therapy","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Medical Research Council; National Health and Medical Research Council","keywords":"Computer science; Statistics; Imperfect; Test (biology); Diagnostic accuracy; Medicine; Mathematics; Internal medicine","score_opus":0.03475759916229025,"score_gpt":0.4109700804001137,"score_spread":0.3762124812378234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111584093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9649546,0.00092837727,0.029392496,0.0015158097,0.0003995179,0.0013213889,0.0002521614,0.00001393624,0.0012216789],"genre_scores_gemma":[0.994568,0.00069588504,0.0042535383,0.00016796072,0.00016927985,0.00005185703,0.000028880813,0.00001736968,0.0000472363],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977454,0.00042918083,0.0005721089,0.0001547703,0.0007894041,0.0003091372],"domain_scores_gemma":[0.9716416,0.027533494,0.00021687243,0.00044525793,0.00008972498,0.00007303814],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004441423,0.00017693028,0.00055394054,0.00012007869,0.000044672248,0.000004022149,0.00022983257,0.00006409952,0.00019511812],"category_scores_gemma":[0.013841848,0.00007846056,0.000025283634,0.00024459616,0.00024277736,0.0000366458,0.00003692007,0.0005130132,0.0000010636799],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005157626,0.00021893278,0.89021325,0.0006868098,0.00007783807,0.00008102994,0.0081823785,0.000024068197,0.001161543,0.0010821036,0.0014297098,0.09632658],"study_design_scores_gemma":[0.011197736,0.012394178,0.95639986,0.0047760927,0.0005651599,0.000102819446,0.00406638,0.0036939124,0.003724933,0.00092409813,0.001861212,0.00029363923],"about_ca_topic_score_codex":0.00071900466,"about_ca_topic_score_gemma":0.00011599365,"teacher_disagreement_score":0.09603294,"about_ca_system_score_codex":0.000095783245,"about_ca_system_score_gemma":0.00011692734,"threshold_uncertainty_score":0.994465},"labels":[],"label_agreement":null},{"id":"W2111616613","doi":"10.1002/sim.5827","title":"Inverse probability weighted estimating equations for randomized trials in transfusion medicine","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research","keywords":"Medicine; Confounding; Randomized controlled trial; Inverse probability; Clinical trial; Platelet transfusion; Intensive care medicine; Platelet; Emergency medicine; Internal medicine; Statistics; Mathematics","score_opus":0.5703369182139181,"score_gpt":0.5825705942847677,"score_spread":0.012233676070849575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111616613","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019687875,0.000047150563,0.9802781,0.0055706403,0.0014337075,0.009570028,0.00018211405,0.00006974602,0.0008797272],"genre_scores_gemma":[0.0035732365,0.000104265746,0.99291474,0.00036748956,0.0006857097,0.0021447372,0.000052667456,0.00004896643,0.000108167544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98408204,0.0076779868,0.0062975558,0.00063726347,0.00076225394,0.00054287346],"domain_scores_gemma":[0.38310555,0.61440885,0.0011338614,0.00056753185,0.0005453125,0.00023891818],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0719812,0.0003763464,0.0047757127,0.00040977108,0.00008790536,0.000016210139,0.00030319963,0.00025929563,0.003334058],"category_scores_gemma":[0.8818281,0.00024849336,0.00015599991,0.0006322368,0.0012723905,0.00008858288,0.000044119308,0.00055274647,0.000014534006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0074456064,0.00039059727,0.00017330499,0.0012707703,0.00011001218,0.00001335658,0.0027995796,0.00004741611,0.00036758106,0.91596526,0.020482318,0.05093422],"study_design_scores_gemma":[0.10784712,0.00025398599,0.00008022649,0.00088454835,0.00027779778,8.673316e-7,0.00019498804,0.1528567,0.000017757548,0.7373855,0.000026081467,0.00017443152],"about_ca_topic_score_codex":0.0010404366,"about_ca_topic_score_gemma":0.00056690443,"teacher_disagreement_score":0.80984694,"about_ca_system_score_codex":0.00017709935,"about_ca_system_score_gemma":0.00011625573,"threshold_uncertainty_score":0.9999967},"labels":[],"label_agreement":null},{"id":"W2114217608","doi":"10.1002/sim.4192","title":"Comparison of two populations of curves with an application in neuronal data analysis","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Control Systems and Identification","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Carnegie Mellon University; University of Pittsburgh","keywords":"Nonparametric statistics; Statistic; Test statistic; Statistical hypothesis testing; Parametric statistics; Bayesian probability; Statistics; Mathematics; Functional data analysis; Histogram; Akaike information criterion; Computer science; Pattern recognition (psychology); Artificial intelligence","score_opus":0.09554432008486988,"score_gpt":0.37469032354282217,"score_spread":0.27914600345795226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114217608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14361167,0.00032573074,0.8553267,0.000014196253,0.000048080754,0.0001786294,0.00020533014,0.000010714158,0.00027893466],"genre_scores_gemma":[0.98789316,0.00002361014,0.011193999,0.0000022268075,0.000012891243,0.000007747459,0.000857929,0.000005259106,0.00000315095],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992844,0.000026450709,0.00040663275,0.00009871033,0.00013267122,0.0000511753],"domain_scores_gemma":[0.9994419,0.00003639448,0.00009692532,0.00035907302,0.00004754913,0.000018117098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002528133,0.000045911806,0.00024390766,0.00019789972,0.000005161367,9.046132e-7,0.00012367607,0.000012124478,0.000023200935],"category_scores_gemma":[0.000046684374,0.000040129613,0.000004083289,0.00042582786,0.000036781727,0.00005373365,0.000008494897,0.000051543637,3.0916357e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018472301,0.00011081871,0.96414685,0.00026956326,0.000060916507,6.742045e-7,0.0012341152,0.013570284,0.001448722,0.0131421015,0.0003532095,0.0056442725],"study_design_scores_gemma":[0.00022903502,0.000034411623,0.5679394,0.000051944466,0.000095654104,9.7965554e-8,0.000088198365,0.43099082,0.000023343473,0.00051221345,0.000008130766,0.00002677069],"about_ca_topic_score_codex":0.0038737431,"about_ca_topic_score_gemma":0.025705328,"teacher_disagreement_score":0.8442815,"about_ca_system_score_codex":0.0000106247735,"about_ca_system_score_gemma":0.0000062452204,"threshold_uncertainty_score":0.992073},"labels":[],"label_agreement":null},{"id":"W2115003020","doi":"10.1002/sim.6178","title":"Impact of the model‐building strategy on inference about nonlinear and time‐dependent covariate effects in survival analysis","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Spurious relationship; Econometrics; Proportional hazards model; Inference; Multivariable calculus; Context (archaeology); Statistics; Computer science; Mathematics; Artificial intelligence","score_opus":0.06310715120089137,"score_gpt":0.43557922383711273,"score_spread":0.37247207263622134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115003020","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20852047,0.000013558311,0.7901307,0.000023072558,0.00005673376,0.00018393727,0.0001466347,0.0000065704544,0.0009183498],"genre_scores_gemma":[0.8130914,0.000020943215,0.18678424,0.000025170159,0.00002648654,0.0000061287255,0.000006417454,0.0000115116,0.000027727761],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799496,0.0005147073,0.0005658895,0.00025703735,0.00041675093,0.00025062732],"domain_scores_gemma":[0.9899536,0.009305975,0.00021187027,0.00034560953,0.00009984637,0.00008312012],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018980955,0.00019237405,0.0007251246,0.00022289573,0.000032501037,0.000011868327,0.0001949449,0.00007674115,0.00008314307],"category_scores_gemma":[0.013898935,0.00011644882,0.00003837272,0.00052027154,0.00021310354,0.000020702466,0.00006712398,0.0003342612,0.0000012277293],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080142796,0.00015044627,0.02413443,0.00022479308,0.00014867609,0.000010093268,0.00055628485,0.018762067,0.0008536592,0.9419674,0.000041869152,0.013070113],"study_design_scores_gemma":[0.0005751739,0.00029613083,0.09416344,0.00018550387,0.00012581119,3.224537e-7,0.000010830718,0.5324996,0.000029158362,0.37203747,2.2478049e-7,0.000076358425],"about_ca_topic_score_codex":0.00063099834,"about_ca_topic_score_gemma":0.0002059883,"teacher_disagreement_score":0.6045709,"about_ca_system_score_codex":0.00006337205,"about_ca_system_score_gemma":0.00006699792,"threshold_uncertainty_score":0.9944074},"labels":[],"label_agreement":null},{"id":"W2115556810","doi":"10.1002/sim.6602","title":"Optimal full matching for survival outcomes: a method that merits more widespread use","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; National Institute of Mental Health; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Matching (statistics); Computer science; Statistics; Survival analysis; Propensity score matching; Econometrics; Mathematics","score_opus":0.33550950521288825,"score_gpt":0.5206100027822268,"score_spread":0.18510049756933855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115556810","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0067818807,0.000035842706,0.9906246,0.0006453011,0.00042169145,0.0006933033,0.0003053893,0.00021219612,0.00027978036],"genre_scores_gemma":[0.011036522,0.00002152428,0.98783815,0.0002762758,0.00009592873,0.00013654948,0.000084533225,0.00007191842,0.00043859362],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978845,0.00016267042,0.0005982985,0.00034273867,0.0005814085,0.0004303471],"domain_scores_gemma":[0.9906164,0.0081773065,0.00025647334,0.0004569849,0.00029583016,0.00019700373],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021452082,0.0003064504,0.0008335517,0.0001801146,0.00004602185,0.000023630444,0.0002802006,0.00011991994,0.000047755297],"category_scores_gemma":[0.013807979,0.00024160316,0.00003665055,0.00014625322,0.0001823218,0.00020312093,0.00010019604,0.0003307874,0.0000040284326],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003229625,0.0001793154,0.0035865745,0.00043752577,0.00011199749,0.00016970362,0.010126838,0.00020691613,0.0012650117,0.9448155,0.028931087,0.009846566],"study_design_scores_gemma":[0.0017136451,0.00045760925,0.00038856504,0.0003126428,0.00010132323,0.000018919887,0.002958239,0.0039536827,0.0005022667,0.98815924,0.0011008888,0.00033296854],"about_ca_topic_score_codex":0.00024445637,"about_ca_topic_score_gemma":0.00023592635,"teacher_disagreement_score":0.04334375,"about_ca_system_score_codex":0.00016923284,"about_ca_system_score_gemma":0.00008108171,"threshold_uncertainty_score":0.99449915},"labels":[],"label_agreement":null},{"id":"W2115650046","doi":"10.1002/sim.1674","title":"Evaluation of Cox's model and logistic regression for matched case‐control data with time‐dependent covariates: a simulation study","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University; Institut National de la Recherche Scientifique; Montreal General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Statistics; Proportional hazards model; Logistic regression; Regression analysis; Econometrics; Population; Regression; Mathematics; Computer science; Demography","score_opus":0.30995005806529696,"score_gpt":0.507983957605554,"score_spread":0.19803389954025707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115650046","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016505983,0.000062630446,0.9805572,0.00002356255,0.000045081786,0.0016614646,0.0009653778,0.00001026631,0.00016842128],"genre_scores_gemma":[0.6040974,0.0000028826285,0.39577702,0.000010720865,0.000011776875,0.000039374423,0.000030349538,0.000012565287,0.000017847551],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974746,0.00068460515,0.0005900689,0.00034363408,0.0007395785,0.000167477],"domain_scores_gemma":[0.99019074,0.008318223,0.00028306074,0.00049239746,0.0006518616,0.000063735795],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008245553,0.00016367767,0.0005109662,0.00008987645,0.000055069053,0.00000917591,0.00010821282,0.000055766766,0.00010916503],"category_scores_gemma":[0.03499035,0.00010963902,0.0000054105813,0.00011316653,0.00014137686,0.000044589277,0.000028994215,0.0001141005,4.6784783e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017552319,0.0026902396,0.0028921848,0.0016560308,0.0006596791,0.00041302995,0.011050986,0.13356397,0.0008317146,0.77480775,0.0010998589,0.068579346],"study_design_scores_gemma":[0.0042246045,0.0005697032,0.00022681999,0.00012835205,0.00075673807,0.000015273637,0.00062334206,0.64266616,0.000004130621,0.35070515,7.845166e-7,0.000078957164],"about_ca_topic_score_codex":0.000062462044,"about_ca_topic_score_gemma":0.00011379583,"teacher_disagreement_score":0.58759147,"about_ca_system_score_codex":0.000054623062,"about_ca_system_score_gemma":0.0001390464,"threshold_uncertainty_score":0.97313833},"labels":[],"label_agreement":null},{"id":"W2115955076","doi":"10.1002/sim.6223","title":"A multiple imputation strategy for sequential multiple assignment randomized trials","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; National Institute on Drug Abuse; National Institutes of Natural Sciences; Natural Sciences and Engineering Research Council of Canada; National Cancer Institute; University of North Carolina at Chapel Hill; National Institutes of Health; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Imputation (statistics); Computer science; Inference; Randomized controlled trial; Machine learning; Data mining; Artificial intelligence; Medicine","score_opus":0.17336014046715387,"score_gpt":0.4659763089343173,"score_spread":0.29261616846716343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115955076","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028642925,0.0000336202,0.9958825,0.0002422681,0.0005701929,0.0019104477,0.00042958456,0.000043431166,0.0006015176],"genre_scores_gemma":[0.22380397,0.000019669333,0.77515537,0.00010459372,0.00035983496,0.00033862036,0.00012112433,0.000027945827,0.00006887357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.995193,0.0020265048,0.001631568,0.00035232236,0.0004301582,0.0003664328],"domain_scores_gemma":[0.9086574,0.09028255,0.00050771225,0.0002249914,0.00020153189,0.00012583449],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013323485,0.0002500536,0.0017920806,0.0001483114,0.00007974993,0.000029395755,0.00014990465,0.000115431256,0.00031097827],"category_scores_gemma":[0.21760914,0.00017663832,0.00009753562,0.00013213238,0.00030694043,0.000039685674,0.000025895017,0.00019127157,0.0000053776444],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058914404,0.00009746493,0.00008263655,0.000269646,0.000071545466,0.000006171736,0.0004206544,0.000039833805,0.0005258854,0.87529844,0.0049419045,0.11235439],"study_design_scores_gemma":[0.079292364,0.00027940536,0.00008266434,0.0001293142,0.00018905022,0.000001770157,0.000107557564,0.18160275,0.0001564199,0.7378105,0.00019650043,0.00015172503],"about_ca_topic_score_codex":0.00014516695,"about_ca_topic_score_gemma":0.00012204624,"teacher_disagreement_score":0.22351754,"about_ca_system_score_codex":0.000076130484,"about_ca_system_score_gemma":0.000066179746,"threshold_uncertainty_score":0.78898126},"labels":[],"label_agreement":null},{"id":"W2117578563","doi":"10.1002/sim.6185","title":"Propensity score methods for estimating relative risks in cluster randomized trials with low‐incidence binary outcomes and selection bias","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Agence Nationale de la Recherche","keywords":"Propensity score matching; Covariate; Selection bias; Statistics; Inverse probability weighting; Weighting; Randomization; Regression; Randomized controlled trial; Selection (genetic algorithm); Relative risk; Cluster (spacecraft); Medicine; Econometrics; Mathematics; Computer science; Internal medicine; Artificial intelligence; Confidence interval","score_opus":0.39037839286313425,"score_gpt":0.5488097609618341,"score_spread":0.15843136809869984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117578563","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041647874,0.000032633467,0.95506805,0.00024965545,0.00007569079,0.0027429555,0.000010616129,0.00007177984,0.00010074537],"genre_scores_gemma":[0.10393599,0.000023667968,0.89546686,0.000111901,0.000046423505,0.00033135636,0.0000101420255,0.000027708875,0.000045962996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99576896,0.0023217485,0.0011276789,0.00032115303,0.0002196726,0.00024078618],"domain_scores_gemma":[0.94126475,0.057576347,0.0007050382,0.00015765263,0.00024019381,0.000056003544],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02144462,0.0002392465,0.0019001022,0.00024290135,0.000067975896,0.000013769708,0.00009047767,0.00010430261,0.000013543294],"category_scores_gemma":[0.19310287,0.00014617693,0.00002940782,0.00023871675,0.0003996468,0.00015532775,0.000050557584,0.00036594865,3.1143094e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05399907,0.00032666457,0.056473892,0.002938574,0.00033717288,0.000046157675,0.010129942,0.0012413551,0.0021716943,0.70821345,0.0012471611,0.16287485],"study_design_scores_gemma":[0.035881948,0.0004933808,0.0025268327,0.0012327835,0.00015718462,0.000008140283,0.000076855635,0.16402851,0.00035182163,0.79506546,0.0000031206582,0.00017396694],"about_ca_topic_score_codex":0.00023132586,"about_ca_topic_score_gemma":0.00030122718,"teacher_disagreement_score":0.17165825,"about_ca_system_score_codex":0.0001045524,"about_ca_system_score_gemma":0.00004966883,"threshold_uncertainty_score":0.813694},"labels":[],"label_agreement":null},{"id":"W2117590223","doi":"10.1002/sim.4392","title":"Relative survival multistate Markov model","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Institutes of Health Research","keywords":"Relative survival; Markov model; Proportional hazards model; Survival analysis; Markov chain; Statistics; Hazard ratio; Hazard; Relative risk; Medicine; Econometrics; Computer science; Mathematics; Cancer; Cancer registry; Internal medicine; Biology; Confidence interval","score_opus":0.1961461722704344,"score_gpt":0.42473856033198565,"score_spread":0.22859238806155124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117590223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009480313,0.000030213223,0.93250227,0.000076649005,0.00031866063,0.00020294836,0.00026309534,0.000041463158,0.06561668],"genre_scores_gemma":[0.062306106,0.000060945502,0.93610126,0.00010674947,0.000059999442,0.000021549464,0.000014389164,0.00003186781,0.001297142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99811065,0.00022681,0.00062659394,0.00030309227,0.0003775553,0.00035529947],"domain_scores_gemma":[0.99601156,0.0031982954,0.0001570682,0.00031952537,0.00016417097,0.00014940114],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012471135,0.00021031698,0.00049309566,0.00011890043,0.000051227882,0.000004728897,0.00019915999,0.00008269599,0.0012414204],"category_scores_gemma":[0.010286345,0.00016543556,0.000019350946,0.00019849095,0.00040071053,0.0000501654,0.000060892387,0.00037856287,0.000025899742],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006105758,0.00007992516,0.00054435316,0.00007094248,0.000019078543,0.00009150498,0.0036646582,0.000001913748,0.00003590704,0.97523016,0.003313392,0.01688712],"study_design_scores_gemma":[0.0008468248,0.00017249612,0.0038073624,0.00012584362,0.00004452696,0.000003078614,0.00034208418,0.0692398,0.000025286765,0.92515737,0.00005238557,0.00018294016],"about_ca_topic_score_codex":0.00025925375,"about_ca_topic_score_gemma":0.00014228458,"teacher_disagreement_score":0.06923789,"about_ca_system_score_codex":0.00005839839,"about_ca_system_score_gemma":0.000050270606,"threshold_uncertainty_score":0.9996716},"labels":[],"label_agreement":null},{"id":"W2117746627","doi":"10.1002/sim.5598","title":"Predictive accuracy of risk factors and markers: a simulation study of the effect of novel markers on different performance measures for logistic regression models","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Logistic regression; Statistics; Brier score; Statistic; Context (archaeology); Econometrics; Risk factor; Mathematics; Computer science; Medicine; Internal medicine; Biology","score_opus":0.1122183754170676,"score_gpt":0.4199947875634422,"score_spread":0.30777641214637463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117746627","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4704825,0.000020079931,0.5283663,0.0000026254627,0.000094795345,0.0006860745,0.00032116365,0.0000027441313,0.000023687458],"genre_scores_gemma":[0.9551641,0.000027954495,0.0447319,0.0000017475891,0.000023874967,0.000028899625,0.000005690273,0.000013876239,0.0000019670465],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981489,0.0004249845,0.0006137595,0.00015778969,0.0004809952,0.00017353975],"domain_scores_gemma":[0.9675275,0.031403758,0.00061891455,0.00025798037,0.00013854436,0.000053305514],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014053392,0.0001924463,0.00062756444,0.00009974306,0.000047859125,0.0000020369034,0.00012418065,0.0000615612,0.000009143329],"category_scores_gemma":[0.028691465,0.00009380694,0.000026683565,0.00012422533,0.00027820157,0.000045755267,0.00004783421,0.00017615926,1.643581e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0070796427,0.0020185467,0.8381395,0.0042667035,0.00032174497,6.028517e-7,0.013612754,0.004101412,0.00043304704,0.050293338,0.0001936742,0.079539046],"study_design_scores_gemma":[0.004203977,0.006005189,0.5418877,0.0017397521,0.0005432036,3.5430745e-7,0.0011597311,0.3671372,0.00071723736,0.076475896,4.894033e-7,0.00012923546],"about_ca_topic_score_codex":0.000102043996,"about_ca_topic_score_gemma":0.000013653139,"teacher_disagreement_score":0.4846816,"about_ca_system_score_codex":0.000035684327,"about_ca_system_score_gemma":0.000012861464,"threshold_uncertainty_score":0.9794903},"labels":[],"label_agreement":null},{"id":"W2118529247","doi":"10.1002/sim.5923","title":"Multiscale analysis of neural spike trains","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Spike train; Spike (software development); Computer science; Train; Point process; Neural coding; Artificial intelligence; Algorithm; Pattern recognition (psychology); Statistics; Mathematics","score_opus":0.03014703907680518,"score_gpt":0.309619638389451,"score_spread":0.27947259931264584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118529247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9634596,0.000016570866,0.031975128,0.0010600089,0.00052470865,0.0002779088,0.00020639035,0.000023702683,0.0024559505],"genre_scores_gemma":[0.9972933,0.000028652496,0.0013687348,0.0006455165,0.000036367404,0.000009450514,0.000030699517,0.000007543669,0.0005797453],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895346,0.00006529457,0.0003274544,0.00021857214,0.00026712046,0.00016812296],"domain_scores_gemma":[0.9990844,0.0005393031,0.0001010981,0.00017065198,0.00004501958,0.000059501093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012869801,0.00008872002,0.00028078048,0.00032567195,0.000027851342,0.0000063852876,0.00012285482,0.00002899614,0.0007860546],"category_scores_gemma":[0.0010720908,0.000067213674,0.000028582863,0.00090858166,0.00022549595,0.00005326855,0.000022548753,0.00012609716,0.000013837337],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041339947,0.00025036378,0.027031804,0.0000857712,0.00007539711,0.000102348466,0.0015095209,0.0038001281,0.8156445,0.055420235,0.009509568,0.086528994],"study_design_scores_gemma":[0.0005982105,0.0002316549,0.25988573,0.000016666818,0.00013874269,0.0000029216994,0.00009477094,0.7319934,0.0013310227,0.0053967102,0.00020077867,0.00010941268],"about_ca_topic_score_codex":0.00039503232,"about_ca_topic_score_gemma":0.00026774767,"teacher_disagreement_score":0.81431353,"about_ca_system_score_codex":0.000018174534,"about_ca_system_score_gemma":0.0000070739948,"threshold_uncertainty_score":0.8606746},"labels":[],"label_agreement":null},{"id":"W2118670046","doi":"10.1002/sim.2518","title":"Confidence intervals for multinomial logistic regression in sparse data","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto; Mount Sinai Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Multinomial logistic regression; Statistics; Logistic regression; Mathematics; Covariate; Confidence interval; Likelihood function; Binary data; Multinomial distribution; Econometrics; Wald test; Maximum likelihood; Binary number; Statistical hypothesis testing","score_opus":0.2664078337446776,"score_gpt":0.4945271978202856,"score_spread":0.228119364075608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118670046","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004609532,0.000094135234,0.9960472,0.00033481908,0.00042249647,0.0005113427,0.001052251,0.00002320184,0.0010535793],"genre_scores_gemma":[0.09904484,0.000028468548,0.9000895,0.00009599074,0.00027431373,0.00004020355,0.000249213,0.0000227593,0.00015473929],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977827,0.00019903957,0.0009110778,0.000457858,0.00028568172,0.0003636077],"domain_scores_gemma":[0.989191,0.009787946,0.00022214322,0.00062445865,0.000107020554,0.000067412024],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019328482,0.00020284347,0.00058806455,0.00015761881,0.00003823682,0.000015988771,0.00047924352,0.000096774245,0.00024221622],"category_scores_gemma":[0.02711602,0.0001532367,0.000013352489,0.00018516836,0.00035900122,0.000057645488,0.00013925265,0.00026394252,0.000006227527],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010486601,0.00011552946,0.0015315883,0.0002958783,0.000004186888,0.00011812464,0.00013812071,0.000002307386,0.00019017188,0.94122463,0.03565139,0.020623209],"study_design_scores_gemma":[0.0017490257,0.00015825042,0.005202849,0.0009250068,0.000033680848,0.0000067303913,0.00010445539,0.03217084,0.00004643983,0.9589484,0.00048259288,0.00017176947],"about_ca_topic_score_codex":0.0009634527,"about_ca_topic_score_gemma":0.0015510375,"teacher_disagreement_score":0.098583885,"about_ca_system_score_codex":0.0000716813,"about_ca_system_score_gemma":0.00006374375,"threshold_uncertainty_score":0.981079},"labels":[],"label_agreement":null},{"id":"W2118844219","doi":"10.1002/sim.5805","title":"Reply to Taguri and Matsuyama","year":2013,"lang":"en","type":"letter","venue":"Statistics in Medicine","topic":"Influenza Virus Research Studies","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"National Institutes of Health","keywords":"Computer science; Computational biology; Biology","score_opus":0.07162140203662545,"score_gpt":0.40929713591478967,"score_spread":0.3376757338781642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118844219","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00019309335,0.0022674405,0.00123199,0.9809923,0.00049521227,0.002324278,0.00040883795,0.00005892623,0.012027912],"genre_scores_gemma":[0.00003776745,0.0012924218,0.02155637,0.9524944,0.003994501,0.00032665126,0.00035720444,0.00009532632,0.019845385],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966357,0.00010716224,0.00070441444,0.0006398574,0.001160618,0.00075226964],"domain_scores_gemma":[0.99754137,0.0009679753,0.00012667985,0.0006851354,0.00042585703,0.00025300105],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00057689805,0.00042747633,0.0012029747,0.00073639356,0.000071451395,0.000021646458,0.0001857189,0.00034550234,0.0012119542],"category_scores_gemma":[0.005273473,0.00032070343,0.00002628791,0.00032244987,0.00062497467,0.000030501718,0.00022516464,0.0024927412,0.00039719677],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006107474,0.00001382152,0.0006023824,0.0012797609,0.00010135016,0.0039051375,0.0007355026,2.3487996e-7,0.000045406934,0.00030162474,0.9864627,0.00649101],"study_design_scores_gemma":[0.0016161001,0.00081948825,0.005122963,0.0014765423,0.000118419164,0.00009854566,0.000117139425,0.000039254304,0.000008844524,0.0020953482,0.98821855,0.00026880697],"about_ca_topic_score_codex":0.0014782435,"about_ca_topic_score_gemma":0.00002866032,"teacher_disagreement_score":0.02849794,"about_ca_system_score_codex":0.00022480403,"about_ca_system_score_gemma":0.0001409391,"threshold_uncertainty_score":0.9999245},"labels":[],"label_agreement":null},{"id":"W2119396122","doi":"10.1002/sim.1484","title":"A relative survival regression model using B‐spline functions to model non‐proportional hazards","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal General Hospital","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ligue Contre le Cancer","keywords":"Proportional hazards model; Covariate; Relative survival; Statistics; Regression analysis; Survival analysis; Population; Inference; Regression; Hazard ratio; Relative risk; Econometrics; Mathematics; Medicine; Computer science; Cancer registry; Confidence interval; Artificial intelligence","score_opus":0.17991573856172782,"score_gpt":0.4606334294214673,"score_spread":0.28071769085973947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119396122","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006207952,0.000019718806,0.9852509,0.00024214842,0.00035074184,0.00032576462,0.000489133,0.00002849016,0.0070851804],"genre_scores_gemma":[0.08356802,0.000011069176,0.9144393,0.00016967743,0.00007823875,0.000027861845,0.000036880778,0.000035670007,0.001633261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976715,0.0001705534,0.0007467399,0.0003898285,0.0006582943,0.00036308853],"domain_scores_gemma":[0.99739265,0.0014897146,0.00017801978,0.0003276194,0.0003778431,0.0002341294],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014829467,0.00024848376,0.00053089723,0.00020380627,0.00014220705,0.00001004023,0.0001186909,0.000111247966,0.0003816466],"category_scores_gemma":[0.014870931,0.00019037383,0.00002823142,0.00039753405,0.00019678033,0.000059244663,0.00004931229,0.00041750428,0.00001495951],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055454137,0.00012294298,0.00018916088,0.00006668979,0.000019540032,0.000023455808,0.0008050483,0.021765502,0.0007784858,0.9684623,0.0058816695,0.001829741],"study_design_scores_gemma":[0.00042699944,0.00008483411,0.000094758536,0.00018082693,0.000042241165,0.0000039220695,0.00014977428,0.5011151,0.00002078422,0.4977294,0.000030927968,0.00012045354],"about_ca_topic_score_codex":0.000047486657,"about_ca_topic_score_gemma":0.000051571842,"teacher_disagreement_score":0.4793496,"about_ca_system_score_codex":0.00016913025,"about_ca_system_score_gemma":0.00029796988,"threshold_uncertainty_score":0.9934272},"labels":[],"label_agreement":null},{"id":"W2119511462","doi":"10.1002/sim.6433","title":"Penalized regression procedures for variable selection in the potential outcomes framework","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of Environmental Health Sciences; National Cancer Institute; National Institute on Drug Abuse; National Institutes of Health","keywords":"Causal inference; Imputation (statistics); Computer science; Inference; Missing data; Regression; Multivariate statistics; Feature selection; Regression analysis; Artificial intelligence; Model selection; Selection (genetic algorithm); Machine learning; Data mining; Econometrics; Statistics; Mathematics","score_opus":0.11775119733631027,"score_gpt":0.4738352817476763,"score_spread":0.356084084411366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119511462","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022162716,0.000047293135,0.9951704,0.0008451408,0.0001516555,0.0007578935,0.000022181934,0.00007072654,0.00071844866],"genre_scores_gemma":[0.11992375,0.000023222994,0.8791226,0.00036555793,0.00012776275,0.00018375504,0.000024329222,0.000021632442,0.00020736404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99866515,0.00012590567,0.00041264802,0.00017977148,0.00038214037,0.00023439499],"domain_scores_gemma":[0.9974202,0.0020232995,0.00015842712,0.00016771154,0.0001852111,0.000045139575],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015632868,0.00014762048,0.0003339271,0.00012737079,0.000044914086,0.000011505498,0.00019818706,0.0001121341,0.000047280526],"category_scores_gemma":[0.022077708,0.00008502322,0.000013081002,0.00029574576,0.000093466064,0.000063041174,0.00002530819,0.00032681992,0.000001203842],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011570201,0.00009160449,0.0021278285,0.00015676762,0.000007885732,0.000011917576,0.002164261,0.00003534145,0.0002892188,0.9636171,0.030680649,0.00070174463],"study_design_scores_gemma":[0.00091993215,0.00025197066,0.0012279848,0.00042078737,0.000027509885,0.000009243181,0.0007140399,0.0014147386,0.00006786412,0.99450105,0.00034635965,0.000098488184],"about_ca_topic_score_codex":0.000072349736,"about_ca_topic_score_gemma":0.00012459446,"teacher_disagreement_score":0.117707476,"about_ca_system_score_codex":0.000102914775,"about_ca_system_score_gemma":0.00011263149,"threshold_uncertainty_score":0.98615974},"labels":[],"label_agreement":null},{"id":"W2119934595","doi":"10.1002/(sici)1097-0258(20000215)19:3<313::aid-sim370>3.0.co;2-k","title":"Bootstrap confidence intervals for the sensitivity of a quantitative diagnostic test","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Confidence interval; Sensitivity (control systems); Statistics; Parametric statistics; Nominal level; Inference; Computer science; Test (biology); Econometrics; Mathematics; Artificial intelligence","score_opus":0.16794440763566826,"score_gpt":0.46817699776453064,"score_spread":0.3002325901288624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119934595","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002909747,0.00016517426,0.99350834,0.00065135275,0.00013312328,0.00056035485,0.0008966538,0.000013215781,0.0011620687],"genre_scores_gemma":[0.5314874,0.00027903504,0.46767402,0.00020602769,0.000063327905,0.00006090445,0.0000087035905,0.000017066895,0.00020350507],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984385,0.0002595191,0.0006088609,0.00019748129,0.00026819672,0.00022744722],"domain_scores_gemma":[0.7983959,0.20100996,0.00013431982,0.00022292441,0.00018873421,0.00004817615],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024598178,0.00014700436,0.00047120926,0.000047178295,0.000053111176,0.000006977517,0.00014278555,0.00004573957,0.0009336445],"category_scores_gemma":[0.1643035,0.0000929941,0.000027385646,0.00016848212,0.0007248908,0.00002284364,0.000018286373,0.00018743656,0.0000066860352],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005667555,0.00010202212,0.00043160818,0.0002439858,0.000024649959,0.000026396421,0.0014938555,0.000009547151,0.00032533042,0.9352373,0.004408325,0.05764029],"study_design_scores_gemma":[0.00072859693,0.00079079124,0.011079833,0.00068452297,0.00011147461,0.000009355509,0.0006755285,0.02812698,0.00025093718,0.95710534,0.0003085714,0.00012806678],"about_ca_topic_score_codex":0.00035605207,"about_ca_topic_score_gemma":0.0002960979,"teacher_disagreement_score":0.5285777,"about_ca_system_score_codex":0.000021015921,"about_ca_system_score_gemma":0.000045122764,"threshold_uncertainty_score":0.9999796},"labels":[],"label_agreement":null},{"id":"W2120330366","doi":"10.1002/sim.1096","title":"Meta‐analyses in systematic reviews of randomized controlled trials in perinatal medicine: comparison of fixed and random effects models","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Meta-analysis; Random effects model; Relative risk; Randomized controlled trial; Confidence interval; Fixed effects model; Medicine; Study heterogeneity; Statistics; Systematic review; Publication bias; MEDLINE; Internal medicine; Mathematics; Biology","score_opus":0.799571230144511,"score_gpt":0.6104975582558801,"score_spread":0.1890736718886309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120330366","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02563097,0.38577828,0.5581669,0.00067461416,0.00049061194,0.026477093,0.000039056238,0.000003816472,0.0027385983],"genre_scores_gemma":[0.9773724,0.009539317,0.011473164,0.00007569885,0.000044879405,0.0010615917,0.0000139214735,0.000013605477,0.0004054117],"study_design_codex":"systematic_review","study_design_gemma":"randomized_trial","domain_scores_codex":[0.5751068,0.29304713,0.11993536,0.0015202758,0.009792223,0.0005982204],"domain_scores_gemma":[0.57963526,0.39163885,0.025855541,0.0017788113,0.0009442594,0.0001472729],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.59970444,0.00052787014,0.10523497,0.0022264097,0.000025058524,0.000037553404,0.0008017531,0.00011496021,0.0021273973],"category_scores_gemma":[0.76059496,0.00018553756,0.0021507847,0.002118344,0.00055407564,0.000111720285,0.000064692125,0.0002644769,0.0000086610535],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.21016623,0.0022992783,0.027420241,0.33723468,0.08630934,0.00075562095,0.09430517,0.020053497,0.0036618297,0.1704233,0.03230149,0.015069325],"study_design_scores_gemma":[0.45835483,0.0003077372,0.0003838424,0.017741935,0.04274667,0.000012887097,0.0033964252,0.41998452,0.000019241303,0.0566935,0.00006805525,0.00029034461],"about_ca_topic_score_codex":0.00045198784,"about_ca_topic_score_gemma":0.0005264905,"teacher_disagreement_score":0.95174146,"about_ca_system_score_codex":0.00003473662,"about_ca_system_score_gemma":0.000051622013,"threshold_uncertainty_score":0.9987848},"labels":[],"label_agreement":null},{"id":"W2122527396","doi":"10.1002/sim.3801","title":"Missing data in the exposure of interest and marginal structural models: A simulation study based on the Framingham Heart Study","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Medical Research Council; National Health and Medical Research Council","keywords":"Missing data; Inverse probability; Framingham Heart Study; Marginal structural model; Statistics; Confounding; Propensity score matching; Computer science; Econometrics; Outcome (game theory); Mathematics; Medicine; Framingham Risk Score; Bayesian probability","score_opus":0.3765319600692848,"score_gpt":0.49942054001456876,"score_spread":0.12288857994528396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122527396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7440605,0.0000312929,0.2535987,0.000853489,0.0000274913,0.0012641712,0.000045747853,0.00002224686,0.00009636941],"genre_scores_gemma":[0.9628218,0.0000016874533,0.03688197,0.0002312934,0.0000272106,0.000009131877,0.000015881096,0.000008870944,0.0000021890648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984796,0.00036525348,0.00045266066,0.00021835558,0.00035111787,0.00013302053],"domain_scores_gemma":[0.99539953,0.003674304,0.00013768842,0.00070723926,0.0000608835,0.000020348643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018829976,0.00014035738,0.00028816098,0.000113445,0.00005088532,0.000015285048,0.00034209283,0.000030944022,0.000015578265],"category_scores_gemma":[0.0028723385,0.00007611579,0.0000050260664,0.00019410528,0.000119931996,0.00008122604,0.000053491338,0.00035650708,8.091795e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001799758,0.008450924,0.18092127,0.00059987075,0.0001264017,0.0006092605,0.19181314,0.029725587,0.00093207916,0.47478625,0.003368959,0.1068665],"study_design_scores_gemma":[0.0009394023,0.0024133392,0.047977347,0.00025429289,0.000035320383,0.0000017097753,0.01218075,0.4453784,0.0000061940955,0.49072635,0.0000024620253,0.000084430816],"about_ca_topic_score_codex":0.00006788295,"about_ca_topic_score_gemma":0.00034041292,"teacher_disagreement_score":0.4156528,"about_ca_system_score_codex":0.000030101324,"about_ca_system_score_gemma":0.000020896168,"threshold_uncertainty_score":0.3438665},"labels":[],"label_agreement":null},{"id":"W2122697238","doi":"10.1002/sim.5761","title":"Relative risk regression models with inverse polynomials","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Inverse; Mathematics; Polynomial; Applied mathematics; Bounded function; Hazard; Polynomial regression; Function (biology); Log-linear model; Polynomial and rational function modeling; Statistics; Regression analysis; Linear model; Mathematical analysis","score_opus":0.06394317640654087,"score_gpt":0.3758390173818452,"score_spread":0.3118958409753043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122697238","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032237908,0.000016738408,0.98521274,0.0011184396,0.000045596415,0.0005258859,0.00046963882,0.000057164376,0.009329991],"genre_scores_gemma":[0.35575557,0.0000673793,0.64231557,0.00025228638,0.0000662556,0.00020605275,0.00023519123,0.000027026865,0.001074653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99866515,0.00011418298,0.00045504855,0.00022790938,0.00032673372,0.00021098857],"domain_scores_gemma":[0.9973422,0.0017672478,0.00023988959,0.00027669946,0.00022630318,0.00014761626],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003018883,0.00015954238,0.00029536456,0.00009901787,0.00010449984,0.000012751412,0.00011124699,0.000065171545,0.0015422303],"category_scores_gemma":[0.0026576149,0.00010538973,0.000011864728,0.00028781177,0.00032791542,0.00014246114,0.000024574632,0.0002666645,0.00013823481],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013326289,0.000056098488,0.00021979578,0.000024421795,0.000013666161,0.000004992914,0.0004411505,0.000060977225,0.00002761712,0.9122701,0.08430665,0.0025611548],"study_design_scores_gemma":[0.0010013926,0.000088813365,0.003730152,0.00016126077,0.000052975705,0.000003617451,0.0004000697,0.07674721,0.000018126017,0.9175104,0.00015922691,0.00012674923],"about_ca_topic_score_codex":0.0002823428,"about_ca_topic_score_gemma":0.0000913652,"teacher_disagreement_score":0.3525318,"about_ca_system_score_codex":0.00007753122,"about_ca_system_score_gemma":0.000043464253,"threshold_uncertainty_score":0.9993705},"labels":[],"label_agreement":null},{"id":"W2124694383","doi":"10.1002/sim.2329","title":"Interval estimation of the mean response in a log‐regression model","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Cancer Institute; American Lebanese Syrian Associated Charities","keywords":"Statistics; Regression analysis; Mathematics; Sample size determination; Prediction interval; Confidence interval; Interval estimation; Interval (graph theory); Regression; Inference; Econometrics; Computer science","score_opus":0.15493030895431098,"score_gpt":0.5154423581120995,"score_spread":0.3605120491577885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124694383","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23627348,0.00013363846,0.7603413,0.0016247475,0.00022170562,0.00022165233,0.000029823912,0.0000064499654,0.0011472178],"genre_scores_gemma":[0.63584673,0.000004755362,0.36363265,0.00016082822,0.000016038488,0.0000051426523,0.0000013753187,0.0000056428876,0.00032681244],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99640995,0.0010834669,0.0009134441,0.00025763924,0.0011740571,0.0001614119],"domain_scores_gemma":[0.9958268,0.0033100995,0.00025680044,0.0004519528,0.000104334795,0.000050044015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008791205,0.00011234831,0.00032792334,0.00033799847,0.00002979448,0.0000109093,0.0005401251,0.000056400408,0.00020624005],"category_scores_gemma":[0.017589597,0.00006110896,0.000023904899,0.0006915811,0.0003545062,0.00011073975,0.00013763312,0.00021381557,0.000014061406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004163803,0.00035706421,0.0037644408,0.000027062732,0.000008763695,0.00003722065,0.034433216,0.44312364,0.06311374,0.037574437,0.015015998,0.39838064],"study_design_scores_gemma":[0.00079195644,0.00017121782,0.010577067,0.000206797,0.0000038220824,0.0000034105456,0.0008916745,0.91059595,0.0029683015,0.07366726,0.00006123903,0.00006127483],"about_ca_topic_score_codex":0.00005170473,"about_ca_topic_score_gemma":0.00010874539,"teacher_disagreement_score":0.46747234,"about_ca_system_score_codex":0.00013350222,"about_ca_system_score_gemma":0.000082092854,"threshold_uncertainty_score":0.99068564},"labels":[],"label_agreement":null},{"id":"W2125238080","doi":"10.1002/sim.5684","title":"Estimating the intensity of ward admission and its effect on emergency department access block","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Emergency and Acute Care Studies","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Australian Research Council; Queensland Health","keywords":"Poisson regression; Emergency department; Block (permutation group theory); Hospital admission; Medicine; Computer science; Emergency medicine; Internal medicine; Mathematics; Population","score_opus":0.03647757346316049,"score_gpt":0.387662823291902,"score_spread":0.3511852498287415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125238080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9880658,0.005586651,0.001085847,0.0015064983,0.0015789928,0.0005391754,0.000040899322,0.000015720145,0.0015804359],"genre_scores_gemma":[0.99758285,0.0009082174,0.0008135082,0.00023089623,0.00034029633,0.000017197306,0.000024532947,0.000010703883,0.00007182364],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99892324,0.00006465435,0.00035658627,0.00013869713,0.0003003306,0.00021649286],"domain_scores_gemma":[0.9991684,0.0003144881,0.00011154652,0.00015568903,0.00013873204,0.00011116726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065045105,0.00014365192,0.00038724137,0.00006620764,0.00007973267,0.0000010736759,0.00007074639,0.000036471014,0.00012533664],"category_scores_gemma":[0.002445906,0.00007673737,0.00001966464,0.00015797708,0.00009356214,0.00003276751,0.000086772685,0.0002052224,0.0000027994056],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00126597,0.0004967653,0.74269986,0.0033496374,0.00045014467,0.00011417243,0.010200171,0.000047815338,0.004469866,0.00521417,0.1841238,0.04756763],"study_design_scores_gemma":[0.004559171,0.0061105937,0.9594,0.003563485,0.0012045308,0.00009590089,0.0010661114,0.008363232,0.009777349,0.0021561016,0.00325614,0.00044736307],"about_ca_topic_score_codex":0.000030166062,"about_ca_topic_score_gemma":0.000010002831,"teacher_disagreement_score":0.21670017,"about_ca_system_score_codex":0.000025669253,"about_ca_system_score_gemma":0.000013122807,"threshold_uncertainty_score":0.31292593},"labels":[],"label_agreement":null},{"id":"W2125296802","doi":"10.1002/sim.5327","title":"An efficient alternative to the stratified Cox model analysis","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Gilead Sciences (Canada)","funders":"","keywords":"Stratum; Proportional hazards model; Statistics; Inference; Categorical variable; Sample size determination; Hazard ratio; Econometrics; Mathematics; Computer science; Confidence interval; Geology; Artificial intelligence","score_opus":0.5116409653596984,"score_gpt":0.6119579326220749,"score_spread":0.10031696726237649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125296802","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014464063,0.000027398615,0.9812558,0.00081522367,0.0006363465,0.00057972845,0.00056009437,0.000033554516,0.0016277373],"genre_scores_gemma":[0.40506166,0.000006937334,0.59391147,0.00046075287,0.0003986397,0.000042219555,0.000010697981,0.000018689336,0.00008897018],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962434,0.0009919598,0.0010745234,0.00034832433,0.0008335674,0.00050823076],"domain_scores_gemma":[0.967865,0.030551208,0.00023708149,0.0007927823,0.00017784322,0.00037611826],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008041374,0.0002257037,0.00081478886,0.00023902814,0.00008783435,0.000018592194,0.0004809946,0.000086603206,0.0005108204],"category_scores_gemma":[0.06838692,0.0001380192,0.00005312698,0.0009350548,0.0002921291,0.000031279556,0.00007115249,0.00039331947,0.000030870364],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009905157,0.00038798046,0.0008566967,0.00003330328,0.0002476612,0.000010704386,0.004894448,0.024392592,0.00008498602,0.95848006,0.0064710747,0.004041468],"study_design_scores_gemma":[0.00053497776,0.00017364846,0.0019484942,0.000032098837,0.0006061092,7.618384e-7,0.0004565354,0.40380478,0.000058212692,0.5921779,0.000056137298,0.00015030659],"about_ca_topic_score_codex":0.0000965689,"about_ca_topic_score_gemma":0.00014612914,"teacher_disagreement_score":0.39059758,"about_ca_system_score_codex":0.00009291739,"about_ca_system_score_gemma":0.00004077506,"threshold_uncertainty_score":0.93946046},"labels":[],"label_agreement":null},{"id":"W2126049444","doi":"10.1002/sim.3697","title":"Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity‐score matched samples","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6487,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Matching (statistics); Quantile; Mathematics; Medicine","score_opus":0.2114497428934903,"score_gpt":0.42025483801624836,"score_spread":0.20880509512275805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126049444","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15230395,0.000098473385,0.84526396,0.00060511025,0.000038748258,0.0009897766,0.0006280991,0.00004157511,0.000030334675],"genre_scores_gemma":[0.85829943,0.00028046273,0.14047512,0.000042493666,0.00008786792,0.00006643381,0.00072704774,0.000012301409,0.000008812349],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985509,0.000099370336,0.0006959968,0.00019594662,0.00020766862,0.00025012056],"domain_scores_gemma":[0.99332684,0.005925904,0.00026210438,0.00028915348,0.00015637324,0.00003959509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095518754,0.00018726294,0.00068605057,0.000064766224,0.00004160957,0.00000616034,0.00016983658,0.00006288834,0.00000838171],"category_scores_gemma":[0.006444343,0.000121877354,0.000019777766,0.00021636648,0.0001741788,0.00004066479,0.000025537585,0.0001542706,3.7994943e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013245367,0.00034301876,0.24192664,0.00024182738,0.000031256703,0.000019887271,0.0014274303,0.00010539878,0.0004952129,0.7422302,0.0022138017,0.0108329],"study_design_scores_gemma":[0.0013323509,0.00079296425,0.15684673,0.0005623271,0.000084649146,0.0000017250096,0.00019095623,0.0031558268,0.0018495648,0.83494973,0.00009535121,0.0001378101],"about_ca_topic_score_codex":0.0001853483,"about_ca_topic_score_gemma":0.00035487273,"teacher_disagreement_score":0.7059955,"about_ca_system_score_codex":0.00019871801,"about_ca_system_score_gemma":0.000036722482,"threshold_uncertainty_score":0.77149457},"labels":[],"label_agreement":null},{"id":"W2126565679","doi":"10.1002/sim.6750","title":"A rare variant association test in family‐based designs and non‐normal quantitative traits","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital; Université du Québec à Montréal; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; National Institute for Health and Care Research; Department of Health and Social Care; Wellcome Trust; Wellcome","keywords":"Normality; Quantitative trait locus; Phenotype; Genetic association; Association test; Trait; Statistics; Biology; Computational biology; Genetics; Computer science; Mathematics; Single-nucleotide polymorphism; Genotype","score_opus":0.04158283716710916,"score_gpt":0.32908024858684204,"score_spread":0.2874974114197329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126565679","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6702998,0.00087320217,0.32383537,0.0017780209,0.0002600964,0.00041068628,0.0003337867,0.0000082380275,0.0022007637],"genre_scores_gemma":[0.9459568,0.00012388833,0.052721456,0.0006350141,0.000082020524,0.000025188361,0.00026655404,0.000011507192,0.0001775313],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99884576,0.00018756256,0.0003444412,0.00023146084,0.00014413455,0.00024665135],"domain_scores_gemma":[0.9990716,0.00045126092,0.00014802902,0.000092286726,0.00014669164,0.00009014062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001369415,0.0001167459,0.0002561528,0.000092662754,0.000026686626,0.000004903986,0.000071154864,0.00015901713,0.000008034494],"category_scores_gemma":[0.006777807,0.00010749298,0.000010625322,0.0001446528,0.00007468429,0.0000025353672,0.000026847672,0.00013127785,0.0000029628172],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015518097,0.00021813107,0.91687685,0.000046608195,0.000048529,0.00008368595,0.001689944,0.0015851806,0.028238488,0.0015780312,0.046672743,0.0028065983],"study_design_scores_gemma":[0.00384177,0.001403545,0.9751659,0.000055130713,0.000030343519,0.000004811331,0.0012083339,0.013830923,0.00014449836,0.002828556,0.0012796422,0.00020653804],"about_ca_topic_score_codex":0.0002494111,"about_ca_topic_score_gemma":0.0009501358,"teacher_disagreement_score":0.275657,"about_ca_system_score_codex":0.00008347538,"about_ca_system_score_gemma":0.00016561506,"threshold_uncertainty_score":0.8114158},"labels":[],"label_agreement":null},{"id":"W2126948068","doi":"10.1002/sim.2747","title":"Assessing local influence in principal component analysis with application to haematology study data","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Principal component analysis; Data set; Eigenvalues and eigenvectors; Data mining; Mathematics; Perturbation (astronomy); Statistics; Computer science; Sensitivity (control systems)","score_opus":0.11621309066097045,"score_gpt":0.5022851333630338,"score_spread":0.38607204270206336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126948068","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1330422,0.000011005493,0.86596024,0.00012168711,0.000019936393,0.00058723736,0.0000836636,0.000018811686,0.00015518998],"genre_scores_gemma":[0.52987504,9.755568e-7,0.46992317,0.000041970256,0.000015248779,0.000041050742,0.000085978165,0.00000996404,0.0000065944723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99778056,0.00023532844,0.00073961547,0.00053307245,0.00042123767,0.00029018478],"domain_scores_gemma":[0.99689794,0.0019842202,0.0001664522,0.00074508117,0.00012080613,0.000085491556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012911865,0.0001736231,0.00072475447,0.0003396455,0.00004298759,0.000014970073,0.00031435516,0.000044246284,0.000013773353],"category_scores_gemma":[0.0013682375,0.00013362047,0.0000067806595,0.00093353674,0.00019661526,0.000104635285,0.00014670962,0.00023764983,0.0000021294427],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020450058,0.0016896514,0.14439479,0.0002731662,0.00016795404,0.001123958,0.0019834742,0.07657735,0.00017635732,0.7348403,0.00028939327,0.03827915],"study_design_scores_gemma":[0.002035867,0.0003901321,0.23040779,0.00015472884,0.000530545,0.000015984206,0.0023817953,0.32697293,0.000010498978,0.43664896,0.00011928271,0.00033147784],"about_ca_topic_score_codex":0.0015763001,"about_ca_topic_score_gemma":0.013689858,"teacher_disagreement_score":0.39683285,"about_ca_system_score_codex":0.00010336297,"about_ca_system_score_gemma":0.00004064002,"threshold_uncertainty_score":0.7639262},"labels":[],"label_agreement":null},{"id":"W2127105291","doi":"10.1002/sim.4463","title":"Bayesian approach to predicting cancer incidence for an area without cancer registration by using cancer incidence data from nearby areas","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cancer registry; Incidence (geometry); Cancer; Cancer incidence; Mortality rate; Statistics; Population; Demography; Medicine; Mathematics; Surgery; Environmental health; Internal medicine","score_opus":0.2254399786217776,"score_gpt":0.4520156101574731,"score_spread":0.22657563153569552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127105291","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24853206,0.008155788,0.7327726,0.0010734451,0.0010712984,0.0018298585,0.0058195144,0.0000852539,0.00066021644],"genre_scores_gemma":[0.89349955,0.00063729985,0.0986486,0.0024270958,0.0023100898,0.0004210944,0.0018488354,0.000070302,0.00013711701],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996135,0.00010552993,0.00086204096,0.0009240656,0.0011067889,0.0008666001],"domain_scores_gemma":[0.99715745,0.00030649922,0.00042676053,0.0009832084,0.0004258395,0.00070022047],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013963399,0.0004039977,0.00080018747,0.00016087791,0.00021924316,0.000044904275,0.00058614044,0.00018432764,0.00022352894],"category_scores_gemma":[0.0018144847,0.00035957494,0.000026647032,0.0005557989,0.000252909,0.00076460757,0.00016649546,0.00048556135,0.0000016406088],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077485666,0.00014383275,0.9229304,0.00026998104,0.00010742743,0.0000138597625,0.003733723,0.0016132798,0.0074404995,0.00017805591,0.04832056,0.014473481],"study_design_scores_gemma":[0.005133916,0.0009022507,0.15720785,0.008209498,0.0016133023,0.00007356203,0.006120822,0.8107302,0.0010243575,0.0009064725,0.006795293,0.0012824627],"about_ca_topic_score_codex":0.14217189,"about_ca_topic_score_gemma":0.02687653,"teacher_disagreement_score":0.80911696,"about_ca_system_score_codex":0.00088072516,"about_ca_system_score_gemma":0.00076597417,"threshold_uncertainty_score":0.9998856},"labels":[],"label_agreement":null},{"id":"W2128212246","doi":"10.1002/sim.4098","title":"Mixture cure model with random effects for the analysis of a multi‐center tonsil cancer study","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Statistics; Maximum likelihood; Covariate; Random effects model; Mathematics; Gaussian; Cure rate; Mixture model; Correlation; Medicine; Surgery; Internal medicine","score_opus":0.01772856284049867,"score_gpt":0.3572900698339538,"score_spread":0.3395615069934551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128212246","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024893617,0.00024723003,0.99516535,0.0006526038,0.00040913105,0.00090359605,0.000090617075,0.00001218005,0.000029948622],"genre_scores_gemma":[0.25792265,0.000038063652,0.7413609,0.0003138295,0.00006878013,0.00015830656,0.0000065227573,0.0000094783045,0.00012146114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988105,0.00010650851,0.0002759326,0.00030411396,0.00030308592,0.00019984103],"domain_scores_gemma":[0.9975397,0.0014010927,0.00013488976,0.0005661706,0.0002965218,0.0000616558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096597575,0.00015262836,0.0005088664,0.00018282938,0.000064065214,0.000013917103,0.0004958856,0.000051403145,0.00000780944],"category_scores_gemma":[0.00045734222,0.000076754564,0.00004066333,0.0006528827,0.00013864506,0.000044954922,0.00005596762,0.00029469773,9.511354e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014495188,0.003136103,0.036356173,0.0006760939,0.006179634,0.00013135307,0.0651672,0.027076684,0.0040880134,0.28450432,0.025029248,0.54620564],"study_design_scores_gemma":[0.0064994926,0.00019602128,0.0043175723,0.000045532375,0.00082263857,7.9937905e-7,0.000052312236,0.9820235,0.00005775229,0.005745001,0.00013457282,0.00010481399],"about_ca_topic_score_codex":0.0002164241,"about_ca_topic_score_gemma":0.004497073,"teacher_disagreement_score":0.9549468,"about_ca_system_score_codex":0.0000117195605,"about_ca_system_score_gemma":0.00006984876,"threshold_uncertainty_score":0.31299603},"labels":[],"label_agreement":null},{"id":"W2129017495","doi":"10.1002/sim.5723","title":"Correction: ‘Generating survival times to simulate Cox proportional hazards models with time‐varying covariates’","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"","keywords":"Covariate; Weibull distribution; Proportional hazards model; Statistics; Mathematics; Cumulative distribution function; Event (particle physics); Hazard; Expression (computer science); Gompertz function; Function (biology); Econometrics; Probability density function; Computer science; Physics","score_opus":0.23952068522826894,"score_gpt":0.49038527983643865,"score_spread":0.2508645946081697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129017495","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020147916,0.000013985214,0.9863764,0.0009025473,0.0015953509,0.0011590513,0.00014800078,0.000113712216,0.007676165],"genre_scores_gemma":[0.027963629,0.0000072374223,0.96733755,0.0005288406,0.00073584303,0.00013965936,0.000036477086,0.0000736916,0.003177088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958164,0.0006293631,0.0014479613,0.0005620365,0.0010404229,0.00050378736],"domain_scores_gemma":[0.96624756,0.032018,0.0003541305,0.0004259531,0.0006463877,0.00030797612],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035078388,0.0003386236,0.0010269715,0.00017285193,0.00014508549,0.000050996958,0.00024330203,0.00014554326,0.004692396],"category_scores_gemma":[0.06031557,0.00024957568,0.000032285156,0.0004879416,0.00030646374,0.000110403205,0.00009847206,0.0005155163,0.00017548336],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006726728,0.0005430035,0.00086378277,0.00040712458,0.00033768394,0.00025946068,0.001879132,0.049537133,0.0012425823,0.68688524,0.21099404,0.04637815],"study_design_scores_gemma":[0.0012552623,0.00043724725,0.00018338657,0.00033332137,0.00006894137,0.000010271654,0.00007424859,0.40813148,0.000050355906,0.58915997,0.000061005783,0.0002345442],"about_ca_topic_score_codex":0.0002379635,"about_ca_topic_score_gemma":0.000032872795,"teacher_disagreement_score":0.35859433,"about_ca_system_score_codex":0.00013246591,"about_ca_system_score_gemma":0.00018826591,"threshold_uncertainty_score":0.99999565},"labels":[],"label_agreement":null},{"id":"W2129802796","doi":"10.1002/sim.2754","title":"Pseudoscore‐based estimation from biased observations","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada","keywords":"Estimation; Computer science; Statistics; Econometrics; Mathematics","score_opus":0.15895267835464572,"score_gpt":0.41798995805961153,"score_spread":0.2590372797049658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129802796","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017551655,0.000029593044,0.9789414,0.00068056816,0.00025809478,0.00020966925,0.00061914854,0.00006125132,0.0016486259],"genre_scores_gemma":[0.16444454,0.0000030220006,0.83459485,0.00027910364,0.0001449149,0.000028825289,0.00038712134,0.000019570569,0.000098035394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983734,0.0001429535,0.0006314217,0.00024438385,0.00038171027,0.00022616558],"domain_scores_gemma":[0.9923105,0.007025167,0.000162323,0.0002989595,0.00013711372,0.00006592667],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004965823,0.00016415995,0.0003505208,0.00012595866,0.000061241524,0.000014743719,0.00013837435,0.00007232998,0.0007529131],"category_scores_gemma":[0.009275195,0.00013793958,0.000015759719,0.00032248048,0.00019407105,0.000034322642,0.000016227641,0.00019408186,0.000017251541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018213672,0.00011833482,0.0047887526,0.000057779747,0.000005997788,0.000030304513,0.000101194535,0.00020089235,0.00059382606,0.96671695,0.019322095,0.008045669],"study_design_scores_gemma":[0.0007998544,0.00006887628,0.056751575,0.00015783799,0.000037645044,4.0380678e-7,0.000032712876,0.20318985,0.00010422034,0.73862064,0.00012374525,0.00011261296],"about_ca_topic_score_codex":0.002583919,"about_ca_topic_score_gemma":0.0005777512,"teacher_disagreement_score":0.22809628,"about_ca_system_score_codex":0.00006732305,"about_ca_system_score_gemma":0.00006433218,"threshold_uncertainty_score":0.9990701},"labels":[],"label_agreement":null},{"id":"W2130247335","doi":"10.1002/sim.3869","title":"Controlling ecological bias in evidence synthesis of trials reporting on collapsed and overlapping covariate categories","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; University of Bristol; Heart and Stroke Foundation of Canada","keywords":"Covariate; Econometrics; Statistics; Computer science; Mathematics","score_opus":0.8103766064910152,"score_gpt":0.5788043668938704,"score_spread":0.2315722395971448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130247335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95623994,0.0005878685,0.03796988,0.0013345367,0.0007780652,0.0011711429,0.00004431086,0.000003849408,0.0018704345],"genre_scores_gemma":[0.9817015,0.00012493129,0.01778944,0.00011789905,0.000079166304,0.00003708514,0.0000018663759,0.0000054895813,0.00014261706],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9613448,0.010333951,0.024103524,0.0007832535,0.0031682113,0.00026629973],"domain_scores_gemma":[0.63826513,0.32807958,0.03021202,0.002002225,0.0012621912,0.0001788823],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.39238068,0.0002034982,0.006065478,0.0005306314,0.000058698697,0.00010668833,0.00045626302,0.000104703046,0.0019429622],"category_scores_gemma":[0.9255049,0.00009361791,0.00017298319,0.000946831,0.00024784947,0.0000696996,0.000055651017,0.00030788104,0.000017304377],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045385482,0.00022531832,0.7020015,0.0006293039,0.00033136833,0.00049000385,0.00496422,0.0010749601,0.01570437,0.1977025,0.007957122,0.06846547],"study_design_scores_gemma":[0.0031188424,0.00054714794,0.7064291,0.0022832905,0.0008052358,0.00003522914,0.0047142925,0.08270364,0.00032064435,0.1968669,0.0017148348,0.0004607886],"about_ca_topic_score_codex":0.00026950368,"about_ca_topic_score_gemma":0.001087383,"teacher_disagreement_score":0.5331242,"about_ca_system_score_codex":0.000025104086,"about_ca_system_score_gemma":0.00010430696,"threshold_uncertainty_score":0.9989694},"labels":[],"label_agreement":null},{"id":"W2130606506","doi":"10.1002/1097-0258(20010115)20:1<63::aid-sim656>3.0.co;2-2","title":"Statistical analysis of repeated measurements with informative censoring times","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Censoring (clinical trials); Parametric statistics; Computer science; Missing data; Statistical hypothesis testing; Statistics; Regression; Econometrics; Artificial intelligence; Machine learning; Mathematics","score_opus":0.10166540638061615,"score_gpt":0.4125996493320424,"score_spread":0.31093424295142624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130606506","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023555761,0.00002272377,0.9455452,0.000046671543,0.000041086,0.00024151981,0.0006214408,0.000030313531,0.02989528],"genre_scores_gemma":[0.33255222,0.000032443528,0.6669319,0.000060299975,0.000018626992,0.000012824484,0.000084263374,0.00001547177,0.0002918836],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976956,0.00019846855,0.00087282987,0.00022355483,0.00071832165,0.00029118502],"domain_scores_gemma":[0.9960779,0.003019571,0.000203801,0.00030849042,0.00027108117,0.0001191464],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001013755,0.00019321949,0.00081860094,0.00033201947,0.000039916853,0.000007475598,0.00014763615,0.00005403179,0.007580421],"category_scores_gemma":[0.003956521,0.0001347552,0.00002120384,0.0010513334,0.00038917526,0.000044656612,0.000017017344,0.00021398903,0.0000091808115],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041157464,0.00021036784,0.01912983,0.000285216,0.0011966185,0.00007420386,0.004383352,0.00027334737,0.00006542828,0.9098595,0.0022996643,0.06181091],"study_design_scores_gemma":[0.0042678304,0.0018755788,0.26733404,0.001001708,0.004179104,0.000010812293,0.0015886223,0.05020687,0.00040121927,0.66806686,0.00033566408,0.00073169905],"about_ca_topic_score_codex":0.00025634735,"about_ca_topic_score_gemma":0.00011334005,"teacher_disagreement_score":0.30899647,"about_ca_system_score_codex":0.0000586598,"about_ca_system_score_gemma":0.0000471372,"threshold_uncertainty_score":0.9933268},"labels":[],"label_agreement":null},{"id":"W2130728435","doi":"10.1002/sim.2103","title":"The partial area under the summary ROC curve","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":246,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Receiver operating characteristic; Truncation (statistics); Measure (data warehouse); Sensitivity (control systems); Statistics; Area under the curve; Area under curve; Mathematics; Computer science; Medicine; Data mining; Internal medicine","score_opus":0.6102396939187572,"score_gpt":0.5384282700556492,"score_spread":0.07181142386310801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130728435","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057380493,0.010173295,0.8486532,0.08049479,0.001927969,0.001298071,0.00011763085,0.000009594609,0.051587425],"genre_scores_gemma":[0.9181996,0.0011043559,0.011655046,0.0065972256,0.0016395266,0.000096937205,0.000040955278,0.000026666898,0.060639694],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98339707,0.005445833,0.0056951223,0.0004804736,0.004678444,0.00030306907],"domain_scores_gemma":[0.97294265,0.022561247,0.0015582358,0.0023708714,0.0004699112,0.00009707197],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.10046454,0.00018676293,0.0013252561,0.00010456702,0.00027341096,0.00023144958,0.0015816187,0.00004134166,0.008326954],"category_scores_gemma":[0.04811865,0.000053712145,0.00018697292,0.0007846904,0.00037375494,0.00005722587,0.00009702093,0.0002660495,0.0009364803],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000056869367,0.000014253403,0.0032005752,0.0000047682547,0.000050348284,0.000005635098,0.0005625327,0.0003749952,0.0000036586566,0.09399304,0.8508113,0.05097319],"study_design_scores_gemma":[0.00024866252,0.00003691652,0.009802543,0.00003640742,0.00011182679,0.0000062398894,0.002602255,0.043570545,0.0000018394563,0.08010708,0.86338824,0.00008746216],"about_ca_topic_score_codex":0.000040025578,"about_ca_topic_score_gemma":0.001615317,"teacher_disagreement_score":0.9124615,"about_ca_system_score_codex":0.000037574213,"about_ca_system_score_gemma":0.000056067664,"threshold_uncertainty_score":0.9998414},"labels":[],"label_agreement":null},{"id":"W2131336573","doi":"10.1002/sim.3398","title":"A geometric confidence ellipse approach to the estimation of the ratio of two variables","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Ellipse; Tangent; Confidence interval; Coverage probability; Mathematics; Confidence distribution; Confidence region; Point estimation; Statistics; Applied mathematics; Geometry","score_opus":0.41984205646303874,"score_gpt":0.5298368237881074,"score_spread":0.10999476732506863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131336573","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002709794,0.00005733646,0.9932517,0.00041434466,0.00040811775,0.0008130453,0.00018234855,0.00000965108,0.0021536541],"genre_scores_gemma":[0.25881734,0.000044558456,0.7407067,0.00014610318,0.000097193406,0.00003270098,0.0000026817274,0.000013200601,0.00013952471],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99648494,0.00082948315,0.0013997214,0.00023198164,0.0008522244,0.00020163182],"domain_scores_gemma":[0.94202924,0.05643355,0.00052860624,0.00066219666,0.000280451,0.000065967426],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0051992936,0.00014774501,0.0006963223,0.00016504223,0.00007366422,0.000003580149,0.0005379015,0.00006657472,0.00012110158],"category_scores_gemma":[0.2649202,0.00007842133,0.00003716365,0.0014477371,0.00082173466,0.000021598731,0.00010683602,0.0002954617,0.000003851157],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005210369,0.0001933874,0.00046163832,0.00027153257,0.000033346663,0.000003357502,0.001517827,0.002717023,0.00013962599,0.9774645,0.012366004,0.0047796555],"study_design_scores_gemma":[0.0010787018,0.00017929309,0.0029066808,0.00024960676,0.00011035761,0.000010439442,0.00016821225,0.025893496,0.0007428184,0.9685143,0.00005381473,0.00009226039],"about_ca_topic_score_codex":0.00019399478,"about_ca_topic_score_gemma":0.000018591414,"teacher_disagreement_score":0.2597209,"about_ca_system_score_codex":0.0000376137,"about_ca_system_score_gemma":0.000116951865,"threshold_uncertainty_score":0.7412717},"labels":[],"label_agreement":null},{"id":"W2131644669","doi":"10.1002/sim.2078","title":"Cost-effectiveness analysis for multinational clinical trials","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; SickKids Foundation; University of Toronto; Population Health Research Institute; St. Joseph’s Healthcare Hamilton; Hospital for Sick Children","funders":"","keywords":"Univariate; Multinational corporation; Econometrics; Estimator; Clinical trial; Estimation; Multivariate statistics; Medicine; Statistics; Multivariate analysis; Computer science; Actuarial science; Economics; Mathematics; Finance; Internal medicine","score_opus":0.7655298801975778,"score_gpt":0.6423986283181136,"score_spread":0.12313125187946428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131644669","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060473043,0.0008366566,0.9670107,0.019636912,0.00085871445,0.0019236696,0.0027749375,0.000021725344,0.0008893906],"genre_scores_gemma":[0.6946446,0.00040328648,0.28228906,0.014705142,0.0038979584,0.0012974327,0.00167073,0.000058151963,0.0010336459],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.98980045,0.001759253,0.0074931355,0.00052031555,0.00012329064,0.00030353008],"domain_scores_gemma":[0.9580652,0.03898824,0.0023225592,0.0003036388,0.00016239175,0.00015794115],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15382825,0.00015345526,0.0022906633,0.0006848951,0.00008829189,0.000018090352,0.00018289921,0.00014192415,0.001042422],"category_scores_gemma":[0.13106687,0.00016723321,0.00016272695,0.0003973091,0.00015084544,0.00012557693,0.000021042488,0.00019063524,0.00024009436],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011800531,0.00023737081,0.28642917,0.0002614189,0.000633632,0.000001284828,0.0008450701,0.0038335843,8.3805025e-7,0.6512588,0.046037294,0.010343514],"study_design_scores_gemma":[0.0072668362,0.00022141486,0.5304446,0.00009382932,0.00017291507,9.457514e-7,0.0003983927,0.23342419,0.0000014900111,0.0846404,0.14301169,0.00032326573],"about_ca_topic_score_codex":0.00031013,"about_ca_topic_score_gemma":0.00063973217,"teacher_disagreement_score":0.68859726,"about_ca_system_score_codex":0.00047240418,"about_ca_system_score_gemma":0.00011114357,"threshold_uncertainty_score":0.9998708},"labels":[],"label_agreement":null},{"id":"W2131715846","doi":"10.1002/sim.3645","title":"Two‐stage design of clinical trials involving recurrent events","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Interim; Interim analysis; Sample size determination; Clinical trial; Event (particle physics); Poisson regression; Poisson distribution; Population; Statistics; Stage (stratigraphy); Medicine; Computer science; Mathematics; Internal medicine","score_opus":0.8501905449859165,"score_gpt":0.7057092213771811,"score_spread":0.14448132360873545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131715846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096807687,0.00026644056,0.99329466,0.0005057636,0.002285058,0.0012293487,0.00029974707,0.00004626546,0.0011046214],"genre_scores_gemma":[0.020857967,0.00069999124,0.97694623,0.00037586794,0.0008608582,0.000019889321,0.000010200869,0.000032041182,0.00019694089],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9767825,0.012692276,0.008246478,0.0006217211,0.0011447375,0.000512279],"domain_scores_gemma":[0.74081695,0.2563162,0.0017632147,0.0005896572,0.00026758478,0.00024636902],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08820321,0.00031514623,0.0033751496,0.00022386342,0.000040993375,0.00000710958,0.0004655099,0.00023601735,0.0009806791],"category_scores_gemma":[0.7832535,0.00023617143,0.00014959517,0.0004273379,0.000412934,0.000042401945,0.00006922685,0.0008408881,0.000012881058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010687545,0.0008236416,0.0016364496,0.00026104643,0.00010446766,0.00009585411,0.0003240647,0.000030535084,0.00021947305,0.7621546,0.018293101,0.21498805],"study_design_scores_gemma":[0.0061173015,0.0017446791,0.00276707,0.000923973,0.00022241703,0.0000018102384,0.00012162929,0.003769808,0.000091057766,0.98387045,0.00015527241,0.0002145155],"about_ca_topic_score_codex":0.000023226188,"about_ca_topic_score_gemma":0.000010210107,"teacher_disagreement_score":0.6950503,"about_ca_system_score_codex":0.00006558933,"about_ca_system_score_gemma":0.00017391563,"threshold_uncertainty_score":0.9999326},"labels":[],"label_agreement":null},{"id":"W2131839274","doi":"10.1002/sim.6621","title":"Terminating observation within matched pairs of subjects in a matched cohort analysis: a Monte Carlo simulation study","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care","keywords":"Censoring (clinical trials); Monte Carlo method; Statistics; Observational study; Cohort; Event (particle physics); Computer science; Cohort study; Econometrics; Mathematics; Physics","score_opus":0.17266836408797095,"score_gpt":0.45042957816131257,"score_spread":0.27776121407334164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131839274","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7817382,0.000016860853,0.21715459,0.000030046496,0.000047279027,0.0008316194,0.000018658635,0.000069724396,0.000093027564],"genre_scores_gemma":[0.82438165,0.0000031528064,0.1754089,0.000020231557,0.000020443731,0.00007963315,0.000022970084,0.000021902728,0.00004109502],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973416,0.00027279663,0.0012191518,0.0002886085,0.00066551,0.00021233356],"domain_scores_gemma":[0.9970763,0.001417411,0.0006120244,0.00039568174,0.0004260639,0.00007256927],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030677083,0.00020336869,0.0008715231,0.0005713999,0.000017522965,0.0000072855405,0.00016355382,0.000089002366,0.000014023644],"category_scores_gemma":[0.008534191,0.00018170236,0.000021731792,0.0013504749,0.000100799734,0.00013217458,0.000051312676,0.00026463406,5.622851e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084941676,0.00040592282,0.92377394,0.00017803928,0.00014650254,0.00009306521,0.036558885,0.033255205,0.0002434475,0.004536859,0.00007621613,0.0006469417],"study_design_scores_gemma":[0.0021136259,0.00069821614,0.32331148,0.0004001662,0.00053121755,0.0000011066895,0.023895135,0.43066865,0.00020972939,0.21791416,7.1701055e-7,0.00025578824],"about_ca_topic_score_codex":0.001484192,"about_ca_topic_score_gemma":0.0050587296,"teacher_disagreement_score":0.6004625,"about_ca_system_score_codex":0.00026955767,"about_ca_system_score_gemma":0.00007621897,"threshold_uncertainty_score":0.9998174},"labels":[],"label_agreement":null},{"id":"W2132469784","doi":"10.1002/sim.3719","title":"Quadratic inference functions in marginal models for longitudinal data","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Paul's Hospital; Alberta Cancer Foundation","funders":"National Science Foundation","keywords":"Inference; Computer science; Robustness (evolution); Statistical inference; Quadratic equation; Macro; Model selection; Applied mathematics; Econometrics; Machine learning; Statistics; Mathematics; Artificial intelligence","score_opus":0.331254591012354,"score_gpt":0.49301774444195917,"score_spread":0.16176315342960518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132469784","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007976721,0.00007891801,0.9937815,0.00092427724,0.00021224016,0.00041341546,0.00075719244,0.000023740151,0.0030110162],"genre_scores_gemma":[0.30451253,0.000033808174,0.69477904,0.00017565061,0.00011410101,0.00003115867,0.00017961359,0.000012434991,0.00016169214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981001,0.000110057,0.00068837986,0.00042222007,0.00031410778,0.00036516166],"domain_scores_gemma":[0.99339765,0.005609929,0.00011992415,0.00063742837,0.00013285269,0.000102234524],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014072126,0.00018812748,0.0004914038,0.00018984203,0.0000542617,0.000016695538,0.00038759975,0.00007197093,0.0002506459],"category_scores_gemma":[0.014636195,0.00015611859,0.000011835066,0.0003169966,0.0001619748,0.0001127383,0.000058386067,0.000302879,0.0000054661973],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058947157,0.0001352676,0.0005811599,0.00010767808,0.000006415683,0.000028035643,0.00032287632,0.000070953814,0.00001823083,0.9668229,0.0069288113,0.024918724],"study_design_scores_gemma":[0.0008862366,0.0003657695,0.0065601612,0.00023318183,0.00003641775,0.0000040865752,0.00019333906,0.22395258,0.0000013886579,0.767508,0.00012648272,0.00013238135],"about_ca_topic_score_codex":0.00014588393,"about_ca_topic_score_gemma":0.0005792759,"teacher_disagreement_score":0.30371484,"about_ca_system_score_codex":0.000065506465,"about_ca_system_score_gemma":0.0001021636,"threshold_uncertainty_score":0.99366397},"labels":[],"label_agreement":null},{"id":"W2133169911","doi":"10.1002/sim.2913","title":"Impact of approximating or ignoring within‐study covariances in multivariate meta‐analyses","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital; Montreal General Hospital; Montreal Children's Hospital; McGill University; Canadian Association of Radiation Oncology","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Multivariate statistics; Covariance; Statistics; Econometrics; Meta-analysis; Multivariate analysis; Correlation; Scale (ratio); Mathematics; Medicine","score_opus":0.8667966181484852,"score_gpt":0.6644247021312913,"score_spread":0.20237191601719384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133169911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25801834,0.00079715566,0.7360187,0.00004600286,0.00029324339,0.0012280543,0.00004694699,0.0000046181217,0.0035469488],"genre_scores_gemma":[0.8587548,0.000009488099,0.14075066,0.000022770382,0.000055438133,0.000019095109,0.000005536755,0.000010212707,0.00037196654],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9687655,0.006275479,0.018124424,0.0009573514,0.0054332754,0.000443949],"domain_scores_gemma":[0.9704131,0.020882957,0.0061128265,0.0016693015,0.0007866933,0.00013513376],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21002795,0.00033721005,0.0058342773,0.0011869469,0.000054729113,0.000080812424,0.0009974653,0.000056477646,0.004399983],"category_scores_gemma":[0.15662788,0.00012858922,0.00042469543,0.0034582876,0.00014007535,0.00013261741,0.00009461732,0.00027569567,0.000038054957],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036371645,0.00099594,0.901361,0.00036030827,0.008229618,0.000597173,0.036918603,0.01394326,0.0009305004,0.0092169605,0.0022905006,0.02479243],"study_design_scores_gemma":[0.0031928325,0.0012566829,0.81199986,0.00038155314,0.005392953,0.000019948291,0.03145719,0.11672143,0.00006539274,0.028954405,0.000087054716,0.00047069378],"about_ca_topic_score_codex":0.0023767648,"about_ca_topic_score_gemma":0.005264631,"teacher_disagreement_score":0.6007365,"about_ca_system_score_codex":0.00007233362,"about_ca_system_score_gemma":0.00010606198,"threshold_uncertainty_score":0.99651015},"labels":[],"label_agreement":null},{"id":"W2133300801","doi":"10.1002/sim.6085","title":"Value of information methods for assessing a new diagnostic test","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto; Public Health Ontario","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Value of information; Test (biology); Value (mathematics); Sample (material); Sample size determination; Statistics; Econometrics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.3956805353606469,"score_gpt":0.635194064645554,"score_spread":0.23951352928490705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133300801","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000092886636,0.000030229032,0.99576056,0.0005185592,0.00081253145,0.00065057795,0.00013540866,0.000032610784,0.0019666296],"genre_scores_gemma":[0.0028046807,0.000032917156,0.9962839,0.00034163744,0.00039658786,0.000043089432,0.000019120376,0.000025114914,0.000052942938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965553,0.0008180749,0.0017891467,0.00019656385,0.00035339565,0.00028749398],"domain_scores_gemma":[0.52094716,0.47782296,0.00055445917,0.00031510813,0.00022769015,0.00013261924],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01096513,0.00018429787,0.0009361801,0.0001848767,0.000039703147,0.0000181862,0.00024190206,0.00013769857,0.0001476288],"category_scores_gemma":[0.89572906,0.00014904446,0.00004320128,0.00030143198,0.00026707348,0.0001117658,0.000052905696,0.00024849092,0.000004662432],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020203426,0.000050832183,0.00039450554,0.00048980815,0.0000132982905,6.15441e-7,0.00027448358,0.000009255777,0.00010035493,0.65074044,0.007889866,0.3400163],"study_design_scores_gemma":[0.0023327887,0.00045290464,0.0021711774,0.0005848526,0.00015955322,0.0000018639694,0.00009795269,0.019832289,0.00026560528,0.9708758,0.0030826936,0.00014253876],"about_ca_topic_score_codex":0.000062410014,"about_ca_topic_score_gemma":0.000006581092,"teacher_disagreement_score":0.88476396,"about_ca_system_score_codex":0.000052931682,"about_ca_system_score_gemma":0.00011547902,"threshold_uncertainty_score":0.60778564},"labels":[],"label_agreement":null},{"id":"W2133313519","doi":"10.1002/sim.5891","title":"A spatial scan statistic for compound Poisson data","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Canadian Institutes of Health Research; Alberta Innovates; University of Alberta; Government of Alberta","keywords":"Scan statistic; Poisson distribution; Cluster analysis; Statistic; Cluster (spacecraft); Spatial epidemiology; Computer science; Statistics; Spatial analysis; Data mining; Poisson regression; Count data; Epidemiology; Econometrics; Medicine; Artificial intelligence; Mathematics; Environmental health; Pathology","score_opus":0.0479821941350101,"score_gpt":0.37055638338498254,"score_spread":0.32257418924997244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133313519","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021483753,0.00089914637,0.9257008,0.005961943,0.0014962989,0.0046676723,0.03565661,0.00020967223,0.003924144],"genre_scores_gemma":[0.8008389,0.00013351608,0.16413383,0.0016979913,0.00083352404,0.00018015478,0.031301837,0.000082725404,0.00079753256],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9977118,0.000078229226,0.00064530014,0.00056671037,0.000535294,0.0004626749],"domain_scores_gemma":[0.99691224,0.0010805125,0.0001666678,0.0012036205,0.00030482106,0.00033212884],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00059776736,0.00023826487,0.0006753731,0.00018272827,0.000061244755,0.000021463047,0.0003990104,0.00006263595,0.0022785894],"category_scores_gemma":[0.00427478,0.00020127436,0.000018331059,0.00020943648,0.00037008262,0.000109266875,0.00015400126,0.00022970342,0.00013543111],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040343523,0.00029259443,0.03202844,0.0008527241,0.00012484768,0.00029003122,0.00029938552,0.0000042957245,0.0006353179,0.006724166,0.82859176,0.12975298],"study_design_scores_gemma":[0.016121557,0.0017744312,0.7170585,0.001090314,0.00045971433,0.00009964527,0.0005516162,0.13542452,0.000023683138,0.033949748,0.092781805,0.00066448306],"about_ca_topic_score_codex":0.004071804,"about_ca_topic_score_gemma":0.0018504662,"teacher_disagreement_score":0.7793551,"about_ca_system_score_codex":0.00012982228,"about_ca_system_score_gemma":0.00021900066,"threshold_uncertainty_score":0.99863344},"labels":[],"label_agreement":null},{"id":"W2133519275","doi":"10.1002/sim.5599","title":"An information criterion for marginal structural models","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Center for Research Resources; National Institute of Child Health and Human Development; National Institute of Allergy and Infectious Diseases; National Cancer Institute; National Institute on Aging","keywords":"Marginal structural model; Marginal model; Econometrics; Specification; Inference; Computer science; Metric (unit); Observational study; Parametric statistics; Causal inference; Regression; Semiparametric regression; Marginal likelihood; Regression analysis; Statistics; Mathematics; Machine learning; Bayesian probability; Artificial intelligence; Economics","score_opus":0.1399503500513534,"score_gpt":0.47609368767591403,"score_spread":0.3361433376245606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133519275","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01124641,0.00002651156,0.98716384,0.0000818087,0.00019969065,0.00036551568,0.0001519375,0.000088515015,0.0006757653],"genre_scores_gemma":[0.43115345,0.000010516183,0.5683576,0.00012253693,0.00012744498,0.00004251565,0.00016231349,0.000009675886,0.000013942394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990676,0.000031441377,0.0003650694,0.00007241829,0.00019957038,0.00026390812],"domain_scores_gemma":[0.99908966,0.0003745916,0.000121224446,0.00018964817,0.0001395521,0.00008531319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005204866,0.00011687951,0.00020393963,0.00012329537,0.000040760922,0.000009172353,0.00010711068,0.000058192338,0.00008812748],"category_scores_gemma":[0.00081377936,0.00009554342,0.00000862482,0.00007709009,0.0000833715,0.0009795795,0.000015415979,0.00012397201,0.0000018535076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003529623,0.000014310609,0.00026774246,0.00013400652,0.0000030475221,5.555923e-7,0.0024134615,0.000021472257,0.0002884211,0.9792293,0.0031756111,0.014416814],"study_design_scores_gemma":[0.0004200889,0.00023177826,0.00064461015,0.000065985456,0.000016036516,0.000006160265,0.00043538056,0.03468682,0.00022139629,0.96269304,0.00046374113,0.00011494656],"about_ca_topic_score_codex":0.000022406664,"about_ca_topic_score_gemma":0.000013531598,"teacher_disagreement_score":0.41990703,"about_ca_system_score_codex":0.00008191967,"about_ca_system_score_gemma":0.000015367197,"threshold_uncertainty_score":0.3896148},"labels":[],"label_agreement":null},{"id":"W2133594561","doi":"10.1002/sim.5938","title":"Estimating successive cancer risks in Lynch Syndrome families using a progressive three‐state model","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic factors in colorectal cancer","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; Alberta Health Services; Memorial University of Newfoundland; Public Health Ontario; University of Toronto; Mount Sinai Hospital; Western University","funders":"Canadian Institutes of Health Research","keywords":"Penetrance; Colorectal cancer; Estimator; Cancer; Statistics; Lynch syndrome; Medicine; Genotype; Estimation; Computer science; Genetics; DNA mismatch repair; Mathematics; Biology; Internal medicine; Gene; Phenotype","score_opus":0.060183370546366306,"score_gpt":0.3910755280911346,"score_spread":0.3308921575447683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133594561","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9161146,0.0015383466,0.07959821,0.00034219632,0.00053253776,0.0014150923,0.00009828332,0.00003840929,0.00032232047],"genre_scores_gemma":[0.8323765,0.00011494644,0.16661538,0.00029246602,0.00010368766,0.0003470802,0.000029962659,0.00005394219,0.00006607465],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722785,0.000063671825,0.00087331183,0.0005116597,0.00068524794,0.0006382852],"domain_scores_gemma":[0.9983957,0.00041211935,0.00030810616,0.00033817504,0.00034455003,0.00020135655],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003576572,0.0003468251,0.0008110633,0.0004401563,0.00006597481,0.000020342395,0.00018855755,0.00013057949,0.0006495254],"category_scores_gemma":[0.0014076263,0.00028265148,0.0000277042,0.0006121558,0.0005185659,0.000103980085,0.00010479883,0.00064012606,0.0000125720935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003773465,0.00035548696,0.59771144,0.002263617,0.00021425236,0.0027170093,0.0141066015,0.2865518,0.00651391,0.0005143484,0.0015187644,0.08715542],"study_design_scores_gemma":[0.0023661887,0.00037191817,0.116470665,0.0021942488,0.00010061834,0.0000855483,0.00052978477,0.86544114,0.00012113638,0.012054091,0.0000031081124,0.00026154728],"about_ca_topic_score_codex":0.013531683,"about_ca_topic_score_gemma":0.002418168,"teacher_disagreement_score":0.5788893,"about_ca_system_score_codex":0.0006266142,"about_ca_system_score_gemma":0.00046701348,"threshold_uncertainty_score":0.99996257},"labels":[],"label_agreement":null},{"id":"W2133707942","doi":"10.1002/sim.5567","title":"Impact of variability on the choice of biosimilarity limits in assessing follow‐on biologics","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Biosimilars and Bioanalytical Methods","field":"Immunology and Microbiology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Biosimilar; Bioequivalence; Econometrics; Limit (mathematics); Statistics; Computer science; Economics; Mathematics; Pharmacology; Medicine; Biotechnology; Biology","score_opus":0.09628629694275934,"score_gpt":0.42570780713145306,"score_spread":0.3294215101886937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133707942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98393077,0.00061574794,0.0063035903,0.0013964304,0.0008768417,0.00040390878,0.00041731226,0.000011273718,0.006044106],"genre_scores_gemma":[0.99664974,0.000071478906,0.0028895158,0.0002961229,0.00003576353,0.0000034463053,0.000021966234,0.0000056241734,0.0000263699],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978195,0.0011226328,0.00051228434,0.00017053961,0.000065579174,0.0003094956],"domain_scores_gemma":[0.9913574,0.008047066,0.00019456126,0.0003029967,0.00007235072,0.000025630938],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004035743,0.00015000631,0.00049475866,0.00012080837,0.000031985095,0.0000016276457,0.00018386391,0.00024923825,0.00052772975],"category_scores_gemma":[0.011854044,0.00007605228,0.000050693932,0.00032892879,0.00070321985,0.00002284088,0.000036824324,0.0005260926,0.0000025624508],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024012427,0.0009704657,0.8854852,0.00006342313,0.00011174692,0.000002155762,0.00029956983,0.0000059644894,0.062303297,0.035958737,0.003107935,0.01145141],"study_design_scores_gemma":[0.00085967046,0.0009921208,0.9857866,0.00017835772,0.000044329932,0.0000013005208,0.0000897976,0.00004977328,0.0064764256,0.0051796315,0.0002509,0.00009105986],"about_ca_topic_score_codex":0.00025408753,"about_ca_topic_score_gemma":0.00003447762,"teacher_disagreement_score":0.10030147,"about_ca_system_score_codex":0.000068616304,"about_ca_system_score_gemma":0.000042774926,"threshold_uncertainty_score":0.99646956},"labels":[],"label_agreement":null},{"id":"W2134646536","doi":"10.1002/sim.2899","title":"Bayesian modelling of tuberculosis clustering from DNA fingerprint data","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Tuberculosis Research and Epidemiology","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Montreal General Hospital; McGill University","funders":"","keywords":"Genotyping; Bayesian probability; Cluster analysis; Categorical variable; Bayes' theorem; Computer science; Statistics; Data mining; Computational biology; Genetics; Biology; Artificial intelligence; Genotype; Mathematics; Machine learning","score_opus":0.10086367248325231,"score_gpt":0.3940453108420791,"score_spread":0.2931816383588268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134646536","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05475659,0.0005954866,0.93930507,0.0021277016,0.00020768867,0.0002476291,0.00030785715,0.000022224964,0.0024297587],"genre_scores_gemma":[0.834835,0.00088253384,0.16242,0.0006290524,0.00035250184,0.0000033055544,0.0008073487,0.000025247211,0.000045022076],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756235,0.000094494324,0.0009105755,0.00044805591,0.00047424488,0.00051025307],"domain_scores_gemma":[0.9967384,0.0018228779,0.00012683355,0.00091061817,0.0001204937,0.0002808098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026057102,0.00017000327,0.0007208132,0.00030775162,0.000033358257,0.0000028031614,0.00031009046,0.00012500818,0.0004195484],"category_scores_gemma":[0.0030832267,0.0001388394,0.000024837325,0.00027207876,0.00028313903,0.000049584145,0.00024498647,0.00047143715,0.000010642302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0051927455,0.0013555497,0.46564364,0.0026202104,0.0016703266,0.0038343521,0.008198781,0.01625349,0.044733215,0.011427686,0.06913205,0.36993796],"study_design_scores_gemma":[0.0028087725,0.00052577903,0.07806955,0.0010134678,0.00018419765,0.000035372144,0.000752702,0.9058144,0.0006404198,0.0078119836,0.002117152,0.00022621658],"about_ca_topic_score_codex":0.005805056,"about_ca_topic_score_gemma":0.0017083014,"teacher_disagreement_score":0.8895609,"about_ca_system_score_codex":0.00010240985,"about_ca_system_score_gemma":0.00007278162,"threshold_uncertainty_score":0.8775547},"labels":[],"label_agreement":null},{"id":"W2135029321","doi":"10.1002/sim.1301","title":"Issues in the meta‐analysis of cluster randomized trials","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":731,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario; Western University","funders":"","keywords":"Meta-analysis; Randomization; Randomized controlled trial; Cluster (spacecraft); Computer science; Research design; Econometrics; Statistics; Medicine; Mathematics; Surgery","score_opus":0.8482658612698941,"score_gpt":0.6110797934992076,"score_spread":0.23718606777068652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135029321","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039357515,0.08432114,0.8266863,0.040613417,0.0006968162,0.006325928,0.0004383724,0.000005261544,0.03697701],"genre_scores_gemma":[0.9092833,0.0029017904,0.06599886,0.0037101256,0.00021364618,0.00033568678,0.000058410296,0.000017776158,0.017480452],"study_design_codex":"not_applicable","study_design_gemma":"meta_analysis","domain_scores_codex":[0.8262555,0.13069509,0.032185055,0.00090775546,0.00962906,0.00032757418],"domain_scores_gemma":[0.8213107,0.16967699,0.0059245485,0.0024375992,0.0005973385,0.0000528232],"candidate_categories":["metaresearch","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.53794825,0.00022345394,0.020082586,0.0014950604,0.000028881494,0.0000866799,0.0013198034,0.000054938533,0.075801596],"category_scores_gemma":[0.44427195,0.00006784457,0.0025606588,0.0044669923,0.000295457,0.000050401544,0.000040646064,0.00016585409,0.0001791769],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010479807,0.00024574535,0.0022153219,0.00012369952,0.1286283,0.000060011364,0.024340509,0.0017689071,0.000009266652,0.0955433,0.7370014,0.009015528],"study_design_scores_gemma":[0.039826754,0.00008846244,0.0017031088,0.000042754204,0.5040606,0.0000031681554,0.0048214407,0.2712018,0.0000026703165,0.15210655,0.025892513,0.00025017443],"about_ca_topic_score_codex":0.00024366468,"about_ca_topic_score_gemma":0.0006489371,"teacher_disagreement_score":0.9053475,"about_ca_system_score_codex":0.000010407755,"about_ca_system_score_gemma":0.000008638802,"threshold_uncertainty_score":0.9944653},"labels":[],"label_agreement":null},{"id":"W2136825758","doi":"10.1002/sim.1601","title":"Estimating linear regression models in the presence of a censored independent variable","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Health and Long-Term Care","keywords":"Statistics; Ordinary least squares; Censored regression model; Variables; Mathematics; Linear regression; Regression analysis; Econometrics; Monte Carlo method; Censoring (clinical trials); Local regression; Segmented regression; Polynomial regression","score_opus":0.07086286344301371,"score_gpt":0.41269204990285613,"score_spread":0.3418291864598424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136825758","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022256672,0.000050350114,0.9950765,0.00026291123,0.00015271308,0.00031391263,0.000073400464,0.000010934742,0.0018336499],"genre_scores_gemma":[0.13665779,0.0000165195,0.8631391,0.00006991489,0.00006099391,0.000020973188,0.000007694844,0.0000116837455,0.000015327822],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99797946,0.00025774134,0.0007000903,0.00021881146,0.0005854653,0.00025842854],"domain_scores_gemma":[0.9949832,0.0042999038,0.00021368008,0.0003412796,0.000112371315,0.00004958897],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020049575,0.0001469436,0.00041682724,0.000118608754,0.000039279726,0.0000068949016,0.0003058212,0.00007697455,0.000075529795],"category_scores_gemma":[0.012214566,0.000087777604,0.000012001503,0.00040064607,0.00022663377,0.00005150957,0.000053301155,0.00039286056,0.0000012044909],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030003108,0.0001252654,0.00017398615,0.00025349786,0.000004612731,0.00007565349,0.0035635808,0.0017197544,0.00017115584,0.98911166,0.0003119802,0.0044588502],"study_design_scores_gemma":[0.00094711385,0.00013371363,0.00052219024,0.0013153034,0.000018102286,0.00001018757,0.0005226442,0.12567766,0.000050931736,0.87071747,0.000005067209,0.00007960598],"about_ca_topic_score_codex":0.00051828695,"about_ca_topic_score_gemma":0.00008358791,"teacher_disagreement_score":0.13443212,"about_ca_system_score_codex":0.00005236596,"about_ca_system_score_gemma":0.00009039993,"threshold_uncertainty_score":0.99610597},"labels":[],"label_agreement":null},{"id":"W2136972950","doi":"10.1002/sim.4453","title":"Hierarchical priors for bias parameters in Bayesian sensitivity analysis for unmeasured confounding","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of British Columbia; Simon Fraser University","funders":"","keywords":"Prior probability; Covariate; Bayesian probability; Econometrics; Confounding; Computer science; Statistics; Mathematics","score_opus":0.15468768461269244,"score_gpt":0.44139871257239166,"score_spread":0.2867110279596992,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136972950","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008164536,0.00002964019,0.989576,0.00032584832,0.00033356823,0.0008622997,0.00050560967,0.00002299332,0.00017954555],"genre_scores_gemma":[0.37697515,0.0000062009312,0.62264645,0.00010071451,0.00009955614,0.00008188175,0.000052186824,0.000019248837,0.000018626759],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973776,0.00047517451,0.00080171716,0.00032330543,0.00035668028,0.00066554087],"domain_scores_gemma":[0.9711333,0.028046088,0.00019940542,0.00027148184,0.00012937616,0.00022036835],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0058181197,0.00023333337,0.0009410294,0.00049302937,0.00007045283,0.000017065811,0.00010664841,0.00012670539,0.000046599118],"category_scores_gemma":[0.040928155,0.00019564074,0.00007875208,0.0006846128,0.00029210252,0.000055509965,0.000025003123,0.00027844706,9.641252e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001768047,0.00016173343,0.04455245,0.00035138044,0.00017218833,0.000016840886,0.0017674888,0.000017093158,0.00012343135,0.9310678,0.00070652313,0.020886254],"study_design_scores_gemma":[0.0018171225,0.00023261354,0.03357058,0.00018489212,0.0005819708,0.0000045839606,0.00047687563,0.053769678,0.000089617664,0.90881866,0.00016045033,0.0002929382],"about_ca_topic_score_codex":0.00014244467,"about_ca_topic_score_gemma":0.0006547609,"teacher_disagreement_score":0.36881062,"about_ca_system_score_codex":0.00014687488,"about_ca_system_score_gemma":0.000058202982,"threshold_uncertainty_score":0.9671505},"labels":[],"label_agreement":null},{"id":"W2137538399","doi":"10.1002/sim.5522","title":"Event‐weighted proportional hazards modelling for recurrent gap time data","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Guelph","funders":"","keywords":"Resampling; Proportional hazards model; Statistics; Independence (probability theory); Computer science; Event (particle physics); Marginal model; Econometrics; Mathematics; Inverse; Applied mathematics; Regression analysis","score_opus":0.2797240781651692,"score_gpt":0.47789476376986334,"score_spread":0.19817068560469414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137538399","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004702146,0.00029134564,0.9948279,0.0003018808,0.0005562629,0.0004956626,0.0019204317,0.000029455896,0.0011068393],"genre_scores_gemma":[0.016375706,0.0000637088,0.9815712,0.00008451585,0.0006333166,0.000053134398,0.0008511187,0.000030201354,0.00033712244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979987,0.00011994625,0.0006948513,0.00028625736,0.0004721696,0.00042806304],"domain_scores_gemma":[0.9957192,0.0032364195,0.0001905197,0.00049079105,0.00019047536,0.00017259642],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0024927028,0.00017687622,0.00041479582,0.0000731762,0.00006484181,0.000008231035,0.00029601986,0.000070393246,0.0010033892],"category_scores_gemma":[0.007062148,0.00013531517,0.000016428246,0.00014283422,0.00015640994,0.0000796313,0.000100547164,0.00021742839,0.000024030744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070871545,0.00020132476,0.00014135835,0.00024883018,0.000025618761,0.0000030395786,0.00029414578,0.0000071600307,0.000031490075,0.91566306,0.04867272,0.034640364],"study_design_scores_gemma":[0.0005117871,0.00015729763,0.000091371716,0.00017290056,0.00006629864,0.0000039163237,0.000044312594,0.38149872,0.000014072558,0.6146127,0.0027004455,0.00012619175],"about_ca_topic_score_codex":0.000018242416,"about_ca_topic_score_gemma":0.0000059614554,"teacher_disagreement_score":0.38149157,"about_ca_system_score_codex":0.0000743386,"about_ca_system_score_gemma":0.00008586676,"threshold_uncertainty_score":0.9999098},"labels":[],"label_agreement":null},{"id":"W2137903189","doi":"10.1002/sim.6572","title":"The Africa Center for Biostatistical Excellence: a proposal for enhancing biostatistics capacity for sub‐Saharan Africa","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health and Medical Research Impacts","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Fogarty International Center; National Institutes of Health; U.S. Public Health Service; Wellcome Trust; U.S. President’s Emergency Plan for AIDS Relief","keywords":"Biostatistics; Brainstorming; Center of excellence; Economic shortage; Excellence; Capacity building; Medical education; Capacity development; Statistician; Library science; Political science; Medicine; Computer science; Geography; Mathematics; Statistics; Environmental planning; Public health; Artificial intelligence; Nursing","score_opus":0.17510408876753647,"score_gpt":0.43606887980124204,"score_spread":0.26096479103370557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137903189","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021836712,0.0009938083,0.9549209,0.030002497,0.0010875658,0.006226105,0.005923295,0.00004449827,0.0005829462],"genre_scores_gemma":[0.053956434,0.001513518,0.93144095,0.0033209804,0.0026437447,0.0031276236,0.0017758621,0.0001833485,0.00203753],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9951103,0.00014905489,0.0010632381,0.00050769036,0.001147815,0.002021919],"domain_scores_gemma":[0.9830719,0.011285176,0.00019087536,0.00040175207,0.0014069802,0.0036432815],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0063451547,0.00032529974,0.0007730602,0.00021060367,0.00032385928,0.000034171528,0.00025112962,0.00019330802,0.000022932865],"category_scores_gemma":[0.2410416,0.0002057479,0.00006690965,0.0003250605,0.0010033866,0.000047326765,0.00004594455,0.00049961044,0.000009632583],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0035797167,0.00029903217,0.00008810381,0.001960634,0.000059140326,0.00004919223,0.0016774527,0.0000012476337,0.0007940553,0.040630363,0.8941183,0.05674273],"study_design_scores_gemma":[0.01905343,0.010097981,0.00019662312,0.0010037059,0.00021543894,0.000043708045,0.0013617362,0.019238066,0.00056531857,0.13166198,0.81620485,0.0003571568],"about_ca_topic_score_codex":0.000077297795,"about_ca_topic_score_gemma":0.00043116344,"teacher_disagreement_score":0.23469645,"about_ca_system_score_codex":0.0004954381,"about_ca_system_score_gemma":0.005042705,"threshold_uncertainty_score":0.89455426},"labels":[],"label_agreement":null},{"id":"W2138393952","doi":"10.1002/sim.3095","title":"Construction of confidence limits about effect measures: A general approach","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":252,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Confidence interval; Computer science; Statistics; Log-normal distribution; Econometrics; Mathematics","score_opus":0.5277622902536679,"score_gpt":0.527346483686242,"score_spread":0.0004158065674259026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138393952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037245646,0.0009940348,0.9411585,0.00006795296,0.00048149904,0.0005124364,0.000028103032,0.0000027956974,0.01950904],"genre_scores_gemma":[0.773428,0.00008979943,0.22464383,0.00013239957,0.00020110454,0.000013059056,0.000020524174,0.000009698619,0.001461563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9811692,0.0041316333,0.0081309015,0.00064387405,0.0056509417,0.00027345374],"domain_scores_gemma":[0.9853996,0.009228762,0.0027885488,0.001390992,0.0010605773,0.00013154447],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.15214857,0.00020774225,0.002763194,0.00052575173,0.00004589814,0.000046617686,0.0007148599,0.000077834724,0.0014404948],"category_scores_gemma":[0.09823371,0.00009885066,0.00019293971,0.0012423968,0.000424111,0.000054590942,0.000028819159,0.00019406574,0.00009033976],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010077524,0.000089903995,0.18605103,0.00051408465,0.0002521593,0.000060975184,0.0029894842,0.00021938878,0.0017859621,0.4207374,0.05795018,0.32924867],"study_design_scores_gemma":[0.007241348,0.0022915748,0.5188615,0.0017025422,0.002020494,0.00044761467,0.010258447,0.08886697,0.0022770935,0.30992046,0.054735716,0.0013762641],"about_ca_topic_score_codex":0.000082188424,"about_ca_topic_score_gemma":0.00009667105,"teacher_disagreement_score":0.7361824,"about_ca_system_score_codex":0.00003316298,"about_ca_system_score_gemma":0.00005114455,"threshold_uncertainty_score":0.9994723},"labels":[],"label_agreement":null},{"id":"W2138878140","doi":"10.1002/sim.2069","title":"The value of information and optimal clinical trial design","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":186,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Population Health Research Institute; SickKids Foundation; Hospital for Sick Children","funders":"Natural Sciences and Engineering Research Council of Canada; Sick Kids Foundation","keywords":"Type I and type II errors; Sample size determination; Null hypothesis; Value (mathematics); Sample (material); Set (abstract data type); Value of information; Computer science; Perspective (graphical); Statistics; Clinical trial; Medicine; Mathematics; Artificial intelligence; Internal medicine","score_opus":0.5587308049738138,"score_gpt":0.6187845387614808,"score_spread":0.060053733787666985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138878140","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029421945,0.00007956684,0.9934734,0.0011440597,0.000808301,0.000795131,0.00006130837,0.000016507225,0.0006795272],"genre_scores_gemma":[0.0077439924,0.0005403189,0.99081933,0.00021127284,0.00059889944,0.000025214345,0.000002594898,0.000011181103,0.00004721653],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99506074,0.001457587,0.002590185,0.00015859936,0.0005026592,0.00023020935],"domain_scores_gemma":[0.8475086,0.1514656,0.00051153946,0.00028184304,0.00013668714,0.00009570134],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018654851,0.00013181522,0.00064774737,0.00006821886,0.000063417596,0.000014540296,0.00022135378,0.00013402995,0.000084873434],"category_scores_gemma":[0.3376411,0.000080769554,0.000030892825,0.00015192125,0.0009333927,0.0000684545,0.0000707949,0.0003898998,0.0000073825613],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0065332497,0.000082585866,0.00006960158,0.000050994557,0.000031500374,0.00000245476,0.00024789886,0.000029109138,0.000002312445,0.7330124,0.013361771,0.24657613],"study_design_scores_gemma":[0.02598109,0.001740946,0.0006570011,0.00010192818,0.00009625724,0.000002700716,0.0001621973,0.014393834,0.00002182247,0.95330745,0.0034345584,0.000100239],"about_ca_topic_score_codex":0.000011612451,"about_ca_topic_score_gemma":0.0000070461006,"teacher_disagreement_score":0.31898624,"about_ca_system_score_codex":0.000028173667,"about_ca_system_score_gemma":0.00008635099,"threshold_uncertainty_score":0.66793823},"labels":[],"label_agreement":null},{"id":"W2138986862","doi":"10.1002/sim.5452","title":"Generating survival times to simulate Cox proportional hazards models with time‐varying covariates","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":198,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Covariate; Proportional hazards model; Statistics; Weibull distribution; Gompertz function; Mathematics; Statistical model; Econometrics; Computer science","score_opus":0.06665911353813758,"score_gpt":0.3846642828112441,"score_spread":0.3180051692731065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138986862","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034393026,0.000021101525,0.9908104,0.00079238514,0.00009256816,0.00043791163,0.0006797309,0.00007628495,0.0036503118],"genre_scores_gemma":[0.4697669,0.0000025391123,0.52863836,0.0002754672,0.00017496035,0.00007398561,0.00049585116,0.000025986075,0.0005459319],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823946,0.00007877347,0.0005464428,0.00021807813,0.00054761674,0.00036962816],"domain_scores_gemma":[0.9978829,0.0012466005,0.00014369907,0.00021247678,0.00026826194,0.0002460326],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007528662,0.00018712031,0.0003379047,0.00009996576,0.00014656513,0.000019577026,0.0001108561,0.00005275891,0.0014610515],"category_scores_gemma":[0.0018757811,0.0001459933,0.000012995952,0.0003335547,0.00014261995,0.00010260774,0.00003661603,0.00016837702,0.00010955667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002977099,0.00012840757,0.00024096784,0.000049946433,0.000023026869,0.000005274624,0.00057181064,0.008439994,0.00026100094,0.9789031,0.010279368,0.0010673159],"study_design_scores_gemma":[0.0009957906,0.000108164226,0.0012410254,0.00014179485,0.00007476882,0.000011047724,0.00013612832,0.6938713,0.00006448283,0.3026638,0.0004208705,0.0002708215],"about_ca_topic_score_codex":0.00003630147,"about_ca_topic_score_gemma":0.000010639903,"teacher_disagreement_score":0.6854313,"about_ca_system_score_codex":0.000094836665,"about_ca_system_score_gemma":0.000083710256,"threshold_uncertainty_score":0.99945176},"labels":[],"label_agreement":null},{"id":"W2139017261","doi":"10.1002/sim.6265","title":"STRengthening Analytical Thinking for Observational Studies: the STRATOS initiative","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Economic and Social Research Council; Medical Research Council; Cancer Research UK; McGill University","keywords":"Observational study; Computer science; Econometrics; Data science; Management science; Statistics; Mathematics; Economics","score_opus":0.8755938676556354,"score_gpt":0.6135030834304239,"score_spread":0.2620907842252115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139017261","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055534514,0.00041667363,0.98256403,0.0062510013,0.00041881885,0.0006359779,0.00009084037,0.0000036349027,0.0040655546],"genre_scores_gemma":[0.84585506,0.000046081354,0.1473355,0.0040936302,0.0007100831,0.00011632045,0.00007242542,0.000016550734,0.0017543571],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9850941,0.003946467,0.0062345103,0.0005418327,0.0039522587,0.00023085879],"domain_scores_gemma":[0.9058325,0.08852912,0.0024162699,0.0012857436,0.0018581816,0.000078150544],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12504554,0.00019505147,0.0020400973,0.00019572325,0.00021759322,0.00013754149,0.0009993659,0.00004108747,0.0014138801],"category_scores_gemma":[0.34679487,0.00007409384,0.0001965036,0.00081808696,0.00027286826,0.00007804228,0.000071964816,0.00020412113,0.000070200076],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000059700733,0.000013217021,0.008360719,0.000038862327,0.00016929001,0.0000016906084,0.004573979,0.00027238604,0.0000021214678,0.8301748,0.1447542,0.011632745],"study_design_scores_gemma":[0.0004455966,0.00012703826,0.015694972,0.00012536999,0.00022767312,0.0000017856689,0.010525479,0.24095267,0.0000010913617,0.69673395,0.03505871,0.00010569221],"about_ca_topic_score_codex":0.000005981417,"about_ca_topic_score_gemma":0.000117942305,"teacher_disagreement_score":0.8403016,"about_ca_system_score_codex":0.000037980135,"about_ca_system_score_gemma":0.000059370675,"threshold_uncertainty_score":0.99949896},"labels":[],"label_agreement":null},{"id":"W2139115743","doi":"10.1002/sim.6633","title":"Knowledge translation in biostatistics: a survey of current practices, preferences, and barriers to the dissemination and uptake of new statistical methods","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; Institute for Work & Health; Institute of Health Services and Policy Research; McGill University; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"Canadian Institutes of Health Research","keywords":"Biostatistics; Statistical software; Computer science; Knowledge translation; Medical education; Perception; Principal (computer security); Data science; Psychology; Public health; Knowledge management; Medicine; Nursing","score_opus":0.8373272864966954,"score_gpt":0.65655898842761,"score_spread":0.18076829806908545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139115743","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015501425,0.0070178914,0.9749882,0.00040355115,0.00026928436,0.0007353603,0.0006278746,9.909713e-7,0.0004553755],"genre_scores_gemma":[0.62419915,0.00040086053,0.3750766,0.000021897276,0.00003201384,0.000016785129,0.000099468816,0.0000085434285,0.00014468598],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98055464,0.010895897,0.005779582,0.0005603942,0.0020346146,0.0001748936],"domain_scores_gemma":[0.9565572,0.038526896,0.0027651133,0.0006851482,0.0011103561,0.00035524942],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11929743,0.00017260486,0.0016737512,0.00044369927,0.000025368345,0.000054701628,0.00038153768,0.00004761666,0.00043038346],"category_scores_gemma":[0.47870085,0.00008363843,0.000025820673,0.0013610774,0.00022910425,0.0000810997,0.00005510259,0.00017230377,0.0000057038756],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054459688,0.00003569724,0.057305515,0.00015537936,0.000027491616,0.000001298643,0.019291861,0.000020031654,0.000022360175,0.012982399,0.033304833,0.8767987],"study_design_scores_gemma":[0.0010675082,0.0004556863,0.8329797,0.00046839818,0.00027959823,0.0000048640795,0.008414883,0.06346934,0.000011074217,0.069125704,0.023528755,0.00019448735],"about_ca_topic_score_codex":0.0008564497,"about_ca_topic_score_gemma":0.008621005,"teacher_disagreement_score":0.8766042,"about_ca_system_score_codex":0.000025081034,"about_ca_system_score_gemma":0.00031438968,"threshold_uncertainty_score":0.90686864},"labels":[],"label_agreement":null},{"id":"W2140085139","doi":"10.1002/sim.3552","title":"Bayesian adjustment for covariate measurement errors: A flexible parametric approach","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Covariate; Bayesian probability; Statistics; Parametric statistics; Computer science; Econometrics; Semiparametric model; Observational error; Mathematics","score_opus":0.17226786948241857,"score_gpt":0.41952464059558425,"score_spread":0.24725677111316569,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140085139","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016100876,0.00026494294,0.99382865,0.0005513286,0.00031110804,0.0010520938,0.00013586512,0.00010700249,0.0037328815],"genre_scores_gemma":[0.03466562,0.000056002635,0.96427757,0.00048329646,0.0002349647,0.00013270468,0.000032427426,0.00003660327,0.00008084096],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971669,0.00019082504,0.00082948804,0.00044844978,0.00082991185,0.00053447136],"domain_scores_gemma":[0.99691665,0.0019553916,0.00021470801,0.0004061804,0.00031089928,0.00019619179],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002624212,0.0002887262,0.0007110382,0.00032050326,0.000065175685,0.00001840837,0.00024695217,0.000108288245,0.0001118386],"category_scores_gemma":[0.012247956,0.00022581423,0.00004095069,0.00062077306,0.00013886504,0.00003743119,0.000021546519,0.00026277598,0.0000032072196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009097455,0.00034242595,0.00004585962,0.0002505856,0.000028889266,0.000011303993,0.00033930587,0.000008148229,0.000057453384,0.8778137,0.017759286,0.10325207],"study_design_scores_gemma":[0.0020285468,0.0009827504,0.0026061658,0.00023537061,0.00013215015,0.0000070371925,0.00019545745,0.02308445,0.00004860615,0.9696355,0.0007885491,0.00025545692],"about_ca_topic_score_codex":0.000047103313,"about_ca_topic_score_gemma":0.000013176798,"teacher_disagreement_score":0.10299661,"about_ca_system_score_codex":0.00022865296,"about_ca_system_score_gemma":0.00010532018,"threshold_uncertainty_score":0.9960723},"labels":[],"label_agreement":null},{"id":"W2141260650","doi":"10.1002/sim.2572","title":"Longitudinal variable selection by cross‐validation in the case of many covariates","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Covariate; Computer science; Markov chain Monte Carlo; Variable (mathematics); Feature selection; Selection (genetic algorithm); Model selection; Markov chain; Scale (ratio); Variety (cybernetics); Econometrics; Marginal model; Statistics; Data mining; Machine learning; Regression analysis; Artificial intelligence; Mathematics; Bayesian probability","score_opus":0.04109148622515056,"score_gpt":0.40199404916491205,"score_spread":0.3609025629397615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141260650","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016154012,0.000038680224,0.98122245,0.000093853596,0.000099423596,0.00020716275,0.00020783662,0.000009735952,0.0019668466],"genre_scores_gemma":[0.35820058,0.0000059187564,0.64157814,0.000026626143,0.000066809254,0.000017222615,0.00004315923,0.000008620769,0.000052929452],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985288,0.0002738013,0.0006041268,0.00017864993,0.0002188816,0.00019574468],"domain_scores_gemma":[0.9955968,0.003927048,0.00017425885,0.00015334606,0.00012668842,0.00002182734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018423718,0.00011738978,0.00028603114,0.00009926294,0.000053156873,0.000018388262,0.00010863128,0.00006531724,0.00035257085],"category_scores_gemma":[0.0033322966,0.00008137031,0.000009023495,0.00045201086,0.0001952335,0.0000414279,0.000014147123,0.0002130542,0.000001666899],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021772026,0.00012772964,0.01022365,0.00014390574,0.000005056532,0.00018056994,0.00021778143,0.000012959746,0.00036888118,0.97832495,0.008783686,0.0015890675],"study_design_scores_gemma":[0.0007014559,0.00014771456,0.010980117,0.00009757926,0.00003653433,0.00015202936,0.00014742304,0.0064417655,0.00022714106,0.98091024,0.00007285215,0.00008512051],"about_ca_topic_score_codex":0.0045107356,"about_ca_topic_score_gemma":0.00048289128,"teacher_disagreement_score":0.3420466,"about_ca_system_score_codex":0.000048456546,"about_ca_system_score_gemma":0.000031852793,"threshold_uncertainty_score":0.6818913},"labels":[],"label_agreement":null},{"id":"W2141508928","doi":"10.1002/sim.1794","title":"Regression methods for cost-effectiveness analysis with censored data","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Population Health Research Institute; University of Toronto; Hospital for Sick Children","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Censoring (clinical trials); Statistics; Weighting; Regression analysis; Inverse probability weighting; Survival analysis; Regression; Inverse probability; Econometrics; Proportional hazards model; Computer science; Censored regression model; Mathematics; Medicine; Propensity score matching","score_opus":0.49929086056699135,"score_gpt":0.5848901660240776,"score_spread":0.08559930545708627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141508928","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016345548,0.001150251,0.9855054,0.0070950477,0.00034068097,0.0013352461,0.0024435408,0.000022868218,0.00047241902],"genre_scores_gemma":[0.046100777,0.000187755,0.94875777,0.0021323652,0.00024559803,0.00028300093,0.0021251289,0.000039944523,0.0001276442],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961276,0.00049209,0.0022356743,0.00070701446,0.000095603486,0.00034199748],"domain_scores_gemma":[0.9925815,0.004990897,0.0011897074,0.0009821777,0.00011100946,0.00014470874],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028546162,0.00018656251,0.0014019945,0.0006186933,0.00011280782,0.00001994039,0.0003921333,0.00009651558,0.00015678961],"category_scores_gemma":[0.013832594,0.000171713,0.000032222986,0.00066580594,0.00016767507,0.00018559411,0.000059225233,0.00016506488,0.00003726701],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027874304,0.0001977004,0.047714785,0.0011086657,0.0007919888,0.000010401645,0.002360754,0.0068596173,0.0000117964,0.92341983,0.009636126,0.007609559],"study_design_scores_gemma":[0.016826484,0.001025514,0.21031846,0.0012766313,0.0005985658,0.000011252221,0.002491594,0.1424808,0.00003277468,0.5407353,0.08312327,0.0010793419],"about_ca_topic_score_codex":0.0017313203,"about_ca_topic_score_gemma":0.00094542117,"teacher_disagreement_score":0.38268456,"about_ca_system_score_codex":0.0005307205,"about_ca_system_score_gemma":0.0001349562,"threshold_uncertainty_score":0.9944743},"labels":[],"label_agreement":null},{"id":"W2141588553","doi":"10.1002/sim.2662","title":"The merits of breaking the matches: a cautionary tale","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Matching (statistics); Outcome (game theory); Computer science; Econometrics; Cluster (spacecraft); Research design; Test (biology); Randomization; Statistics; Intervention (counseling); Restricted randomization; Scale (ratio); Mathematics; Clinical trial; Psychology; Medicine","score_opus":0.037239099333314964,"score_gpt":0.3812329515603517,"score_spread":0.3439938522270367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141588553","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000916163,0.00031104687,0.98985744,0.001403329,0.00021043733,0.00019385466,0.00012865714,0.000013790504,0.0069652954],"genre_scores_gemma":[0.14313757,0.00008711317,0.85596406,0.00011649829,0.0002233477,0.000032231987,0.000013654357,0.000019382374,0.00040611695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99857765,0.00019152129,0.00053247967,0.00012651537,0.0003610149,0.00021080441],"domain_scores_gemma":[0.98961926,0.00978823,0.00018052569,0.0002778131,0.000108152686,0.000026013002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012252561,0.00011005896,0.00025201042,0.00003619656,0.00013583267,0.000009470832,0.00022705985,0.000038619874,0.00013132521],"category_scores_gemma":[0.0037285157,0.000054518317,0.000017068782,0.00021815406,0.0007316727,0.000015542966,0.00004203727,0.00019623857,0.0000031408592],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000119712795,0.000029224942,0.00041911445,0.00006760357,0.000008394948,0.000016253009,0.00031652313,5.6897085e-7,0.00014007397,0.9664795,0.015575132,0.01693564],"study_design_scores_gemma":[0.00025587672,0.000058843234,0.009784738,0.00014473466,0.000035254205,0.000013673404,0.00036739281,0.0009204469,0.00006116989,0.9867075,0.0015859824,0.00006436846],"about_ca_topic_score_codex":0.00059593626,"about_ca_topic_score_gemma":0.000362125,"teacher_disagreement_score":0.14222142,"about_ca_system_score_codex":0.000027386714,"about_ca_system_score_gemma":0.000042714924,"threshold_uncertainty_score":0.4463651},"labels":[],"label_agreement":null},{"id":"W2141848375","doi":"10.1002/sim.5951","title":"Multiple‐objective response‐adaptive repeated measurement designs in clinical trials for binary responses","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Binary number; Computer science; Basis (linear algebra); Binary data; Function (biology); Mathematical optimization; Algorithm; Mathematics","score_opus":0.716823768290405,"score_gpt":0.608469569222505,"score_spread":0.1083541990679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141848375","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.085150905,0.0006621059,0.90496975,0.0014882252,0.001558305,0.005174044,0.00028996158,0.00004999827,0.0006566739],"genre_scores_gemma":[0.54507834,0.000036747322,0.4530936,0.0003899835,0.00016613938,0.0005381291,0.000009724306,0.000033014396,0.00065430836],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9575358,0.03251019,0.0053455085,0.0012350599,0.0027214882,0.00065193477],"domain_scores_gemma":[0.82434934,0.17206478,0.0009832422,0.00077272044,0.0015524083,0.00027751407],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.19958463,0.00034457853,0.0017787791,0.0011354641,0.000107546584,0.00006690883,0.00069578853,0.00023111455,0.00063349004],"category_scores_gemma":[0.64270383,0.00023973633,0.00013882447,0.0012604293,0.0007535795,0.00021735048,0.00013270228,0.000498704,0.000100780926],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15854746,0.0018598071,0.04052957,0.00004303313,0.00028172383,0.00060298044,0.012494338,0.00065030827,0.33172762,0.008625367,0.2008538,0.24378401],"study_design_scores_gemma":[0.024491249,0.015803413,0.6512699,0.00072330073,0.00010708318,0.0000151836,0.02248097,0.08723338,0.009445006,0.18529008,0.0021657639,0.0009746684],"about_ca_topic_score_codex":0.00053209666,"about_ca_topic_score_gemma":0.00018100713,"teacher_disagreement_score":0.6107403,"about_ca_system_score_codex":0.0005192709,"about_ca_system_score_gemma":0.00052657374,"threshold_uncertainty_score":0.97761637},"labels":[],"label_agreement":null},{"id":"W2142200036","doi":"10.1002/sim.3110","title":"Reliability analysis for continuous measurements: Equivalence test for agreement","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Western Hospital; University Health Network; Memorial University of Newfoundland; Canadian Blood Services; University of Toronto","funders":"","keywords":"Repeatability; Equivalence (formal languages); Reliability (semiconductor); Inter-rater reliability; Computer science; Reliability engineering; Intra-rater reliability; Statistics; Test (biology); Consistency (knowledge bases); Mathematics; Rating scale; Artificial intelligence; Engineering","score_opus":0.20769671851629035,"score_gpt":0.4449493606354994,"score_spread":0.23725264211920905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142200036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010049454,0.0001833444,0.9830931,0.0015159923,0.0008430755,0.002070747,0.00048037284,0.000020824322,0.0017431062],"genre_scores_gemma":[0.8380165,0.00003212174,0.1591485,0.0007489221,0.00030672463,0.000198937,0.00009821016,0.000015350226,0.0014347372],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99248743,0.00016993032,0.0023654676,0.0009747833,0.003288802,0.0007135741],"domain_scores_gemma":[0.9791664,0.016481029,0.00057605945,0.0010637984,0.00248739,0.00022535429],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051765397,0.00027481257,0.00092440966,0.00063164433,0.00020334753,0.000058914266,0.0008814587,0.000100455356,0.0006228099],"category_scores_gemma":[0.0931019,0.00019376467,0.00017811779,0.0016629042,0.00040737854,0.00011252827,0.00007777477,0.00016861067,0.000020313939],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001004784,0.001353057,0.7889188,0.00028767646,0.00040535623,0.000012834078,0.0016732379,0.0033454993,0.004115014,0.011130948,0.08845501,0.09929781],"study_design_scores_gemma":[0.007352343,0.0039929515,0.5142854,0.00023428233,0.0011701988,0.0000012220845,0.00407656,0.01746142,0.0012203467,0.3865453,0.062896974,0.00076299394],"about_ca_topic_score_codex":0.00013186247,"about_ca_topic_score_gemma":0.001169081,"teacher_disagreement_score":0.82796705,"about_ca_system_score_codex":0.00035074487,"about_ca_system_score_gemma":0.000088698864,"threshold_uncertainty_score":0.97640705},"labels":[],"label_agreement":null},{"id":"W2143015220","doi":"10.1002/sim.4328","title":"Information in the sample covariate distribution in prevalent cohorts: Addendum","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"Medical Research Council; Health Canada; Pfizer Canada; University of Ottawa; Pfizer","keywords":"Addendum; Library science; Acknowledgement; Sample (material); Gerontology; Medicine; Political science; Family medicine; Law","score_opus":0.04777589730579668,"score_gpt":0.3156718643223418,"score_spread":0.2678959670165451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143015220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3974816,0.0056187008,0.45864806,0.031238511,0.003976661,0.012075125,0.014305415,0.00018485921,0.07647107],"genre_scores_gemma":[0.99160194,0.0010308762,0.003777991,0.0011125385,0.00013484819,0.00009446578,0.002223533,0.0000051330453,0.000018685221],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99887383,0.00005829198,0.0004647747,0.00008591733,0.00032729082,0.00018991868],"domain_scores_gemma":[0.9993576,0.0003147933,0.000076467164,0.00013414945,0.00008005991,0.000036938414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077215396,0.000093831906,0.00024220395,0.000097727476,0.00002511079,0.0000035583716,0.00006750209,0.000044160413,0.00024155785],"category_scores_gemma":[0.001341486,0.000062390835,0.000011661597,0.00029011897,0.0001085645,0.00006553991,0.000022706481,0.00021930323,0.000011133456],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012456385,0.0009822419,0.5118223,0.0007813532,0.00004759466,0.00026225197,0.0159144,0.000014709,0.000013438291,0.26588383,0.19225651,0.010775717],"study_design_scores_gemma":[0.0036945913,0.00046629223,0.9429717,0.00043002403,0.000038047852,0.00001219191,0.0033386995,0.0004308892,0.0000037018992,0.032544915,0.015985196,0.00008377263],"about_ca_topic_score_codex":0.002890921,"about_ca_topic_score_gemma":0.0008970327,"teacher_disagreement_score":0.5941203,"about_ca_system_score_codex":0.00013406339,"about_ca_system_score_gemma":0.000031311058,"threshold_uncertainty_score":0.4370227},"labels":[],"label_agreement":null},{"id":"W2143134812","doi":"10.1002/sim.4180","title":"Information in the sample covariate distribution in prevalent cohorts","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; University of Waterloo","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Statistics; Sample (material); Econometrics; Computer science; Mathematics","score_opus":0.13063176353298864,"score_gpt":0.39900020257419255,"score_spread":0.2683684390412039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143134812","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01081174,0.00001864607,0.9855529,0.00015886847,0.00017692955,0.00044485438,0.0005034642,0.000010466443,0.0023221273],"genre_scores_gemma":[0.71182805,0.00008447198,0.28749096,0.00024829677,0.000034531506,0.000073382726,0.00022645178,0.0000066502153,0.0000071974914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983925,0.00029302636,0.0006777961,0.00009821835,0.00031361156,0.00022483952],"domain_scores_gemma":[0.9962621,0.003283307,0.00013423107,0.00021650386,0.00006785077,0.00003602567],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024444133,0.000112244925,0.00026724895,0.00009818172,0.000023977422,0.000008554614,0.00016125484,0.000056601115,0.000389341],"category_scores_gemma":[0.015245618,0.0000744423,0.000008266047,0.00030782234,0.00012581078,0.00007616509,0.000027342068,0.00027109683,0.00000812911],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037296217,0.00008904962,0.009694021,0.00012968364,0.0000029414932,0.000016580849,0.008997199,0.000002244501,0.0000018003011,0.96596926,0.0016480173,0.01341191],"study_design_scores_gemma":[0.00065952016,0.00013039932,0.20258752,0.0001745987,0.00001375686,0.0000029653606,0.0009372751,0.003521175,0.000005823118,0.79156655,0.00032264175,0.00007778867],"about_ca_topic_score_codex":0.0015978323,"about_ca_topic_score_gemma":0.0005141593,"teacher_disagreement_score":0.7010163,"about_ca_system_score_codex":0.000087676104,"about_ca_system_score_gemma":0.000033207984,"threshold_uncertainty_score":0.9930494},"labels":[],"label_agreement":null},{"id":"W2143710665","doi":"10.1002/sim.5529","title":"Mixture distributions in multi‐state modelling: Some considerations in a study of psoriatic arthritis","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Medical Research Council","keywords":"Mixture model; Econometrics; Poisson distribution; Psoriatic arthritis; Computer science; Population; Inverse Gaussian distribution; Statistics; Mathematics; Arthritis; Medicine","score_opus":0.05109171537922794,"score_gpt":0.3417578543330217,"score_spread":0.2906661389537938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143710665","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018739318,0.0011214868,0.97883755,0.00035485168,0.00036055475,0.0004543272,0.00007314997,0.000013858945,0.00004493075],"genre_scores_gemma":[0.5826842,0.0001231193,0.4170566,0.00005380343,0.000028120206,0.000029222869,0.000008999167,0.0000050869994,0.0000108499835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980452,0.00035148108,0.00072942016,0.00025412347,0.0002650949,0.0003546856],"domain_scores_gemma":[0.99868596,0.00064624095,0.00012843114,0.00035759225,0.00007878582,0.00010298797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012718725,0.00014859397,0.0004344502,0.00031752663,0.000040111612,0.000012492826,0.00019450825,0.00005670391,0.0000127133335],"category_scores_gemma":[0.0006086196,0.00013396538,0.000013050234,0.0005348259,0.00009133639,0.00022798155,0.000068382295,0.0003435831,0.0000015653578],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000110580995,0.0021714775,0.010942001,0.00006640417,0.000020785303,0.00019045266,0.046270996,0.005818693,0.00010896684,0.90455985,0.0006110539,0.02922827],"study_design_scores_gemma":[0.0045365924,0.0002731058,0.018289065,0.00027871388,0.000013786277,0.000013349116,0.00042959274,0.3918795,0.00004648928,0.5839676,0.000038357834,0.00023382979],"about_ca_topic_score_codex":0.00062970584,"about_ca_topic_score_gemma":0.0018882719,"teacher_disagreement_score":0.5639449,"about_ca_system_score_codex":0.00006737747,"about_ca_system_score_gemma":0.000074635565,"threshold_uncertainty_score":0.546295},"labels":[],"label_agreement":null},{"id":"W2143887617","doi":"10.1002/sim.2748","title":"A new estimation method for the semiparametric accelerated failure time mixture cure model","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Identifiability; Accelerated failure time model; Computer science; Estimator; Parametric statistics; Semiparametric model; Semiparametric regression; Rank (graph theory); Nonparametric statistics; Estimation; Covariate; Mathematics; Statistics; Artificial intelligence; Machine learning","score_opus":0.07505516488088816,"score_gpt":0.42820516346295245,"score_spread":0.3531499985820643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143887617","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038811042,0.0001693293,0.9954055,0.0023501436,0.00012606778,0.000727552,0.00033708554,0.000052242216,0.00079326576],"genre_scores_gemma":[0.0018013866,0.000016551267,0.9952238,0.00025585562,0.00024394882,0.00006801746,0.00011085364,0.00003654112,0.0022430432],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998195,0.00014827501,0.00062203134,0.0002991017,0.00040098222,0.000334614],"domain_scores_gemma":[0.98577106,0.0133642135,0.00020733464,0.00033012978,0.00023906182,0.000088214925],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013420111,0.00023809834,0.00048676427,0.00016595461,0.000108523076,0.000033360444,0.00026484785,0.00014743047,0.0004385499],"category_scores_gemma":[0.011166436,0.00014901208,0.00003174246,0.0006893282,0.00009471977,0.00004176152,0.000033095846,0.00035456553,0.000010457562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030277919,0.000033271062,0.000010024608,0.000096709424,0.000017770002,0.000004091567,0.00021475893,0.003240955,0.0002876896,0.62758595,0.31767198,0.05080653],"study_design_scores_gemma":[0.0005481299,0.00006456969,0.00007500191,0.00005816962,0.0000856209,0.0000034663376,0.000026077789,0.50156945,0.000049903105,0.4968929,0.0005354076,0.00009130435],"about_ca_topic_score_codex":0.0002898928,"about_ca_topic_score_gemma":0.000091840935,"teacher_disagreement_score":0.4983285,"about_ca_system_score_codex":0.000065642766,"about_ca_system_score_gemma":0.0001247458,"threshold_uncertainty_score":0.99716294},"labels":[],"label_agreement":null},{"id":"W2144168223","doi":"10.1002/sim.5984","title":"The use of propensity score methods with survival or time‐to‐event outcomes: reporting measures of effect similar to those used in randomized experiments","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1441,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Observational study; Marginal structural model; Inverse probability weighting; Medicine; Covariate; Randomized controlled trial; Confounding; Average treatment effect; Statistics; Hazard ratio; Selection bias; Population; Survival analysis; Matching (statistics); Proportional hazards model; Confidence interval; Internal medicine; Mathematics","score_opus":0.45447001760427186,"score_gpt":0.5290019207742545,"score_spread":0.0745319031699826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144168223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26381022,0.0000207472,0.7315506,0.00019229752,0.00006227529,0.0042370833,0.000013176203,0.000038798327,0.00007485471],"genre_scores_gemma":[0.12916155,0.000013644712,0.8699784,0.00007559598,0.0000111978125,0.00045910204,0.0000049330006,0.00003945955,0.00025609948],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99514264,0.001510572,0.0020939852,0.00027012636,0.0006896854,0.00029299516],"domain_scores_gemma":[0.97988665,0.017772425,0.0012502897,0.00058957766,0.00040212512,0.00009893163],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010290257,0.0002563637,0.0019802502,0.0001833278,0.000035023404,0.000011108426,0.00022484535,0.00005974404,0.00008089279],"category_scores_gemma":[0.11958004,0.00011961341,0.00004162958,0.00036492586,0.00030610565,0.00007398292,0.00012142702,0.00022299838,0.0000019682043],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15205052,0.0023175764,0.21000072,0.004554696,0.0020690882,0.0008961363,0.05569208,0.0021018754,0.30385748,0.04768069,0.015617619,0.20316154],"study_design_scores_gemma":[0.18452807,0.011637685,0.041002546,0.020066367,0.0010538317,0.000037480706,0.0031927081,0.009401509,0.44179448,0.2845741,0.00040970356,0.0023015132],"about_ca_topic_score_codex":0.00061079394,"about_ca_topic_score_gemma":0.0003401974,"teacher_disagreement_score":0.2368934,"about_ca_system_score_codex":0.00009655355,"about_ca_system_score_gemma":0.0000781067,"threshold_uncertainty_score":0.8878361},"labels":[],"label_agreement":null},{"id":"W2144420447","doi":"10.1002/sim.1099","title":"Properties of the summary receiver operating characteristic (SROC) curve for diagnostic test data","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Ovarian cancer diagnosis and treatment","field":"Medicine","cited_by":694,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Receiver operating characteristic; Diagnostic odds ratio; Area under the curve; Statistics; Homogeneous; Meta-analysis; Odds ratio; Area under curve; Coverage probability; Standard error; Mathematics; Medicine; Confidence interval; Internal medicine; Combinatorics","score_opus":0.08867909890496116,"score_gpt":0.31968617351874695,"score_spread":0.23100707461378578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144420447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5195694,0.11445716,0.033029243,0.20725618,0.015806224,0.040327094,0.046832643,0.0004269275,0.022295108],"genre_scores_gemma":[0.9895924,0.0025977711,0.0052238908,0.0007785183,0.00041029087,0.00014879649,0.00032116706,0.000032926477,0.0008942402],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998605,0.000047119043,0.0005081047,0.00031588235,0.00029877838,0.0002250972],"domain_scores_gemma":[0.99670506,0.0021828413,0.00015582639,0.0007278759,0.00015608409,0.00007230721],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00033833281,0.00016540455,0.00045013265,0.00006071466,0.00007632808,0.000008002486,0.00024216017,0.000047890524,0.00029769936],"category_scores_gemma":[0.013522811,0.000095382624,0.000022613965,0.00018129262,0.00026106733,0.000051322557,0.00010041579,0.00016532883,0.0000066959233],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001621128,0.002443464,0.56978947,0.0033962235,0.00040124843,0.00028936262,0.004857919,0.000019070152,0.003415035,0.0029635609,0.33279082,0.07947169],"study_design_scores_gemma":[0.021245426,0.004456701,0.849469,0.021426799,0.0024991687,0.00014617987,0.0013164639,0.04372391,0.0025967632,0.0011495723,0.051187307,0.00078271865],"about_ca_topic_score_codex":0.00021609473,"about_ca_topic_score_gemma":0.00013831857,"teacher_disagreement_score":0.47002298,"about_ca_system_score_codex":0.000095071824,"about_ca_system_score_gemma":0.00006965039,"threshold_uncertainty_score":0.9947867},"labels":[],"label_agreement":null},{"id":"W2144443379","doi":"10.1002/sim.1613","title":"A Bayesian analysis of the 4‐year follow‐up data of the Wisconsin epidemiologic study of diabetic retinopathy","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Eye Institute","keywords":"Covariate; Bayesian probability; Baseline (sea); Diabetic retinopathy; Medicine; Population; Data set; Statistics; Computer science; Demography; Mathematics; Diabetes mellitus; Environmental health","score_opus":0.1301802120599601,"score_gpt":0.4246668987784154,"score_spread":0.2944866867184553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144443379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16564298,0.000057620295,0.83152413,0.0003981104,0.00031111288,0.0006388844,0.0010324046,0.000006465321,0.00038830895],"genre_scores_gemma":[0.7277475,0.000013183591,0.272141,0.000042091197,0.000015845477,0.0000059678873,0.000010553502,0.0000094027355,0.000014464759],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965396,0.0010075034,0.0013428838,0.00031582365,0.00057681923,0.00021735828],"domain_scores_gemma":[0.9901869,0.0070331995,0.0008185597,0.0017333397,0.00017873755,0.00004924668],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031873176,0.0001724866,0.0011724563,0.0001673141,0.000045649253,0.000002428568,0.0009939753,0.00006949578,0.00014701813],"category_scores_gemma":[0.043209065,0.00008727537,0.00006344592,0.0014898984,0.0008640257,0.000019564968,0.0003489649,0.0002889959,2.9989323e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008040532,0.00082358747,0.25764695,0.00039949824,0.00068898435,0.000010630521,0.005773723,0.00007813757,0.0004700354,0.7293588,0.0008813441,0.0037879266],"study_design_scores_gemma":[0.0014564529,0.0004302088,0.18046762,0.00039322602,0.0019128843,8.957742e-7,0.0021674116,0.0019837995,0.00011578971,0.8109771,0.0000028857135,0.00009172802],"about_ca_topic_score_codex":0.000762964,"about_ca_topic_score_gemma":0.0013760534,"teacher_disagreement_score":0.5621045,"about_ca_system_score_codex":0.000033233373,"about_ca_system_score_gemma":0.00010715434,"threshold_uncertainty_score":0.96485037},"labels":[],"label_agreement":null},{"id":"W2145394717","doi":"10.1002/sim.4373","title":"Short‐term cancer mortality projections: A comparative study of prediction methods","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Public Health Agency of Canada; HIV Legal Network; Simon Fraser University","funders":"","keywords":"Term (time); Cancer; Statistics; Computer science; Econometrics; Mathematics; Medicine; Internal medicine","score_opus":0.22206470472513787,"score_gpt":0.4958846590628696,"score_spread":0.27381995433773176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145394717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9048231,0.0002701034,0.088753775,0.000015743415,0.00067090796,0.0011236996,0.00010089653,0.00005636929,0.004185358],"genre_scores_gemma":[0.98178977,0.00007555935,0.01762159,0.000019125751,0.00014208064,0.00022487718,0.000022358236,0.000010940612,0.00009369782],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998547,0.00019342535,0.0005263864,0.00026269557,0.00032401265,0.00014648098],"domain_scores_gemma":[0.99919087,0.00012900727,0.00012107327,0.00023588221,0.00024538356,0.0000777698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006703854,0.0001338183,0.0004987652,0.0002477294,0.00004527293,0.0000017873057,0.00005232553,0.00005616714,0.00019696604],"category_scores_gemma":[0.00021759969,0.00010709589,0.000020615998,0.00047373812,0.00017010164,0.000040476276,0.000022448308,0.0002789111,6.1810726e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003573955,0.0014264659,0.8921595,0.00023563174,0.00038730443,0.000049121507,0.050565112,0.00001973915,0.001835757,0.00029580132,0.00087523996,0.048576377],"study_design_scores_gemma":[0.0019622352,0.009099023,0.9758598,0.0002179655,0.00040498658,0.0000158745,0.008278172,0.002357885,0.0011626707,0.00052039773,0.000036475416,0.0000844772],"about_ca_topic_score_codex":0.00640757,"about_ca_topic_score_gemma":0.0042132516,"teacher_disagreement_score":0.08370034,"about_ca_system_score_codex":0.00013680388,"about_ca_system_score_gemma":0.00007763953,"threshold_uncertainty_score":0.9686372},"labels":[],"label_agreement":null},{"id":"W2146976162","doi":"10.1002/(sici)1097-0258(20000215)19:3<373::aid-sim337>3.0.co;2-y","title":"Testing the equality of two dependent kappa statistics","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Kappa; Correlation; Monte Carlo method; Mathematics; Cohen's kappa; Goodness of fit; Dependency (UML); Sample size determination; Variable (mathematics); Computer science; Artificial intelligence","score_opus":0.2670104097609483,"score_gpt":0.4556427207423286,"score_spread":0.18863231098138028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146976162","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18723473,0.00054637075,0.74531734,0.0034487566,0.0013127177,0.0012227242,0.001363933,0.000038839516,0.059514623],"genre_scores_gemma":[0.922231,0.00005878457,0.07571973,0.0005517206,0.00016818439,0.000014503446,0.00001900848,0.000010077611,0.0012269821],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99383336,0.0007102268,0.0015993909,0.0003923825,0.0031550494,0.00030958533],"domain_scores_gemma":[0.9887842,0.009418523,0.00034098257,0.00078289735,0.000582,0.00009143108],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014635624,0.00015965826,0.00043650178,0.00010610052,0.00012871117,0.00003519339,0.0008215466,0.00003758503,0.0054663597],"category_scores_gemma":[0.016682744,0.00008785782,0.000021917085,0.0007223649,0.0006210688,0.000054083335,0.00007111597,0.0002935005,0.00010873619],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009540518,0.00028521835,0.09400722,0.00006967088,0.000030911684,0.00004357227,0.0032044826,0.00447572,0.0011688197,0.09661052,0.04216598,0.7578425],"study_design_scores_gemma":[0.0018952189,0.00043297387,0.1491368,0.00017189271,0.000052426283,0.000006656131,0.0015842917,0.012749433,0.00014007238,0.8244635,0.00915303,0.00021370706],"about_ca_topic_score_codex":0.0010010153,"about_ca_topic_score_gemma":0.0006780621,"teacher_disagreement_score":0.7576288,"about_ca_system_score_codex":0.00006649305,"about_ca_system_score_gemma":0.00009942054,"threshold_uncertainty_score":0.9954428},"labels":[],"label_agreement":null},{"id":"W2147497323","doi":"10.1002/sim.4176","title":"Bayesian inference of gene–environment interaction from incomplete data: What happens when information on environment is disjoint from data on gene and disease?","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Environmental data; Inference; Mendelian randomization; Population; Disjoint sets; Computer science; Disease; Bayesian probability; Genotype; Statistics; Econometrics; Biology; Genetics; Mathematics; Medicine; Environmental health; Gene; Artificial intelligence; Ecology","score_opus":0.056889990450539225,"score_gpt":0.2997278995458502,"score_spread":0.242837909095311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147497323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2504086,0.0007606408,0.7304223,0.0015589971,0.00040068032,0.00042174163,0.01580566,0.0000053748286,0.00021602081],"genre_scores_gemma":[0.903231,0.005565423,0.055811845,0.0013190755,0.00013619832,0.000011485668,0.0338989,0.000011799841,0.000014249242],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986891,0.00010532703,0.000475907,0.00040173394,0.00018335808,0.00014454305],"domain_scores_gemma":[0.99838495,0.00013616194,0.00027246994,0.0010780747,0.000014310533,0.000114008246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002848193,0.00015218252,0.00023598662,0.000049616436,0.00003727292,0.000008889264,0.00031748603,0.0000806419,0.0002909274],"category_scores_gemma":[0.00045387298,0.00013301375,0.000009618576,0.000016552993,0.00014871266,0.000029154819,0.000371411,0.000109845605,0.000017809012],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002695133,0.0015076055,0.4761183,0.00016796759,0.0012482166,0.000046661586,0.013300557,0.0024615603,0.03612545,0.0024445532,0.09499152,0.3688925],"study_design_scores_gemma":[0.0020265027,0.001118543,0.9106936,0.00023258298,0.00021415071,0.0000011576602,0.0013519747,0.034461822,0.0018191409,0.020159464,0.02748817,0.0004328772],"about_ca_topic_score_codex":0.0011624484,"about_ca_topic_score_gemma":0.000098956574,"teacher_disagreement_score":0.67461044,"about_ca_system_score_codex":0.000034073775,"about_ca_system_score_gemma":0.000026887406,"threshold_uncertainty_score":0.5424143},"labels":[],"label_agreement":null},{"id":"W2147506537","doi":"10.1002/sim.5571","title":"Scientific considerations for assessing biosimilar products","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Biosimilars and Bioanalytical Methods","field":"Immunology and Microbiology","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Biosimilar; Interchangeability; Risk analysis (engineering); Bioequivalence; Drug approval; Business; Computer science; Drug; Medicine; Management science; Pharmacology; Engineering; Pharmacokinetics","score_opus":0.09295416366638011,"score_gpt":0.3965204339961872,"score_spread":0.3035662703298071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147506537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049930353,0.038219288,0.7732834,0.070927165,0.046697617,0.0045278654,0.0026085938,0.00031088953,0.013494825],"genre_scores_gemma":[0.73930067,0.000026519605,0.2575055,0.0010554412,0.00025483713,0.000028511802,0.00014930815,0.0000142935405,0.0016649301],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99894184,0.00014057649,0.0002968216,0.00020746802,0.000042534615,0.0003707653],"domain_scores_gemma":[0.9983035,0.0012263047,0.000067155735,0.00018631815,0.00018403318,0.000032739823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016159851,0.00010463328,0.00023773439,0.00013025585,0.0002198661,0.00002079152,0.00006321355,0.00010950671,0.00069411466],"category_scores_gemma":[0.0060628997,0.00007690838,0.000014375819,0.00019745197,0.00075419346,0.00007571087,0.000024104866,0.00017618737,0.000018172772],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031222164,0.0002868486,0.008546891,0.00014846171,0.000077275734,0.000004781913,0.0010038562,8.1847634e-7,0.25820583,0.21370734,0.5065666,0.011420072],"study_design_scores_gemma":[0.0057071806,0.00055434945,0.06990846,0.0003964531,0.0005339351,0.00012727191,0.0017361596,0.00025817886,0.11159884,0.14642283,0.6619162,0.0008401112],"about_ca_topic_score_codex":0.0000070160304,"about_ca_topic_score_gemma":0.000013984588,"teacher_disagreement_score":0.6893703,"about_ca_system_score_codex":0.000027232152,"about_ca_system_score_gemma":0.00006367779,"threshold_uncertainty_score":0.76000684},"labels":[],"label_agreement":null},{"id":"W2147898530","doi":"10.1002/sim.3078","title":"CoPlot: A tool for visualizing multivariate data in medicine","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Multivariate statistics; Multidimensional scaling; Computer science; Multivariate analysis; Data mining; Set (abstract data type); Data science; Data visualization; Data set; Visualization; Interpretation (philosophy); Artificial intelligence; Machine learning","score_opus":0.04385822664028715,"score_gpt":0.39284796707206726,"score_spread":0.3489897404317801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147898530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051786486,0.00018331406,0.93996865,0.0018759897,0.00034855312,0.0004610451,0.00012314892,0.000027358548,0.0052254307],"genre_scores_gemma":[0.9407206,0.000076468394,0.056539703,0.0014531071,0.0002301901,0.000014129216,0.0004910994,0.000019712146,0.00045499537],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998252,0.00006677013,0.00057414616,0.00040980708,0.00031509,0.00038222535],"domain_scores_gemma":[0.9980759,0.0012811786,0.00010678465,0.00044824972,0.000010223006,0.0000776382],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0038939873,0.00013729338,0.00037382578,0.00014674547,0.00006054558,0.0000023802427,0.00038128765,0.00008465319,0.001756644],"category_scores_gemma":[0.0026333402,0.000107776425,0.000009143504,0.00047558817,0.0004955052,0.00009176903,0.00017176781,0.00019579781,0.000045352946],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008580029,0.0004892581,0.7578426,0.0001688009,0.00012272125,0.0010203456,0.013429021,0.0012877142,0.009635302,0.026002677,0.09785334,0.091290236],"study_design_scores_gemma":[0.012959079,0.0010038174,0.58742,0.0004086517,0.00032539014,0.000023663442,0.0016552571,0.2606164,0.00014197256,0.06763928,0.06705704,0.00074948167],"about_ca_topic_score_codex":0.0036023397,"about_ca_topic_score_gemma":0.0124317845,"teacher_disagreement_score":0.88893414,"about_ca_system_score_codex":0.000111094734,"about_ca_system_score_gemma":0.000010064991,"threshold_uncertainty_score":0.9991559},"labels":[],"label_agreement":null},{"id":"W2148216078","doi":"10.1002/sim.3619","title":"Modelling heterogeneity in clustered count data with extra zeros using compound Poisson random effect","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Count data; Poisson distribution; Random effects model; Overdispersion; Poisson regression; Statistics; Zero-inflated model; Quasi-likelihood; Variance (accounting); Multilevel model; Computer science; Hierarchical database model; Compound Poisson distribution; Mathematics; Econometrics; Data mining; Medicine; Population; Meta-analysis","score_opus":0.15086653236908357,"score_gpt":0.43161931460224834,"score_spread":0.2807527822331648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148216078","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049226906,0.00013236055,0.94935644,0.00009996113,0.00011657644,0.00056693837,0.00029140213,0.000025314825,0.00018407656],"genre_scores_gemma":[0.34810272,0.000031595828,0.65159863,0.00009366157,0.00007080061,0.0000045744177,0.00007509391,0.00001889712,0.0000040552454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734825,0.0004574554,0.0007452986,0.00049392594,0.0005270034,0.00042808655],"domain_scores_gemma":[0.9943392,0.004557755,0.00019589903,0.0007025032,0.00008110506,0.0001235213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023637447,0.00029134843,0.0008889884,0.00016029575,0.000067560606,0.00003188822,0.00037449718,0.00009521643,0.000048001435],"category_scores_gemma":[0.001965626,0.0002097067,0.000013330103,0.000290905,0.00020938877,0.000092479764,0.000061424864,0.00042231215,0.0000015466433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010491026,0.0020253968,0.024915166,0.0038975421,0.00032932116,0.0058895443,0.0054981164,0.018302435,0.006131755,0.7536512,0.0044692536,0.16439924],"study_design_scores_gemma":[0.005140107,0.00051380746,0.0007337872,0.0008920374,0.00009187498,0.000035239715,0.00004674658,0.677674,0.00006471366,0.31456828,0.000018943107,0.00022048774],"about_ca_topic_score_codex":0.00042871712,"about_ca_topic_score_gemma":0.0002545774,"teacher_disagreement_score":0.65937155,"about_ca_system_score_codex":0.00012440875,"about_ca_system_score_gemma":0.00006218335,"threshold_uncertainty_score":0.8551591},"labels":[],"label_agreement":null},{"id":"W2148357625","doi":"10.1002/sim.4434","title":"Weighted multiple testing correction for correlated tests","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hamilton Health Sciences; McMaster University; Population Health Research Institute","funders":"","keywords":"Bonferroni correction; Type I and type II errors; Multiple comparisons problem; Sequence (biology); Mathematics; Correlation; Statistics; False discovery rate; Statistical hypothesis testing; Null hypothesis; Statistical power; Algorithm; Computer science","score_opus":0.6250874573824682,"score_gpt":0.5510253799376074,"score_spread":0.07406207744486082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148357625","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022961511,0.00002370112,0.986422,0.000054145996,0.004147218,0.0010176401,0.00021172118,0.00015183003,0.005675578],"genre_scores_gemma":[0.03874521,0.00001086246,0.9600566,0.00013251534,0.00035423916,0.00011496625,0.000019982337,0.00005740513,0.0005082242],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971684,0.00036548226,0.0013147783,0.00040919692,0.00033227474,0.00040982311],"domain_scores_gemma":[0.86600465,0.1327642,0.00037238037,0.0003207228,0.00039569483,0.00014234723],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003341958,0.00023648908,0.0007473304,0.00016762108,0.00008757331,0.0000066297243,0.00021003315,0.00019365692,0.0005195954],"category_scores_gemma":[0.48747438,0.00019422964,0.00003363566,0.0004962209,0.00033112845,0.000035245972,0.000045425222,0.00042648235,0.000019736315],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015354318,0.0012704835,0.06430301,0.0008560711,0.0002021319,0.00023414899,0.0039299857,0.0000059366457,0.0011058949,0.44765088,0.14055964,0.3383464],"study_design_scores_gemma":[0.0031939368,0.000720533,0.010464695,0.00043578056,0.00013940889,0.000010916392,0.00014484326,0.042487003,0.00021323083,0.9417349,0.00023436984,0.00022037303],"about_ca_topic_score_codex":0.00017938482,"about_ca_topic_score_gemma":0.00011691187,"teacher_disagreement_score":0.49408403,"about_ca_system_score_codex":0.00008803698,"about_ca_system_score_gemma":0.000057569603,"threshold_uncertainty_score":0.7920455},"labels":[],"label_agreement":null},{"id":"W2148441587","doi":"10.1002/sim.2757","title":"A residuals‐based transition model for longitudinal analysis with estimation in the presence of missing data","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Institute on Drug Abuse; National Institute on Alcohol Abuse and Alcoholism; Rural Development Administration","keywords":"Imputation (statistics); Missing data; Covariate; Econometrics; Computer science; Longitudinal data; Statistics; Regression; Autoregressive model; Data mining; Mathematics","score_opus":0.14013846414275608,"score_gpt":0.4426742623897916,"score_spread":0.30253579824703547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148441587","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00084818347,0.000022381133,0.9972165,0.0006587215,0.000009877646,0.00033060653,0.00079051655,0.000006016001,0.00011719684],"genre_scores_gemma":[0.33339944,0.0000012363071,0.6662777,0.00002475088,0.000012958804,0.000017313216,0.00025814475,0.0000054603784,0.0000029731855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985839,0.00016431652,0.00049569434,0.00023242022,0.00037103042,0.00015264617],"domain_scores_gemma":[0.9934624,0.0058167223,0.00016443702,0.00043037772,0.00010632285,0.000019735866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018341574,0.000103914026,0.00036378097,0.00019669064,0.000036382156,0.000010873172,0.00023203196,0.000035888745,0.000017613824],"category_scores_gemma":[0.0028642842,0.00006488519,0.000012017719,0.00059083046,0.00020259552,0.00005268796,0.00000989471,0.00010945186,6.628973e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033425982,0.000339954,0.0025756443,0.000933241,0.0000655313,0.000052179334,0.0019591688,0.032413594,0.00008672892,0.9423075,0.0025909182,0.016341284],"study_design_scores_gemma":[0.00042782465,0.00006651676,0.003808408,0.00014627876,0.0002535122,9.3872984e-7,0.000065065244,0.54439133,0.000010729421,0.45078743,5.7984823e-7,0.000041384228],"about_ca_topic_score_codex":0.00041741953,"about_ca_topic_score_gemma":0.0016534548,"teacher_disagreement_score":0.51197773,"about_ca_system_score_codex":0.000019853649,"about_ca_system_score_gemma":0.000066380766,"threshold_uncertainty_score":0.34290224},"labels":[],"label_agreement":null},{"id":"W2150563978","doi":"10.1002/sim.1018","title":"Cost‐effectiveness analysis when the WTA is greater than the WTP","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Joseph’s Healthcare Hamilton; McMaster University; St. Joseph's Hospital","funders":"","keywords":"Willingness to pay; Interpretability; Willingness to accept; Cost effectiveness; Actuarial science; Cost–benefit analysis; Econometrics; Medicine; Computer science; Economics; Risk analysis (engineering); Microeconomics","score_opus":0.4059551580570371,"score_gpt":0.48038368130171705,"score_spread":0.07442852324467997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150563978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12543035,0.004015638,0.589751,0.255791,0.0020220848,0.0031047466,0.0020514985,0.00006618143,0.017767483],"genre_scores_gemma":[0.9700139,0.0005397096,0.0020108072,0.024214469,0.00063928665,0.0002706592,0.00012886536,0.000037045545,0.0021452685],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9960455,0.00074290234,0.002208972,0.00044657572,0.00016485885,0.00039122993],"domain_scores_gemma":[0.99387676,0.004231411,0.0009016856,0.0008080157,0.00008136753,0.000100770514],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.021716518,0.00018998154,0.00095040764,0.0003639615,0.00023882811,0.000045352255,0.0004554876,0.00008585314,0.0025149086],"category_scores_gemma":[0.0040353443,0.00013173732,0.00007551491,0.00065439,0.00030966036,0.00010062538,0.000055925593,0.0002829067,0.00056937675],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038540282,0.000045826997,0.73631984,0.00011546489,0.0005195344,0.000011426472,0.014969555,0.00039051595,4.472314e-7,0.16668062,0.07993414,0.00097410294],"study_design_scores_gemma":[0.001205406,0.00009562317,0.7399464,0.00008882411,0.00014717544,0.000007838083,0.002619238,0.019506628,0.0000012501142,0.13886397,0.0972614,0.0002562351],"about_ca_topic_score_codex":0.005934546,"about_ca_topic_score_gemma":0.002020086,"teacher_disagreement_score":0.8445836,"about_ca_system_score_codex":0.00034603904,"about_ca_system_score_gemma":0.000055814202,"threshold_uncertainty_score":0.99839693},"labels":[],"label_agreement":null},{"id":"W2151248340","doi":"10.1002/sim.5889","title":"Using confidence intervals to compare several correlated areas under the receiver operating characteristic curves","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Receiver operating characteristic; Confidence interval; Statistics; Computer science; Mathematics","score_opus":0.5440103651787387,"score_gpt":0.569237814890378,"score_spread":0.02522744971163926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151248340","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025243677,0.00010820476,0.96698016,0.003621644,0.0014603247,0.0015913195,0.00021868477,0.00006078491,0.000715229],"genre_scores_gemma":[0.2715498,0.000088636276,0.7212158,0.0062350947,0.00035201633,0.000093657356,0.000020728983,0.000056283567,0.0003880422],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954056,0.001381882,0.0016391092,0.00044989004,0.00064336596,0.00048012618],"domain_scores_gemma":[0.9508122,0.047458023,0.00038901455,0.0005822801,0.0005139989,0.0002444562],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035809884,0.00031471666,0.0010352569,0.00010235075,0.0001447492,0.000057320034,0.0005040503,0.000081403174,0.0044047534],"category_scores_gemma":[0.11900029,0.00020543324,0.000039328537,0.00042456546,0.00052801205,0.00008311261,0.0001821871,0.00070629973,0.00013041569],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022209175,0.00046484632,0.0072143073,0.0020626353,0.00041146754,0.00025133352,0.0061292327,0.00068020105,0.0032878076,0.7011559,0.26493925,0.013180944],"study_design_scores_gemma":[0.0013280388,0.00022824504,0.028662547,0.006007723,0.0002111558,0.00003767393,0.0013479321,0.045760717,0.0000503817,0.9158216,0.000115005285,0.00042894302],"about_ca_topic_score_codex":0.00082992,"about_ca_topic_score_gemma":0.00009387428,"teacher_disagreement_score":0.26482424,"about_ca_system_score_codex":0.00014520639,"about_ca_system_score_gemma":0.000079148704,"threshold_uncertainty_score":0.9965054},"labels":[],"label_agreement":null},{"id":"W2151617875","doi":"10.1002/sim.2116","title":"Bayesian modelling of imperfect ascertainment methods in cancer studies","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital; Montreal General Hospital","funders":"Canadian Arthritis Network; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Cancer registry; Cancer; Population; Statistics; Bayesian probability; Incidence (geometry); Gold standard (test); Medicine; Mathematics; Internal medicine; Environmental health","score_opus":0.05725572175604364,"score_gpt":0.44193500957810483,"score_spread":0.3846792878220612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151617875","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.122011565,0.010284736,0.86584216,0.0010947478,0.00017183911,0.0001584609,0.000035246634,0.0000022947793,0.00039896998],"genre_scores_gemma":[0.68878967,0.0063808165,0.30427447,0.00022205111,0.0001407924,0.000027981816,0.000029067403,0.000008342751,0.00012682652],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989057,0.00019967112,0.00043553766,0.0001900425,0.000079487436,0.00018957228],"domain_scores_gemma":[0.9994578,0.00018215588,0.00011534588,0.00014336067,0.00007052608,0.0000308104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011237623,0.000096589334,0.0003173425,0.000074221665,0.000016922393,6.566763e-7,0.00007690141,0.000077376426,0.000034802062],"category_scores_gemma":[0.00065069913,0.000080833706,0.000016989983,0.000094337745,0.000111402784,8.63625e-7,0.00003835007,0.00008870153,4.0974007e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012552724,0.0002372346,0.1896188,0.00021926728,0.00034909023,0.000009141516,0.004167585,0.5563506,0.059640046,0.002792474,0.01430455,0.1721857],"study_design_scores_gemma":[0.00918918,0.0028163888,0.1049427,0.0007776297,0.0002997057,0.000012835564,0.008437069,0.78155637,0.023292482,0.040085215,0.027356153,0.0012342716],"about_ca_topic_score_codex":0.000376865,"about_ca_topic_score_gemma":0.0012045343,"teacher_disagreement_score":0.56677806,"about_ca_system_score_codex":0.00006273609,"about_ca_system_score_gemma":0.000044836965,"threshold_uncertainty_score":0.3296303},"labels":[],"label_agreement":null},{"id":"W2151722761","doi":"10.1002/sim.3094","title":"Hierarchical Bayesian spatiotemporal analysis of revascularization odds using smoothing splines","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; Simon Fraser University","funders":"Fundação para a Ciência e a Tecnologia","keywords":"Markov chain Monte Carlo; Odds; Bayesian probability; Random effects model; Smoothing; Bayesian inference; Statistics; Computer science; Inference; Econometrics; Markov chain; Mathematics; Artificial intelligence; Logistic regression; Medicine; Internal medicine","score_opus":0.25380343357457186,"score_gpt":0.47357443580603237,"score_spread":0.2197710022314605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151722761","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07770763,0.0005576428,0.9174863,0.0026256284,0.0003584063,0.00026421848,0.00024071564,0.000013501664,0.0007459397],"genre_scores_gemma":[0.8559435,0.000076380755,0.14164406,0.0015761725,0.00032152914,0.000004398693,0.0003347605,0.000024410336,0.00007478148],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944732,0.00019991859,0.0044718273,0.00037153426,0.0001850159,0.00029849136],"domain_scores_gemma":[0.9961225,0.0015520861,0.0017196327,0.00036770158,0.00011066914,0.00012745522],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02330867,0.00014356621,0.0012215689,0.0015872666,0.00007494671,0.0000123381005,0.00016054689,0.00012804012,0.00039128057],"category_scores_gemma":[0.008639793,0.00017075252,0.000067756395,0.0011705692,0.00017384844,0.0001380722,0.000028054157,0.00020215318,0.000012268255],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028997621,0.0000851793,0.46128488,0.0004351605,0.00039242476,0.000009871736,0.00436198,0.0059633823,0.000028894638,0.5256096,0.000814956,0.0009846517],"study_design_scores_gemma":[0.0010696194,0.000091492475,0.3472052,0.00021697403,0.00018363274,0.0000019482936,0.0008378545,0.5965705,0.00000794263,0.05255385,0.0009879074,0.00027308956],"about_ca_topic_score_codex":0.004197974,"about_ca_topic_score_gemma":0.0018642133,"teacher_disagreement_score":0.77823585,"about_ca_system_score_codex":0.00033655265,"about_ca_system_score_gemma":0.000087934015,"threshold_uncertainty_score":0.99971086},"labels":[],"label_agreement":null},{"id":"W2151923367","doi":"10.1002/sim.2868","title":"Regression B‐spline smoothing in Bayesian disease mapping: with an application to patient safety surveillance","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Child and Family Research Institute; University of British Columbia; Providence Health Care","funders":"","keywords":"Smoothing; Computer science; Prior probability; Bayesian probability; Deviance information criterion; Bayes' theorem; Marginal likelihood; Smoothing spline; Random effects model; Context (archaeology); Statistics; Bayesian inference; Econometrics; Mathematics; Artificial intelligence; Geography","score_opus":0.030658900740926413,"score_gpt":0.37988102876256025,"score_spread":0.3492221280216338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151923367","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073086675,0.000030516474,0.99057025,0.0005840479,0.000096663825,0.0006168531,0.00011639507,0.000038601367,0.0006380317],"genre_scores_gemma":[0.31417307,0.000011907222,0.6853584,0.00025325455,0.000076901226,0.000026758751,0.00006214717,0.00002416433,0.000013400914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976495,0.00018551895,0.00080064463,0.00044518444,0.0005114226,0.00040775115],"domain_scores_gemma":[0.9966527,0.0021754557,0.00019164322,0.00045782165,0.00013822973,0.0003841351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020180922,0.0002245407,0.00044430455,0.00027725392,0.00006412897,0.000011405451,0.00017549976,0.00006352997,0.00007530603],"category_scores_gemma":[0.004052812,0.00016201868,0.000009513055,0.00062896236,0.00013054897,0.000049068625,0.000043604505,0.00029693972,0.0000031726152],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010961982,0.00030879644,0.047432598,0.0003174717,0.0000077643745,0.00038922526,0.0033249804,0.00003712601,0.00022545844,0.52196926,0.00051887473,0.42437226],"study_design_scores_gemma":[0.0013850287,0.00064720545,0.25164244,0.0012113636,0.00001507898,0.00000606929,0.00093365647,0.015522188,0.000030206516,0.72744995,0.0007718982,0.00038488334],"about_ca_topic_score_codex":0.00018750253,"about_ca_topic_score_gemma":0.0014551365,"teacher_disagreement_score":0.42398736,"about_ca_system_score_codex":0.0001577988,"about_ca_system_score_gemma":0.000053406075,"threshold_uncertainty_score":0.660693},"labels":[],"label_agreement":null},{"id":"W2153045803","doi":"10.1002/sim.3358","title":"Estimation method of the semiparametric mixture cure gamma frailty model","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Unobservable; Mixture model; Covariate; Expectation–maximization algorithm; Computer science; Imputation (statistics); Statistics; Accelerated failure time model; Econometrics; Maximum likelihood; Mathematics; Artificial intelligence; Missing data; Machine learning","score_opus":0.1371487357945214,"score_gpt":0.44413282114809916,"score_spread":0.3069840853535778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153045803","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028750142,0.000084297346,0.9937236,0.00036293248,0.0001879512,0.00026051607,0.00020108321,0.000017990731,0.00228663],"genre_scores_gemma":[0.09943617,0.00006754639,0.8998842,0.00015796408,0.000044387798,0.00001357393,0.00000891612,0.000017817536,0.00036940287],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99807066,0.00027955972,0.0006384656,0.00021687837,0.0005749172,0.00021951231],"domain_scores_gemma":[0.99378043,0.005260529,0.00027158085,0.0004292324,0.00018589674,0.00007231888],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010191239,0.00016987462,0.00048687673,0.0001399047,0.0000747295,0.0000028547377,0.0002734609,0.00011513166,0.00017650507],"category_scores_gemma":[0.022667607,0.00010490269,0.000031654254,0.00070767,0.00035759044,0.000026206033,0.000060292794,0.0004146437,0.0000025180111],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022379707,0.00009907066,0.00065641984,0.00026371627,0.000019659534,0.000015585274,0.002038984,0.0015849225,0.00035540113,0.92394084,0.023506118,0.047496933],"study_design_scores_gemma":[0.00033934086,0.000056563666,0.0017966315,0.00012375403,0.00003857005,0.000016076041,0.000044369157,0.41160876,0.00031605654,0.585536,0.000048649974,0.000075226664],"about_ca_topic_score_codex":0.000071787705,"about_ca_topic_score_gemma":0.000016363065,"teacher_disagreement_score":0.41002384,"about_ca_system_score_codex":0.000047919544,"about_ca_system_score_gemma":0.0000999963,"threshold_uncertainty_score":0.9855649},"labels":[],"label_agreement":null},{"id":"W2153200786","doi":"10.1002/sim.6044","title":"An empirical comparison of univariate and multivariate meta‐analyses for categorical outcomes","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Sudbury","funders":"Agency for Healthcare Research and Quality; U.S. Department of Health and Human Services","keywords":"Univariate; Multivariate statistics; Categorical variable; Statistics; Multivariate analysis; Meta-analysis; Context (archaeology); Econometrics; Bayesian probability; Prior probability; Correlation; Mathematics; Computer science; Medicine; Internal medicine","score_opus":0.8756302530372296,"score_gpt":0.6790142308790336,"score_spread":0.19661602215819607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153200786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026161477,0.00079058413,0.969618,0.0018280367,0.00018337664,0.0008710417,0.00008955353,0.0000036289991,0.00045430148],"genre_scores_gemma":[0.8368289,0.00001263587,0.1621319,0.00021169521,0.000036181693,0.000057126672,0.000030661588,0.0000094005145,0.0006815197],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9856209,0.00394958,0.0072903484,0.0006352523,0.0022778579,0.00022605644],"domain_scores_gemma":[0.97674346,0.018014826,0.0024948525,0.0014100733,0.0011309639,0.0002058124],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.032495584,0.00026565892,0.0057806806,0.00044101215,0.00006144854,0.0001068065,0.00072338013,0.00007652685,0.004455129],"category_scores_gemma":[0.04998691,0.00010734928,0.0003286553,0.0007094532,0.00021409859,0.00012453333,0.000060158713,0.00014116507,0.000059736696],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004121718,0.0006050496,0.7043044,0.00032055328,0.005315533,0.000010573196,0.0075201923,0.00071253657,0.0013656755,0.11143975,0.13841574,0.029948758],"study_design_scores_gemma":[0.0011228014,0.0004167952,0.41018155,0.000016788896,0.0049197823,0.0000024797298,0.0029025283,0.34373465,0.000028087534,0.23281738,0.003629708,0.00022742637],"about_ca_topic_score_codex":0.0007045098,"about_ca_topic_score_gemma":0.00017307681,"teacher_disagreement_score":0.8106674,"about_ca_system_score_codex":0.00001660214,"about_ca_system_score_gemma":0.000035757614,"threshold_uncertainty_score":0.99645495},"labels":[],"label_agreement":null},{"id":"W2153784930","doi":"10.1002/sim.1101","title":"Estimating cancer prevalence using mixture models for cancer survival","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency","funders":"","keywords":"Hazard; Hazard ratio; Cancer; Disease; Medicine; Population; Cancer survival; Proportional hazards model; Demography; Survival analysis; Environmental health; Internal medicine; Confidence interval; Biology","score_opus":0.10269196972644017,"score_gpt":0.39283956274252446,"score_spread":0.2901475930160843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153784930","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017624743,0.003804722,0.9921877,0.0010978213,0.0017667057,0.00034031927,0.00014073588,0.00004222023,0.00044353897],"genre_scores_gemma":[0.010383759,0.000540559,0.9875093,0.0004904645,0.0005070103,0.00008345983,0.0000028893276,0.000020819014,0.00046174863],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982766,0.00010800383,0.00038982337,0.00045980336,0.00035661404,0.0004091892],"domain_scores_gemma":[0.99871665,0.0004777276,0.00015462025,0.00036065426,0.00017780295,0.00011256447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007258106,0.00019705303,0.0003676098,0.00010903917,0.00011190824,0.000030390043,0.00051802036,0.00008075648,0.00011245392],"category_scores_gemma":[0.00028829413,0.00016398705,0.000024345467,0.0003221833,0.000105663,0.0002129173,0.00007956147,0.00022528443,6.884934e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000123004,0.00006194762,0.00040526586,0.00082490983,0.000037493028,0.000039952167,0.00545654,0.040674184,0.00067017914,0.39026323,0.008300226,0.55325377],"study_design_scores_gemma":[0.0004894111,0.000041519983,0.000050836818,0.00039983593,0.000026847181,0.0000038399544,0.0000076152273,0.8272811,0.000029495895,0.17130405,0.00020763492,0.00015779547],"about_ca_topic_score_codex":0.00043793215,"about_ca_topic_score_gemma":0.00015958342,"teacher_disagreement_score":0.78660697,"about_ca_system_score_codex":0.00011266331,"about_ca_system_score_gemma":0.00006411364,"threshold_uncertainty_score":0.66871977},"labels":[],"label_agreement":null},{"id":"W2154400783","doi":"10.1002/sim.821","title":"The use of mixture models for identifying high risks in disease mapping","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Overdispersion; Poisson distribution; Frequentist inference; Econometrics; Statistics; Autocorrelation; Parametric model; Computer science; Parametric statistics; Bayes' theorem; Random effects model; Mixture model; Bayesian probability; Population; Inference; Bayesian inference; Mathematics; Negative binomial distribution; Artificial intelligence; Medicine","score_opus":0.16375861163825192,"score_gpt":0.38095295121453415,"score_spread":0.21719433957628223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154400783","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012292905,0.0006145094,0.99582213,0.001503344,0.00041120115,0.00032397918,0.00003947022,0.000013214217,0.00004284402],"genre_scores_gemma":[0.13617104,0.0005985732,0.8627002,0.00029261608,0.000074678916,0.000032528213,0.000009925851,0.000009700317,0.00011069628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985971,0.00015129751,0.00044461357,0.00026180138,0.0002674178,0.0002777869],"domain_scores_gemma":[0.9977051,0.0015307026,0.00013316823,0.00043628903,0.00010598541,0.00008874466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011296282,0.000117803305,0.00024915754,0.00015273086,0.00007415296,0.000035855024,0.00044629682,0.000043467975,0.0000030256924],"category_scores_gemma":[0.00091878546,0.0000804723,0.00002213162,0.00039351714,0.00011632599,0.00018881036,0.00008836517,0.00017939079,2.9493165e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042022693,0.00003246835,0.0006675113,0.00008295868,0.000009189377,0.000076209355,0.0016435715,0.0019260643,0.00007801434,0.8361197,0.0018461444,0.15747611],"study_design_scores_gemma":[0.0004828997,0.000023689465,0.0041305223,0.00016531517,0.000006774045,0.0000016276568,0.000019296247,0.41904944,0.000004820685,0.57492036,0.0011301482,0.00006511829],"about_ca_topic_score_codex":0.0003732572,"about_ca_topic_score_gemma":0.00018402316,"teacher_disagreement_score":0.41712338,"about_ca_system_score_codex":0.00003593862,"about_ca_system_score_gemma":0.00005396484,"threshold_uncertainty_score":0.3281565},"labels":[],"label_agreement":null},{"id":"W2154910915","doi":"10.1002/sim.2525","title":"Models for assisted conception data with embryo‐specific covariates","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Assisted Reproductive Technology and Twin Pregnancy","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Covariate; Outcome (game theory); Random effects model; Embryo; Statistics; Computer science; Data set; Econometrics; Medicine; Mathematics; Biology; Internal medicine; Genetics","score_opus":0.05828472769053113,"score_gpt":0.33604692622526994,"score_spread":0.2777621985347388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2154910915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023034203,0.0023194188,0.9856881,0.0021961452,0.00029127087,0.0009848797,0.0005375716,0.00013548805,0.0055437176],"genre_scores_gemma":[0.7148833,0.00018532567,0.27769342,0.0001619586,0.00056231645,0.00008810124,0.004727497,0.00004342425,0.0016546204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99843204,0.000036579513,0.00041171268,0.0005903095,0.0002585479,0.0002708188],"domain_scores_gemma":[0.9983632,0.00027545355,0.00014894088,0.00091988477,0.00024511735,0.000047416957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046083433,0.00018300618,0.0004565392,0.00018064561,0.00008004625,0.0000050035446,0.00019331671,0.00014290684,0.00009626678],"category_scores_gemma":[0.00030839848,0.00013120286,0.000012715946,0.00030926242,0.0006312395,0.000091804184,0.000050010603,0.0002982993,0.000005466205],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001990135,0.0008652955,0.01536674,0.0005871852,0.00024779522,0.0005151982,0.00035716727,0.00031105135,0.006361144,0.7464988,0.17369051,0.05320893],"study_design_scores_gemma":[0.038671747,0.0049815727,0.28571352,0.0041001337,0.0013945801,0.0007826903,0.002094525,0.051402796,0.00088448834,0.5707269,0.03807833,0.0011687187],"about_ca_topic_score_codex":0.00009374781,"about_ca_topic_score_gemma":0.00010367416,"teacher_disagreement_score":0.7125799,"about_ca_system_score_codex":0.0000738071,"about_ca_system_score_gemma":0.00008383148,"threshold_uncertainty_score":0.5350297},"labels":[],"label_agreement":null},{"id":"W2156667592","doi":"10.1002/sim.5754","title":"Armitage Lecture 2011: the design and analysis of life history studies","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Data Analysis and Archiving","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Statistics; Mathematics","score_opus":0.06506782028851961,"score_gpt":0.3518201170214288,"score_spread":0.2867522967329092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156667592","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04072584,0.04319876,0.8894196,0.015059115,0.0006439537,0.0008259489,0.00012436176,0.000033003875,0.009969383],"genre_scores_gemma":[0.9665476,0.00896935,0.021354774,0.0011675316,0.00015993178,0.000021293406,0.000033614644,0.000007833122,0.0017380905],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9989639,0.00030915978,0.0002248886,0.00011337462,0.00026492035,0.00012374332],"domain_scores_gemma":[0.99775225,0.0018671389,0.00010860967,0.00013265426,0.00008506532,0.00005429972],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013391515,0.000058598023,0.00030884737,0.00017669094,0.00010527859,0.000005640755,0.0001433828,0.00001749748,0.0009188122],"category_scores_gemma":[0.0024507197,0.000033965684,0.000017555783,0.00027187748,0.00093707774,0.000041487052,0.000032509633,0.00008878278,0.0000032772634],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014500263,0.00006587897,0.051292304,0.00007986384,0.0027016525,0.000012426759,0.17997341,0.00074685505,0.00039065426,0.11296815,0.5900051,0.06174919],"study_design_scores_gemma":[0.0015317968,0.0004262714,0.4945503,0.0002794422,0.008282686,5.0375434e-7,0.15579264,0.07397285,0.000011375163,0.14509556,0.1192859,0.0007707118],"about_ca_topic_score_codex":0.0042196866,"about_ca_topic_score_gemma":0.0037443219,"teacher_disagreement_score":0.9258217,"about_ca_system_score_codex":0.00004539894,"about_ca_system_score_gemma":0.00005762182,"threshold_uncertainty_score":0.99999446},"labels":[],"label_agreement":null},{"id":"W2157347940","doi":"10.1002/sim.698","title":"A comparison of methods to detect publication bias in meta‐analysis","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1297,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Statistics; Publication bias; Funnel plot; Sample size determination; Meta-analysis; Type I and type II errors; Nominal level; Linear regression; Mathematics; Econometrics; Censoring (clinical trials); Logistic regression; Meta-regression; Statistical power; Logit; Confidence interval; Medicine","score_opus":0.8953613622891847,"score_gpt":0.6824856965509237,"score_spread":0.212875665738261,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157347940","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029204465,0.0020280802,0.9884496,0.0019030883,0.00008262603,0.00047366068,0.000031875075,0.000002218338,0.004108423],"genre_scores_gemma":[0.37218505,0.000046015397,0.62570304,0.0003409669,0.000023681067,0.00006128823,0.000026311189,0.000006763404,0.0016068635],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96514636,0.015469366,0.014330598,0.0008700597,0.0039045406,0.00027910134],"domain_scores_gemma":[0.9749687,0.017431289,0.0036836853,0.0023857357,0.0013725342,0.00015807153],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18088403,0.00020918276,0.0071753864,0.0029469898,0.000026600892,0.000080831975,0.0010790676,0.00005978642,0.017014666],"category_scores_gemma":[0.1887139,0.00010037837,0.00066628965,0.0118113095,0.00008300998,0.000068759604,0.00007520962,0.00016925366,0.00017723278],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050916027,0.00027267027,0.4828337,0.00014106736,0.029928613,0.00002268782,0.008033151,0.0067777373,0.00038967305,0.030579222,0.1414376,0.29953295],"study_design_scores_gemma":[0.0010909803,0.0005034874,0.3142297,0.00006316178,0.11993765,0.0000072614134,0.0053237635,0.29890493,0.00018182328,0.10660471,0.15253265,0.000619885],"about_ca_topic_score_codex":0.0003757007,"about_ca_topic_score_gemma":0.002864133,"teacher_disagreement_score":0.3692646,"about_ca_system_score_codex":0.000039695165,"about_ca_system_score_gemma":0.000036489655,"threshold_uncertainty_score":0.9838839},"labels":[],"label_agreement":null},{"id":"W2157860153","doi":"10.1002/sim.3523","title":"Confidence interval construction for a difference between two dependent intraclass correlation coefficients","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Confidence interval; Intraclass correlation; Statistics; Point estimation; Interval estimation; Inference; Mathematics; Sample size determination; Confidence distribution; Nominal level; Variance (accounting); Correlation; Coverage probability; CDF-based nonparametric confidence interval; Standard error; Computer science; Reproducibility; Artificial intelligence","score_opus":0.06250443287661349,"score_gpt":0.41815188558518207,"score_spread":0.35564745270856857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157860153","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028986032,0.000019374243,0.9946875,0.0004535913,0.00051756896,0.00054088037,0.00030657044,0.000041104242,0.0005348045],"genre_scores_gemma":[0.3969963,0.000009115467,0.60262924,0.00009410139,0.00014650606,0.000016865202,0.000047796275,0.000009278392,0.0000508443],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980544,0.00015838596,0.00073603244,0.0003323302,0.00040218016,0.00031669],"domain_scores_gemma":[0.99424034,0.0049364814,0.0002501249,0.00022201221,0.00023055944,0.000120456745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089043425,0.00019915748,0.00051432644,0.00014227605,0.00007887364,0.000023467559,0.00019064765,0.00008789129,0.0001063202],"category_scores_gemma":[0.007848845,0.00016768232,0.000021923264,0.00018684453,0.0002953437,0.00004178475,0.000022484764,0.0003003409,0.0000050607114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004965315,0.00004480058,0.0021963147,0.000056480636,0.000008619837,0.000008875769,0.00029461895,0.000004043285,0.00013583855,0.793672,0.00043291663,0.20309578],"study_design_scores_gemma":[0.0017662693,0.0005760461,0.016053218,0.00038339934,0.00008184991,0.000012052746,0.00017859854,0.015173947,0.00009042143,0.96548057,0.00002942079,0.00017419271],"about_ca_topic_score_codex":0.000042805746,"about_ca_topic_score_gemma":0.000042042124,"teacher_disagreement_score":0.3940977,"about_ca_system_score_codex":0.000106681495,"about_ca_system_score_gemma":0.0000523408,"threshold_uncertainty_score":0.93963677},"labels":[],"label_agreement":null},{"id":"W2159452805","doi":"10.1002/sim.6791","title":"A tutorial on Bayesian bivariate meta‐analysis of mixed binary‐continuous outcomes with missing treatment effects","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Public Health Ontario; University Health Network; University of Toronto; Toronto Public Health; Osteoporosis Canada","funders":"Canadian Institutes of Health Research","keywords":"Bivariate analysis; Random effects model; Computer science; Meta-analysis; Categorical variable; Bayesian probability; Missing data; Univariate; Statistics; Econometrics; Data mining; Multivariate statistics; Medicine; Mathematics; Machine learning; Artificial intelligence","score_opus":0.5665462388726342,"score_gpt":0.5224215384526055,"score_spread":0.044124700420028695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159452805","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05964865,0.0034054713,0.9174458,0.0039362544,0.0025610153,0.0028324402,0.00041798217,0.000020806518,0.009731624],"genre_scores_gemma":[0.9138164,0.000018729766,0.08243323,0.00018137683,0.00013161267,0.00006598806,0.000053811356,0.000021972344,0.003276878],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9817899,0.006160377,0.0052708,0.0007605315,0.005758162,0.0002602364],"domain_scores_gemma":[0.9792826,0.014099002,0.0031231022,0.0021638637,0.0010612955,0.00027010374],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.046979602,0.00040317755,0.009429595,0.0014214389,0.00004851992,0.000099067554,0.00061282306,0.00006569426,0.0015028918],"category_scores_gemma":[0.046596248,0.00014859572,0.0009082528,0.0028792517,0.00015298877,0.000054278134,0.000035475947,0.00010754079,0.0000636014],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086709094,0.001952142,0.1837483,0.0004470675,0.5396175,0.0015841038,0.019004922,0.011042214,0.00019482036,0.08372692,0.09489787,0.06291708],"study_design_scores_gemma":[0.009312677,0.007906082,0.084332965,0.00022298003,0.76462847,0.000010839903,0.0026444562,0.06995092,0.00009263315,0.043693744,0.016299834,0.0009043817],"about_ca_topic_score_codex":0.00053216296,"about_ca_topic_score_gemma":0.000662413,"teacher_disagreement_score":0.85416776,"about_ca_system_score_codex":0.0001158046,"about_ca_system_score_gemma":0.00013539521,"threshold_uncertainty_score":0.99940985},"labels":[],"label_agreement":null},{"id":"W2159741108","doi":"10.1002/sim.1335","title":"Power and sample size for DNA microarray studies","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":171,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Heart, Lung, and Blood Institute","keywords":"Sample size determination; Statistics; Computer science; Sample (material); Power (physics); Computational biology; Mathematics; Biology; Chromatography; Chemistry; Physics","score_opus":0.03013445253274159,"score_gpt":0.33393307553954465,"score_spread":0.30379862300680305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159741108","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49703145,0.060527015,0.41144946,0.017096085,0.0033139382,0.0021774743,0.0013520272,0.00005334599,0.0069992184],"genre_scores_gemma":[0.9532593,0.0039904504,0.039270446,0.0010555595,0.00020779992,0.00006219557,0.00004586714,0.00001564623,0.002092717],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994848,0.000018767056,0.00014386835,0.00018297699,0.00006296333,0.00010667259],"domain_scores_gemma":[0.9995223,0.00019962093,0.000042431395,0.00013041499,0.00006857104,0.000036627345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012476728,0.00007264991,0.00011368826,0.000025017482,0.000035945268,0.0000031234345,0.00004824803,0.000041424315,0.000103804494],"category_scores_gemma":[0.0020340532,0.000058525835,0.0000083056275,0.000041317042,0.00012664517,8.4076e-7,0.000020031572,0.000033644163,9.711761e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058494683,0.000041137857,0.0016629905,0.00007615019,0.000040713352,0.0000015813731,0.0010495759,0.0000020718808,0.5592846,0.0016604725,0.4260972,0.010024966],"study_design_scores_gemma":[0.006236137,0.00180241,0.01525531,0.00018558568,0.00006276015,0.00001268687,0.0051792976,0.0003673874,0.057448395,0.027615847,0.88530463,0.0005295271],"about_ca_topic_score_codex":0.000003477041,"about_ca_topic_score_gemma":0.000018773811,"teacher_disagreement_score":0.50183624,"about_ca_system_score_codex":0.0000087041335,"about_ca_system_score_gemma":0.0000066155276,"threshold_uncertainty_score":0.24350984},"labels":[],"label_agreement":null},{"id":"W2159848039","doi":"10.1002/sim.5808","title":"State‐space size considerations for disease‐progression models","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Markov chain; State space; Stochastic matrix; Computer science; Set (abstract data type); Disease; Markov model; Basis (linear algebra); State (computer science); Space (punctuation); Econometrics; Markov process; Statistics; Mathematics; Algorithm; Medicine","score_opus":0.03652017716464257,"score_gpt":0.3702021972862839,"score_spread":0.33368202012164133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159848039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047116715,0.0019080957,0.7999521,0.05761062,0.0039798664,0.011139439,0.0014777227,0.00041837833,0.07639704],"genre_scores_gemma":[0.92972684,0.00058232225,0.06692551,0.0007838416,0.00022411397,0.00038909525,0.00003022704,0.00001864514,0.0013194027],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99819934,0.00017284829,0.00036082757,0.000270414,0.0005982163,0.0003983457],"domain_scores_gemma":[0.9973238,0.0017947049,0.00012276815,0.00022760301,0.00031568433,0.00021544234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009123997,0.0001321991,0.00022816758,0.00011420548,0.00039061264,0.00005758915,0.0001399481,0.00004170874,0.00064337975],"category_scores_gemma":[0.0025977627,0.00011507084,0.00002752217,0.00022957337,0.00067734433,0.00018038256,0.000031035623,0.00011849583,0.000018172372],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022000617,0.00011036653,0.0130251935,0.00009847705,0.000028871642,0.000025311812,0.008268314,0.00045029836,0.000011821631,0.80026746,0.16875795,0.008933956],"study_design_scores_gemma":[0.0007440773,0.00006235399,0.030241609,0.0000969149,0.000035658024,1.03652155e-7,0.0023253202,0.008345348,0.0000016243218,0.9527945,0.0051972917,0.00015521611],"about_ca_topic_score_codex":0.0028917775,"about_ca_topic_score_gemma":0.003952683,"teacher_disagreement_score":0.88261014,"about_ca_system_score_codex":0.00007801252,"about_ca_system_score_gemma":0.00013110686,"threshold_uncertainty_score":0.70445573},"labels":[],"label_agreement":null},{"id":"W2159915215","doi":"10.1002/sim.3012","title":"Effect of exposure misclassification on the mean squared error of population attributable risk and prevented fraction estimates","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Statistics; Mean squared error; Attributable risk; Fraction (chemistry); Observational error; Population; Variance (accounting); Econometrics; Accuracy and precision; Mathematics; Medicine; Chemistry; Environmental health; Economics","score_opus":0.07347620403333992,"score_gpt":0.4348047438118476,"score_spread":0.36132853977850765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159915215","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49907443,0.000042231717,0.50018185,0.00004085501,0.0000337957,0.00043945198,0.000051012812,0.000027548818,0.000108850436],"genre_scores_gemma":[0.93930626,0.000041258467,0.060515754,0.0000059603212,0.000018379907,0.000014969833,0.000071446695,0.000012365552,0.000013587926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99881476,0.00017298173,0.00050046894,0.00012789035,0.00026862728,0.0001152856],"domain_scores_gemma":[0.9926399,0.006487976,0.00050495996,0.00022812218,0.00011363172,0.000025393485],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025012575,0.000113299095,0.00033300673,0.00011731935,0.000037771344,0.000002004074,0.000065357395,0.00006793692,0.000030273735],"category_scores_gemma":[0.008448125,0.000072271825,0.000011326406,0.00017967298,0.00013281543,0.000041784435,0.000012662559,0.00018336078,3.223971e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001579141,0.00045525533,0.27435744,0.0027346625,0.0001103843,0.000011795228,0.0035938704,0.00025557465,0.06664604,0.53266364,0.0023631244,0.115229055],"study_design_scores_gemma":[0.0012502699,0.0033358692,0.14686874,0.0012436936,0.0002094663,0.0000033877914,0.0006029409,0.006619196,0.09706731,0.7426176,0.000022669172,0.00015882766],"about_ca_topic_score_codex":0.00019999768,"about_ca_topic_score_gemma":0.00011893232,"teacher_disagreement_score":0.44023186,"about_ca_system_score_codex":0.000061964776,"about_ca_system_score_gemma":0.0000060218026,"threshold_uncertainty_score":0.99990416},"labels":[],"label_agreement":null},{"id":"W2159968952","doi":"10.1002/sim.3243","title":"Discussion of ‘A critical appraisal of propensity‐score matching in the medical literature between 1996 and 2003’","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Institute for Clinical Evaluative Sciences","keywords":"Critical appraisal; Matching (statistics); Library science; Citation; Propensity score matching; Psychology; Operations research; Computer science; Medicine; Alternative medicine; Mathematics; Pathology; Surgery","score_opus":0.12894851090037607,"score_gpt":0.4533669741319672,"score_spread":0.3244184632315911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159968952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5304736,0.0005043293,0.4640504,0.0032038277,0.00016715021,0.000641431,0.00019893129,0.000042118307,0.0007182053],"genre_scores_gemma":[0.8902272,0.0001914082,0.10937708,0.000057587557,0.00008022059,0.000010202655,0.000032142056,0.000012795821,0.000011349806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981646,0.0002066867,0.0006224179,0.00016380419,0.00066583155,0.00017666443],"domain_scores_gemma":[0.99557406,0.0038555476,0.00012275565,0.00022930383,0.00015391919,0.00006439177],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012082474,0.00013255727,0.0005084225,0.00012761082,0.000029888446,0.0000021050935,0.00020343046,0.000125124,0.00003346062],"category_scores_gemma":[0.019819997,0.000065244996,0.000009561496,0.00038778508,0.0009385181,0.000062942956,0.00008054409,0.0005781499,1.8885568e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000951887,0.00044562906,0.11672717,0.0025425586,0.000020187714,0.0012425793,0.043575745,9.655671e-7,0.000951992,0.8168668,0.006728148,0.010803007],"study_design_scores_gemma":[0.0008417381,0.00049648015,0.09199639,0.0036737565,0.000040748564,0.00015047133,0.0013442455,0.00015152586,0.00040547163,0.90066147,0.00007107785,0.00016661556],"about_ca_topic_score_codex":0.000059783168,"about_ca_topic_score_gemma":0.000062686,"teacher_disagreement_score":0.3597536,"about_ca_system_score_codex":0.000014938898,"about_ca_system_score_gemma":0.000061314364,"threshold_uncertainty_score":0.98843646},"labels":[],"label_agreement":null},{"id":"W2160269073","doi":"10.1002/1097-0258(20000730)19:14<1901::aid-sim514>3.0.co;2-v","title":"The generalization of the odds ratio, risk ratio and risk difference tor �k tables","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Victoria Hospital","funders":"","keywords":"Odds ratio; Confidence interval; Statistics; Pooling; Generalization; Statistic; Mathematics; Relative risk; Standard error; Diagnostic odds ratio; Odds; Absolute risk reduction; Type I and type II errors; Econometrics; Computer science; Logistic regression; Artificial intelligence","score_opus":0.21131445457799014,"score_gpt":0.4951114708605551,"score_spread":0.283797016282565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160269073","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055317063,0.00036928293,0.94102484,0.00046546335,0.0005997391,0.00065140304,0.00083482196,0.000018326231,0.0007190333],"genre_scores_gemma":[0.12158923,0.0143546965,0.8608297,0.00021302963,0.0004959337,0.000069383255,0.000014270071,0.00004816056,0.0023856002],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962225,0.0017404398,0.0010837236,0.00024148,0.0004955659,0.000216273],"domain_scores_gemma":[0.9498299,0.048993286,0.0004774862,0.00049572246,0.00013748731,0.000066120185],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038280406,0.00016643107,0.00048759545,0.000030857784,0.00024493458,0.000021593722,0.00028405408,0.00009243979,0.0006683361],"category_scores_gemma":[0.13022582,0.00008439568,0.000025803112,0.00026187152,0.0009325657,0.000021913378,0.000054858483,0.00035449813,0.0000024481828],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012914302,0.00007848373,0.017137779,0.000109650755,0.00007072624,0.000002861987,0.0009966431,0.000085159634,0.00018218083,0.81534725,0.007913848,0.1579463],"study_design_scores_gemma":[0.001036535,0.00014622234,0.04575221,0.00013492443,0.00019372805,0.0000013851262,0.00010660894,0.01907642,0.00018493542,0.9327676,0.0004990021,0.00010038589],"about_ca_topic_score_codex":0.0003527236,"about_ca_topic_score_gemma":0.00054711965,"teacher_disagreement_score":0.15784591,"about_ca_system_score_codex":0.00003001906,"about_ca_system_score_gemma":0.000049777762,"threshold_uncertainty_score":0.87710065},"labels":[],"label_agreement":null},{"id":"W2160329317","doi":"10.1002/sim.1617","title":"Two‐sample scale tests for comparison of metabolic rates for styrene in previously exposed and unexposed groups","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Science Council","keywords":"Statistics; Styrene; Sample size determination; Estimator; Inference; Statistical inference; Scale (ratio); Sample (material); Mathematics; Econometrics; Chemistry; Chromatography; Computer science; Organic chemistry; Physics","score_opus":0.13106755298798983,"score_gpt":0.4701442731845786,"score_spread":0.33907672019658874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160329317","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11529782,0.0007335007,0.8815162,0.0001203907,0.00012254242,0.0011704079,0.00096887315,0.000012610454,0.00005764298],"genre_scores_gemma":[0.33725166,0.000063751104,0.66237795,0.00004108628,0.00005064189,0.00012706945,0.00006025738,0.000019292504,0.000008297574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980726,0.00009587388,0.0009827148,0.0002883781,0.0002176087,0.00034282848],"domain_scores_gemma":[0.98737556,0.01187184,0.00024413416,0.00021744463,0.0001905582,0.00010048331],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012872042,0.00019846023,0.0009585081,0.00016727587,0.00004091244,0.000008944002,0.00013726587,0.00006806177,0.000029032151],"category_scores_gemma":[0.01736143,0.00016263587,0.000023499393,0.00023408729,0.0002868764,0.00003269807,0.000031328287,0.00014084876,3.0160422e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016675703,0.00031264406,0.011488778,0.00083522673,0.000021936909,0.0000022882357,0.0037659174,0.000029383933,0.002514304,0.95873713,0.0003244837,0.021801148],"study_design_scores_gemma":[0.007480127,0.0010292515,0.012246963,0.0004576537,0.00009629062,0.0000012950683,0.0010374588,0.0061968938,0.0030199417,0.96819055,0.000078990255,0.00016455966],"about_ca_topic_score_codex":0.0002992331,"about_ca_topic_score_gemma":0.0012742736,"teacher_disagreement_score":0.22195384,"about_ca_system_score_codex":0.00003309197,"about_ca_system_score_gemma":0.00007039637,"threshold_uncertainty_score":0.9909158},"labels":[],"label_agreement":null},{"id":"W2160393348","doi":"10.1002/sim.2206","title":"SARS incubation and quarantine times: when is an exposed individual known to be disease free?","year":2005,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Medical Research Council","keywords":"Biostatistics; Queen (butterfly); Library science; Public health; History; Medicine; Computer science; Pathology","score_opus":0.2196670982091016,"score_gpt":0.4390063802517846,"score_spread":0.21933928204268302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160393348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6796037,0.0008618566,0.22150104,0.09358472,0.00022369342,0.0014527419,0.0018000235,0.00018938759,0.00078282977],"genre_scores_gemma":[0.7021181,0.00021259888,0.279134,0.017345661,0.0005650546,0.000078443314,0.00018509233,0.0000409602,0.00032009342],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99805284,0.00018252143,0.0006282675,0.00039050507,0.00044125714,0.00030459152],"domain_scores_gemma":[0.99631333,0.0028002018,0.0001327284,0.0004011065,0.00009398507,0.00025862872],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013227263,0.00022032611,0.00051594584,0.00015144557,0.00009448838,0.000013151412,0.00024431324,0.0000679512,0.00048617105],"category_scores_gemma":[0.019918157,0.00016728662,0.000015963033,0.0001728292,0.00022862737,0.00007437085,0.00019550783,0.00019313849,0.000012549189],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028691304,0.0004688773,0.044143427,0.00043409978,0.00010172867,0.00007020504,0.032686077,0.000033045588,0.00014833375,0.1327227,0.74079573,0.048108872],"study_design_scores_gemma":[0.0021403162,0.00063968805,0.06584865,0.0001734924,0.00015544728,0.0000013862674,0.00083640334,0.0036951571,0.00002324537,0.91492087,0.011249051,0.00031628623],"about_ca_topic_score_codex":0.00019133835,"about_ca_topic_score_gemma":0.0011030292,"teacher_disagreement_score":0.7821982,"about_ca_system_score_codex":0.00007921948,"about_ca_system_score_gemma":0.000031297117,"threshold_uncertainty_score":0.9883375},"labels":[],"label_agreement":null},{"id":"W2160577585","doi":"10.1002/sim.6466","title":"Frailty models for pneumonia to death with a left‐censored covariate","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Estimator; Statistics; Inference; Mathematics; Nonparametric statistics; Multiplicative function; Hazard ratio; Proportional hazards model; Confidence interval; Computer science; Econometrics; Artificial intelligence","score_opus":0.5341691921754336,"score_gpt":0.4810747424250354,"score_spread":0.053094449750398176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160577585","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011084228,0.0004270337,0.9544823,0.02611273,0.0005622847,0.0013363678,0.0017677903,0.000037483023,0.004189767],"genre_scores_gemma":[0.43907735,0.00006237402,0.5356112,0.021621143,0.00069199386,0.0003427921,0.00031397847,0.00009967936,0.0021794667],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963747,0.00012234034,0.0023915337,0.00051270565,0.00015063093,0.00044808665],"domain_scores_gemma":[0.9970393,0.0011714941,0.0007539705,0.0004337531,0.00020028988,0.00040116897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010193603,0.00019994516,0.0010391109,0.00035751774,0.00007255709,0.000025257652,0.00023521151,0.000092999646,0.000106248044],"category_scores_gemma":[0.007135216,0.00020657676,0.000021113787,0.000173578,0.000076919496,0.00015979673,0.00003175741,0.00015152569,0.00024611852],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014740699,0.00006633402,0.010610378,0.00022102844,0.000050010447,0.0000069078287,0.008338651,0.008580858,0.000002753869,0.89099425,0.080785505,0.00019591497],"study_design_scores_gemma":[0.0055757854,0.0011804204,0.01197658,0.00028817068,0.00002173636,0.000011790773,0.0020237567,0.17072909,0.0000023048156,0.75791055,0.049759522,0.0005203174],"about_ca_topic_score_codex":0.0019289724,"about_ca_topic_score_gemma":0.0011346843,"teacher_disagreement_score":0.42799315,"about_ca_system_score_codex":0.0005442947,"about_ca_system_score_gemma":0.00023611891,"threshold_uncertainty_score":0.8542036},"labels":[],"label_agreement":null},{"id":"W2160628682","doi":"10.1002/sim.5374","title":"A Bayesian method for estimating prevalence in the presence of a hidden sub‐population","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Statistics; Posterior probability; Bayesian probability; Population; Sampling (signal processing); Markov chain Monte Carlo; Sample (material); Gibbs sampling; Computer science; Econometrics; Mathematics; Demography","score_opus":0.03508214765957837,"score_gpt":0.3825456648440279,"score_spread":0.34746351718444957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160628682","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00038890913,0.0003120461,0.9978408,0.00048380785,0.00030539682,0.00047313748,0.000014223841,0.00001004104,0.00017164367],"genre_scores_gemma":[0.18028511,0.000013056387,0.81938034,0.00013435508,0.000112987786,0.000051283714,0.0000046328787,0.000005347893,0.000012909654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983439,0.000446798,0.00042804275,0.00019799112,0.00030747234,0.00027579427],"domain_scores_gemma":[0.9967179,0.0026395551,0.0001722537,0.00036397143,0.000058970978,0.0000473951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004819502,0.000103282124,0.00024140488,0.00012244412,0.000035925117,0.000010447051,0.00052049675,0.000045196102,0.0000045000943],"category_scores_gemma":[0.0023150495,0.000069793314,0.000015787367,0.000375731,0.00005657019,0.00017924294,0.000055069475,0.00015151386,2.6427932e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010145504,0.000055416316,0.005506428,0.00038778124,0.0000039696697,0.000003586534,0.011613361,0.00008183571,0.00031395658,0.5573747,0.0005633028,0.42408547],"study_design_scores_gemma":[0.00035370924,0.00008912222,0.017814754,0.00023888303,0.000012701403,0.000009257713,0.000054012886,0.6848104,0.00008490676,0.29643264,0.000022578213,0.000077052006],"about_ca_topic_score_codex":0.00018717161,"about_ca_topic_score_gemma":0.000049675393,"teacher_disagreement_score":0.68472856,"about_ca_system_score_codex":0.00002597255,"about_ca_system_score_gemma":0.000026227613,"threshold_uncertainty_score":0.28460887},"labels":[],"label_agreement":null},{"id":"W2161040745","doi":"10.1002/sim.2073","title":"Using generalized additive models to reduce residual confounding","year":2004,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal General Hospital","funders":"","keywords":"Covariate; Confounding; Statistics; Logistic regression; Mathematics; Parametric statistics; Context (archaeology); Generalized linear model; Econometrics; Linear regression","score_opus":0.3116101435216381,"score_gpt":0.5048658643751648,"score_spread":0.19325572085352666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161040745","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02462987,0.00003233004,0.9711519,0.00030294602,0.00016849113,0.0004518037,0.00015219956,0.00012824421,0.0029822534],"genre_scores_gemma":[0.13183816,0.000044589575,0.86731184,0.00035910023,0.00020873822,0.000035023328,0.00003456514,0.000039005146,0.00012897384],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99838525,0.00006805241,0.0005174557,0.00028216967,0.00039720937,0.00034986986],"domain_scores_gemma":[0.99861205,0.00063138426,0.00014215962,0.00029054942,0.00019240691,0.00013145384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056639174,0.00019953104,0.00043292082,0.00024029127,0.000066403576,0.000010779456,0.00017443432,0.00007740207,0.00012696002],"category_scores_gemma":[0.0024022306,0.00018193117,0.000012382848,0.0003007567,0.00018543174,0.00011077431,0.00006827216,0.00026171506,0.0000056719173],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000384617,0.000028120421,0.000003828779,0.000030218029,0.000011487801,0.00009646357,0.0026342492,0.0019469938,0.008514339,0.9826795,0.0029734431,0.0010428885],"study_design_scores_gemma":[0.0009825913,0.0001741059,0.000011255109,0.00058121997,0.000030409275,0.00001739374,0.0007267386,0.0016542365,0.007301025,0.9882061,0.00011469425,0.00020024058],"about_ca_topic_score_codex":0.00039670483,"about_ca_topic_score_gemma":0.00018239395,"teacher_disagreement_score":0.10720828,"about_ca_system_score_codex":0.00044035516,"about_ca_system_score_gemma":0.00011877996,"threshold_uncertainty_score":0.7418938},"labels":[],"label_agreement":null},{"id":"W2162274668","doi":"10.1002/sim.2624","title":"Using mixed treatment comparisons and meta‐regression to perform indirect comparisons to estimate the efficacy of biologic treatments in rheumatoid arthritis","year":2006,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":152,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; St. Paul's Hospital","funders":"","keywords":"Meta-analysis; Medicine; Odds ratio; Rheumatoid arthritis; Internal medicine; Random effects model; Meta-regression; Placebo; Randomized controlled trial; Sample size determination; Statistics; Pathology; Mathematics","score_opus":0.14527511481052424,"score_gpt":0.45913485076603355,"score_spread":0.3138597359555093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162274668","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010191881,0.9843983,0.00091727014,0.00019816513,0.00013413,0.0033302838,0.00068095257,0.000022811959,0.00012617566],"genre_scores_gemma":[0.0070601003,0.9738185,0.018071555,0.000025060805,0.000037695983,0.00032198933,0.000557314,0.000054562483,0.000053246837],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99640304,0.00045984917,0.0014284007,0.0005700712,0.0005204785,0.00061818416],"domain_scores_gemma":[0.99709874,0.0016221902,0.00035343616,0.00050340674,0.0000910451,0.00033118052],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067976804,0.0006925463,0.005021826,0.00087617815,0.00014284693,0.000021676831,0.00020426483,0.0001772635,0.00011083911],"category_scores_gemma":[0.0007087594,0.00034295578,0.00016689619,0.0008008598,0.00044331356,0.000026796302,0.00012002532,0.00044442763,0.00001195657],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024566206,0.0008054816,0.006257115,0.0015808076,0.0016223636,0.00029269778,0.00079455174,0.000055384848,0.000009723011,0.0003701435,0.0028863328,0.98507977],"study_design_scores_gemma":[0.01912236,0.010724782,0.030805202,0.10083941,0.0032965245,0.0007439642,0.000696897,0.0014274358,0.000047632417,0.0003106163,0.8306381,0.0013470355],"about_ca_topic_score_codex":0.0031411077,"about_ca_topic_score_gemma":0.004781723,"teacher_disagreement_score":0.9837327,"about_ca_system_score_codex":0.00037741713,"about_ca_system_score_gemma":0.00027979034,"threshold_uncertainty_score":0.99990225},"labels":[],"label_agreement":null},{"id":"W2162875017","doi":"10.1002/sim.707","title":"Estimating the number needed to treat (NNT) index when the data are subject to error","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Number needed to treat; Statistics; Medicine; Event (particle physics); Randomized controlled trial; Reliability (semiconductor); Adverse effect; Confidence interval; Mathematics; Relative risk; Internal medicine","score_opus":0.4318392061353256,"score_gpt":0.49505066292947963,"score_spread":0.06321145679415402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162875017","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.105220474,0.00052717206,0.42312443,0.45542967,0.0018029875,0.0020742018,0.0021304695,0.000057507088,0.00963307],"genre_scores_gemma":[0.70169544,0.00008814932,0.110108994,0.17838544,0.0033038992,0.00038660422,0.00047687572,0.0001299546,0.0054246443],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957394,0.0003418011,0.0026474241,0.000594191,0.00019540114,0.0004818031],"domain_scores_gemma":[0.9936996,0.0035649033,0.0009116555,0.0015298929,0.00007903106,0.00021492038],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.016969291,0.00021542564,0.00080752943,0.00020351939,0.00027341352,0.0000665236,0.0010815775,0.00007669978,0.0012511549],"category_scores_gemma":[0.024754794,0.00016257881,0.000021582431,0.00044561736,0.000133757,0.00015792144,0.00023557275,0.00030732012,0.0017032898],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039276245,0.000053298194,0.12182585,0.00013018439,0.000033444237,0.000013511868,0.013055064,0.0017899325,6.6351845e-7,0.026611287,0.83458567,0.0018618121],"study_design_scores_gemma":[0.003827193,0.000271813,0.23986354,0.00088872114,0.000058258174,0.00006941772,0.030460313,0.27638865,0.0000010815628,0.14837374,0.2988158,0.0009814663],"about_ca_topic_score_codex":0.01201979,"about_ca_topic_score_gemma":0.00576139,"teacher_disagreement_score":0.59647495,"about_ca_system_score_codex":0.00036706086,"about_ca_system_score_gemma":0.0000992228,"threshold_uncertainty_score":0.99966186},"labels":[],"label_agreement":null},{"id":"W2163071463","doi":"10.1002/sim.1121","title":"Sample size re‐estimation in cluster randomization trials","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario; University of Toronto","funders":"","keywords":"Sample size determination; Randomization; Statistics; Cluster (spacecraft); Cluster randomised controlled trial; Computer science; Statistical power; Sample (material); Restricted randomization; Econometrics; Clinical trial; Mathematics; Randomized controlled trial; Medicine","score_opus":0.5611285954998531,"score_gpt":0.5843085060944774,"score_spread":0.02317991059462432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163071463","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005430362,0.0000707675,0.9924818,0.002019197,0.00093671645,0.0012655573,0.00025796678,0.000049490976,0.002375441],"genre_scores_gemma":[0.026354782,0.00025424678,0.9720133,0.00059540384,0.00033552002,0.00009929096,0.00001668218,0.000040387786,0.00029038734],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99166036,0.0036996983,0.0031973594,0.00041036893,0.00066116155,0.00037103577],"domain_scores_gemma":[0.6030126,0.39584044,0.0005656013,0.00036279627,0.000114852686,0.0001037008],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.020180231,0.00024235032,0.0017577864,0.00023502237,0.000041883442,0.00001934165,0.0002030821,0.00020152968,0.0069457763],"category_scores_gemma":[0.87335247,0.00018996927,0.000053746622,0.0005463638,0.00025125538,0.000064999804,0.000045316167,0.00042038292,0.000038014365],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00218767,0.00083640416,0.0018125776,0.0008021953,0.000108454515,0.00012505232,0.0038055254,0.00074260274,0.00009636153,0.64069,0.16727835,0.18151481],"study_design_scores_gemma":[0.016771475,0.00016692712,0.0005337466,0.00035620734,0.00009668407,0.0000017954179,0.00008702866,0.09702975,0.000017669796,0.88455397,0.00021442147,0.00017031879],"about_ca_topic_score_codex":0.00009411191,"about_ca_topic_score_gemma":0.00012569907,"teacher_disagreement_score":0.85317224,"about_ca_system_score_codex":0.00013970939,"about_ca_system_score_gemma":0.000021480508,"threshold_uncertainty_score":0.993962},"labels":[],"label_agreement":null},{"id":"W2163077119","doi":"10.1002/sim.3788","title":"Risk‐adjusted survival time monitoring with an updating exponentially weighted moving average (EWMA) control chart","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":99,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"EWMA chart; Control chart; Chart; Computer science; Statistics; Moving average; Set (abstract data type); Data mining; Medicine; Mathematics; Process (computing)","score_opus":0.047221581457835254,"score_gpt":0.3800120459529197,"score_spread":0.3327904644950844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163077119","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063002415,0.00012063745,0.93318254,0.0002499036,0.00083191803,0.0003619047,0.00020961267,0.00012497706,0.0019160755],"genre_scores_gemma":[0.8337959,0.000026041324,0.16492182,0.00007619913,0.00082547794,0.000011765708,0.000041453277,0.000037822854,0.00026354156],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99349535,0.0005902422,0.0014220908,0.0009483627,0.0027893246,0.000754624],"domain_scores_gemma":[0.99227995,0.0051635895,0.0006923999,0.00071589864,0.00073775987,0.00041038523],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0038449178,0.00040793707,0.0009370653,0.00045500367,0.00035935175,0.00014162192,0.0007854902,0.000112661124,0.00041996178],"category_scores_gemma":[0.012637308,0.00030217256,0.000027393391,0.0010468465,0.00029383815,0.00057156093,0.000060011334,0.0007724555,0.00008139797],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027197592,0.00064920785,0.17726038,0.000085555956,0.00018605894,0.0028079844,0.006815806,0.017996125,0.015431862,0.03649199,0.0012480493,0.73830724],"study_design_scores_gemma":[0.011731616,0.0034946336,0.3543335,0.00086598785,0.00023131774,0.000040596147,0.0045111347,0.34349617,0.0007487784,0.27872664,0.0003705584,0.0014490767],"about_ca_topic_score_codex":0.000113087845,"about_ca_topic_score_gemma":0.00005027819,"teacher_disagreement_score":0.77079344,"about_ca_system_score_codex":0.00015257957,"about_ca_system_score_gemma":0.0000975917,"threshold_uncertainty_score":0.999943},"labels":[],"label_agreement":null},{"id":"W2163654519","doi":"10.1002/sim.4321","title":"Bayesian inference on joint models of HIV dynamics for time‐to‐event and longitudinal data with skewness and covariate measurement errors","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Covariate; Skewness; Bayesian probability; Computer science; Event (particle physics); Econometrics; Random effects model; Bayesian inference; Statistics; Inference; Mathematics; Artificial intelligence; Medicine","score_opus":0.1320334529644685,"score_gpt":0.3338156581999011,"score_spread":0.2017822052354326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163654519","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018443483,0.000056786335,0.99833655,0.0004856929,0.00006663584,0.00041042382,0.00017199325,0.00001677712,0.00027072948],"genre_scores_gemma":[0.26855335,0.000019635898,0.7312615,0.00008902454,0.000013368165,0.00001315952,0.000017473576,0.000011952774,0.00002056529],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846715,0.0000804223,0.000355667,0.0004874415,0.0003904965,0.00021882151],"domain_scores_gemma":[0.9987145,0.00017399107,0.000137464,0.00063424645,0.00019421491,0.00014554824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016842356,0.00017157636,0.00038273504,0.00014571777,0.00003817459,0.000012873842,0.00041188006,0.00004161515,0.0000050380254],"category_scores_gemma":[0.00028232177,0.00012393208,0.000006250034,0.00015790122,0.00014858686,0.0001213279,0.00022880283,0.00011834497,3.9647566e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000160446,0.00011584914,0.00034409182,0.00021127825,0.000046558438,0.000027992182,0.0025588998,0.00024033041,0.0000628947,0.90991294,0.0004398616,0.085878834],"study_design_scores_gemma":[0.00078872574,0.0007125216,0.0027074935,0.00035543376,0.000034088716,0.000007320061,0.000020376581,0.7166032,0.00003464633,0.27858853,0.000015174231,0.00013244852],"about_ca_topic_score_codex":0.00012483349,"about_ca_topic_score_gemma":0.00026082553,"teacher_disagreement_score":0.7163629,"about_ca_system_score_codex":0.000044268105,"about_ca_system_score_gemma":0.000088698616,"threshold_uncertainty_score":0.50538033},"labels":[],"label_agreement":null},{"id":"W2164498941","doi":"10.1002/sim.2580","title":"A comparison of the ability of different propensity score models to balance measured variables between treated and untreated subjects: a Monte Carlo study","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1134,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Propensity score matching; Confounding; Observational study; Outcome (game theory); Statistics; Matching (statistics); Medicine; Average treatment effect; Variables; Econometrics; Mathematics","score_opus":0.20433493146265783,"score_gpt":0.40639983108407973,"score_spread":0.2020648996214219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164498941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9213251,0.000050990846,0.07656187,0.00003576731,0.00002073529,0.0016865195,0.00017516842,0.0000431576,0.00010071483],"genre_scores_gemma":[0.98680407,0.000005662152,0.013075461,0.000005283802,0.000016126805,0.000048040885,0.000008825689,0.00001791994,0.000018586725],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99790883,0.00027424892,0.00086632,0.00027802837,0.0004722729,0.00020029886],"domain_scores_gemma":[0.9976801,0.0010334514,0.0003561664,0.0005111599,0.0003652949,0.00005382825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055361516,0.00022124,0.0010504442,0.0000942553,0.000040097548,0.0000042505644,0.00020798844,0.00006638189,0.0000050348162],"category_scores_gemma":[0.0013395334,0.00013472083,0.00001687129,0.0003598006,0.00030181766,0.000037096033,0.00010911928,0.00020485187,5.2703072e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001052001,0.00063173217,0.98031086,0.00032172006,0.00004533335,0.000004212744,0.0031102516,0.00017142517,0.0058745127,0.008849548,0.00023459565,0.0003405868],"study_design_scores_gemma":[0.0014005833,0.00096096337,0.68677014,0.00074221875,0.00023533191,6.8247135e-7,0.0005533664,0.0037595704,0.010285085,0.29513085,6.1446383e-7,0.00016060237],"about_ca_topic_score_codex":0.0042367293,"about_ca_topic_score_gemma":0.003110834,"teacher_disagreement_score":0.29354075,"about_ca_system_score_codex":0.000109178196,"about_ca_system_score_gemma":0.000032588752,"threshold_uncertainty_score":0.6404696},"labels":[],"label_agreement":null},{"id":"W2164627526","doi":"10.1002/sim.6395","title":"Sample size and robust marginal methods for cluster‐randomized trials with censored event times","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Censoring (clinical trials); Statistics; Sample size determination; Estimator; Copula (linguistics); Marginal model; Mathematics; Econometrics; Proportional hazards model; Censored regression model; Regression analysis; Computer science","score_opus":0.09310038489766441,"score_gpt":0.46693814710278747,"score_spread":0.37383776220512305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164627526","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004942261,0.0000900879,0.9964143,0.0009061969,0.00020634392,0.0014200676,0.00031005876,0.000028251254,0.0005752683],"genre_scores_gemma":[0.0010448023,0.00007264482,0.99798745,0.0002658515,0.0002133226,0.00020439459,0.000024245077,0.000036073856,0.00015120216],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946398,0.0032185267,0.0011519074,0.00036383013,0.0002746674,0.0003512407],"domain_scores_gemma":[0.7486437,0.25048253,0.00035440832,0.00022442872,0.00016380832,0.00013112326],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019103562,0.0002687256,0.0021670582,0.00010257891,0.00007878235,0.000025610798,0.00013161472,0.000090144815,0.0005005705],"category_scores_gemma":[0.339014,0.00016279033,0.00005070407,0.00013635374,0.0005650951,0.000027392853,0.000036729918,0.00019679149,8.2678247e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009324173,0.00004401247,0.000034036333,0.0003809047,0.00007623743,0.000002611588,0.00032249422,0.00000473453,0.000037243557,0.88747114,0.0031845458,0.099117875],"study_design_scores_gemma":[0.058329318,0.0005142935,0.00014759981,0.0003088891,0.00041399934,0.000008869261,0.00011557021,0.05499956,0.00003124828,0.884337,0.0006009844,0.00019266321],"about_ca_topic_score_codex":0.00009756223,"about_ca_topic_score_gemma":0.000032708085,"teacher_disagreement_score":0.31991044,"about_ca_system_score_codex":0.00003274291,"about_ca_system_score_gemma":0.000045194487,"threshold_uncertainty_score":0.6665538},"labels":[],"label_agreement":null},{"id":"W2164652223","doi":"10.1002/sim.6387","title":"Effects of categorization method, regression type, and variable distribution on the inflation of Type‐I error rate when categorizing a confounding variable","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Q & T Research; Université de Sherbrooke","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Statistics; Confounding; Econometrics; Proxy (statistics); Type I and type II errors; Logistic regression; Categorization; Latent variable; Variable (mathematics); Regression analysis; Regression; Mathematics; Inflation (cosmology); Linear regression; Computer science; Artificial intelligence","score_opus":0.059187419105748394,"score_gpt":0.4150197663453947,"score_spread":0.35583234723964635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164652223","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022386375,0.000041129293,0.9963813,0.00007945143,0.00027465043,0.00034621896,0.00003757771,0.00001104365,0.00058999774],"genre_scores_gemma":[0.1790196,0.00005298025,0.82055235,0.000051016577,0.00006394816,0.000012026224,0.00010653816,0.000019864927,0.000121648474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983481,0.0005944135,0.00048343267,0.00018540437,0.00023054397,0.0001581005],"domain_scores_gemma":[0.98723483,0.011816785,0.00036087356,0.00018573512,0.0003563163,0.000045440578],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026469214,0.00013614226,0.00040970146,0.000067205736,0.000068967165,0.000005770266,0.00007562056,0.00007930933,0.000031197047],"category_scores_gemma":[0.029603956,0.00008726688,0.0000065365384,0.00033626772,0.00012537872,0.00004928417,0.00003206069,0.00018034234,4.6372435e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009853811,0.00002878208,0.000053118147,0.00058112975,0.000014013458,9.357449e-7,0.0004908599,0.00027447453,0.019566244,0.9751158,0.00044711694,0.0033290242],"study_design_scores_gemma":[0.000632805,0.00033488296,0.00021979769,0.0005873305,0.000093414856,0.0000010173426,0.000081882165,0.09988285,0.0032007322,0.89458907,0.00029571468,0.00008048373],"about_ca_topic_score_codex":0.00011796927,"about_ca_topic_score_gemma":0.000004710186,"teacher_disagreement_score":0.17678095,"about_ca_system_score_codex":0.00004574764,"about_ca_system_score_gemma":0.00004279589,"threshold_uncertainty_score":0.9785701},"labels":[],"label_agreement":null},{"id":"W2166148588","doi":"10.1002/sim.3828","title":"A nonstationary Markov transition model for computing the relative risk of dementia before death","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute on Aging; Robert J. Kleberg, Jr. and Helen C. Kleberg Foundation","keywords":"Dementia; Markov model; Transition (genetics); Markov chain; Computer science; Econometrics; Medicine; Mathematics; Disease; Machine learning; Internal medicine","score_opus":0.043449792847671864,"score_gpt":0.3868699731316014,"score_spread":0.3434201802839295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166148588","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045967777,0.000018350125,0.99282765,0.00034808542,0.00015451663,0.00047701216,0.001030651,0.000012107265,0.0005348281],"genre_scores_gemma":[0.2786275,0.00000809348,0.7211683,0.000054885488,0.000056294728,0.0000181723,0.000040286013,0.0000120374225,0.00001442028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987199,0.0001346471,0.000544314,0.00017017916,0.00024984032,0.00018111941],"domain_scores_gemma":[0.9913841,0.007898885,0.00026258454,0.0001885488,0.00022043337,0.00004548569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015774337,0.00012448736,0.00029218692,0.00007116129,0.00011423714,0.000004830874,0.00013074416,0.00006572334,0.00007871016],"category_scores_gemma":[0.007042003,0.00008135314,0.000028619612,0.00012295938,0.00029809427,0.000034722663,0.000017975768,0.00036354546,5.005532e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043038985,0.000048938953,0.0009463544,0.00013210782,0.000052578125,0.0000025314173,0.0050767544,0.000035535093,0.000092706134,0.9590753,0.00077110867,0.033723053],"study_design_scores_gemma":[0.000451366,0.00009832753,0.0031864913,0.00007343437,0.00015580232,0.0000018574649,0.00017405783,0.41872156,0.000009060709,0.5770767,0.000005304861,0.000046064713],"about_ca_topic_score_codex":0.000048897575,"about_ca_topic_score_gemma":0.00023905929,"teacher_disagreement_score":0.41868603,"about_ca_system_score_codex":0.000014519741,"about_ca_system_score_gemma":0.00005645515,"threshold_uncertainty_score":0.8430444},"labels":[],"label_agreement":null},{"id":"W2166900700","doi":"10.1002/sim.5970","title":"Age‐period‐cohort models using smoothing splines: a generalized additive model approach","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Smoothing; Smoothing spline; Identifiability; Box spline; Computer science; Mathematics; Applied mathematics; Dependency (UML); Econometrics; Cohort effect; Mathematical optimization; Cohort; Statistics; Artificial intelligence","score_opus":0.05897676816116972,"score_gpt":0.35134934774278764,"score_spread":0.29237257958161794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166900700","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060710177,0.00025663088,0.8773786,0.0004176263,0.0005439952,0.0016851539,0.00014513465,0.0001067088,0.058756],"genre_scores_gemma":[0.6866851,0.00066711043,0.31027016,0.00068832916,0.00047417387,0.00019719724,0.0001460856,0.000042405605,0.0008294708],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967791,0.00030310047,0.00065361237,0.0005149592,0.0010955385,0.00065373443],"domain_scores_gemma":[0.99880946,0.00014364702,0.00021380906,0.00036045013,0.00028283248,0.00018979624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016584246,0.00026675238,0.0005447464,0.00033401125,0.00041267305,0.00009544942,0.00041162962,0.0001332257,0.00026875993],"category_scores_gemma":[0.0004022913,0.00024473495,0.000052401876,0.0006194455,0.0010756754,0.00036830624,0.00009235667,0.00033855267,0.000009424217],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031642754,0.00025734978,0.012726144,0.00016583897,0.0002042401,0.00014928452,0.063029066,0.12290292,0.000081764745,0.77173114,0.021113439,0.0076071816],"study_design_scores_gemma":[0.00072354265,0.000022542332,0.0030037244,0.000088368164,0.00008337822,9.874283e-7,0.0070455046,0.8095023,9.861909e-7,0.17886224,0.00038016046,0.00028628114],"about_ca_topic_score_codex":0.026480665,"about_ca_topic_score_gemma":0.0018925666,"teacher_disagreement_score":0.6865994,"about_ca_system_score_codex":0.00023225014,"about_ca_system_score_gemma":0.00015059789,"threshold_uncertainty_score":0.99800014},"labels":[],"label_agreement":null},{"id":"W2167706052","doi":"10.1002/sim.4015","title":"Interval estimation for the area under the receiver operating characteristic curve when data are subject to error","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada","keywords":"Receiver operating characteristic; Confidence interval; Statistics; Variance (accounting); Computer science; Observational error; Interval (graph theory); Function (biology); Mathematics; Algorithm","score_opus":0.6034699099556665,"score_gpt":0.5849274279005707,"score_spread":0.018542482055095788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167706052","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00322415,0.000017163544,0.97768635,0.012267271,0.0027207062,0.001702955,0.0021800355,0.000039760398,0.00016161407],"genre_scores_gemma":[0.061387938,0.00001322971,0.935059,0.0019881933,0.000950856,0.00020805949,0.00011800563,0.000056912577,0.00021780322],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99670094,0.0005980328,0.0012313762,0.00054083654,0.0005403432,0.0003884703],"domain_scores_gemma":[0.8621573,0.13539508,0.0004306802,0.0015880729,0.00029968948,0.00012922165],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010716652,0.00026575057,0.00069508335,0.000074402145,0.0002437709,0.000073873874,0.0012646929,0.00013059254,0.0007086526],"category_scores_gemma":[0.37864628,0.00014107849,0.000035056008,0.00021632662,0.0004929796,0.00007501252,0.00035201534,0.00087191194,0.000021656697],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005127595,0.0003784597,0.0014254849,0.0006115377,0.00029735712,0.000042327512,0.0048748204,0.00011632599,0.0008134583,0.5970887,0.26244983,0.13138895],"study_design_scores_gemma":[0.0013283944,0.00023582696,0.011644579,0.00040146764,0.00027912867,0.0000093704775,0.0010982848,0.12808423,0.00002669049,0.85503066,0.001636464,0.00022489767],"about_ca_topic_score_codex":0.0001206143,"about_ca_topic_score_gemma":0.0011937126,"teacher_disagreement_score":0.3679296,"about_ca_system_score_codex":0.000052764484,"about_ca_system_score_gemma":0.00007934837,"threshold_uncertainty_score":0.7759249},"labels":[],"label_agreement":null},{"id":"W2168082315","doi":"10.1002/sim.6020","title":"Marginal structural models for skewed outcomes: identifying causal relationships in health care utilization","year":2013,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de Santé Publique du Québec; Sante Montreal; McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Negative binomial distribution; Causal inference; Generalized linear model; Marginal structural model; Inference; Marginal model; Emergency department; Propensity score matching; Econometrics; Poisson distribution; Psychological intervention; Statistics; Baseline (sea); Generalized linear mixed model; Robustness (evolution); Count data; Medicine; Computer science; Mathematics","score_opus":0.3202027902674543,"score_gpt":0.4968382609247534,"score_spread":0.17663547065729912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168082315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009649905,0.0001702917,0.98759514,0.0005866741,0.00016574057,0.0013811509,0.00011392846,0.00009764819,0.00023950031],"genre_scores_gemma":[0.5277285,0.000035917896,0.47160044,0.00010679208,0.000032083295,0.00016668993,0.00021140653,0.00002671609,0.00009147762],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980972,0.00015239742,0.0008445088,0.0002529872,0.00030706782,0.00034588654],"domain_scores_gemma":[0.997546,0.0016021187,0.00026841363,0.0002528939,0.00024760643,0.000082925144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066669617,0.00019053655,0.00045579122,0.0002926702,0.00010081748,0.000016394628,0.00014233297,0.000091909125,0.000095473675],"category_scores_gemma":[0.0032569796,0.00016440329,0.000016753283,0.00024320824,0.00010394723,0.0002495614,0.00003377474,0.0003575879,0.0000024959982],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015659944,0.000017833983,0.010550478,0.00077702035,0.000008670732,0.0000053109197,0.0078046443,0.00034609364,0.000031449268,0.97321385,0.0027683768,0.004460609],"study_design_scores_gemma":[0.0008571559,0.00011817773,0.013633044,0.00036312168,0.0000100200195,0.000002314722,0.0036229189,0.034715746,0.000015655689,0.9464912,0.000025891262,0.00014479707],"about_ca_topic_score_codex":0.0005518526,"about_ca_topic_score_gemma":0.0018506531,"teacher_disagreement_score":0.51807857,"about_ca_system_score_codex":0.00041839486,"about_ca_system_score_gemma":0.00009192228,"threshold_uncertainty_score":0.67041713},"labels":[],"label_agreement":null},{"id":"W2168158999","doi":"10.1002/sim.3356","title":"Two‐stage design for dose‐finding that accounts for both efficacy and safety","year":2008,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"Stage (stratigraphy); Computer science; Statistics; Econometrics; Mathematics; Biology","score_opus":0.34766234225019504,"score_gpt":0.5197216396087865,"score_spread":0.17205929735859143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168158999","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054853815,0.00040600367,0.9904995,0.00020267218,0.0005897167,0.0014799676,0.0003226353,0.000020932112,0.0009931651],"genre_scores_gemma":[0.14294478,0.00012857337,0.8547421,0.0003415147,0.0001540768,0.00008471996,0.000024249466,0.000030108666,0.0015498715],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970332,0.00029022762,0.0007582186,0.0005775079,0.0009267807,0.00041410985],"domain_scores_gemma":[0.97842014,0.020642078,0.00026068927,0.00035765045,0.00016109436,0.00015835777],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0071358774,0.00022096992,0.0005895959,0.0003118919,0.00028410877,0.000044937693,0.0004151735,0.00007513678,0.00020356917],"category_scores_gemma":[0.013864223,0.00016267218,0.00003125757,0.00035931286,0.00049276365,0.00016332834,0.00007675168,0.00014147756,0.000008149917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0139706135,0.00074481004,0.028584423,0.00030428966,0.00019560521,0.00043894377,0.029368056,0.004161478,0.038716946,0.26820025,0.21339303,0.40192157],"study_design_scores_gemma":[0.086433426,0.009719736,0.11798875,0.00078356185,0.00023546649,0.00021976286,0.013810877,0.23003048,0.015088809,0.43333387,0.08980787,0.0025474033],"about_ca_topic_score_codex":0.000040578096,"about_ca_topic_score_gemma":0.000011653987,"teacher_disagreement_score":0.39937416,"about_ca_system_score_codex":0.00009646926,"about_ca_system_score_gemma":0.00009244185,"threshold_uncertainty_score":0.9944424},"labels":[],"label_agreement":null},{"id":"W2168289333","doi":"10.1002/sim.2554","title":"A comparison of methods for the analysis of recurrent health outcome data with environmental covariates","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Population and Public Health; University of Ottawa; University of Windsor","funders":"","keywords":"Covariate; Estimator; Statistics; Poisson distribution; Outcome (game theory); Crossover; Generalized linear model; Poisson regression; Constant (computer programming); Mathematics; Econometrics; Computer science; Medicine; Artificial intelligence","score_opus":0.20357769507771378,"score_gpt":0.5379687256093808,"score_spread":0.334391030531667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168289333","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029160704,0.0006648079,0.9920796,0.002498671,0.000060269565,0.00040782872,0.0012911642,0.0000031380068,0.00007844418],"genre_scores_gemma":[0.40243086,0.00021467553,0.5960095,0.0004962798,0.000022785664,0.00001027009,0.0007824637,0.000007736332,0.00002547179],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998387,0.00019067348,0.00077061023,0.00019137788,0.00026512129,0.00019521349],"domain_scores_gemma":[0.9972629,0.0017728562,0.00046712236,0.00043490512,0.0000046420323,0.000057601384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027990232,0.00008865679,0.00055213924,0.000098268094,0.00006376771,0.0000016760632,0.0002825102,0.000024127947,0.00036597045],"category_scores_gemma":[0.00029064133,0.000052462317,0.0000147970495,0.00049765536,0.00050721224,0.00003084642,0.000089916124,0.00010574051,8.615052e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021630175,0.00047331466,0.8313572,0.00021754619,0.00017718713,4.731217e-7,0.0028653012,0.0076533398,0.000081871054,0.005029315,0.030140646,0.121787556],"study_design_scores_gemma":[0.0006911161,0.00062794116,0.7773468,0.00003161623,0.00038790726,3.2068812e-7,0.00094071304,0.21225247,0.000018818044,0.0014327825,0.0062012337,0.00006827912],"about_ca_topic_score_codex":0.0064186053,"about_ca_topic_score_gemma":0.0045068515,"teacher_disagreement_score":0.39951476,"about_ca_system_score_codex":0.00008366376,"about_ca_system_score_gemma":0.000018943932,"threshold_uncertainty_score":0.9703054},"labels":[],"label_agreement":null},{"id":"W2169111089","doi":"10.1002/sim.3694","title":"Bayesian analysis of a matched case–control study with expert prior information on both the misclassification of exposure and the exposure–disease association","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Alberta; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alberta Heritage Foundation for Medical Research","keywords":"Dirichlet distribution; Multinomial distribution; Bayesian probability; Statistics; Association (psychology); Prior probability; Disease; Computer science; A priori and a posteriori; Econometrics; Medicine; Mathematics; Internal medicine; Psychology","score_opus":0.02053217632805361,"score_gpt":0.33561580847107075,"score_spread":0.31508363214301716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169111089","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044826705,0.00004269389,0.9480812,0.004429178,0.000020230298,0.0013996933,0.0009066858,0.00001806172,0.00027555364],"genre_scores_gemma":[0.9950667,0.000015202303,0.0043439157,0.0003399825,0.000015407966,0.00010019682,0.00009313178,0.0000046139585,0.000020827152],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99818844,0.00028480554,0.00075490255,0.0001271865,0.00053121534,0.00011342949],"domain_scores_gemma":[0.99547654,0.0031668253,0.00064786343,0.00035161202,0.00029731408,0.000059826307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012959049,0.00012472208,0.00041192406,0.0001633418,0.00010987071,0.000016135751,0.00010518167,0.000038354807,0.000070377246],"category_scores_gemma":[0.0036813112,0.000066385845,0.000027822656,0.0006623068,0.0001915176,0.000058768415,0.000006504462,0.00012724024,6.414718e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009085812,0.0006159298,0.0084337685,0.00006518224,0.00050529366,0.000011444529,0.011909247,0.0005046179,0.000024679797,0.96340996,0.0013996866,0.012211584],"study_design_scores_gemma":[0.008303103,0.00083876686,0.83283806,0.00009079941,0.0027187786,0.000004988463,0.009845358,0.096122645,0.000010319034,0.049039584,0.000033029995,0.00015457609],"about_ca_topic_score_codex":0.00006544849,"about_ca_topic_score_gemma":0.00010275725,"teacher_disagreement_score":0.95024,"about_ca_system_score_codex":0.000070934344,"about_ca_system_score_gemma":0.00004162446,"threshold_uncertainty_score":0.4407139},"labels":[],"label_agreement":null},{"id":"W2169258359","doi":"10.1002/sim.2981","title":"Characterizing the functional MRI response using Tikhonov regularization","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Tikhonov regularization; Regularization (linguistics); Computer science; Artificial intelligence; Mathematics; Inverse problem; Mathematical analysis","score_opus":0.04072377874506911,"score_gpt":0.37546591047137423,"score_spread":0.3347421317263051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169258359","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017382173,0.00006311008,0.97681755,0.00430835,0.00012803455,0.00035690636,0.000018900828,0.000045891502,0.00087909296],"genre_scores_gemma":[0.4637457,0.0001414832,0.5292993,0.0034946399,0.0008582723,0.00003374313,0.0003310266,0.00004756533,0.0020482282],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990285,0.000032468437,0.00033625006,0.00016518643,0.00025146888,0.00018613647],"domain_scores_gemma":[0.99904513,0.00040962928,0.000105390995,0.0002534675,0.00012215639,0.00006424482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012287708,0.0000947378,0.00016256371,0.0001352399,0.000111559406,0.0000040094014,0.000054061948,0.000054847576,0.00012801902],"category_scores_gemma":[0.0005130641,0.000065673106,0.0000132738,0.00035720418,0.00019050724,0.00003214149,0.000021773696,0.00022986099,0.0000047774515],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039420817,0.00026980595,0.00870525,0.00010325661,0.000033387445,0.00026425233,0.0019645367,0.00038993728,0.62660116,0.3036174,0.012875867,0.04123307],"study_design_scores_gemma":[0.0049908706,0.00094766606,0.6962357,0.0010578017,0.0002910092,0.00066989195,0.0023833732,0.03117935,0.01562544,0.07719691,0.16887069,0.0005512922],"about_ca_topic_score_codex":0.000019376293,"about_ca_topic_score_gemma":0.0000098475975,"teacher_disagreement_score":0.68753046,"about_ca_system_score_codex":0.00013498339,"about_ca_system_score_gemma":0.00006164275,"threshold_uncertainty_score":0.26780716},"labels":[],"label_agreement":null},{"id":"W2169425545","doi":"10.1002/sim.6276","title":"The use of bootstrapping when using propensity‐score matching without replacement: a simulation study","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":278,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Health Services and Policy Research; University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Bootstrapping (finance); Statistics; Resampling; Standard error; Matching (statistics); Confidence interval; Sample size determination; Standard deviation; Sampling distribution; Observational study; Econometrics; Mathematics","score_opus":0.38854138632668395,"score_gpt":0.46673056535998564,"score_spread":0.07818917903330169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169425545","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31987023,0.0000061196915,0.67930335,0.000026313342,0.000048531776,0.0006330695,0.000004784818,0.0000396364,0.00006794722],"genre_scores_gemma":[0.7771273,0.000005420867,0.22270605,0.000033700395,0.000040195144,0.000011784634,0.000004000333,0.000021405865,0.00005013562],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982763,0.00024544442,0.00066654215,0.00019718845,0.0004172755,0.00019727722],"domain_scores_gemma":[0.995978,0.0029356012,0.0004056042,0.00044436674,0.00020079683,0.00003562573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001554607,0.00014870871,0.00037340203,0.00009781491,0.000114230155,0.000020143661,0.00014278518,0.000037873004,0.000014553941],"category_scores_gemma":[0.0053917686,0.00009968238,0.000010903054,0.00012532446,0.0001730461,0.00011642481,0.0000767536,0.00022750636,3.8824962e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010276241,0.0010832993,0.26446727,0.0013212413,0.00031423292,0.00006763865,0.054051206,0.058833282,0.01238253,0.5664105,0.0016546133,0.038386587],"study_design_scores_gemma":[0.0010021781,0.00071802764,0.0042902287,0.00088823575,0.000103881386,0.0000036604122,0.0012680774,0.18751277,0.00018580774,0.8036195,0.00021564313,0.00019194983],"about_ca_topic_score_codex":0.00023055822,"about_ca_topic_score_gemma":0.0002849462,"teacher_disagreement_score":0.45725706,"about_ca_system_score_codex":0.00007613562,"about_ca_system_score_gemma":0.000025302415,"threshold_uncertainty_score":0.64548403},"labels":[],"label_agreement":null},{"id":"W2169649310","doi":"10.1002/sim.2892","title":"Accelerated failure time models with covariates subject to measurement error","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Observational error; Estimator; Econometrics; Statistics; Proportional hazards model; Extrapolation; Computer science; Errors-in-variables models; Accelerated failure time model; Data set; Mathematics","score_opus":0.12878516186870306,"score_gpt":0.39882542307849034,"score_spread":0.2700402612097873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169649310","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011878365,0.000022232176,0.9931136,0.00057443645,0.00009783909,0.0005111055,0.00009747078,0.00006150147,0.004333973],"genre_scores_gemma":[0.091285795,0.0000032359417,0.9081151,0.00029471118,0.00009863002,0.000021346166,0.000017512944,0.00003747645,0.00012619846],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974536,0.00013272083,0.0006311961,0.00035808716,0.0009183015,0.00050612655],"domain_scores_gemma":[0.9970579,0.0017088254,0.0001278046,0.0003253008,0.00052528805,0.00025488785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030652683,0.00026308032,0.0005650531,0.00022530396,0.00006599605,0.000020839163,0.00021695413,0.00008566383,0.0008185664],"category_scores_gemma":[0.0044540623,0.00018302657,0.000012824523,0.00058533286,0.00015172531,0.00004998131,0.00003962724,0.00029150269,0.0000367142],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003305671,0.00014163615,0.00041134466,0.00015809946,0.00006043034,0.00027155335,0.0017304306,0.000029236946,0.0013643631,0.96371126,0.019926095,0.011864963],"study_design_scores_gemma":[0.001434079,0.0007872775,0.0019993002,0.0005583479,0.000087857086,0.000016630029,0.0003899251,0.007960874,0.00040129374,0.985764,0.0002702371,0.00033014355],"about_ca_topic_score_codex":0.00015506004,"about_ca_topic_score_gemma":0.0006871249,"teacher_disagreement_score":0.09009796,"about_ca_system_score_codex":0.00016239264,"about_ca_system_score_gemma":0.00010650049,"threshold_uncertainty_score":0.8962728},"labels":[],"label_agreement":null},{"id":"W2169900945","doi":"10.1002/sim.2733","title":"Accounting for expected attrition in the planning of community intervention trials","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University; Ottawa Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Attrition; Sample size determination; Statistics; Randomization; Cohort; Demography; Population; Cluster randomised controlled trial; Sample (material); Cluster (spacecraft); Psychological intervention; Standard error; Econometrics; Medicine; Randomized controlled trial; Mathematics; Computer science; Environmental health; Surgery","score_opus":0.39420011802620225,"score_gpt":0.5438528487911372,"score_spread":0.1496527307649349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169900945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14355926,0.000075915865,0.8551678,0.00010663973,0.000050440984,0.0005597048,0.0000679499,0.000028700204,0.0003835768],"genre_scores_gemma":[0.8455027,0.0000053996814,0.1541224,0.000031711577,0.00007039058,0.00009633086,0.00015187403,0.0000093746185,0.000009870144],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99816483,0.00058521517,0.0008919515,0.00005978696,0.00017734092,0.000120859026],"domain_scores_gemma":[0.9895637,0.009725047,0.0004154799,0.00017729643,0.0001119944,0.0000064803044],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062972116,0.000083283994,0.00039515604,0.00015990608,0.0000422721,0.0000050918898,0.00015342719,0.00005010928,0.000019036574],"category_scores_gemma":[0.01397869,0.00005925373,0.000023478418,0.00018909073,0.00009816399,0.000050365914,0.000019137473,0.0002591323,1.1175649e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021972426,0.00067850976,0.005497543,0.0013447335,0.000019698453,0.000012059555,0.011205573,0.000053754156,0.00952422,0.9361147,0.022615956,0.012713517],"study_design_scores_gemma":[0.00121013,0.00021468951,0.0061284713,0.00085966353,0.000025200165,0.0000016039638,0.005225524,0.00032619148,0.001157003,0.9847501,0.000045080644,0.000056337663],"about_ca_topic_score_codex":0.00051953073,"about_ca_topic_score_gemma":0.00048177174,"teacher_disagreement_score":0.7019434,"about_ca_system_score_codex":0.000052684318,"about_ca_system_score_gemma":0.000007925539,"threshold_uncertainty_score":0.994327},"labels":[],"label_agreement":null},{"id":"W2169987255","doi":"10.1002/sim.6619","title":"Inference on cancer screening exam accuracy using population‐level administrative data","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University; Public Health Ontario; University of Toronto; Cancer Care Ontario","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Cancer Society; Cancer Care Ontario","keywords":"Covariate; Markov chain Monte Carlo; Bayesian probability; Statistics; Breast cancer; Inference; Computer science; Population; Cancer registry; Posterior probability; Bayesian inference; Disease; Econometrics; Cancer; Medicine; Artificial intelligence; Mathematics; Internal medicine; Environmental health","score_opus":0.7226447359803319,"score_gpt":0.5708361636674781,"score_spread":0.15180857231285372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169987255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3547337,0.0024016416,0.6205755,0.0054256287,0.0019286445,0.0016631276,0.0034115573,0.00015442893,0.0097058145],"genre_scores_gemma":[0.90445244,0.00010028866,0.09241164,0.001464733,0.0005460178,0.000010895567,0.00083748787,0.000021186483,0.00015529736],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977208,0.000081245176,0.0005255859,0.00044780632,0.0008891794,0.00033540986],"domain_scores_gemma":[0.9979547,0.00058612076,0.00021062868,0.00062766235,0.00031153148,0.0003093506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008355977,0.00021286252,0.00045494174,0.0001705992,0.000071322545,0.00001749323,0.000294007,0.000081874445,0.00022258142],"category_scores_gemma":[0.007819927,0.0001756865,0.000012163297,0.00039647205,0.00016209773,0.00021317716,0.00012896518,0.0004165266,0.000008587445],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019172758,0.00018640919,0.78086495,0.00021312838,0.00017734252,0.0013564301,0.0034380648,0.0035572597,0.0003202676,0.015922084,0.047253642,0.14479314],"study_design_scores_gemma":[0.009063498,0.0023181096,0.8217886,0.006647633,0.00048641767,0.00014797585,0.005891374,0.13861977,0.00011558272,0.0084474,0.005720058,0.00075356365],"about_ca_topic_score_codex":0.011109583,"about_ca_topic_score_gemma":0.0020543803,"teacher_disagreement_score":0.54971874,"about_ca_system_score_codex":0.00028347375,"about_ca_system_score_gemma":0.0005139622,"threshold_uncertainty_score":0.99547553},"labels":[],"label_agreement":null},{"id":"W2170153043","doi":"10.1002/sim.4244","title":"Assessing noninferiority in a three‐arm trial using the Bayesian approach","year":2011,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Bayesian probability; Parametric statistics; Computer science; Placebo; Statistical hypothesis testing; Clinical trial; Statistics; Machine learning; Medicine; Artificial intelligence; Mathematics; Alternative medicine","score_opus":0.7454022113351202,"score_gpt":0.6058046770374885,"score_spread":0.13959753429763166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170153043","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012049367,0.000036318786,0.9748003,0.000098284174,0.0012095025,0.0011858476,0.00004106398,0.000036008547,0.010543318],"genre_scores_gemma":[0.15726788,0.000012595818,0.8419321,0.00012787036,0.00055224384,0.000048577615,0.0000028218578,0.000040524006,0.000015346719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99509656,0.0014756193,0.0017564923,0.00047682767,0.000673212,0.00052125857],"domain_scores_gemma":[0.9667728,0.031901173,0.00043347233,0.0006492859,0.000110777684,0.00013252499],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0113572255,0.00028577045,0.0011018243,0.00018440121,0.00010200026,0.00003628254,0.00047101662,0.00021142833,0.0006029268],"category_scores_gemma":[0.10871535,0.00018718031,0.0000507309,0.00060600997,0.0008020882,0.00008906551,0.0001334576,0.0009935489,0.0000030295237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032732387,0.0011286394,0.0062622232,0.0003101361,0.000061056184,0.00023004357,0.0035393464,0.000007898449,0.00003997599,0.9655089,0.00044763598,0.019190924],"study_design_scores_gemma":[0.01644186,0.00032656203,0.003984314,0.00026622924,0.00011874118,0.000009462376,0.0008360042,0.019323386,0.000012195122,0.9584605,0.000012767568,0.0002079734],"about_ca_topic_score_codex":0.0006360086,"about_ca_topic_score_gemma":0.00031104055,"teacher_disagreement_score":0.14521852,"about_ca_system_score_codex":0.00015459646,"about_ca_system_score_gemma":0.0001676223,"threshold_uncertainty_score":0.8987923},"labels":[],"label_agreement":null},{"id":"W2170987805","doi":"10.1002/sim.5378","title":"Variable selection in semiparametric cure models based on penalized likelihood, with application to breast cancer clinical trials","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Science Foundation","keywords":"Breast cancer; Feature selection; Proportional hazards model; Computer science; Logistic regression; Model selection; Semiparametric regression; Accelerated failure time model; Clinical trial; Cure rate; Variable (mathematics); Statistics; Regression analysis; Econometrics; Cancer; Medicine; Mathematics; Artificial intelligence; Machine learning; Internal medicine","score_opus":0.17296653638878065,"score_gpt":0.5074455559875256,"score_spread":0.33447901959874493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170987805","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012451268,0.000045353092,0.99557877,0.000510448,0.00019882241,0.00095513806,0.0003190072,0.000029578692,0.0011177666],"genre_scores_gemma":[0.19373603,0.000034904264,0.80466074,0.0007715717,0.00036030274,0.00033978318,0.000024094537,0.000032475866,0.00004011367],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962293,0.0011819534,0.0012460838,0.00035586115,0.0005337683,0.00045303116],"domain_scores_gemma":[0.9845295,0.014388519,0.000332812,0.00024127329,0.00022586425,0.0002820207],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010725451,0.00022167072,0.0009654367,0.00037950292,0.000038255996,0.000012003106,0.00014197885,0.00014684077,0.00057011127],"category_scores_gemma":[0.01572842,0.00015392725,0.000022165614,0.0013833486,0.0000837188,0.000058861922,0.00001945944,0.0004919335,0.00000982688],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001634478,0.0011073702,0.02462848,0.00031783857,0.000045130153,0.00000577039,0.0005364522,0.0038211462,0.00014220247,0.85259235,0.012319563,0.10284922],"study_design_scores_gemma":[0.003687467,0.00057621143,0.016081441,0.00067373074,0.00014938744,0.000005071417,0.00008674696,0.44582695,0.00001955657,0.5323249,0.000293435,0.00027511016],"about_ca_topic_score_codex":0.000818727,"about_ca_topic_score_gemma":0.00019229474,"teacher_disagreement_score":0.44200578,"about_ca_system_score_codex":0.00020250065,"about_ca_system_score_gemma":0.00017009792,"threshold_uncertainty_score":0.99256253},"labels":[],"label_agreement":null},{"id":"W2171380912","doi":"10.1002/sim.969","title":"A model for foetal growth and diagnosis of intrauterine growth restriction","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Birth, Development, and Health","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gestational age; Intrauterine growth restriction; Fetal growth; Residual; Pregnancy; Fetus; Growth model; Birth weight; Covariance; Obstetrics; Growth curve (statistics); Medicine; Statistics; Mathematics; Biology; Algorithm","score_opus":0.04616301159606384,"score_gpt":0.34571737856377327,"score_spread":0.29955436696770943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171380912","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33816934,0.0006480324,0.64787966,0.008191257,0.00039503307,0.0012952819,0.00025498032,0.000048450926,0.0031179767],"genre_scores_gemma":[0.6477566,0.29212335,0.05930103,0.0005059018,0.00012946919,0.000062638544,0.00009549296,0.000015114871,0.00001041203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988502,0.000018126604,0.00046437775,0.00020903043,0.00022823726,0.00022998676],"domain_scores_gemma":[0.99922466,0.00024785704,0.00011369506,0.0001067141,0.00016269165,0.0001444053],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003176141,0.00012547377,0.0004088813,0.00023573932,0.00004094662,0.0000023053879,0.000042566036,0.000073066985,0.000025022202],"category_scores_gemma":[0.00083660526,0.000103834616,0.000013776572,0.00022439603,0.0001543103,0.000034411845,0.000019162784,0.00015304476,4.9600635e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004304288,0.00016864612,0.16057141,0.001377258,0.00003638908,0.000053828397,0.0013436909,0.0000029264334,0.00032506796,0.8230207,0.007350242,0.0053194365],"study_design_scores_gemma":[0.007110923,0.0016167696,0.19936629,0.00061530556,0.00014934644,0.00006549974,0.00026487827,0.04057164,0.00021920554,0.7497073,0.00013674925,0.00017609946],"about_ca_topic_score_codex":0.00031254333,"about_ca_topic_score_gemma":0.00017338658,"teacher_disagreement_score":0.58857864,"about_ca_system_score_codex":0.000052701063,"about_ca_system_score_gemma":0.0001193014,"threshold_uncertainty_score":0.4234253},"labels":[],"label_agreement":null},{"id":"W2171999085","doi":"10.1002/sim.1336","title":"Improved up‐and‐down designs for phase I trials","year":2002,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":130,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Estimator; Isotonic regression; Maximum tolerated dose; Sample size determination; Statistics; Computer science; Zero (linguistics); Sample (material); Mathematics; Clinical trial; Medicine","score_opus":0.7965506191140403,"score_gpt":0.6475064483633985,"score_spread":0.1490441707506418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171999085","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002763792,0.00024970382,0.9931621,0.0011842052,0.0014823986,0.0017561952,0.00104739,0.000059370217,0.0007822768],"genre_scores_gemma":[0.0056630843,0.00034616466,0.9912041,0.00048162165,0.00083941396,0.00023426297,0.000013384733,0.000055291675,0.0011627175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99521136,0.001205024,0.0022849808,0.00047366018,0.00036543582,0.00045951275],"domain_scores_gemma":[0.81319976,0.18561591,0.0004563694,0.00035709701,0.0001626865,0.00020814083],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014277091,0.00028075988,0.0018013542,0.00015979641,0.000080157544,0.000020259573,0.0002179133,0.0001897138,0.0021168026],"category_scores_gemma":[0.57650644,0.00020863337,0.00006975028,0.00021215586,0.0004817281,0.000034042572,0.00004880371,0.00033497633,0.000009129459],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005009795,0.00037768626,0.00001842247,0.00045768303,0.00010694723,0.000029096858,0.00076170824,2.6271553e-7,0.0015197501,0.5930954,0.1197172,0.28341487],"study_design_scores_gemma":[0.015437975,0.001487097,0.000013004166,0.00018428054,0.00032734248,0.000005238471,0.00013702043,0.016758392,0.00025746663,0.9626739,0.002487878,0.0002304091],"about_ca_topic_score_codex":0.000016284224,"about_ca_topic_score_gemma":0.000014141954,"teacher_disagreement_score":0.5622294,"about_ca_system_score_codex":0.000054692322,"about_ca_system_score_gemma":0.000025614772,"threshold_uncertainty_score":0.9987954},"labels":[],"label_agreement":null},{"id":"W2172095467","doi":"10.1002/sim.2663","title":"On estimating treatment effects under non‐compliance in randomized clinical trials: are intent‐to‐treat or instrumental variables analyses perfect solutions?","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Food and Drug Administration; Ministère de l'Économie, de la Science et de l'Innovation - Québec","keywords":"Instrumental variable; Estimator; Protocol (science); Econometrics; Estimation; Randomized controlled trial; Average treatment effect; Statistics; Computer science; Medicine; Mathematics; Economics; Surgery; Alternative medicine","score_opus":0.5017714453619644,"score_gpt":0.591935176063639,"score_spread":0.0901637307016746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172095467","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031147245,0.00009740709,0.9650119,0.0002904267,0.0003438477,0.0022050925,0.00008671127,0.00011621967,0.0007011769],"genre_scores_gemma":[0.4517892,0.00008745116,0.5470322,0.0001839411,0.00019760887,0.0004320075,0.00006623706,0.00003693964,0.00017445204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9944526,0.0020564443,0.0021571596,0.0004943327,0.00038178364,0.00045766396],"domain_scores_gemma":[0.94734854,0.051411115,0.0006509892,0.00038297745,0.00009537979,0.00011100581],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0067505664,0.0004092062,0.0027133485,0.00042472003,0.000087416076,0.00002254219,0.0001778023,0.00013663886,0.00012989627],"category_scores_gemma":[0.056348767,0.0002559892,0.00011686396,0.00045744685,0.0003654315,0.0000679058,0.000064358544,0.00036025976,0.000012210398],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0572212,0.0058817146,0.004442085,0.0019396357,0.00064353045,0.0012738425,0.0016379405,0.009429422,0.002923042,0.7617544,0.02137059,0.13148262],"study_design_scores_gemma":[0.0835676,0.001779157,0.0007648306,0.0047692396,0.00043532663,0.000011853082,0.00044024407,0.07647093,0.00074826996,0.8306346,0.00000737662,0.0003705877],"about_ca_topic_score_codex":0.00085094635,"about_ca_topic_score_gemma":0.0009769944,"teacher_disagreement_score":0.42064196,"about_ca_system_score_codex":0.0006811937,"about_ca_system_score_gemma":0.00008908296,"threshold_uncertainty_score":0.9999892},"labels":[],"label_agreement":null},{"id":"W2178694734","doi":"10.1002/sim.6803","title":"Bias due to composite reference standards in diagnostic accuracy studies","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"Canadian Institutes of Health Research; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Statistics; Computer science; Data mining; Mathematics","score_opus":0.7570256031050993,"score_gpt":0.6499421358043234,"score_spread":0.10708346730077589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2178694734","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03802528,0.0011459389,0.9425698,0.0047663385,0.0030863695,0.0021316065,0.0023619046,0.00013871762,0.005774039],"genre_scores_gemma":[0.06618645,0.00039643236,0.9319358,0.00084365025,0.00033380036,0.00011674285,0.000013032691,0.00004618796,0.00012790709],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99421614,0.0013998272,0.0020158188,0.00051630015,0.0013336814,0.00051823864],"domain_scores_gemma":[0.7136772,0.28425038,0.00031720015,0.00054640934,0.0008174087,0.00039137216],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013741654,0.00031209292,0.0015622356,0.00031215028,0.00003852756,0.000018770786,0.00040063844,0.00013115369,0.00017213197],"category_scores_gemma":[0.88697225,0.00024208793,0.000022075972,0.00073658297,0.00046762408,0.000051011993,0.00024541354,0.0006196013,0.000046559464],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007405202,0.00047971052,0.008545923,0.00078351994,0.00012660844,0.002725663,0.0092445295,0.00008659883,0.000055972247,0.6948063,0.21547674,0.066927955],"study_design_scores_gemma":[0.003050093,0.0007318479,0.0041535688,0.0014658945,0.00007277916,0.000010961595,0.0014261091,0.00016947425,0.00004359719,0.9858708,0.0027308092,0.00027407147],"about_ca_topic_score_codex":0.0001708585,"about_ca_topic_score_gemma":0.00071375805,"teacher_disagreement_score":0.8732306,"about_ca_system_score_codex":0.0004985101,"about_ca_system_score_gemma":0.00023667731,"threshold_uncertainty_score":0.9872059},"labels":[],"label_agreement":null},{"id":"W2180200726","doi":"10.1002/sim.6808","title":"2 × 2 Tables: a note on Campbell's recommendation","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Essar Steel Algoma (Canada); St. Joseph's Care Group; NOSM University; Lakehead University","funders":"","keywords":"Statistic; Pearson's chi-squared test; Statistics; Chi-square test; Pearson product-moment correlation coefficient; Mathematics; Mean squared error; Test statistic; Statistical hypothesis testing","score_opus":0.20562809733330492,"score_gpt":0.5035358811184455,"score_spread":0.2979077837851406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180200726","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00011590869,0.000019470725,0.97800714,0.0008010097,0.00048576173,0.00024464217,0.00021596243,0.000035470308,0.02007462],"genre_scores_gemma":[0.011479933,0.000040269242,0.9866185,0.0006695636,0.0002097415,0.000029147846,0.00011773602,0.00003160938,0.0008034896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99852616,0.0001777815,0.00045090108,0.00025382443,0.00032396702,0.00026738405],"domain_scores_gemma":[0.99639946,0.0029094133,0.0001289156,0.00023070117,0.00014303093,0.00018849391],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013014931,0.00015989516,0.00036542572,0.00012042328,0.000036629834,0.0000062207237,0.00010076325,0.00006389648,0.00032092517],"category_scores_gemma":[0.013310493,0.00012526945,0.000010306745,0.00018127175,0.00012025977,0.00004375725,0.000029144096,0.00027149305,0.00002681629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000076954064,0.00008626523,0.000021256403,0.000053974374,0.0000061811884,0.000038826398,0.0010813117,0.000053522017,0.000029063594,0.81113946,0.047242202,0.14017096],"study_design_scores_gemma":[0.0012924932,0.00042576154,0.00002393193,0.00012971897,0.000021586684,0.000004234613,0.00036509833,0.009855367,0.000030948093,0.96103096,0.026681907,0.00013796361],"about_ca_topic_score_codex":0.00008014551,"about_ca_topic_score_gemma":0.00011750209,"teacher_disagreement_score":0.14989151,"about_ca_system_score_codex":0.0001548433,"about_ca_system_score_gemma":0.000056234443,"threshold_uncertainty_score":0.99500084},"labels":[],"label_agreement":null},{"id":"W2211643105","doi":"10.1002/1097-0258(20000915/30)19:17/18<2437::aid-sim580>3.0.co;2-j","title":"Methodological issues in the development of theCanadian Cancer Incidence Atlas","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Saskatchewan Cancer Agency; Cancer Care Ontario; McMaster University; BC Cancer Agency; Health Canada","funders":"","keywords":"Poisson regression; Confidence interval; Statistics; Poisson distribution; Atlas (anatomy); Demography; Cancer registry; Population; Correlation; Census; Cartography; Geography; Medicine; Mathematics","score_opus":0.12879942501858482,"score_gpt":0.4343008291345362,"score_spread":0.3055014041159514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2211643105","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97806126,0.0017547638,0.007907934,0.0043560034,0.0001649372,0.0003964926,0.000016620941,0.000015920969,0.0073260595],"genre_scores_gemma":[0.95107335,0.00041398473,0.04750347,0.00043491414,0.000118823846,0.000045504643,0.000011475927,0.000006006622,0.0003924695],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988289,0.0001701944,0.00036752285,0.00015196114,0.0003169356,0.00016452152],"domain_scores_gemma":[0.9990897,0.00062374864,0.000050170325,0.00013674372,0.000047848425,0.000051792318],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001147354,0.00008672241,0.0003027447,0.00011552248,0.00003075125,0.0000021951134,0.000097599535,0.0000506509,0.0012090716],"category_scores_gemma":[0.000771579,0.00005205992,0.0000110060355,0.00038230256,0.00015366702,0.000014267988,0.000008605729,0.00024353717,0.0000045391066],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019542957,0.00009240131,0.048176754,0.00016546366,0.000030044752,0.00022882393,0.03234723,0.00011069195,0.00062061707,0.0010756063,0.0047704056,0.9104277],"study_design_scores_gemma":[0.0019459585,0.0017420184,0.961866,0.0009561921,0.000052501942,0.000064342574,0.0030061349,0.0013303561,0.0009432539,0.00446034,0.023467015,0.00016585355],"about_ca_topic_score_codex":0.009382514,"about_ca_topic_score_gemma":0.045345657,"teacher_disagreement_score":0.91368926,"about_ca_system_score_codex":0.00011687244,"about_ca_system_score_gemma":0.0001712219,"threshold_uncertainty_score":0.99970394},"labels":[],"label_agreement":null},{"id":"W2226573656","doi":"10.1002/sim.6845","title":"A comparison of change point models with application to longitudinal lung function measurements in children with cystic fibrosis","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Cystic Fibrosis Research Advances","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Cystic Fibrosis Foundation","keywords":"Cystic fibrosis; Random effects model; Lung function; Demography; Population; Lung disease; Time point; Medicine; Pulmonary function testing; Lung; Statistics; Mathematics; Internal medicine; Physics","score_opus":0.07383692652110245,"score_gpt":0.37621764581914946,"score_spread":0.302380719298047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2226573656","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16778813,0.00034938872,0.82907945,0.00076459063,0.000026969807,0.0017580119,0.00008817475,0.000019295789,0.0001259656],"genre_scores_gemma":[0.9533828,0.000030422725,0.046015352,0.00006215776,0.00007887624,0.00030012833,0.0000826732,0.000026423857,0.000021147585],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9977315,0.00005823399,0.00047281472,0.000381119,0.0010229314,0.00033338985],"domain_scores_gemma":[0.9988117,0.00022416444,0.00015322883,0.00033231574,0.000298962,0.0001795789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048269474,0.00018514389,0.00055573793,0.00043584747,0.00002526163,0.000003720153,0.00010048933,0.000042853673,0.000051683535],"category_scores_gemma":[0.0004105459,0.00010616874,0.000010305905,0.00062931824,0.00020911757,0.00014940523,0.000032565582,0.00015494213,0.0000052887685],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0037224372,0.00024781976,0.96544003,0.0002407339,0.00007142364,0.000005442186,0.00050237525,0.00039625293,0.009170807,0.0010969957,0.00037021044,0.01873547],"study_design_scores_gemma":[0.005731156,0.004447378,0.97952825,0.0029039935,0.00013451207,0.000019440866,0.0001432552,0.0055124904,0.00061970775,0.00078276335,0.000027246128,0.00014982282],"about_ca_topic_score_codex":0.0006511848,"about_ca_topic_score_gemma":0.0011010965,"teacher_disagreement_score":0.7855947,"about_ca_system_score_codex":0.0003105907,"about_ca_system_score_gemma":0.000078070596,"threshold_uncertainty_score":0.43294358},"labels":[],"label_agreement":null},{"id":"W2242307981","doi":"10.1002/sim.6818","title":"The missing cause approach to unmeasured confounding in pharmacoepidemiology","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Bruyère; University of Ottawa; McGill University; Ottawa Public Health; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Confounding; Pharmacoepidemiology; Spurious relationship; Statistics; Observational study; Missing data; Econometrics; Medicine; Instrumental variable; Average treatment effect; Variance (accounting); Mathematics; Propensity score matching; Medical prescription","score_opus":0.2739779879782596,"score_gpt":0.5135117581148383,"score_spread":0.23953377013657867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2242307981","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020755273,0.00010243481,0.989832,0.003354589,0.00021039299,0.00043269497,0.000017935521,0.0000765446,0.0038978711],"genre_scores_gemma":[0.37677744,0.00036675102,0.62099206,0.00094307953,0.0001999915,0.00014635213,0.000006484426,0.000048355916,0.0005194894],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980557,0.00034951261,0.0006622752,0.00025606962,0.00024534558,0.00043110567],"domain_scores_gemma":[0.990234,0.009102212,0.00015110247,0.00031815784,0.00008889699,0.00010562343],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033512677,0.00016621586,0.00041151507,0.00016109514,0.000068085916,0.000006415013,0.00026218905,0.00007031633,0.000032307405],"category_scores_gemma":[0.025932798,0.00008845701,0.000010857695,0.0002510189,0.0003294943,0.00004693848,0.000059001395,0.0002625448,0.000006692476],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005569847,0.0000438532,0.0022511801,0.000051820658,0.000014909547,0.00003613747,0.0009805382,0.0000056078757,0.00978998,0.9317049,0.017100181,0.03796519],"study_design_scores_gemma":[0.0008402463,0.000089972535,0.0007938003,0.0004395252,0.000017108518,0.0000123329255,0.00030421442,0.00053284166,0.0006782817,0.992992,0.0031397492,0.00015993681],"about_ca_topic_score_codex":0.000057418165,"about_ca_topic_score_gemma":0.00014501835,"teacher_disagreement_score":0.3747019,"about_ca_system_score_codex":0.00026696385,"about_ca_system_score_gemma":0.000047428613,"threshold_uncertainty_score":0.9822722},"labels":[],"label_agreement":null},{"id":"W2268470382","doi":"10.1002/sim.6812","title":"Methods to adjust for misclassification in the quantiles for the generalized linear model with measurement error in continuous exposures","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical and numerical algorithms","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Environmental Health Sciences; National Institute of Mental Health; National Cancer Institute; National Heart, Lung, and Blood Institute","keywords":"Quantile; Statistics; Generalized linear model; Observational error; Linear model; Econometrics; Computer science; Mathematics","score_opus":0.37371390643757485,"score_gpt":0.4800672643962178,"score_spread":0.10635335795864292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2268470382","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008936068,0.00024261946,0.9909485,0.005610923,0.00012564154,0.0019219909,0.00017440763,0.000012348086,0.00006996046],"genre_scores_gemma":[0.026464414,0.000016131467,0.97146016,0.00063163426,0.00012639888,0.0011365789,0.000030044997,0.000026720161,0.00010792435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980153,0.0002670428,0.00060973736,0.00025702667,0.00054691243,0.0003039952],"domain_scores_gemma":[0.99405396,0.005104766,0.00012336254,0.00028172447,0.0003502247,0.00008593645],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004631691,0.00017710196,0.00045248005,0.000095803174,0.000048576083,0.00001249539,0.00027965294,0.000053208685,0.000006617382],"category_scores_gemma":[0.011205348,0.00008482479,0.00002055659,0.0002894638,0.00014807229,0.000019444955,0.000019152292,0.00016908882,8.564411e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022568041,0.00070068246,0.00047763722,0.00042978,0.000077660006,0.000019850853,0.018884495,0.0052912054,0.00058140064,0.7976337,0.07531321,0.098333545],"study_design_scores_gemma":[0.0037121729,0.00072672655,0.0008466261,0.00013990815,0.0000906192,0.0000023759985,0.0038578447,0.6236019,0.00007404883,0.36388525,0.0029039746,0.00015851622],"about_ca_topic_score_codex":0.00027733983,"about_ca_topic_score_gemma":0.0015922365,"teacher_disagreement_score":0.61831075,"about_ca_system_score_codex":0.000097880824,"about_ca_system_score_gemma":0.0000887007,"threshold_uncertainty_score":0.9971237},"labels":[],"label_agreement":null},{"id":"W2280398094","doi":"10.1002/sim.6904","title":"A latent process model for forecasting multiple time series in environmental public health surveillance","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"BC Centre for Disease Control; University of British Columbia; McGill University; McGill University Health Centre","funders":"Canadian Institutes of Health Research; Health Canada; British Columbia Centre for Disease Control; University of British Columbia","keywords":"Univariate; Bivariate analysis; Environmental epidemiology; Laplace's method; Computer science; Bayesian probability; Outcome (game theory); Econometrics; Statistics; Multivariate statistics; Environmental health; Machine learning; Mathematics; Medicine; Artificial intelligence","score_opus":0.09898888752182965,"score_gpt":0.34136953729052444,"score_spread":0.24238064976869478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2280398094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18317457,0.00013552765,0.76320344,0.04962095,0.00016331207,0.0017680373,0.0014624706,0.00005143517,0.00042025628],"genre_scores_gemma":[0.96567154,0.0002225411,0.031627193,0.0017594786,0.000041930576,0.00007149716,0.000071025264,0.000019850593,0.00051493064],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829656,0.00008385404,0.00048178792,0.0002743474,0.0002957093,0.0005677625],"domain_scores_gemma":[0.9990337,0.00045545903,0.000156023,0.00013503777,0.000005090412,0.00021467441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001668411,0.00012930708,0.0002805853,0.000080825484,0.00008962662,0.0000047453423,0.00012831116,0.00004635288,0.00035726567],"category_scores_gemma":[0.0011155208,0.00009112733,0.000009277951,0.00016199339,0.00030123536,0.0001641073,0.000049740203,0.000096301825,0.000030830393],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002981439,0.00035499735,0.7920362,0.00044041773,0.00000866527,0.000019984527,0.0147269,0.00480431,0.0004431507,0.00094725407,0.026487658,0.15943235],"study_design_scores_gemma":[0.0035208473,0.00064442254,0.1726542,0.0002277095,0.0000018923215,0.000008625708,0.0003717994,0.80208766,0.000012951889,0.018068152,0.0021346533,0.0002670717],"about_ca_topic_score_codex":0.00023089114,"about_ca_topic_score_gemma":0.002917981,"teacher_disagreement_score":0.79728335,"about_ca_system_score_codex":0.00041551987,"about_ca_system_score_gemma":0.00005448758,"threshold_uncertainty_score":0.39118087},"labels":[],"label_agreement":null},{"id":"W2288666460","doi":"10.1002/sim.6907","title":"Inference on treatment‐covariate interaction based on a nonparametric measure of treatment effects and censored survival data","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Covariate; Nonparametric statistics; Statistics; Inference; Parametric statistics; Econometrics; Data set; Confidence interval; Survival analysis; Estimator; Computer science; Mathematics; Artificial intelligence","score_opus":0.5481851531616271,"score_gpt":0.5778375376790365,"score_spread":0.02965238451740937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288666460","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011058366,0.000034210407,0.9813624,0.0006687237,0.0013727809,0.0012727033,0.0024296823,0.000048151953,0.0017529791],"genre_scores_gemma":[0.49102765,0.00024518286,0.5082875,0.00006867598,0.0001683354,0.000045455596,0.000034652207,0.000034030763,0.000088511864],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966197,0.0011970584,0.0008746329,0.00055812544,0.00049128203,0.00025918882],"domain_scores_gemma":[0.8190564,0.17956339,0.000325547,0.00083398586,0.00010037208,0.00012031684],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019544917,0.00031298652,0.0010924243,0.0003131701,0.00003137634,0.000008266367,0.00021520363,0.00012387944,0.00015500262],"category_scores_gemma":[0.21538246,0.0001643672,0.000029143906,0.0003226184,0.0002897661,0.00003701994,0.000046213183,0.00014022597,0.00001074837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003553564,0.002095566,0.0047688284,0.00050437433,0.00032854392,0.00015219649,0.00035743273,0.000021765089,0.0012046297,0.22821668,0.00096356455,0.7578329],"study_design_scores_gemma":[0.03199575,0.029831987,0.018061666,0.0046318234,0.000996268,0.0000035954931,0.00009840541,0.020194316,0.0021474743,0.89105046,0.00041770499,0.0005705388],"about_ca_topic_score_codex":0.0001505655,"about_ca_topic_score_gemma":0.000083853374,"teacher_disagreement_score":0.75726235,"about_ca_system_score_codex":0.0003564418,"about_ca_system_score_gemma":0.00009619048,"threshold_uncertainty_score":0.7912267},"labels":[],"label_agreement":null},{"id":"W2300752603","doi":"10.1002/sim.6909","title":"Type‐II generalized family‐wise error rate formulas with application to sample size determination","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Type I and type II errors; Sample size determination; False discovery rate; Null hypothesis; Statistical power; Word error rate; Statistics; Multiple comparisons problem; Statistical hypothesis testing; Computer science; Mathematics; Nominal level; Algorithm; Artificial intelligence; Confidence interval","score_opus":0.30340492714075973,"score_gpt":0.5395663056930371,"score_spread":0.23616137855227737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2300752603","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01839591,0.000009295434,0.97771376,0.001487116,0.00038874685,0.0010268359,0.0003892387,0.000069728216,0.0005193797],"genre_scores_gemma":[0.048715185,0.000041356892,0.9493572,0.00080654747,0.00030048031,0.00016820058,0.000009137397,0.00005373085,0.00054815185],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972021,0.00044310823,0.0010056983,0.00046854795,0.0005073348,0.00037321445],"domain_scores_gemma":[0.92752725,0.07105046,0.00029711178,0.0005468799,0.00036614964,0.00021215148],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0025374936,0.00024863216,0.0007043993,0.00012679964,0.000082254446,0.000009387872,0.0002576237,0.00012177166,0.00045801155],"category_scores_gemma":[0.21488649,0.0001469484,0.000022326802,0.00044025728,0.00024079646,0.000050526185,0.00008585716,0.00015870635,0.000040540057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019722306,0.00026258916,0.00080179574,0.00023859787,0.000058772726,0.000043305077,0.00066737656,0.000009896432,0.016458342,0.64916945,0.016136426,0.31418124],"study_design_scores_gemma":[0.0039038423,0.0012995276,0.0031087247,0.0003187944,0.000102009806,0.0000027160518,0.000055026,0.0012714452,0.0005051743,0.9870271,0.002147274,0.00025836623],"about_ca_topic_score_codex":0.00008033211,"about_ca_topic_score_gemma":0.00016447311,"teacher_disagreement_score":0.33785766,"about_ca_system_score_codex":0.00015157738,"about_ca_system_score_gemma":0.00007119902,"threshold_uncertainty_score":0.7917268},"labels":[],"label_agreement":null},{"id":"W2304400665","doi":"10.1002/sim.7278","title":"Estimating cross‐validatory predictive <i>p</i>‐values with integrated importance sampling for disease mapping models","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saskatchewan Health Authority; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Posterior probability; Markov chain Monte Carlo; Markov chain; Sampling (signal processing); Bayesian probability; Cross-validation; Pattern recognition (psychology)","score_opus":0.18728641016175812,"score_gpt":0.46136737297218855,"score_spread":0.27408096281043043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2304400665","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012052746,0.000079633806,0.9847129,0.00013772046,0.00034367794,0.0006694364,0.0010188232,0.000061564184,0.000923484],"genre_scores_gemma":[0.16863906,0.000012251204,0.8306977,0.000097327415,0.0002168313,0.00013806028,0.000064629094,0.000044121996,0.00008997892],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99790376,0.00008373466,0.00069598743,0.00046998909,0.00042070632,0.0004258266],"domain_scores_gemma":[0.9943277,0.0037591085,0.0005461516,0.00068913406,0.0004487283,0.00022914619],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014912137,0.000282921,0.0005800165,0.0000920535,0.00044966355,0.00010062503,0.00039846636,0.000067393994,0.0000605038],"category_scores_gemma":[0.02430166,0.00020722409,0.000025444093,0.00008357667,0.00080833485,0.00017907341,0.00007687325,0.00031729147,9.831335e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065137335,0.00014358964,0.029641343,0.0015250345,0.00010920479,0.0001364575,0.0027393505,0.0017438793,0.00008656593,0.9379742,0.0021912034,0.023057774],"study_design_scores_gemma":[0.0009468138,0.00014462264,0.007015398,0.0010846091,0.000059669506,0.0000018516483,0.00024303231,0.38848567,0.000008468679,0.6018233,0.00002253396,0.00016406471],"about_ca_topic_score_codex":0.00009250577,"about_ca_topic_score_gemma":0.000034739947,"teacher_disagreement_score":0.3867418,"about_ca_system_score_codex":0.00009942921,"about_ca_system_score_gemma":0.00017174182,"threshold_uncertainty_score":0.98391706},"labels":[],"label_agreement":null},{"id":"W2343906356","doi":"10.1002/sim.6969","title":"Handling incomplete correlated continuous and binary outcomes in meta‐analysis of individual participant data","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; U.S. Food and Drug Administration; Hamilton Health Sciences Foundation","keywords":"Binary data; Meta-analysis; Computer science; Binary number; Statistics; Mathematics; Medicine; Internal medicine","score_opus":0.8426618781836268,"score_gpt":0.5676160556797044,"score_spread":0.2750458225039224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2343906356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5990916,0.0202429,0.36395094,0.006079987,0.0006741418,0.0018583176,0.0073093255,0.000012449313,0.0007803478],"genre_scores_gemma":[0.9875089,0.00014773913,0.011436582,0.00015677213,0.000011722858,0.0000140932525,0.000103556325,0.0000074496006,0.00061318424],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9831855,0.0043591163,0.00824481,0.0008176665,0.0031334492,0.00025940526],"domain_scores_gemma":[0.97115606,0.022777291,0.0028415981,0.0027295689,0.00037485728,0.000120648736],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0911598,0.00023914788,0.0076297927,0.0014176846,0.000033958357,0.0000587729,0.0014667533,0.00006152693,0.004695919],"category_scores_gemma":[0.07647911,0.000088582994,0.00028596062,0.0022669786,0.00031497033,0.0001235562,0.00041684989,0.0001300077,0.000036345882],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030659,0.00014734472,0.87941235,0.00007459478,0.08128835,0.00012978424,0.0034492924,0.00018936666,0.00015931796,0.0076751662,0.011281636,0.016162144],"study_design_scores_gemma":[0.0017165355,0.00019734906,0.6877024,0.00013181157,0.23311915,0.00000402634,0.0020742682,0.05890519,0.0000031754132,0.014132658,0.0017272,0.00028623838],"about_ca_topic_score_codex":0.00021851335,"about_ca_topic_score_gemma":0.0014372146,"teacher_disagreement_score":0.3884173,"about_ca_system_score_codex":0.000009812615,"about_ca_system_score_gemma":0.000038903683,"threshold_uncertainty_score":0.9962139},"labels":[],"label_agreement":null},{"id":"W2345136754","doi":"10.1002/sim.6955","title":"Linear models of coregionalization for multivariate lattice data: a general framework for coregionalized multivariate CAR models","year":2016,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate statistics; Univariate; Autoregressive model; Covariance; Bayesian probability; Computer science; Multivariate analysis; Gaussian; Conditional independence; Multivariate normal distribution; Econometrics; Statistics; Mathematics; Artificial intelligence; Machine learning","score_opus":0.39298559087138896,"score_gpt":0.5257090736074782,"score_spread":0.13272348273608925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2345136754","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.1463127e-8,0.21334065,0.7622342,0.00006070954,0.0005260699,0.002760015,0.021003153,0.000030162075,0.000045017827],"genre_scores_gemma":[4.6722442e-7,0.38984042,0.6069246,0.00004592617,0.00052148924,0.00042803976,0.0020189262,0.00011256504,0.00010758471],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99491143,0.0005303331,0.0023684192,0.0009886083,0.00062601635,0.0005751836],"domain_scores_gemma":[0.9584505,0.037732594,0.0016072736,0.0011960658,0.0008309261,0.00018266671],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00228986,0.00070447364,0.0036488553,0.00031924312,0.000095005285,0.000015087288,0.00093431416,0.0006221768,0.00005916047],"category_scores_gemma":[0.021807143,0.0004787033,0.00018122056,0.00033584895,0.0004567341,0.00014111286,0.00020609036,0.000414929,0.0000018548686],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012246928,0.000101455385,1.5977211e-7,0.022098988,0.00022006698,0.0000067160568,0.00018494304,0.000016257778,6.210634e-7,0.80241257,0.0028217419,0.172014],"study_design_scores_gemma":[0.0016268695,0.00014959562,2.336811e-7,0.026632352,0.0011192677,0.000005514543,0.000011203879,0.25049275,2.0147016e-7,0.6883966,0.031207481,0.0003579525],"about_ca_topic_score_codex":0.00011425454,"about_ca_topic_score_gemma":0.000015401763,"teacher_disagreement_score":0.2504765,"about_ca_system_score_codex":0.00014597477,"about_ca_system_score_gemma":0.0005187771,"threshold_uncertainty_score":0.99976647},"labels":[],"label_agreement":null},{"id":"W2378268168","doi":"10.1002/sim.6979","title":"A flexible parametric approach for estimating continuous‐time inverse probability of treatment and censoring weights","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cancer Care Ontario; Public Health Ontario; University of Toronto","funders":"","keywords":"Inverse probability; Censoring (clinical trials); Marginal structural model; Inverse probability weighting; Parametric statistics; Statistics; Weighting; Event (particle physics); Computer science; Marginal distribution; Proportional hazards model; Confounding; Parametric model; Econometrics; Mathematics; Posterior probability; Medicine; Estimator; Random variable","score_opus":0.13772868312824896,"score_gpt":0.40989090075438367,"score_spread":0.2721622176261347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2378268168","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030613244,0.000030315412,0.96743536,0.00004777326,0.000031314365,0.00097552227,0.00011596638,0.00008133832,0.0006691497],"genre_scores_gemma":[0.044040788,0.00003456295,0.955419,0.000007991401,0.000042598745,0.00015423546,0.000011243853,0.00001938531,0.00027020773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99882144,0.000055402325,0.0005085285,0.00025810758,0.0001309219,0.00022558574],"domain_scores_gemma":[0.99594,0.0033595215,0.00023840241,0.00025632943,0.00014005473,0.00006567089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006184448,0.00016699906,0.0005381357,0.00017004421,0.00003162282,0.0000032962605,0.00007980157,0.00006134546,0.00002568682],"category_scores_gemma":[0.0062149963,0.000099697936,0.000017589546,0.00016964358,0.00031454716,0.000056475816,0.00003068544,0.000058269336,5.738456e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019196831,0.00051968347,0.0075698425,0.0017211791,0.00009150749,0.0000075923517,0.002018473,0.00003412476,0.008836021,0.8458502,0.0013440968,0.13181525],"study_design_scores_gemma":[0.0016457463,0.0010882235,0.00013153793,0.000404662,0.000064017084,0.0000044535755,0.00009328488,0.016926,0.0038904236,0.9755436,0.00006697378,0.0001410766],"about_ca_topic_score_codex":0.00004468844,"about_ca_topic_score_gemma":0.000007684099,"teacher_disagreement_score":0.13167419,"about_ca_system_score_codex":0.00020595247,"about_ca_system_score_gemma":0.000038803595,"threshold_uncertainty_score":0.744038},"labels":[],"label_agreement":null},{"id":"W2400385987","doi":"10.1002/sim.6986","title":"Quantifying the impact of different approaches for handling continuous predictors on the performance of a prognostic model","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":177,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Population Health Research Institute","funders":"Medical Research Council; National Institute for Health and Care Research; Cancer Research UK","keywords":"Computer science; Outcome (game theory); Ignorance; Calibration; Statistics; Econometrics; Machine learning; Mathematics","score_opus":0.6090490742207253,"score_gpt":0.5329850486829449,"score_spread":0.07606402553778036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2400385987","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39533547,0.000024558773,0.6026335,0.00029030695,0.00015506524,0.001030751,0.00041634616,0.000009793811,0.00010421063],"genre_scores_gemma":[0.85115314,0.00007501791,0.14847216,0.000013896793,0.00010366379,0.00011979564,0.0000020229245,0.000025470112,0.000034826167],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997444,0.0004068706,0.001170678,0.00022469567,0.000470792,0.00028301045],"domain_scores_gemma":[0.8604295,0.13844524,0.0005214434,0.0004059188,0.00014896636,0.000048883783],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0043846183,0.00020507547,0.0008513732,0.00006930033,0.000059866994,0.000004519154,0.00035253877,0.00007944301,0.000044545915],"category_scores_gemma":[0.15361683,0.00007045064,0.00008970518,0.000128932,0.00079478533,0.0000163228,0.000053945856,0.00020716648,4.573518e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009997964,0.00045833038,0.035522006,0.0009509864,0.0002925588,0.0000015943046,0.0015936876,0.00044794322,0.0012115198,0.92903996,0.001633613,0.027848015],"study_design_scores_gemma":[0.0021849317,0.0020554964,0.009312034,0.001963553,0.00020674332,8.396643e-7,0.00020923378,0.19864559,0.0009474216,0.784352,0.0000013350508,0.000120810764],"about_ca_topic_score_codex":0.000007620549,"about_ca_topic_score_gemma":0.000006848236,"teacher_disagreement_score":0.4558177,"about_ca_system_score_codex":0.000051110645,"about_ca_system_score_gemma":0.0000644866,"threshold_uncertainty_score":0.8535126},"labels":[],"label_agreement":null},{"id":"W2401995712","doi":"10.1002/sim.6998","title":"Estimating the cumulative mean function for history process with time‐dependent covariates and censoring mechanism","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Censoring (clinical trials); Covariate; Estimator; Inverse probability weighting; Computer science; Inverse probability; Weighting; Statistics; Consistency (knowledge bases); Cumulative distribution function; Econometrics; Mathematics; Probability density function; Artificial intelligence; Medicine; Posterior probability","score_opus":0.07753858154408844,"score_gpt":0.37604131994293466,"score_spread":0.2985027383988462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401995712","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028194808,0.000040496627,0.99558413,0.00028145112,0.00022810181,0.0004406502,0.000073792726,0.000027431945,0.0005044619],"genre_scores_gemma":[0.17598023,0.0000062656027,0.82315385,0.00010585209,0.00014683654,0.00009003512,0.000004662202,0.00002736471,0.00048488282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988517,0.000104508596,0.00032262786,0.00023795929,0.00027683793,0.0002063654],"domain_scores_gemma":[0.9925539,0.0068566743,0.00018102965,0.00015502468,0.0001955592,0.000057849913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012260606,0.00014817652,0.00028277756,0.00005327211,0.0000821874,0.000006602304,0.00008627804,0.000040393483,0.00019954587],"category_scores_gemma":[0.006455253,0.000069779664,0.0000068635877,0.000055900244,0.00023143907,0.000041546,0.000021527701,0.00011213319,0.0000021092103],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001261389,0.000022319351,0.0000642223,0.00020450552,0.00003087356,0.000005484841,0.0026399617,0.000011200171,0.00065701886,0.9761926,0.00051039696,0.019535275],"study_design_scores_gemma":[0.0012022366,0.0005252376,0.00026894096,0.00049543707,0.00010434052,0.0000063929133,0.00034057564,0.04551815,0.00010877294,0.9512588,0.000048547412,0.00012261719],"about_ca_topic_score_codex":0.000033955967,"about_ca_topic_score_gemma":0.00002737078,"teacher_disagreement_score":0.17316075,"about_ca_system_score_codex":0.000115129034,"about_ca_system_score_gemma":0.00004659718,"threshold_uncertainty_score":0.7728007},"labels":[],"label_agreement":null},{"id":"W2407438980","doi":"10.1002/sim.6994","title":"Developing points‐based risk‐scoring systems in the presence of competing risks","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences","keywords":"Event (particle physics); Computer science; Risk assessment; Set (abstract data type); Medicine; Intensive care medicine; Risk analysis (engineering)","score_opus":0.4536856419470451,"score_gpt":0.48069930320661425,"score_spread":0.027013661259569166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407438980","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16572969,0.0028509137,0.7958328,0.030540576,0.0013378435,0.0011803398,0.00079721434,0.000024139783,0.0017064969],"genre_scores_gemma":[0.97560674,0.00029749965,0.022518743,0.0012435123,0.00020390927,0.000068951405,0.00001315499,0.000018131028,0.000029378303],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9946376,0.0008678481,0.0036516811,0.00033999357,0.00016889382,0.00033399876],"domain_scores_gemma":[0.9855996,0.0118545415,0.0020035112,0.00041681612,0.0000715301,0.0000540292],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.033322755,0.00013943487,0.00081117393,0.0003893567,0.00007449064,0.000013881578,0.00031607266,0.00006903819,0.00008188025],"category_scores_gemma":[0.028905716,0.00010698434,0.000020842928,0.0002953649,0.00018579574,0.00010815346,0.000033213433,0.00020462515,0.00007645596],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013656674,0.00003077081,0.47859305,0.00059208897,0.00001456117,0.0000075310163,0.0036102966,0.00061187276,0.000005527536,0.51273847,0.0032849875,0.0004971744],"study_design_scores_gemma":[0.0056928657,0.0002655588,0.7450605,0.0067585367,0.000017645953,0.00001056708,0.01341279,0.07311039,0.000014765117,0.14393437,0.011089332,0.0006326682],"about_ca_topic_score_codex":0.0070503885,"about_ca_topic_score_gemma":0.00078568544,"teacher_disagreement_score":0.80987704,"about_ca_system_score_codex":0.0003931218,"about_ca_system_score_gemma":0.00013044223,"threshold_uncertainty_score":0.9995617},"labels":[],"label_agreement":null},{"id":"W2410992638","doi":"10.1002/sim.6996","title":"Bayesian adjustment for the misclassification in both dependent and independent variables with application to a breast cancer study","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada; American Cancer Society","keywords":"Concordance; Covariate; Logistic regression; Breast cancer; Statistics; Medicine; Econometrics; Internal medicine; Oncology; Cancer; Mathematics","score_opus":0.18434440924207227,"score_gpt":0.501049341478635,"score_spread":0.3167049322365627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2410992638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020234059,0.000053434298,0.9891391,0.004408217,0.00018935,0.0036069548,0.00051021035,0.000016149552,0.000053181542],"genre_scores_gemma":[0.51419073,0.00014691407,0.48218492,0.00026152068,0.0002666405,0.0027791983,0.000002778679,0.000037283895,0.0001299965],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99764645,0.0003350231,0.000791964,0.00046450275,0.00049406965,0.00026796653],"domain_scores_gemma":[0.9711017,0.028018517,0.0002185498,0.000412356,0.00013108602,0.00011780073],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0037114986,0.00018384973,0.00047223998,0.00011483509,0.00005449093,0.000011941926,0.0002104202,0.00006695285,0.00010276844],"category_scores_gemma":[0.010254235,0.0000893518,0.0000094981615,0.00022556944,0.00015927124,0.000026630052,0.000054111137,0.00014509527,0.0000013649264],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017633713,0.0011471894,0.04898826,0.0002906732,0.00017723528,0.000017226428,0.002513377,0.000055249067,0.0008344949,0.35625768,0.0027862617,0.58516896],"study_design_scores_gemma":[0.0075805155,0.0008611238,0.31059578,0.00055799715,0.00026725695,0.00000751572,0.0016737141,0.002483693,0.000024860938,0.6755612,0.00015130095,0.00023503965],"about_ca_topic_score_codex":0.00046429716,"about_ca_topic_score_gemma":0.0041187196,"teacher_disagreement_score":0.58493394,"about_ca_system_score_codex":0.00021992851,"about_ca_system_score_gemma":0.000073198484,"threshold_uncertainty_score":0.9980828},"labels":[],"label_agreement":null},{"id":"W2421687783","doi":"10.1002/sim.7606","title":"A threshold‐free summary index of prediction accuracy for censored time to event data","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Alberta","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Estimator; Event (particle physics); Cutoff; Nonparametric statistics; Inference; Index (typography); Risk assessment; Measure (data warehouse); Ordinal regression","score_opus":0.10933726131374259,"score_gpt":0.44081132255934224,"score_spread":0.33147406124559964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2421687783","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00066090433,0.000029374805,0.9868462,0.00050596904,0.0003038796,0.0007112389,0.008706965,0.000025730496,0.0022097148],"genre_scores_gemma":[0.019841082,0.000022564433,0.978393,0.00025448416,0.00051025854,0.00004478607,0.00036361843,0.00003251403,0.00053764344],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99814755,0.00008122604,0.0007427393,0.00034271978,0.00041507528,0.0002707133],"domain_scores_gemma":[0.9932648,0.0050141467,0.00019362099,0.0010550156,0.0003461699,0.00012624727],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015612595,0.00015468213,0.00046068814,0.00014067013,0.000044469303,0.000006381208,0.0006103993,0.00007450892,0.0009514562],"category_scores_gemma":[0.046878833,0.00012414587,0.00001370053,0.00024348355,0.00029134058,0.00004995557,0.00027256465,0.00013415107,0.000017128983],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036471165,0.00017383415,0.00059792615,0.00039165333,0.00004868911,0.0000075603325,0.00081006833,0.0000021512462,0.001059548,0.3149912,0.6330164,0.048536234],"study_design_scores_gemma":[0.0016895736,0.0012615827,0.0036118638,0.0005980535,0.000091697526,0.0000029604025,0.00011939046,0.07452882,0.00018119224,0.91261923,0.0051428047,0.00015281442],"about_ca_topic_score_codex":0.00006321676,"about_ca_topic_score_gemma":0.00006537264,"teacher_disagreement_score":0.6278736,"about_ca_system_score_codex":0.000043467888,"about_ca_system_score_gemma":0.00007395465,"threshold_uncertainty_score":0.9999618},"labels":[],"label_agreement":null},{"id":"W2466391332","doi":"10.1002/sim.7012","title":"Martingale residual‐based method to control for confounders measured only in a validation sample in time‐to‐event analysis","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Statistics; Residual; Confounding; Computer science; Econometrics; Control chart; Event (particle physics); Sample (material); Sample size determination; Martingale (probability theory); Mathematics; Algorithm; Chromatography","score_opus":0.1189508705834617,"score_gpt":0.47092695879781293,"score_spread":0.3519760882143512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2466391332","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002987596,0.0000052108003,0.99195147,0.0030833385,0.000024731116,0.0013711643,0.0004189697,0.00005618663,0.000101349804],"genre_scores_gemma":[0.16111888,0.000001664468,0.83754647,0.0007338543,0.000031915304,0.00030578807,0.000058087433,0.00002818352,0.00017513099],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99750555,0.00037879977,0.00090642937,0.00036218896,0.000476616,0.00037039135],"domain_scores_gemma":[0.9886385,0.010446747,0.00021399514,0.0003465413,0.00023633885,0.000117843854],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004717727,0.00019256257,0.0007224172,0.0009460287,0.000023714842,0.000010074417,0.00020257487,0.000083148865,0.00035432357],"category_scores_gemma":[0.026184538,0.00014947775,0.00003226524,0.00090110494,0.000059175447,0.00005151264,0.000026729827,0.00012548637,0.000009491867],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005090242,0.0016520254,0.07342194,0.0010422568,0.0008975516,0.00016461371,0.00995247,0.011248651,0.14142866,0.5175306,0.061785195,0.17578575],"study_design_scores_gemma":[0.0057086926,0.0008067351,0.0054316004,0.0008176804,0.000317794,7.858217e-7,0.00025631976,0.010319468,0.006528274,0.9687545,0.00065250456,0.00040567474],"about_ca_topic_score_codex":0.0003929376,"about_ca_topic_score_gemma":0.0032017021,"teacher_disagreement_score":0.45122385,"about_ca_system_score_codex":0.00047709193,"about_ca_system_score_gemma":0.00012672582,"threshold_uncertainty_score":0.98201835},"labels":[],"label_agreement":null},{"id":"W2471145407","doi":"10.1002/sim.7011","title":"Statistical issues related to dietary intake as the response variable in intervention trials","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute; Medical Research Council; National Institutes of Health","keywords":"Reliability (semiconductor); Biomarker; Context (archaeology); Calibration; Observational error; Statistics; Computer science; Intervention (counseling); Clinical trial; Medicine; Mathematics; Internal medicine; Biology","score_opus":0.05277491442254351,"score_gpt":0.41833186008813683,"score_spread":0.3655569456655933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2471145407","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3827965,0.008653616,0.122015305,0.4610493,0.0037868435,0.00623983,0.0030857332,0.00018541016,0.012187486],"genre_scores_gemma":[0.93796086,0.002242999,0.043713078,0.0048485505,0.00055568985,0.000266077,0.00030289785,0.000059587088,0.010050254],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.99734044,0.0006648891,0.0009989175,0.0002751483,0.00043703231,0.00028357666],"domain_scores_gemma":[0.99361753,0.005782272,0.00010453562,0.00023452031,0.00013273623,0.00012839939],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0054129255,0.00015563416,0.00067094277,0.00019529386,0.000052716958,0.0000060526436,0.00009841051,0.00007332298,0.0024145816],"category_scores_gemma":[0.029073086,0.00007830095,0.000031426094,0.0004080545,0.00024836126,0.000029099145,0.0000676703,0.00022296586,0.000118826574],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03475961,0.0010665075,0.022821521,0.00032160737,0.00029910542,0.0015848795,0.0025049646,0.000008285837,0.007847004,0.35170892,0.49063733,0.08644027],"study_design_scores_gemma":[0.016395902,0.00548878,0.4906349,0.004107934,0.00019815104,0.00007455846,0.0021979457,0.00008008661,0.00009414973,0.3567813,0.12367791,0.00026840743],"about_ca_topic_score_codex":0.0008890902,"about_ca_topic_score_gemma":0.00022293047,"teacher_disagreement_score":0.5551644,"about_ca_system_score_codex":0.00017825104,"about_ca_system_score_gemma":0.000056664514,"threshold_uncertainty_score":0.99849737},"labels":[],"label_agreement":null},{"id":"W2516585541","doi":"10.1002/sim.3925","title":"Comments on ‘Some methodological issues in biosurveillance’","year":2011,"lang":"en","type":"letter","venue":"Statistics in Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Canada Research Chairs","keywords":"Biostatistics; Library science; Citation; Computer science; Epidemiology; Medicine","score_opus":0.14166287861213966,"score_gpt":0.42258403642489334,"score_spread":0.2809211578127537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516585541","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001076616,0.0039744074,0.0016736084,0.96366936,0.0037678431,0.0025373574,0.008104964,0.00028632267,0.014909505],"genre_scores_gemma":[0.0019769545,0.0041961307,0.032508295,0.93644977,0.0045831073,0.00015208253,0.01640498,0.00019198631,0.0035366847],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99454457,0.0012676633,0.0012548099,0.0009907378,0.0011097195,0.00083248614],"domain_scores_gemma":[0.9951943,0.0028675343,0.00037978205,0.0012109474,0.00014614066,0.00020127457],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018441423,0.00066505023,0.0023898748,0.00084849744,0.000032437663,0.000009914617,0.00049287383,0.0007774439,0.002112056],"category_scores_gemma":[0.0064353026,0.00051274616,0.000076263466,0.00045248505,0.00065919134,0.00004075664,0.00015168043,0.0033211596,0.00028548168],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037922323,0.00018856868,0.018928982,0.00066409673,0.00008671409,0.0149757285,0.00017882566,6.451551e-7,0.000011625226,0.0010821284,0.95967853,0.003824939],"study_design_scores_gemma":[0.004679311,0.0014490503,0.11050883,0.0024080372,0.00010087783,0.000060990456,0.000045962697,0.000053705982,0.000010122157,0.01752473,0.86256933,0.0005890585],"about_ca_topic_score_codex":0.000759004,"about_ca_topic_score_gemma":0.0001451086,"teacher_disagreement_score":0.0971092,"about_ca_system_score_codex":0.00034790306,"about_ca_system_score_gemma":0.00012650983,"threshold_uncertainty_score":0.99973243},"labels":[],"label_agreement":null},{"id":"W2516839318","doi":"10.1002/sim.7079","title":"Estimation for zero-inflated over-dispersed count data model with missing response","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Count data; Negative binomial distribution; Missing data; Poisson distribution; Zero-inflated model; Expectation–maximization algorithm; Statistics; Estimator; Maximum likelihood; Mathematics; Zero (linguistics); Overdispersion; Mixture model; Censoring (clinical trials); Poisson regression; Applied mathematics; Econometrics; Population","score_opus":0.1297925260737236,"score_gpt":0.4484117459185901,"score_spread":0.3186192198448665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2516839318","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014525928,0.000015607236,0.99458754,0.0013789736,0.00008877445,0.00043402048,0.0018190191,0.0000431261,0.00018036172],"genre_scores_gemma":[0.03780314,0.000012918169,0.96165323,0.00014355898,0.0000419548,0.00002515521,0.000093312796,0.00003539794,0.00019131438],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99824953,0.00015891719,0.0005186056,0.00038076637,0.00038968172,0.00030249494],"domain_scores_gemma":[0.9881981,0.010676222,0.0001890258,0.00066203024,0.00015973455,0.000114860784],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020513309,0.00019230646,0.0004056045,0.00011375258,0.00007382392,0.000017692617,0.0002759228,0.00007580713,0.00012870172],"category_scores_gemma":[0.023320466,0.00011073202,0.00000881782,0.0001535709,0.00028946286,0.0001083022,0.000051461502,0.000113216,0.0000030741708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024366297,0.00007979414,0.00012592279,0.0002702065,0.000037402537,0.000048184025,0.0005419213,0.000032332602,0.004600169,0.79037386,0.023762625,0.17769094],"study_design_scores_gemma":[0.0018774944,0.00021772218,0.00034515295,0.00059794076,0.000060430928,0.0000041128314,0.000025608693,0.42321235,0.00006616335,0.5733519,0.00011782337,0.0001233129],"about_ca_topic_score_codex":0.000025465348,"about_ca_topic_score_gemma":0.00003581351,"teacher_disagreement_score":0.42318,"about_ca_system_score_codex":0.000108706954,"about_ca_system_score_gemma":0.00018044304,"threshold_uncertainty_score":0.9849065},"labels":[],"label_agreement":null},{"id":"W2517825627","doi":"10.1002/sim.7074","title":"Trivariate mover‐stayer counting process models for investigating joint damage in psoriatic arthritis","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Spondyloarthritis Studies and Treatments","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Connaught Fund; University of Toronto","keywords":"Psoriatic arthritis; Covariate; Econometrics; Computer science; Joint (building); Feature (linguistics); Event (particle physics); Statistics; Population; Mathematics; Arthritis; Demography; Medicine; Engineering","score_opus":0.044325215750139216,"score_gpt":0.3280716948314211,"score_spread":0.2837464790812819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517825627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8046102,0.0038902683,0.17153925,0.007520285,0.0013661528,0.004387719,0.0011122117,0.00014616849,0.0054277433],"genre_scores_gemma":[0.9737155,0.001056508,0.023631986,0.0005815407,0.0002881357,0.00028821614,0.00008502055,0.000053905136,0.00029922323],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99771994,0.000045228706,0.0008397923,0.0004223817,0.000445972,0.00052666315],"domain_scores_gemma":[0.99860144,0.00057953235,0.00021305658,0.00024105722,0.00021977453,0.00014512167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071165565,0.0002576684,0.0008100097,0.00024503327,0.00008681301,0.000009580651,0.00007520543,0.00008598617,0.00010988141],"category_scores_gemma":[0.0031882597,0.00017783079,0.000033000077,0.00030884668,0.00022008321,0.000120618424,0.00003856879,0.00017634824,0.000006568007],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001915723,0.0022793445,0.16859661,0.004477458,0.0008016409,0.0038889446,0.025716892,0.0007436381,0.007397541,0.2105652,0.017796455,0.5558206],"study_design_scores_gemma":[0.118397884,0.004401141,0.09476959,0.02552265,0.0004026004,0.000116335155,0.0042962506,0.055743016,0.00086560135,0.6932564,0.0011515259,0.0010770052],"about_ca_topic_score_codex":0.00033136818,"about_ca_topic_score_gemma":0.0008247812,"teacher_disagreement_score":0.5547435,"about_ca_system_score_codex":0.00021427633,"about_ca_system_score_gemma":0.00013098367,"threshold_uncertainty_score":0.7251729},"labels":[],"label_agreement":null},{"id":"W2527117517","doi":"10.1002/sim.7137","title":"Choosing appropriate analysis methods for cluster randomised cross‐over trials with a binary outcome","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"National Institute for Health and Care Research; National Institute on Handicapped Research","keywords":"Statistics; Type I and type II errors; Cluster (spacecraft); Correlation; Cluster analysis; Outcome (game theory); Hierarchical clustering; Random effects model; Binary number; Cluster randomised controlled trial; Regression; Mathematics; Computer science; Meta-analysis; Medicine; Randomized controlled trial","score_opus":0.5289356418669582,"score_gpt":0.6556294378967649,"score_spread":0.12669379602980668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527117517","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019569558,0.00006226625,0.99244773,0.00095436355,0.00082617585,0.0026362673,0.0006977358,0.000070506685,0.00034800387],"genre_scores_gemma":[0.0045674164,0.000046004363,0.99297196,0.00045048483,0.00056609896,0.00043134313,0.000016212383,0.00008605609,0.0008644489],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9883741,0.0054650605,0.0040710038,0.0007969505,0.0006546286,0.00063826557],"domain_scores_gemma":[0.6786235,0.3191183,0.0010845591,0.0006545623,0.0003113569,0.0002077444],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.054562595,0.0004513198,0.004115792,0.0005333356,0.00010470161,0.000041726933,0.00039385143,0.00026056299,0.0013740971],"category_scores_gemma":[0.5677755,0.00022358735,0.00030910206,0.0008928839,0.0007849655,0.000076844,0.00009408881,0.00031733577,0.0000061962874],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.09122325,0.00092934584,0.02864546,0.0021631825,0.008640903,0.0001204094,0.0013895737,0.00010917315,0.0040406613,0.39027107,0.012788282,0.4596787],"study_design_scores_gemma":[0.08453471,0.00059839233,0.0029477132,0.00036439134,0.004276812,0.0000024387584,0.000038227085,0.0045860894,0.00016788811,0.9016105,0.00048048748,0.00039236815],"about_ca_topic_score_codex":0.000025968,"about_ca_topic_score_gemma":0.000024548941,"teacher_disagreement_score":0.5132129,"about_ca_system_score_codex":0.00015951849,"about_ca_system_score_gemma":0.00008564524,"threshold_uncertainty_score":0.9995388},"labels":[],"label_agreement":null},{"id":"W2531230258","doi":"10.1002/sim.7148","title":"Understanding the effects of conditional dependence in research studies involving imperfect diagnostic tests","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Econometrics; Covariance; Statistics; Mathematics; Conditional variance; Autoregressive conditional heteroskedasticity","score_opus":0.8096974943345971,"score_gpt":0.6540817036197748,"score_spread":0.15561579071482234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2531230258","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028084295,0.0014916807,0.96477777,0.002155628,0.0012819922,0.0015534216,0.00019057644,0.000029097046,0.00043553085],"genre_scores_gemma":[0.8668494,0.0017504347,0.13098621,0.000073478106,0.0001628103,0.00011079842,0.0000013371008,0.000024002366,0.000041501877],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99422586,0.002738546,0.0011331027,0.00034282668,0.001102967,0.0004567101],"domain_scores_gemma":[0.43293917,0.5663451,0.0001677442,0.0002727597,0.00021680871,0.000058445603],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015056978,0.00017014674,0.0007528466,0.00029051487,0.00009253649,0.00000666086,0.0003442947,0.00009951,0.00012035758],"category_scores_gemma":[0.85910296,0.00008774078,0.000025417647,0.0005985211,0.0022525925,0.000045331828,0.0001797686,0.00054105785,0.0000068467198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005768141,0.00010396706,0.016934957,0.0009880018,0.00005921549,0.00023946009,0.0012544461,0.000001567761,0.0015977304,0.97002447,0.0059924643,0.0027460414],"study_design_scores_gemma":[0.0019515157,0.00050487387,0.015270624,0.004624893,0.00004274158,0.0000043062605,0.001169251,0.00007852559,0.000335363,0.97591096,0.0000050649464,0.00010186823],"about_ca_topic_score_codex":0.0000474845,"about_ca_topic_score_gemma":0.00048080756,"teacher_disagreement_score":0.844046,"about_ca_system_score_codex":0.00043242762,"about_ca_system_score_gemma":0.00010801817,"threshold_uncertainty_score":0.8299771},"labels":[],"label_agreement":null},{"id":"W2545262557","doi":"10.1002/sim.7153","title":"Goodness‐of‐fit test for monotone proportional subdistribution hazards assumptions based on weighted residuals","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Institute of Cancer Research; Institut National Du Cancer","keywords":"Goodness of fit; Mathematics; Monotone polygon; Statistics; Regression analysis; Monte Carlo method; Regression; Proportional hazards model; Applied mathematics","score_opus":0.11451533146660954,"score_gpt":0.4452264803293031,"score_spread":0.3307111488626936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2545262557","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043833065,0.000011938921,0.9894035,0.0014515637,0.00009137557,0.00080341945,0.0033107225,0.000105109924,0.0004390994],"genre_scores_gemma":[0.5963473,0.000032871016,0.40245184,0.000067223235,0.000107089254,0.0003092917,0.00033193207,0.000030281568,0.00032222705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982867,0.00005645357,0.00070634315,0.00024811758,0.0004548991,0.00024748218],"domain_scores_gemma":[0.9936077,0.0051780352,0.00035024693,0.0003349553,0.00045769467,0.00007138254],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008859973,0.00017635089,0.000391523,0.00019555826,0.00005419342,0.0000033942981,0.00013737791,0.00010592101,0.00031416045],"category_scores_gemma":[0.01227056,0.00011726486,0.000026384376,0.00020432427,0.00032935996,0.00005796542,0.000018189809,0.00012479506,0.00000472818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013081847,0.00040276902,0.0037603842,0.00023463923,0.000014078767,0.0000102310105,0.000047364818,0.0000042106158,0.011329438,0.9550577,0.023157384,0.005850992],"study_design_scores_gemma":[0.0016272047,0.00096955895,0.0047143754,0.00090857537,0.000052409374,0.0000018358293,0.000030307041,0.0024143867,0.01857009,0.96993923,0.0005972322,0.00017477527],"about_ca_topic_score_codex":0.000013042643,"about_ca_topic_score_gemma":0.000039499286,"teacher_disagreement_score":0.59196395,"about_ca_system_score_codex":0.00021075738,"about_ca_system_score_gemma":0.00014683073,"threshold_uncertainty_score":0.9960495},"labels":[],"label_agreement":null},{"id":"W2558645513","doi":"10.1002/sim.7189","title":"Estimation of state occupancy probabilities in multistate models with dependent intermittent observation, with application to HIV viral rebounds","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo; Lunenfeld-Tanenbaum Research Institute","funders":"Canadian Institutes of Health Research","keywords":"Smoothing; Context (archaeology); Estimation; Occupancy; Nonparametric statistics; Statistics; Observational study; Econometrics; Inverse probability; Cohort; Human immunodeficiency virus (HIV); Computer science; Medicine; Mathematics; Biology; Virology; Bayesian probability; Economics","score_opus":0.04233541563109173,"score_gpt":0.35590498400765236,"score_spread":0.31356956837656064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2558645513","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05806129,0.000009221828,0.9401592,0.00042078807,0.000031605978,0.0008354219,0.00031673283,0.000022938128,0.00014280422],"genre_scores_gemma":[0.40703,0.000010542608,0.5926358,0.000034633893,0.000010059967,0.00014936506,0.000016062566,0.000016768665,0.00009678215],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979448,0.00013834728,0.0008116107,0.0003485589,0.00048500102,0.0002717387],"domain_scores_gemma":[0.99744314,0.0015600255,0.00027286095,0.00035239107,0.00028020472,0.000091404974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075711455,0.00020680024,0.0004698699,0.00020327776,0.000026031526,0.000010091865,0.00016075718,0.00004095223,0.000027995404],"category_scores_gemma":[0.0015384853,0.00011954893,0.000008302462,0.00028516713,0.0002795123,0.00013368238,0.000034271765,0.00012328576,0.0000026526377],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00066036155,0.00017728626,0.013292679,0.00053701433,0.000021221183,0.000027652583,0.0037859555,0.00091473665,0.00039191724,0.70927006,0.00021631745,0.2707048],"study_design_scores_gemma":[0.001896648,0.00067453086,0.019590842,0.0015878312,0.000027028931,0.000005280299,0.00025077723,0.04708178,0.0002917661,0.92839265,0.000008317131,0.00019257238],"about_ca_topic_score_codex":0.00030555148,"about_ca_topic_score_gemma":0.0013942549,"teacher_disagreement_score":0.34896868,"about_ca_system_score_codex":0.00018713406,"about_ca_system_score_gemma":0.00009497099,"threshold_uncertainty_score":0.4875064},"labels":[],"label_agreement":null},{"id":"W2559470641","doi":"10.1002/sim.7188","title":"The median hazard ratio: a useful measure of variance and general contextual effects in multilevel survival analysis","year":2016,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Medicinska Forskningsrådet; Ontario Ministry of Health and Long-Term Care","keywords":"Multilevel model; Statistics; Proportional hazards model; Hazard ratio; Random effects model; Econometrics; Regression analysis; Cluster (spacecraft); Hierarchical database model; Marginal model; Hazard; Demography; Medicine; Mathematics; Computer science; Confidence interval; Data mining; Internal medicine; Meta-analysis","score_opus":0.032975172927863575,"score_gpt":0.36317528383708475,"score_spread":0.3302001109092212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559470641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3880297,0.0031793425,0.50928116,0.0896927,0.003648611,0.001832048,0.0006191874,0.000043230608,0.0036740312],"genre_scores_gemma":[0.9963529,0.00086089864,0.0017165856,0.00041782978,0.0001594732,0.000016067981,0.000003997688,0.000005177751,0.000467083],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981867,0.0005181897,0.00037899436,0.00015116492,0.00045417994,0.0003107417],"domain_scores_gemma":[0.99435246,0.0051862276,0.00010417122,0.00012545474,0.000107657965,0.00012403031],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025609962,0.000083203246,0.00037185274,0.00010396366,0.00013847335,0.000009778626,0.00013843912,0.00005255843,0.000047169466],"category_scores_gemma":[0.007853881,0.000046045952,0.000016682698,0.00032626427,0.00069369975,0.00004262704,0.00001939509,0.000099252844,9.2894453e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045263187,0.000017664806,0.6338449,0.00006662732,0.00005989287,0.00002092185,0.009436001,0.0000042754127,0.000020930103,0.31544736,0.001216024,0.03982016],"study_design_scores_gemma":[0.0014383638,0.00003791711,0.9841592,0.00015957495,0.000053029762,1.2805704e-7,0.0019518293,0.00088206405,0.000004474882,0.00962679,0.001610872,0.00007577366],"about_ca_topic_score_codex":0.01715785,"about_ca_topic_score_gemma":0.30606976,"teacher_disagreement_score":0.6083232,"about_ca_system_score_codex":0.00007771883,"about_ca_system_score_gemma":0.00019280211,"threshold_uncertainty_score":0.989387},"labels":[],"label_agreement":null},{"id":"W2579663487","doi":"10.1002/sim.7215","title":"Accounting for competing risks in randomized controlled trials: a review and recommendations for improvement","year":2017,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":152,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Randomized controlled trial; Cumulative incidence; Incidence (geometry); Outcome (game theory); Event (particle physics); Survival analysis; Medicine; Relative risk; Actuarial science; Confidence interval; Cohort; Internal medicine","score_opus":0.8315391831852751,"score_gpt":0.7107421776711227,"score_spread":0.1207970055141524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579663487","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.17117835e-8,0.63250124,0.33634475,0.0008899962,0.0008931131,0.02712273,0.0020865402,0.000015228124,0.00014638541],"genre_scores_gemma":[5.440304e-8,0.52876306,0.46131414,0.00017830383,0.00042305427,0.009068119,0.00012806125,0.0000561188,0.00006906847],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9755104,0.008749117,0.01383447,0.0008662472,0.00043373677,0.00060603226],"domain_scores_gemma":[0.41351634,0.5783305,0.0071986145,0.00053257204,0.000321333,0.0001006024],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.20009318,0.0007115617,0.039821856,0.0004235818,0.0001681697,0.000066490495,0.00048389297,0.00038478302,0.00018371595],"category_scores_gemma":[0.94162685,0.00043480695,0.0009916383,0.00015902321,0.0004564319,0.000038227456,0.00013556144,0.00078436785,0.0000012320187],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028343138,0.00006227433,2.230432e-7,0.12129552,0.000597849,0.0000028684817,0.000040538587,1.631567e-8,2.7833277e-8,0.08028455,0.005893324,0.7889885],"study_design_scores_gemma":[0.17983185,0.00014031646,6.98928e-8,0.1361159,0.014998064,0.0000017255388,0.000030642816,0.00026436712,1.8423625e-8,0.5131682,0.1551688,0.000280026],"about_ca_topic_score_codex":0.00006427499,"about_ca_topic_score_gemma":0.00005271671,"teacher_disagreement_score":0.78870845,"about_ca_system_score_codex":0.00017544924,"about_ca_system_score_gemma":0.00029486258,"threshold_uncertainty_score":0.9998104},"labels":[],"label_agreement":null},{"id":"W2582712477","doi":"10.1002/sim.7234","title":"Estimation of parametric failure time distributions based on interval‐censored data with irregular dependent follow‐up","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Truncation (statistics); Statistics; Observational study; Inverse probability; Estimator; Confidence interval; Parametric statistics; Confounding; Mathematics; Interval (graph theory); Event (particle physics); Marginal structural model; Medicine; Computer science; Econometrics; Bayesian probability","score_opus":0.0851947569602915,"score_gpt":0.4119459126927523,"score_spread":0.32675115573246083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2582712477","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035446414,0.000010456082,0.99147123,0.0006097482,0.00015159654,0.000318811,0.0031014814,0.000019946698,0.00077209866],"genre_scores_gemma":[0.4771301,0.000003502844,0.52229816,0.000022561728,0.000025284593,0.000010604439,0.0004113075,0.000013928792,0.00008456332],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809194,0.00016089676,0.00055023277,0.00035047712,0.0006105382,0.00023589429],"domain_scores_gemma":[0.9939949,0.0036274036,0.00044707733,0.0016450897,0.0001799713,0.00010559238],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011266612,0.0001952889,0.00054371875,0.00016608527,0.00013105072,0.000031266703,0.0006869048,0.00007630844,0.00039187647],"category_scores_gemma":[0.036950566,0.0001396946,0.00001590907,0.0001857057,0.00050818204,0.000071096845,0.00012211545,0.00025596828,0.000012522629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040596115,0.0004976295,0.0015214627,0.0005873507,0.00010182079,0.00013257493,0.00028558515,0.0003137405,0.00013648323,0.86811054,0.020532297,0.10737455],"study_design_scores_gemma":[0.0027949668,0.0008406085,0.009163113,0.0010518344,0.00021971334,0.0000051503575,0.00008648739,0.63431716,0.00025446314,0.35096097,0.000084435684,0.00022112088],"about_ca_topic_score_codex":0.00013747468,"about_ca_topic_score_gemma":0.00010842571,"teacher_disagreement_score":0.6340034,"about_ca_system_score_codex":0.000064132415,"about_ca_system_score_gemma":0.00008168673,"threshold_uncertainty_score":0.9711616},"labels":[],"label_agreement":null},{"id":"W2587412035","doi":"10.1002/sim.7242","title":"Quantifying the bias in the estimated treatment effect in randomized trials having interim analyses and a rule for early stopping for futility","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Interim; Interim analysis; Early stopping; Treatment effect; Econometrics; Randomized controlled trial; Statistics; Computer science; Medicine; Mathematics; Law; Artificial intelligence; Surgery","score_opus":0.9144447875273284,"score_gpt":0.717800957027186,"score_spread":0.19664383050014234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587412035","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19711831,0.00034096788,0.7918386,0.0015667952,0.00070251,0.007900658,0.00042158677,0.000019326117,0.00009124239],"genre_scores_gemma":[0.50876683,0.00012528557,0.48964074,0.00008051566,0.0001603824,0.0011808681,0.000009483428,0.000023272056,0.000012585235],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9894207,0.007008751,0.0024321307,0.0004303505,0.00031521704,0.0003928468],"domain_scores_gemma":[0.56111085,0.43741563,0.00081190234,0.0005403384,0.00007726091,0.00004402097],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07987711,0.0003025834,0.0032791113,0.00016885014,0.00025522444,0.000121394805,0.00042246107,0.00012186553,0.0000200861],"category_scores_gemma":[0.7910778,0.00013567935,0.00017139144,0.00012991908,0.000823119,0.000048975056,0.0000701411,0.00027964983,3.8779933e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.15504335,0.0010959095,0.03795758,0.00395612,0.0013182171,0.00017651272,0.023124099,0.000036839225,0.0013952554,0.2928916,0.0017040374,0.4813005],"study_design_scores_gemma":[0.12082438,0.0008141121,0.015339726,0.0013107812,0.0008470198,0.0000018246477,0.0005338018,0.02738866,0.00015502912,0.8326129,0.000013664207,0.00015814461],"about_ca_topic_score_codex":0.0010745818,"about_ca_topic_score_gemma":0.0013422198,"teacher_disagreement_score":0.71120065,"about_ca_system_score_codex":0.000103676124,"about_ca_system_score_gemma":0.000050475704,"threshold_uncertainty_score":0.9474602},"labels":[],"label_agreement":null},{"id":"W2589124067","doi":"10.1002/sim.7251","title":"Binocular sensitivity and specificity of screening tests in cross‐sectional diagnostic studies of paired organs","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Systemic Lupus Erythematosus Research","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Copula (linguistics); Medical diagnosis; Probit model; Computer science; Artificial intelligence; Correlation; Statistics; Mathematics; Optometry; Medicine; Pathology; Econometrics","score_opus":0.09399225451713349,"score_gpt":0.414452970517695,"score_spread":0.3204607160005615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589124067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9941496,0.0013335745,0.003294611,0.0002791783,0.00017126068,0.00043325775,0.00009749925,0.0000075239036,0.00023343955],"genre_scores_gemma":[0.9934168,0.0008212449,0.005500033,0.000013988929,0.00011797386,0.00000864239,0.000015814787,0.000016837897,0.000088704866],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979784,0.00015879767,0.0006888906,0.00027398515,0.0006635289,0.00023641835],"domain_scores_gemma":[0.9943254,0.0043520927,0.00030283263,0.0004453947,0.00048550018,0.00008875873],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002417778,0.00014295195,0.0007808096,0.00028921897,0.00008104774,0.0000075702214,0.000091704125,0.00007900792,0.000031236017],"category_scores_gemma":[0.040374707,0.00011513991,0.000020025835,0.0001561851,0.0015635587,0.00005250821,0.00013118575,0.00026760122,0.000001113254],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001530148,0.00008841129,0.98776287,0.0016072614,0.00007214635,0.0006655627,0.0015679849,0.000012268412,0.0059244162,0.00071314507,0.00019378425,0.001239154],"study_design_scores_gemma":[0.0035580834,0.0002811887,0.9884357,0.0029699502,0.000032236414,0.00045734085,0.0012509375,0.000910818,0.0010030607,0.0010116247,0.000010138764,0.00007895987],"about_ca_topic_score_codex":0.0012161405,"about_ca_topic_score_gemma":0.0014151954,"teacher_disagreement_score":0.03795693,"about_ca_system_score_codex":0.00009385509,"about_ca_system_score_gemma":0.000093770286,"threshold_uncertainty_score":0.96770865},"labels":[],"label_agreement":null},{"id":"W2604188292","doi":"10.1002/sim.7289","title":"Correcting covariate‐dependent measurement error with non‐zero mean","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Biotechnology Research Institute; McGill University","funders":"","keywords":"Covariate; Statistics; Observational error; Extrapolation; Regression; Imputation (statistics); Econometrics; Calibration; Standard error; Mathematics; Computer science; Missing data","score_opus":0.07450561637566287,"score_gpt":0.3482761329384653,"score_spread":0.27377051656280244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604188292","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00022540806,0.00006293228,0.9893817,0.0010431723,0.0012128985,0.00023385473,0.0000069460284,0.00003333508,0.0077997963],"genre_scores_gemma":[0.40224364,0.0000087428125,0.5971445,0.00024740925,0.00009111748,0.000011565094,0.0000016213412,0.0000109995635,0.00024039147],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979015,0.00011465624,0.00033437123,0.00044341266,0.00085587794,0.00035016015],"domain_scores_gemma":[0.99812835,0.00014562496,0.0002830374,0.0010442255,0.0002552414,0.0001434927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028198091,0.0001922254,0.00035840392,0.00010190757,0.00029917576,0.00010512158,0.0009891471,0.000054393506,0.000027670618],"category_scores_gemma":[0.0007565232,0.00013697312,0.000013441244,0.000094838004,0.00016175091,0.0001599963,0.00017868479,0.00031347232,0.000007799933],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000790219,0.00013920642,0.0023433494,0.00012877813,0.00008475825,0.00088461215,0.008792831,0.00010565214,0.00092760794,0.34637877,0.0087878425,0.6313476],"study_design_scores_gemma":[0.012894093,0.0024698323,0.04454056,0.0026213957,0.00021221238,0.00043398503,0.00047874136,0.27560815,0.0025289669,0.654564,0.0019885716,0.0016594598],"about_ca_topic_score_codex":0.00069058244,"about_ca_topic_score_gemma":0.0010345057,"teacher_disagreement_score":0.62968814,"about_ca_system_score_codex":0.00011501832,"about_ca_system_score_gemma":0.00013759293,"threshold_uncertainty_score":0.55856013},"labels":[],"label_agreement":null},{"id":"W2605130264","doi":"10.1002/sim.7298","title":"A comparison of Bayesian and Monte Carlo sensitivity analysis for unmeasured confounding","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Frequentist inference; Bayes' theorem; Prior probability; Sensitivity (control systems); Bayesian probability; Econometrics; Monte Carlo method; Statistics; Confounding; Posterior probability; Contrast (vision); Computer science; Mathematics; Bayesian inference; Artificial intelligence","score_opus":0.1480890340324776,"score_gpt":0.49242406635217234,"score_spread":0.34433503231969476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605130264","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008846886,0.00004511879,0.9896213,0.00019049576,0.00012711188,0.00026228256,0.00037786193,0.000008855813,0.00052013405],"genre_scores_gemma":[0.5418695,0.0000076207702,0.4580462,0.000009780416,0.00003098415,0.0000065537765,0.0000042417355,0.0000068598206,0.000018206236],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985738,0.00015991417,0.00055058504,0.00023616347,0.00026996274,0.00020960109],"domain_scores_gemma":[0.9932566,0.005591143,0.00043925203,0.0004103341,0.0002063163,0.00009634275],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018689963,0.00014298272,0.00096618774,0.00016255822,0.00015891498,0.000025689418,0.00011492157,0.000067046785,0.000030413226],"category_scores_gemma":[0.02021332,0.00011917814,0.000033627985,0.00011293785,0.00052665145,0.00003489977,0.000042641845,0.00014349396,1.5167853e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009200934,0.000077959055,0.20858414,0.00049353915,0.00028165735,0.000026590693,0.0018105016,0.0000073214933,0.00041919173,0.7568853,0.00064405386,0.030677764],"study_design_scores_gemma":[0.0012384426,0.00023876692,0.16064046,0.000251814,0.00093381247,0.0000024211638,0.0006325024,0.17158408,0.0001439234,0.6641193,0.00003832716,0.0001761381],"about_ca_topic_score_codex":0.00055088225,"about_ca_topic_score_gemma":0.0018253641,"teacher_disagreement_score":0.53302264,"about_ca_system_score_codex":0.000028689545,"about_ca_system_score_gemma":0.000028432944,"threshold_uncertainty_score":0.98803985},"labels":[],"label_agreement":null},{"id":"W2609432052","doi":"10.1002/sim.7300","title":"Constructing longitudinal disease progression curves using sparse, short‐term individual data with an application to Alzheimer's disease","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; IXICO; H. Lundbeck A/S; Servier; Eisai; Department of Health, Government of Western Australia; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; Eli Lilly and Company; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; University of Southern California; F. Hoffmann-La Roche; Australian Government; Novartis Pharmaceuticals Corporation; Government of Western Australia; Bristol-Myers Squibb; Alzheimer's Drug Discovery Foundation; Australian Institute of Health and Welfare, Australian Government; Foundation for the National Institutes of Health","keywords":"Term (time); Trajectory; Construct (python library); Regression; Computer science; Longitudinal data; Disease; Regression analysis; Statistics; Algorithm; Mathematics; Applied mathematics; Machine learning; Medicine; Data mining; Pathology","score_opus":0.2365476554198065,"score_gpt":0.48871271654198184,"score_spread":0.25216506112217535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2609432052","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07206267,0.000829499,0.91580254,0.0058798054,0.000097426295,0.0027859479,0.0021437574,0.00018307658,0.00021529829],"genre_scores_gemma":[0.7396867,0.00010528943,0.2573706,0.0003424516,0.00021441076,0.000097316,0.002142973,0.000035248373,0.000004970158],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982585,0.000028506402,0.0003242892,0.0006441359,0.00048455698,0.0002600353],"domain_scores_gemma":[0.99703056,0.00006896299,0.00019808022,0.00198858,0.00013218289,0.00058163976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003015567,0.00019783502,0.0003014004,0.00010977865,0.00029075262,0.00003617883,0.0005288349,0.000024603536,0.000017162043],"category_scores_gemma":[0.0005398644,0.00015595065,0.000009189654,0.00012809121,0.00052196026,0.00022877492,0.0002978724,0.00024060177,0.0000013792652],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038555358,0.00020034431,0.8899533,0.00022309466,0.000028240504,0.0003396603,0.000045043464,0.000016006366,0.00012246717,0.004200578,0.0009883085,0.1034974],"study_design_scores_gemma":[0.0010311397,0.00034868193,0.96578485,0.0036758394,0.0010704044,0.00006846707,0.0000840089,0.024218358,0.000053881995,0.0028384505,0.0005052366,0.00032069045],"about_ca_topic_score_codex":0.000055152992,"about_ca_topic_score_gemma":0.000055460263,"teacher_disagreement_score":0.66762406,"about_ca_system_score_codex":0.000042325286,"about_ca_system_score_gemma":0.00014658805,"threshold_uncertainty_score":0.6359483},"labels":[],"label_agreement":null},{"id":"W2618058430","doi":"10.1002/sim.7336","title":"Intermediate and advanced topics in multilevel logistic regression analysis","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":657,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Vetenskapsrådet; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Marginal model; Logistic regression; Covariate; Multilevel model; Statistics; Hierarchical clustering; Econometrics; Regression analysis; Population; Odds ratio; Regression; Cluster analysis; Computer science; Mathematics; Demography","score_opus":0.1141231773850907,"score_gpt":0.47828034943776926,"score_spread":0.36415717205267856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618058430","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0149254305,0.00007295243,0.9828474,0.00039745646,0.0002591764,0.00017243628,0.00011347763,0.000012588442,0.0011990911],"genre_scores_gemma":[0.38641074,0.00017235769,0.6131126,0.000050770515,0.000060291586,0.000013127112,0.000011607172,0.000009490599,0.00015898752],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99859196,0.000118766184,0.00051082915,0.00030100436,0.0002274729,0.00024994786],"domain_scores_gemma":[0.99692535,0.0021635208,0.0002552666,0.00048856135,0.00006779583,0.00009948996],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00074178557,0.00016552427,0.00061134965,0.00024872547,0.000090996444,0.000027006023,0.00024080984,0.00007906852,0.00015258761],"category_scores_gemma":[0.023244465,0.00012059141,0.000016863874,0.00012952372,0.0004990573,0.000053007137,0.000114975664,0.0002833541,0.0000018246442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005892026,0.00006520665,0.07124351,0.00021430597,0.000042612526,0.0003053071,0.00089357997,0.0000018453894,0.000048394013,0.51685023,0.00043916298,0.40983692],"study_design_scores_gemma":[0.0008455173,0.00007113545,0.35879153,0.00030487063,0.00009436935,0.0000013868158,0.00009716185,0.013344642,0.000008733343,0.626288,0.00004762696,0.00010504394],"about_ca_topic_score_codex":0.00021187917,"about_ca_topic_score_gemma":0.0009492463,"teacher_disagreement_score":0.40973186,"about_ca_system_score_codex":0.00004516376,"about_ca_system_score_gemma":0.000021294156,"threshold_uncertainty_score":0.98498315},"labels":[],"label_agreement":null},{"id":"W2625352524","doi":"10.1002/sim.7346","title":"Analysis of panel data under hidden mover-stayer models","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Inference; Expectation–maximization algorithm; Econometrics; Latent variable; Maximum likelihood; Panel data; Maximization; Population; Statistics; Data mining; Artificial intelligence; Mathematical optimization; Mathematics","score_opus":0.31928921598111903,"score_gpt":0.479378919571194,"score_spread":0.16008970359007496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2625352524","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00097385276,0.000049818893,0.98922443,0.00033770793,0.00016457522,0.00013018194,0.0023005374,0.000012381116,0.0068064877],"genre_scores_gemma":[0.22882892,0.0000953482,0.77058864,0.00009279534,0.00006574611,0.00000456407,0.00014380696,0.000017311555,0.00016284839],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99804354,0.00012499139,0.0006750131,0.00037980784,0.0005207449,0.0002559269],"domain_scores_gemma":[0.9940241,0.0031314653,0.0004336165,0.0021449286,0.00016194074,0.00010392943],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0013358102,0.00017003813,0.00083452306,0.00023939363,0.00009607788,0.000025556654,0.0010351668,0.00008196314,0.0007494864],"category_scores_gemma":[0.008880854,0.00013170362,0.00002762139,0.00023968422,0.0005199944,0.00012585947,0.00033125156,0.00021342453,0.0000030760013],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021800584,0.00006952881,0.002655135,0.00010252951,0.00032611002,0.000035801575,0.0003166906,0.000016087717,0.000031876774,0.96107864,0.0040191594,0.031326655],"study_design_scores_gemma":[0.00044251516,0.000047293022,0.019833257,0.00009597616,0.0008949093,7.8041694e-7,0.00017693284,0.16208567,0.0000076491115,0.8162607,0.000037842467,0.00011644859],"about_ca_topic_score_codex":0.0008256266,"about_ca_topic_score_gemma":0.00062405603,"teacher_disagreement_score":0.22785507,"about_ca_system_score_codex":0.000032029675,"about_ca_system_score_gemma":0.00005769907,"threshold_uncertainty_score":0.9994678},"labels":[],"label_agreement":null},{"id":"W2736786428","doi":"10.1002/sim.8673","title":"Developing biomarker combinations in multicenter studies via direct maximization and penalization","year":2020,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Pritzker School of Medicine; National Institutes of Health; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; Institute for Clinical Evaluative Sciences; U.S. Department of Veterans Affairs","keywords":"Biomarker; Logistic regression; Maximization; Computer science; Data mining; Machine learning; Mathematics; Mathematical optimization; Biology","score_opus":0.24837774175540903,"score_gpt":0.4778237775230547,"score_spread":0.2294460357676457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736786428","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010933318,0.00050155906,0.99467874,0.0018548991,0.0005178857,0.0006101942,0.0001535008,0.00003470951,0.0005551912],"genre_scores_gemma":[0.15606937,0.0016480038,0.8415655,0.00026481488,0.000056009758,0.000093468196,0.0002287002,0.000036819223,0.00003732218],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99777585,0.00038659637,0.00087338884,0.00044016063,0.00031889605,0.00020511255],"domain_scores_gemma":[0.99538505,0.0037657283,0.00028955913,0.0001933584,0.0002990024,0.00006728806],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009320758,0.00026744834,0.0007467582,0.0002872852,0.000048832644,0.000020913421,0.00013023947,0.00013870018,0.00006090598],"category_scores_gemma":[0.022803154,0.00023313284,0.000012687987,0.0003062225,0.0002503662,0.000029579367,0.0003105932,0.0003958697,0.0000019133006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053606745,0.0001375333,0.005807503,0.0038187774,0.0001287288,0.00012996992,0.009245455,0.000042707168,0.000054238182,0.9527308,0.0024025915,0.025448108],"study_design_scores_gemma":[0.0011052304,0.000046950485,0.019992378,0.0018449534,0.00008111714,0.0000017828786,0.00056206156,0.09770492,0.00001062577,0.87837625,0.00004453321,0.00022917442],"about_ca_topic_score_codex":0.0001293339,"about_ca_topic_score_gemma":0.00026614816,"teacher_disagreement_score":0.15497603,"about_ca_system_score_codex":0.00020389323,"about_ca_system_score_gemma":0.00007361418,"threshold_uncertainty_score":0.9854282},"labels":[],"label_agreement":null},{"id":"W2739069932","doi":"10.1002/sim.7397","title":"Dynamic classification using credible intervals in longitudinal discriminant analysis","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; Belgian Federal Science Policy Office; Institut National de la Santé et de la Recherche Médicale; Medical Research Council; National Institute for Health and Care Research","keywords":"Linear discriminant analysis; False positive paradox; Bayesian probability; Multivariate statistics; Context (archaeology); Time point; Discriminant; Computer science; Confidence interval; Bayes' theorem; Statistics; Data mining; Set (abstract data type); Data set; Artificial intelligence; Machine learning; Mathematics","score_opus":0.10170984138903208,"score_gpt":0.42324950014943274,"score_spread":0.3215396587604007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739069932","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008819102,0.000114518065,0.9889868,0.000955573,0.0003605447,0.00010368023,0.0000132838395,0.000011781351,0.00063474337],"genre_scores_gemma":[0.50864744,0.00004873907,0.49118853,0.000031510095,0.000019753228,0.000003842767,0.0000071495015,0.0000039934102,0.000049074835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853075,0.00012830546,0.00042678913,0.0003981151,0.0002643542,0.0002516773],"domain_scores_gemma":[0.99854445,0.00015528395,0.0002513126,0.000908399,0.00007014612,0.0000704116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013308435,0.00012952446,0.0003958727,0.00046615128,0.00012223845,0.0000830653,0.00080680195,0.00005444393,0.000020242345],"category_scores_gemma":[0.0006065754,0.00010445652,0.000029826373,0.0004065167,0.0001862979,0.00022945643,0.00016869941,0.00020140164,0.0000018595928],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025412804,0.00015139488,0.09679378,0.00011338865,0.00011688525,0.00039257845,0.003729735,0.00031597473,0.0025324796,0.6537408,0.00038178536,0.24170578],"study_design_scores_gemma":[0.00025855008,0.0000323311,0.3293081,0.00008657495,0.000058930043,0.0000032808782,0.000033349374,0.5999577,0.000009926328,0.07015875,0.000013267615,0.00007927174],"about_ca_topic_score_codex":0.0008287589,"about_ca_topic_score_gemma":0.0017777983,"teacher_disagreement_score":0.5996417,"about_ca_system_score_codex":0.00012012026,"about_ca_system_score_gemma":0.000049060185,"threshold_uncertainty_score":0.42596135},"labels":[],"label_agreement":null},{"id":"W2743866054","doi":"10.1002/sim.7401","title":"A joint modeling and estimation method for multivariate longitudinal data with mixed types of responses to analyze physical activity data generated by accelerometers","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada","keywords":"Multivariate statistics; Accelerometer; Computer science; Longitudinal data; Estimation; Multivariate analysis; Joint (building); Statistics; Econometrics; Data mining; Mathematics; Machine learning","score_opus":0.2269431800474397,"score_gpt":0.4798321457310576,"score_spread":0.25288896568361785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2743866054","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43330252,0.000013205653,0.56461537,0.00042235383,0.000035183297,0.00018570968,0.0014101008,0.000004748874,0.000010827008],"genre_scores_gemma":[0.74338514,0.000008739241,0.2561827,0.0000069078965,0.000046613543,0.0000049506184,0.0003411851,0.000005242902,0.000018506596],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99890095,0.00012415531,0.00017647847,0.00038859784,0.00025779483,0.00015200258],"domain_scores_gemma":[0.99844027,0.0004816288,0.00016423588,0.00071555155,0.000119344135,0.00007895123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018729285,0.00008989854,0.00030832563,0.00005979975,0.00024628456,0.000040759212,0.0005320993,0.00003156381,0.000006896204],"category_scores_gemma":[0.0033572963,0.00006757822,0.000005081408,0.00010628381,0.0002830413,0.0003458559,0.00012222979,0.00008193529,9.9610745e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010003777,0.0017569353,0.2721619,0.0012297357,0.0008517137,0.00006341189,0.031262953,0.007816137,0.045444995,0.0062127705,0.011088464,0.6121072],"study_design_scores_gemma":[0.00070022716,0.00011045223,0.09952665,0.00007981781,0.00012262508,8.76143e-8,0.00020773686,0.89778,0.00018180003,0.0011733165,0.00002603739,0.000091270726],"about_ca_topic_score_codex":0.015160053,"about_ca_topic_score_gemma":0.008922304,"teacher_disagreement_score":0.88996387,"about_ca_system_score_codex":0.000022394464,"about_ca_system_score_gemma":0.00010220084,"threshold_uncertainty_score":0.9913981},"labels":[],"label_agreement":null},{"id":"W2744856250","doi":"10.1002/sim.7427","title":"Bayesian analysis of pair‐matched case‐control studies subject to outcome misclassification","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"British Columbia Centre of Excellence for Women's Health; Vancouver Coastal Health; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Multiple Sclerosis Society","keywords":"Outcome (game theory); Bayesian probability; Computer science; Subject (documents); Statistics; Econometrics; Artificial intelligence; Mathematics","score_opus":0.17087201834420754,"score_gpt":0.48955020471738364,"score_spread":0.31867818637317613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2744856250","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0055558416,0.00007019223,0.99099237,0.0015150324,0.00023370264,0.0003487966,0.0005946644,0.000019989664,0.00066942757],"genre_scores_gemma":[0.53621346,0.000014016006,0.46351933,0.000088121415,0.00004619002,0.000025063546,0.0000063788175,0.00001159453,0.000075846976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976162,0.00026873645,0.0010824625,0.00034080306,0.00040588272,0.00028594973],"domain_scores_gemma":[0.9914391,0.006558069,0.0005675315,0.0009317853,0.00035614622,0.00014734667],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022604726,0.00021441121,0.0013317417,0.00043952605,0.00016595483,0.000022103424,0.00032374205,0.000074933545,0.00023713557],"category_scores_gemma":[0.044911265,0.00016191171,0.000060215596,0.00040141633,0.00042824677,0.00004173876,0.00005845656,0.0001859875,0.0000039306788],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010132318,0.00014334422,0.13156937,0.0005686696,0.0016646774,0.00096304755,0.004024197,0.00001169788,0.00036835286,0.8033129,0.0031381932,0.054134212],"study_design_scores_gemma":[0.0015157803,0.00033926856,0.19942074,0.00026567664,0.0038639402,0.000022209537,0.002395073,0.019178983,0.00006897669,0.77256787,0.00004919409,0.00031227482],"about_ca_topic_score_codex":0.00038273542,"about_ca_topic_score_gemma":0.0017517424,"teacher_disagreement_score":0.5306576,"about_ca_system_score_codex":0.00007844513,"about_ca_system_score_gemma":0.000032774,"threshold_uncertainty_score":0.9631339},"labels":[],"label_agreement":null},{"id":"W2752127454","doi":"10.1002/sim.7440","title":"Algorithms for evaluating reference scaled average bioequivalence: power, bias, and consumer risk","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Bioequivalence; Computer science; Statistics; Econometrics; Sample size determination; Statistical power; Mathematics; Medicine","score_opus":0.7233084269583646,"score_gpt":0.6410520296377792,"score_spread":0.08225639732058543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752127454","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013167807,0.0002688239,0.9791681,0.0004929342,0.0013080041,0.00124927,0.0023934755,0.00004860527,0.0019029838],"genre_scores_gemma":[0.053495836,0.00083623204,0.94485235,0.00012383853,0.00022453944,0.00008921942,0.000011909843,0.000043214,0.00032284655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99612904,0.00081004185,0.0013334651,0.0006074937,0.00064955145,0.00047041746],"domain_scores_gemma":[0.9087291,0.088851176,0.00097162393,0.0008841884,0.00035635845,0.00020754838],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013381693,0.00028887126,0.0010424008,0.00010902139,0.0004243693,0.00006922319,0.00048207477,0.00020383149,0.0004873788],"category_scores_gemma":[0.57324785,0.0002255301,0.00003658815,0.00007690348,0.0014445771,0.000066574336,0.00019658302,0.000557314,0.000009823902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005269368,0.00021105242,0.014743194,0.00092799217,0.00017138946,0.000094315576,0.00088180474,0.0000020474479,0.00034187204,0.5531629,0.014554517,0.41438198],"study_design_scores_gemma":[0.004779784,0.0007759284,0.011406591,0.00055193336,0.00023629666,0.000005752645,0.00012296635,0.00913182,0.00005475599,0.9722644,0.0004032659,0.00026650605],"about_ca_topic_score_codex":0.00014830248,"about_ca_topic_score_gemma":0.000049697428,"teacher_disagreement_score":0.5598662,"about_ca_system_score_codex":0.00005200998,"about_ca_system_score_gemma":0.00008058419,"threshold_uncertainty_score":0.91968507},"labels":[],"label_agreement":null},{"id":"W2752310745","doi":"10.1002/sim.7449","title":"Modeling conditional dependence among multiple diagnostic tests","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Medical Research Council; South African Medical Research Council","keywords":"Diagnostic test; Conditional dependence; Statistics; Pairwise comparison; Bayesian probability; Conditional independence; Statistical hypothesis testing; Econometrics; Random effects model; Mathematics; Computer science; Medicine","score_opus":0.10206920322916589,"score_gpt":0.42708298095350533,"score_spread":0.3250137777243394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752310745","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018008715,0.000013575182,0.9780379,0.0006452352,0.00011984728,0.0002777952,0.0010312417,0.00004453,0.0018211677],"genre_scores_gemma":[0.93394834,0.000018550281,0.06524445,0.00008437567,0.00009254364,0.00010065121,0.00038555538,0.000014106994,0.000111404064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986724,0.00003602335,0.00044791657,0.00023752924,0.0003838187,0.00022228244],"domain_scores_gemma":[0.99474114,0.004307903,0.00016505511,0.00044795635,0.00020190935,0.00013603878],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00035157765,0.00013582084,0.00023785267,0.00006307387,0.00037303308,0.000040047948,0.00029257123,0.000060191447,0.0005537719],"category_scores_gemma":[0.05681795,0.00012405502,0.000015157976,0.00006265819,0.00047045326,0.000101719765,0.000055940247,0.00021439778,0.00005622323],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044829108,0.00007785854,0.015113986,0.00004485093,0.000007453,0.000034916113,0.000090632486,0.00048035325,0.00002361468,0.97765064,0.005457058,0.0010141465],"study_design_scores_gemma":[0.000606359,0.000016651016,0.13462254,0.000105311134,0.00002028811,0.0000037436118,0.000054576703,0.34948084,0.0000065058352,0.5149564,0.000033770353,0.00009298852],"about_ca_topic_score_codex":0.00024660002,"about_ca_topic_score_gemma":0.0007107215,"teacher_disagreement_score":0.9159396,"about_ca_system_score_codex":0.0000642049,"about_ca_system_score_gemma":0.000042811673,"threshold_uncertainty_score":0.9511269},"labels":[],"label_agreement":null},{"id":"W2752545986","doi":"10.1002/sim.7453","title":"Improving phase II oncology trials using best observed RECIST response as an endpoint by modelling continuous tumour measurements","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; Cancer Research UK; AstraZeneca","keywords":"Response Evaluation Criteria in Solid Tumors; Sample size determination; Clinical endpoint; Clinical trial; Estimator; Medicine; Oncology; Outcome (game theory); Complete response; Computer science; Statistics; Internal medicine; Phases of clinical research; Mathematics; Chemotherapy","score_opus":0.8504567930226415,"score_gpt":0.6474845982302354,"score_spread":0.20297219479240614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752545986","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.120083526,0.00011160245,0.87391126,0.0006187667,0.002094568,0.0013372721,0.00117072,0.000058602473,0.0006136931],"genre_scores_gemma":[0.110947594,0.00006676291,0.8874193,0.00022493373,0.00076086476,0.000057318375,0.000033286324,0.00010451992,0.00038542258],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9852203,0.0076897703,0.004076589,0.00095245277,0.0012449083,0.00081597816],"domain_scores_gemma":[0.9195884,0.07474177,0.0030329425,0.0014847446,0.0006196282,0.0005325479],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06316792,0.0005162362,0.0031005854,0.00020451858,0.00075882766,0.00011154463,0.00097554026,0.0004051194,0.00055670977],"category_scores_gemma":[0.65066653,0.0004389139,0.00010913484,0.00013214143,0.0009182497,0.00018015545,0.00030496175,0.00091462315,0.000011824708],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06065699,0.010826881,0.0003967336,0.0011528439,0.0008279409,0.002847681,0.005255764,0.0002770263,0.36416683,0.0864288,0.015968623,0.45119387],"study_design_scores_gemma":[0.025001619,0.0087303715,0.000030981555,0.0009559603,0.00089885667,0.00002661865,0.00073642563,0.065172054,0.0042337407,0.8925462,0.0009959247,0.00067124603],"about_ca_topic_score_codex":0.0015404961,"about_ca_topic_score_gemma":0.0001377277,"teacher_disagreement_score":0.8061174,"about_ca_system_score_codex":0.0005306067,"about_ca_system_score_gemma":0.00044799125,"threshold_uncertainty_score":0.9998063},"labels":[],"label_agreement":null},{"id":"W2754160328","doi":"10.1002/sim.7501","title":"Practical recommendations for reporting<scp>F</scp>ine‐<scp>G</scp>ray model analyses for competing risk data","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1176,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Covariate; Proportional hazards model; Statistics; Regression analysis; Econometrics; Regression; Event (particle physics); Hazard; Mathematics; Biology","score_opus":0.7862327183202007,"score_gpt":0.6125248362078489,"score_spread":0.17370788211235177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754160328","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004036563,0.00046535156,0.94184023,0.032365408,0.0012314207,0.0015560761,0.014490387,0.00004706723,0.003967512],"genre_scores_gemma":[0.037725106,0.0007363761,0.94851923,0.003814131,0.0015321289,0.00041445054,0.00454492,0.00010353244,0.0026101195],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9897964,0.00027062788,0.007963895,0.0010768601,0.00018511224,0.00070709665],"domain_scores_gemma":[0.94914997,0.032552198,0.015550384,0.0021136983,0.00034564993,0.00028808968],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047267534,0.0003092443,0.0016824772,0.00040968595,0.0010045737,0.00017538873,0.000867067,0.00019484197,0.00004023663],"category_scores_gemma":[0.6004921,0.0003551218,0.000085598265,0.00012475999,0.00028092592,0.0006327703,0.00024804097,0.0004482993,0.000073504096],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006728931,0.00012613214,0.016800454,0.0005337979,0.00015885998,0.0000037994537,0.0023418956,0.001406271,0.000003277862,0.12112793,0.8570197,0.00047112996],"study_design_scores_gemma":[0.0018063165,0.00014122076,0.0047029327,0.00020459497,0.000099691686,0.000005644085,0.004555591,0.70993257,0.0000025089444,0.09595138,0.1824918,0.000105760504],"about_ca_topic_score_codex":0.0011991606,"about_ca_topic_score_gemma":0.00091007916,"teacher_disagreement_score":0.7085263,"about_ca_system_score_codex":0.00032083524,"about_ca_system_score_gemma":0.0003778379,"threshold_uncertainty_score":0.9998901},"labels":[],"label_agreement":null},{"id":"W2755786236","doi":"10.1002/sim.8013","title":"One‐sample aggregate data meta‐analysis of medians","year":2018,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé","keywords":"Median; Meta-analysis; Statistics; Weighting; Sample size determination; Pooled variance; Standard deviation; Variance (accounting); Sample (material); Outcome (game theory); Mathematics; Data set; Computer science; Confidence interval; Medicine","score_opus":0.327383040627426,"score_gpt":0.4826645932734693,"score_spread":0.15528155264604326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755786236","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000035299665,0.0009581308,0.957466,0.00046259255,0.00050401984,0.00041938093,0.03892918,0.00003578073,0.0011896194],"genre_scores_gemma":[0.0017972596,0.0007292032,0.9936893,0.00013278068,0.00026787427,0.000045382723,0.0032354651,0.000051204275,0.000051559793],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951755,0.00061841134,0.0017336644,0.0009691413,0.0010650503,0.00043826888],"domain_scores_gemma":[0.9763991,0.018920565,0.0010442671,0.002950986,0.00048658077,0.00019850642],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036435728,0.00045310342,0.0037952184,0.0008222502,0.0000420883,0.00002023205,0.0016085192,0.00032433326,0.0054999893],"category_scores_gemma":[0.03742552,0.00037038026,0.00018253239,0.00092710525,0.0010747769,0.00003412188,0.0013728141,0.00084256154,0.000007073046],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005002191,0.00030462435,0.00038024888,0.0022884477,0.11287395,0.000057860434,0.001550931,0.000009541134,0.000012745049,0.85469043,0.014747558,0.013033654],"study_design_scores_gemma":[0.00023318002,0.000096594515,0.00055757974,0.00023328181,0.19974376,5.358206e-7,0.0000623447,0.013814077,0.000010838349,0.78479874,0.00018731758,0.000261739],"about_ca_topic_score_codex":0.0023399298,"about_ca_topic_score_gemma":0.0029628028,"teacher_disagreement_score":0.086869806,"about_ca_system_score_codex":0.00004870566,"about_ca_system_score_gemma":0.00022177538,"threshold_uncertainty_score":0.99987483},"labels":[],"label_agreement":null},{"id":"W2756610413","doi":"10.1002/sim.7532","title":"Measures of clustering and heterogeneity in multilevel <scp>P</scp>oisson regression analyses of rates/count data","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":206,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island; University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Vetenskapsrådet; Heart and Stroke Foundation of Canada","keywords":"Statistics; Poisson regression; Multilevel model; Poisson distribution; Hazard ratio; Proportional hazards model; Count data; Random effects model; Regression analysis; Cluster analysis; Confidence interval; Mathematics; Odds ratio; Rate ratio; Linear regression; Hierarchical clustering; Cluster (spacecraft); Econometrics; Medicine; Meta-analysis; Computer science; Internal medicine; Population","score_opus":0.4042531616015181,"score_gpt":0.5285301629397802,"score_spread":0.12427700133826208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756610413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07328229,0.00029375107,0.9250822,0.000040486782,0.00012513755,0.00018086465,0.0006493783,0.000005246029,0.00034062803],"genre_scores_gemma":[0.5082842,0.00022531537,0.491415,0.000008362808,0.000025913714,0.0000030602118,0.000017996768,0.000010117575,0.000010041807],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99815583,0.00019926416,0.00074531854,0.00030419198,0.00039514567,0.00020027053],"domain_scores_gemma":[0.99381894,0.0044729016,0.0005664403,0.0009211642,0.00014834144,0.00007221516],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018155711,0.00016506614,0.0007155885,0.00015292288,0.000057021123,0.000013884023,0.00047119896,0.00007978216,0.000015187135],"category_scores_gemma":[0.045503356,0.00011876967,0.000011301183,0.00007465965,0.00049749407,0.00007783343,0.00032837526,0.00019417806,2.5068394e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026511712,0.00080519594,0.32128432,0.007428375,0.00027140402,0.00042138842,0.0066975243,0.000024641897,0.058842596,0.16849649,0.0064072227,0.42905572],"study_design_scores_gemma":[0.0024477597,0.00028169242,0.4138441,0.0037407153,0.0001614488,0.000009468451,0.0006479456,0.08211432,0.0076564425,0.48889562,0.00006126775,0.00013920652],"about_ca_topic_score_codex":0.0011048521,"about_ca_topic_score_gemma":0.001943266,"teacher_disagreement_score":0.4350019,"about_ca_system_score_codex":0.000022128565,"about_ca_system_score_gemma":0.000038394515,"threshold_uncertainty_score":0.96253675},"labels":[],"label_agreement":null},{"id":"W2765200233","doi":"10.1002/sim.7534","title":"Three‐part joint modeling methods for complex functional data mixed with zero‐and‐one–inflated proportions and zero‐inflated continuous outcomes with skewness","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Mental Health Research Topics","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Cancer Institute; National Heart, Lung, and Blood Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Bivariate analysis; Skewness; Statistics; Mathematics; Zero (linguistics); Econometrics; Interval (graph theory); Combinatorics","score_opus":0.4264507123200055,"score_gpt":0.5347583986790945,"score_spread":0.108307686359089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765200233","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0090319505,0.00017315893,0.98409647,0.0027677543,0.00035789487,0.0015368216,0.0013555248,0.00003752436,0.0006428866],"genre_scores_gemma":[0.19331275,0.000086550215,0.80001247,0.00035428948,0.00019857567,0.00038695385,0.0042732893,0.00008069798,0.0012944477],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99776477,0.00015570744,0.0006246809,0.0005926877,0.0003803848,0.00048177913],"domain_scores_gemma":[0.9973548,0.00073341036,0.0003278646,0.0010166798,0.00032016492,0.00024706143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00185693,0.00023262593,0.00064218545,0.00014477376,0.00050294265,0.00004726595,0.00028517406,0.00010330831,0.00048120882],"category_scores_gemma":[0.0012657809,0.00015923296,0.000008561399,0.00008584559,0.0007930584,0.00011067918,0.00018983372,0.00040902948,0.0000037226594],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0062895385,0.00085765304,0.14029732,0.0022920987,0.001762868,0.0004279079,0.0032786464,0.0002442566,0.00044273856,0.25149643,0.05411895,0.5384916],"study_design_scores_gemma":[0.02006528,0.0030414534,0.49796692,0.0010830472,0.0004233049,0.00016189268,0.0010561869,0.37599447,0.000008900742,0.0892858,0.010209556,0.0007032109],"about_ca_topic_score_codex":0.0014284996,"about_ca_topic_score_gemma":0.0025583298,"teacher_disagreement_score":0.5377884,"about_ca_system_score_codex":0.000052246418,"about_ca_system_score_gemma":0.0001463707,"threshold_uncertainty_score":0.6493332},"labels":[],"label_agreement":null},{"id":"W2765966791","doi":"10.1002/sim.7515","title":"A mechanistic nonlinear model for censored and mismeasured covariates in longitudinal models, with application in AIDS studies","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; HIV Legal Network; St. Paul's Hospital","funders":"","keywords":"Covariate; Censoring (clinical trials); Econometrics; Inference; Observational error; Computer science; Statistics; Mathematics; Artificial intelligence","score_opus":0.1472845397461962,"score_gpt":0.438050019936488,"score_spread":0.2907654801902918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765966791","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017045811,0.000107404456,0.99649,0.00031425973,0.000043344025,0.00088929915,0.0002903316,0.000009975828,0.00015082926],"genre_scores_gemma":[0.2609938,0.00010134547,0.738589,0.0000284286,0.00002692193,0.00020199943,0.000015007263,0.000018615734,0.000024907364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984998,0.00007385187,0.0005206567,0.00039274807,0.00023378035,0.0002791228],"domain_scores_gemma":[0.99698716,0.0021244285,0.00023382004,0.0003789464,0.00020782446,0.00006781488],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001422065,0.00020053732,0.0006881245,0.00014143108,0.00011235122,0.000038976923,0.00027701864,0.00007339607,0.000003388166],"category_scores_gemma":[0.007459203,0.000151622,0.000007743748,0.0001001983,0.00032946424,0.00008803714,0.00009153853,0.00019834157,2.4251025e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028819457,0.000106912084,0.0022758914,0.00044547854,0.000022100268,0.00002855383,0.0011848081,0.00013797192,0.000058313595,0.9859852,0.00008052912,0.009386032],"study_design_scores_gemma":[0.0017772662,0.00016469488,0.0014512598,0.00033679052,0.000035176192,0.0000022528193,0.00019855399,0.4611382,0.0000053141885,0.5347931,0.0000012227972,0.000096175674],"about_ca_topic_score_codex":0.0004080903,"about_ca_topic_score_gemma":0.0039768727,"teacher_disagreement_score":0.4610002,"about_ca_system_score_codex":0.000078343925,"about_ca_system_score_gemma":0.00006902441,"threshold_uncertainty_score":0.8929901},"labels":[],"label_agreement":null},{"id":"W2766219675","doi":"10.1002/sim.7527","title":"Collaborative targeted learning using regression shrinkage","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Université de Montréal","keywords":"Covariate; Causal inference; Propensity score matching; Estimator; Statistics; Regression; Regression analysis; Inference; Computer science; Stepwise regression; Mean squared error; Model selection; Outcome (game theory); Econometrics; Mathematics; Artificial intelligence","score_opus":0.11734741745116913,"score_gpt":0.4830962113690352,"score_spread":0.3657487939178661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766219675","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034637213,0.00014522833,0.95516336,0.00026169128,0.0003031296,0.00040988057,0.000048919446,0.00017529096,0.008855278],"genre_scores_gemma":[0.41122296,0.0001229522,0.58793604,0.00003440642,0.000115003975,0.0000128425545,0.000018556777,0.000031407628,0.0005058172],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987165,0.00011713724,0.0003732885,0.00022679541,0.00031392393,0.00025237116],"domain_scores_gemma":[0.9980329,0.00071699923,0.00047520633,0.00047169032,0.00023209862,0.00007105491],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006804601,0.00017738824,0.00039801883,0.00012079759,0.00032625988,0.000026586886,0.0002700661,0.00009004935,0.00021222775],"category_scores_gemma":[0.014082884,0.00013832765,0.000010240207,0.00011377334,0.00039689126,0.00014488178,0.000118848366,0.00045476216,0.0000040534733],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013271089,0.0001317737,0.01668538,0.00036287206,0.000052783616,0.00084948906,0.007268868,0.0001223152,0.049524385,0.8863316,0.014836272,0.02370156],"study_design_scores_gemma":[0.0009297723,0.00025462924,0.0022800965,0.001278945,0.00003641454,0.0000074887525,0.0012931516,0.006878219,0.0049367305,0.98079675,0.0010364199,0.0002713956],"about_ca_topic_score_codex":0.00008229046,"about_ca_topic_score_gemma":0.00008219129,"teacher_disagreement_score":0.37658575,"about_ca_system_score_codex":0.00011970517,"about_ca_system_score_gemma":0.000060165523,"threshold_uncertainty_score":0.9942219},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W2766434410","doi":"10.1002/sim.7522","title":"Weighted estimation for confounded binary outcomes subject to misclassification","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Institute of Population and Public Health; University of Ottawa","funders":"","keywords":"Covariate; Estimator; Statistics; Logistic regression; Confounding; Computer science; Estimation; Inverse probability; Econometrics; Inverse probability weighting; Consistency (knowledge bases); Identification (biology); Mathematics; Artificial intelligence; Posterior probability","score_opus":0.19441443568362424,"score_gpt":0.500652691376323,"score_spread":0.3062382556926987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766434410","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009126054,0.000007642056,0.98479486,0.002928382,0.00024169683,0.0009816721,0.00010567234,0.00011968516,0.0016943433],"genre_scores_gemma":[0.27810165,0.000011705452,0.72071,0.00016040241,0.00005220443,0.00020258677,0.00008735901,0.000024880525,0.00064919976],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99882066,0.00003361659,0.00045256317,0.00023201758,0.0002446101,0.00021651875],"domain_scores_gemma":[0.9971729,0.0015693638,0.0003128475,0.00064956845,0.00021770642,0.000077649944],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00066054787,0.00016159439,0.00037540332,0.00016114692,0.00017957644,0.000029070008,0.00030148454,0.00007503601,0.000063129395],"category_scores_gemma":[0.012009269,0.00013210725,0.000017171473,0.000063858606,0.00018197832,0.000111768895,0.000043184707,0.00012344276,0.000010215016],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060272992,0.00006172657,0.0017863736,0.0001557388,0.00001687499,0.000010519982,0.00057047757,0.000004536176,0.0024047054,0.9578194,0.015994104,0.021115271],"study_design_scores_gemma":[0.0008515369,0.0003061075,0.016018009,0.00020324407,0.00003610973,0.0000016530705,0.0001101054,0.010771705,0.0010747315,0.9697453,0.0007157731,0.00016575168],"about_ca_topic_score_codex":0.00006618059,"about_ca_topic_score_gemma":0.00017028273,"teacher_disagreement_score":0.26897562,"about_ca_system_score_codex":0.00014255312,"about_ca_system_score_gemma":0.00004525783,"threshold_uncertainty_score":0.996313},"labels":[],"label_agreement":null},{"id":"W2768383839","doi":"10.1002/sim.7502","title":"A state transition framework for patient‐level modeling of engagement and retention in HIV care using longitudinal cohort data","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"HIV/AIDS Research and Interventions","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Allergy and Infectious Diseases; National Institute of Mental Health; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Center for AIDS Research, University of Washington; National Institutes of Health","keywords":"Cascade; Disengagement theory; Health care; Computer science; Human immunodeficiency virus (HIV); Observational study; Econometrics; Medicine; Gerontology; Statistics; Mathematics; Family medicine; Engineering; Political science","score_opus":0.2299358649159377,"score_gpt":0.4522708781184758,"score_spread":0.22233501320253812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768383839","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2006857,0.00032390145,0.7959987,0.00027830625,0.000051688436,0.00066421577,0.0018584933,0.000003618287,0.00013540973],"genre_scores_gemma":[0.8602497,0.00027200856,0.13827206,0.000014700134,0.00004552807,0.000020833015,0.001073917,0.00001221569,0.000039034712],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867344,0.00006596913,0.00046483325,0.00027033527,0.00032322409,0.00020220545],"domain_scores_gemma":[0.9989514,0.00012974578,0.00012401238,0.00048499877,0.00022928863,0.000080552054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008558998,0.00009436915,0.00030920867,0.00020637912,0.00011896038,0.0000132555615,0.00012372524,0.000046536083,0.000044030035],"category_scores_gemma":[0.0023885136,0.00008420091,0.000018557123,0.00006286802,0.00016432787,0.000115305105,0.00008137447,0.00026716408,3.2602676e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005467238,0.0014710401,0.47519946,0.017982407,0.00086033833,0.0008152122,0.06532217,0.0038335812,0.006762007,0.03098231,0.009754078,0.38155016],"study_design_scores_gemma":[0.003379282,0.0017722128,0.02264186,0.0055708326,0.00018193736,0.0000078673975,0.0045234724,0.94906855,0.000059519323,0.01262175,0.00005873324,0.00011400603],"about_ca_topic_score_codex":0.0010636264,"about_ca_topic_score_gemma":0.00059109327,"teacher_disagreement_score":0.94523495,"about_ca_system_score_codex":0.00008195516,"about_ca_system_score_gemma":0.00006220852,"threshold_uncertainty_score":0.34336132},"labels":[],"label_agreement":null},{"id":"W2768417485","doi":"10.1002/sim.7539","title":"Exponential decay for binary time‐varying covariates in Cox models","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Proportional hazards model; Statistics; Event (particle physics); Econometrics; Exponential growth; Binary data; Computer science; Mathematics; Binary number","score_opus":0.5055243770677599,"score_gpt":0.5754043878517637,"score_spread":0.06988001078400385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768417485","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024663734,0.000062160725,0.98943913,0.0008827561,0.0012839815,0.0010528426,0.00063026586,0.000041343388,0.00414113],"genre_scores_gemma":[0.052077007,0.000082066545,0.9465853,0.0001450033,0.00051154854,0.00013512354,0.000027458147,0.000059571328,0.00037695045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996647,0.0004286547,0.0014401322,0.0004906634,0.0004712413,0.0005222825],"domain_scores_gemma":[0.9414227,0.05695774,0.00051950803,0.0007948683,0.00015649393,0.00014871621],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0064833816,0.00026539952,0.0011327165,0.00019322158,0.00019126086,0.000043773478,0.0006141466,0.00020529456,0.0005072263],"category_scores_gemma":[0.14759113,0.0002277655,0.000050284143,0.000102604696,0.0005819606,0.00011080702,0.00017955208,0.00039967362,0.000018678915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071804057,0.0002988916,0.00037739705,0.0004519904,0.000057419897,0.00021828385,0.00065024005,0.00011397613,0.0010620794,0.9669411,0.015160193,0.013950367],"study_design_scores_gemma":[0.00498547,0.00030908073,0.00061006565,0.000585428,0.000085539505,0.0000029014898,0.000043768905,0.07959841,0.00014503588,0.9133061,0.00010522819,0.00022293944],"about_ca_topic_score_codex":0.00015353077,"about_ca_topic_score_gemma":0.000056367644,"teacher_disagreement_score":0.14110774,"about_ca_system_score_codex":0.00009255147,"about_ca_system_score_gemma":0.00008651905,"threshold_uncertainty_score":0.92880076},"labels":[],"label_agreement":null},{"id":"W2774445575","doi":"10.1002/sim.7555","title":"Bayesian inference for unidirectional misclassification of a binary response trait","year":2017,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Identifiability; Covariate; Computer science; Inference; Poisson distribution; Identification (biology); Binary data; Bayesian probability; Binary number; Statistics; Econometrics; Bayesian inference; Binary classification; Bayes' theorem; Machine learning; Artificial intelligence; Mathematics","score_opus":0.1210735242408162,"score_gpt":0.4597409341384469,"score_spread":0.3386674098976307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774445575","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00304476,0.000017657643,0.99334747,0.0010936597,0.00025704046,0.00032724405,0.00063580304,0.000015469082,0.0012608723],"genre_scores_gemma":[0.32187828,0.0000144125,0.677742,0.000024097533,0.00006723892,0.000047352285,0.000017828208,0.000013010446,0.00019575814],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985393,0.00019857043,0.00055829855,0.00023246054,0.00027377802,0.00019756415],"domain_scores_gemma":[0.9891103,0.009683018,0.000398456,0.00047442195,0.00025313045,0.00008069075],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018510384,0.00013587669,0.00040065928,0.00014140458,0.00015960276,0.000015623908,0.00029443248,0.00008148391,0.0002439455],"category_scores_gemma":[0.049001954,0.00011370084,0.000024349052,0.00008321065,0.00056444306,0.000050596536,0.00003208745,0.00015000293,0.0000010527447],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006186895,0.00010044539,0.0009851143,0.0002500762,0.000016169533,0.000010577686,0.00042326088,7.4074006e-7,0.0035762026,0.9569433,0.003636399,0.033439048],"study_design_scores_gemma":[0.0010375772,0.00047115798,0.07885703,0.00032834648,0.000040324576,0.000002819042,0.00012700199,0.00811485,0.00024682534,0.9100887,0.0005677614,0.00011759478],"about_ca_topic_score_codex":0.00007898063,"about_ca_topic_score_gemma":0.000073335716,"teacher_disagreement_score":0.31883353,"about_ca_system_score_codex":0.0000467226,"about_ca_system_score_gemma":0.00013272351,"threshold_uncertainty_score":0.9590087},"labels":[],"label_agreement":null},{"id":"W2784307041","doi":"10.1002/sim.7553","title":"Modeling clustering and treatment effect heterogeneity in parallel and stepped‐wedge cluster randomized trials","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Canada","funders":"National Health and Medical Research Council; Medical Research Council; National Institute for Health and Care Research","keywords":"Cluster analysis; Cluster (spacecraft); Computer science; Random effects model; Econometrics; Wedge (geometry); Statistics; Data mining; Mathematics; Medicine; Artificial intelligence; Meta-analysis","score_opus":0.1332079247993277,"score_gpt":0.4520500531089921,"score_spread":0.3188421283096644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784307041","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.083474815,0.0002811091,0.91428375,0.00013798627,0.0001835643,0.0013295171,0.000050511095,0.000016092145,0.00024265095],"genre_scores_gemma":[0.31106585,0.0004326851,0.68808293,0.00008308254,0.00017089682,0.00011689601,0.0000071353757,0.000020608246,0.000019936704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961243,0.001949793,0.0010694646,0.00035448943,0.00019994794,0.00030197253],"domain_scores_gemma":[0.979658,0.019819533,0.00014893735,0.00019753574,0.000054432447,0.00012156005],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007080373,0.00027400386,0.0019128541,0.00016938393,0.000057898906,0.000025086743,0.00006763611,0.0000966077,0.000058806923],"category_scores_gemma":[0.020723127,0.0001689191,0.000032617863,0.000103636485,0.00046475691,0.000035747264,0.00006730818,0.00015006302,0.000001842273],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.085424,0.00037250476,0.0061311927,0.0018385199,0.0004867825,0.00034512693,0.010389329,0.000131934,0.0004196012,0.34674534,0.00061388034,0.5471018],"study_design_scores_gemma":[0.10616693,0.000696734,0.00027390575,0.00043838075,0.00019061603,0.000013754153,0.000074593976,0.46396682,0.000024323217,0.42797118,0.000007449207,0.0001753181],"about_ca_topic_score_codex":0.00040138557,"about_ca_topic_score_gemma":0.0013869611,"teacher_disagreement_score":0.5469265,"about_ca_system_score_codex":0.00006767355,"about_ca_system_score_gemma":0.00002119719,"threshold_uncertainty_score":0.98752576},"labels":[],"label_agreement":null},{"id":"W2785825193","doi":"10.1002/sim.7589","title":"Meta‐analysis of Gaussian individual patient data: Two‐stage or not two‐stage?","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"Stage (stratigraphy); Meta-analysis; Computer science; Flexibility (engineering); Econometrics; Random effects model; Outcome (game theory); Aggregate data; Sample size determination; Aggregate (composite); Range (aeronautics); Statistics; Mathematics; Medicine","score_opus":0.8323632235708937,"score_gpt":0.5893490509411681,"score_spread":0.24301417262972558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785825193","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02520167,0.0031212086,0.92302835,0.0022970783,0.001800235,0.0024268501,0.024179764,0.00002066221,0.017924163],"genre_scores_gemma":[0.82682127,0.00010699609,0.15119755,0.0019042173,0.00034502274,0.000049645078,0.0011382656,0.000036676534,0.01840036],"study_design_codex":"not_applicable","study_design_gemma":"meta_analysis","domain_scores_codex":[0.97100246,0.0065321024,0.011768927,0.0014842784,0.008778334,0.00043391524],"domain_scores_gemma":[0.9740565,0.010948831,0.006203445,0.007118028,0.0013993153,0.00027389702],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09533073,0.00044561378,0.008211532,0.0018317847,0.00012253992,0.000186758,0.003460098,0.000073441064,0.09528253],"category_scores_gemma":[0.05251025,0.00019095669,0.00074185454,0.0057319766,0.00068737514,0.00020855949,0.00060757133,0.00026952976,0.00042328655],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003614024,0.00072368496,0.028056344,0.0005061855,0.33432588,0.00054571824,0.023011692,0.0018048936,0.00017471157,0.11932988,0.4332234,0.057936218],"study_design_scores_gemma":[0.003071721,0.0014687366,0.023451438,0.0001185286,0.5233831,0.000012240271,0.010838398,0.18391196,0.00011094897,0.008540419,0.24403822,0.0010543251],"about_ca_topic_score_codex":0.00071181584,"about_ca_topic_score_gemma":0.007907816,"teacher_disagreement_score":0.8016196,"about_ca_system_score_codex":0.00003359648,"about_ca_system_score_gemma":0.00015420375,"threshold_uncertainty_score":0.95547086},"labels":[],"label_agreement":null},{"id":"W2790095428","doi":"10.1002/sim.7611","title":"Discrimination surfaces with application to region‐specific brain asymmetry analysis","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundação para a Ciência e a Tecnologia; University of British Columbia; University of South Carolina; National Science Foundation","keywords":"Estimator; Statistic; Asymmetry; Brain asymmetry; Mathematics; Statistics; Confidence interval; Pattern recognition (psychology); Psychology; Computer science; Artificial intelligence; Cognitive psychology; Physics","score_opus":0.04038446706239159,"score_gpt":0.3465978518653931,"score_spread":0.30621338480300153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790095428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0143563,0.00002158483,0.97732973,0.003208308,0.00006464813,0.00029817005,0.000039445284,0.000037449103,0.004644369],"genre_scores_gemma":[0.740939,0.000011977629,0.2578883,0.00039293148,0.0001616489,0.000031727002,0.00009802187,0.000012993161,0.00046340545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986442,0.000088321634,0.00038206973,0.000327441,0.00036193265,0.00019604141],"domain_scores_gemma":[0.9981962,0.0009538793,0.00015239992,0.00038340964,0.00022027164,0.000093834955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064979255,0.00013775706,0.00033027664,0.00044568066,0.00008774098,0.000015616835,0.00015840994,0.000060849223,0.00023780233],"category_scores_gemma":[0.001018935,0.00009461743,0.000017638751,0.0020063063,0.00017995799,0.000039810107,0.00003067433,0.00012226384,0.000030245388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005079739,0.00014215214,0.011192619,0.00003677222,0.000096463504,0.000019665105,0.0009066905,0.00004603941,0.0002708841,0.8885472,0.08654499,0.012145719],"study_design_scores_gemma":[0.0024506175,0.0020946357,0.37624454,0.00025473317,0.00090981164,0.000018550525,0.003272576,0.021751856,0.00030282067,0.56796384,0.023898145,0.0008378474],"about_ca_topic_score_codex":0.00012082358,"about_ca_topic_score_gemma":0.0006142854,"teacher_disagreement_score":0.7265827,"about_ca_system_score_codex":0.000070478425,"about_ca_system_score_gemma":0.000013711858,"threshold_uncertainty_score":0.38583872},"labels":[],"label_agreement":null},{"id":"W2791924225","doi":"10.1002/sim.7615","title":"Assessing the performance of the generalized propensity score for estimating the effect of quantitative or continuous exposures on binary outcomes","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":85,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Covariate; Statistics; Confounding; Mathematics; Ordinary least squares; Medicine","score_opus":0.215693518484249,"score_gpt":0.4913806844402001,"score_spread":0.2756871659559511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791924225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8471548,0.000021146489,0.15088344,0.00029613377,0.00021314235,0.001265712,0.000034650908,0.00002246565,0.000108538334],"genre_scores_gemma":[0.7409655,0.0000051489533,0.25872532,0.00010096638,0.000048774447,0.00007636656,0.0000030391104,0.000017385053,0.000057512243],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984256,0.00034904666,0.00055570115,0.00014553833,0.00034602208,0.00017808944],"domain_scores_gemma":[0.98858196,0.010085502,0.00059881806,0.0004434255,0.00027484866,0.000015434618],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021940824,0.00017102456,0.00055051007,0.000046419413,0.00018597778,0.000009728106,0.00035846664,0.000042703417,0.000014956632],"category_scores_gemma":[0.014820239,0.00005881996,0.000032979362,0.00019334696,0.0011623912,0.00006186778,0.000085301435,0.00021251156,3.0369324e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034606275,0.0003759703,0.38690004,0.0059718615,0.0004779983,0.000023744888,0.024422543,0.00082843174,0.045712028,0.4650874,0.018922761,0.047816586],"study_design_scores_gemma":[0.0077026365,0.03643276,0.17109728,0.0101885265,0.00084748573,0.000027952816,0.0029249575,0.15874153,0.28071278,0.33045095,0.000115859635,0.00075727777],"about_ca_topic_score_codex":0.00003983119,"about_ca_topic_score_gemma":0.00006123195,"teacher_disagreement_score":0.23500076,"about_ca_system_score_codex":0.000033705688,"about_ca_system_score_gemma":0.000048769256,"threshold_uncertainty_score":0.99347836},"labels":[],"label_agreement":null},{"id":"W2794650963","doi":"10.1002/sim.7641","title":"Design of cancer trials based on progression‐free survival with intermittent assessment","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Censoring (clinical trials); Sample size determination; Medicine; Clinical trial; Randomized controlled trial; Clinical endpoint; Progression-free survival; Survival analysis; Confidence interval; Cancer; Clinical study design; Research design; Intensive care medicine; Oncology; Overall survival; Statistics; Internal medicine; Mathematics","score_opus":0.6283440379913406,"score_gpt":0.6537779914408499,"score_spread":0.025433953449509272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794650963","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034239757,0.000020977888,0.9939245,0.00096184417,0.0012679755,0.0012816603,0.0003936835,0.000032907963,0.0017740545],"genre_scores_gemma":[0.031075828,0.000030640484,0.9677166,0.00028495808,0.00059127394,0.00017959955,0.000005803719,0.000046724086,0.000068571935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9924922,0.0033799657,0.0019888184,0.00043285103,0.0013610541,0.0003451234],"domain_scores_gemma":[0.874663,0.12312911,0.00089382706,0.0007221411,0.000450597,0.00014131067],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018568445,0.0002810335,0.0017375668,0.0001936702,0.000047151225,0.000009700466,0.00043064976,0.00012432273,0.0018110315],"category_scores_gemma":[0.19240174,0.00016502301,0.000040265844,0.00034429476,0.0010722047,0.000017379638,0.00007312739,0.00038745793,0.0000032516098],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009262231,0.0022803172,0.0105021,0.0013874935,0.0005322801,0.00028603786,0.000760358,0.00024483702,0.0012362801,0.6041833,0.06061654,0.30870822],"study_design_scores_gemma":[0.010341949,0.0076114913,0.004863686,0.003727078,0.00041911914,0.0000010446859,0.0001278015,0.021525554,0.0012115008,0.94973385,0.00014267622,0.00029421895],"about_ca_topic_score_codex":0.000045034805,"about_ca_topic_score_gemma":0.0000689359,"teacher_disagreement_score":0.34555057,"about_ca_system_score_codex":0.00013159642,"about_ca_system_score_gemma":0.00030386169,"threshold_uncertainty_score":0.99910146},"labels":[],"label_agreement":null},{"id":"W2799472749","doi":"10.1002/sim.7658","title":"Exposure, hazard, and survival analysis of diffusion on social networks","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Yale Center for Clinical Investigation, Yale School of Medicine; Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Center for Advancing Translational Sciences; National Institute of Mental Health; Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health; Yale University; Bill and Melinda Gates Foundation","keywords":"Social network (sociolinguistics); Psychological intervention; Realization (probability); Diffusion; Computer science; Population; Social network analysis; Relevance (law); Diffusion of innovations; Intervention (counseling); Process (computing); Econometrics; Actuarial science; Data science; Psychology; Statistics; Business; Sociology; Economics; Marketing; Demography; Mathematics; Political science","score_opus":0.0185726490180078,"score_gpt":0.32509458966867677,"score_spread":0.30652194065066896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2799472749","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4136183,0.00006222368,0.5781394,0.00011717421,0.00014712146,0.00012548504,0.000108887005,0.000021935168,0.0076594525],"genre_scores_gemma":[0.9969422,0.000018566336,0.0021431344,0.00003538524,0.0006208872,0.000004488977,0.00016508841,0.000008913207,0.00006131317],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990142,0.00008227518,0.0003374629,0.0001900675,0.00021957389,0.00015642328],"domain_scores_gemma":[0.9992856,0.00026264455,0.00014620714,0.00016508004,0.00010055596,0.000039936327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036376662,0.00011416026,0.0004837171,0.00026915834,0.000069017064,0.000005312097,0.000092893235,0.00003071035,0.00042766496],"category_scores_gemma":[0.000023475788,0.000095938594,0.000038811333,0.00072548265,0.00031115973,0.000012605866,0.000050877672,0.00012758376,7.4334577e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009711486,0.00018230165,0.5554659,0.000011577302,0.00096366,0.0000041670414,0.0010635341,0.00012640079,0.0002505753,0.29743478,0.010454163,0.13394584],"study_design_scores_gemma":[0.0010108921,0.00045947556,0.8546743,0.00006695902,0.0012735052,7.377491e-8,0.00041902318,0.10986293,0.000036343063,0.031209398,0.0007656762,0.00022145589],"about_ca_topic_score_codex":0.00043424344,"about_ca_topic_score_gemma":0.00036866078,"teacher_disagreement_score":0.58332396,"about_ca_system_score_codex":0.000013614338,"about_ca_system_score_gemma":0.000008632656,"threshold_uncertainty_score":0.46826315},"labels":[],"label_agreement":null},{"id":"W2800193779","doi":"10.1002/sim.7675","title":"Dynamic thresholds and a summary ROC curve: Assessing prognostic accuracy of longitudinal markers","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Receiver operating characteristic; Computer science; Statistics; Mathematics; Machine learning","score_opus":0.020997980025216547,"score_gpt":0.35293424950437674,"score_spread":0.3319362694791602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800193779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8364415,0.0020110449,0.12859471,0.002336717,0.000667668,0.0013355042,0.000109015906,0.00007019742,0.028433623],"genre_scores_gemma":[0.9487804,0.00036008054,0.049777683,0.00026927402,0.00015265125,0.000016686916,0.00011728596,0.00003010658,0.0004958154],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99823284,0.000045858258,0.00055539206,0.0003520901,0.0004946135,0.000319221],"domain_scores_gemma":[0.9983488,0.00076530286,0.00022261307,0.0003341654,0.00020057875,0.00012856709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066832535,0.00020664283,0.00051996997,0.00027748692,0.000047654863,0.000010315001,0.000118914824,0.00007359289,0.0002377855],"category_scores_gemma":[0.003020334,0.00016971596,0.000018924007,0.00033603804,0.00090666005,0.000082321356,0.00014126532,0.00026959137,0.0000047784047],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039974658,0.00016610447,0.87984145,0.001267039,0.00021028305,0.0005349987,0.0007036867,0.0000016529633,0.0026111808,0.0010969583,0.07703455,0.036132358],"study_design_scores_gemma":[0.003933293,0.0013226647,0.9759091,0.0027272853,0.0005141264,0.00014703935,0.0012316565,0.010764026,0.000102957514,0.0009954985,0.0021233873,0.00022893792],"about_ca_topic_score_codex":0.00009912225,"about_ca_topic_score_gemma":0.00007808083,"teacher_disagreement_score":0.11233889,"about_ca_system_score_codex":0.0001048751,"about_ca_system_score_gemma":0.000099321325,"threshold_uncertainty_score":0.6920816},"labels":[],"label_agreement":null},{"id":"W2801071792","doi":"10.1002/sim.7646","title":"Tracing studies in cohorts with attrition: Selection models for efficient sampling","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Liver Disease Diagnosis and Treatment","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Cohort; Estimator; Statistics; Sampling (signal processing); Attrition; Tracing; Selection (genetic algorithm); Simple random sample; Computer science; Medicine; Cohort study; Econometrics; Mathematics; Machine learning; Environmental health","score_opus":0.11554361333381112,"score_gpt":0.40594295539019143,"score_spread":0.2903993420563803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801071792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69751483,0.0024979482,0.29609773,0.0009451861,0.000356971,0.0019105559,0.00011800304,0.00004313645,0.0005156272],"genre_scores_gemma":[0.96800613,0.00020199145,0.030956823,0.00021102597,0.00028942802,0.00020180512,0.00008787937,0.000016114853,0.000028809667],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989914,0.000021149484,0.0002838223,0.00025325245,0.00023956886,0.00021085251],"domain_scores_gemma":[0.9991127,0.00037002322,0.000058094833,0.00009779156,0.00028674005,0.00007463009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026549157,0.00012751501,0.00037822095,0.0001798063,0.00006710363,0.0000037480108,0.00002245208,0.000031451364,0.000027101625],"category_scores_gemma":[0.0002040894,0.00008958882,0.000014212104,0.0002443538,0.00020414402,0.000024640865,0.00000813293,0.00008088801,0.0000016178099],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010387156,0.008632175,0.69704986,0.008232114,0.002587617,0.0018924058,0.053081073,0.043487396,0.00081496645,0.08696483,0.022470357,0.06440006],"study_design_scores_gemma":[0.059952874,0.020502951,0.47771737,0.022427808,0.0030047814,0.00021823322,0.011689997,0.3530537,0.002543174,0.047206737,0.0006283673,0.0010539967],"about_ca_topic_score_codex":0.00011120689,"about_ca_topic_score_gemma":0.00034583668,"teacher_disagreement_score":0.30956632,"about_ca_system_score_codex":0.0002507138,"about_ca_system_score_gemma":0.000059134076,"threshold_uncertainty_score":0.36533263},"labels":[],"label_agreement":null},{"id":"W2801251405","doi":"10.1002/sim.7680","title":"Time series analysis of fMRI data: Spatial modelling and Bayesian computation","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Institute of Neurological Disorders and Stroke; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Computer science; Computation; Approximate Bayesian computation; Bayesian probability; Bayes' theorem; Statistical inference; Algorithm; Inference; Bayesian inference; Statistical parametric mapping; Parametric statistics; Artificial intelligence; Machine learning; Statistics; Mathematics","score_opus":0.07775302964608646,"score_gpt":0.4042363175240131,"score_spread":0.3264832878779267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801251405","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013864584,0.000025869063,0.9969084,0.0001269067,0.00008253386,0.000107089625,0.00063861144,0.000013988297,0.00071011565],"genre_scores_gemma":[0.12804835,0.000030121264,0.8715585,0.00002767074,0.00010439915,0.0000017675451,0.00018791988,0.000010532269,0.000030763822],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986141,0.00013842186,0.00054130575,0.00027081373,0.0002781391,0.00015722286],"domain_scores_gemma":[0.99719024,0.0020750104,0.00018129774,0.00030816783,0.00017829101,0.00006699342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089407025,0.00012229502,0.00055984536,0.00026067052,0.00004639727,0.000009009098,0.00014651717,0.00005119959,0.00034332575],"category_scores_gemma":[0.0020377752,0.000100983445,0.000010099263,0.0004813504,0.00070646073,0.0000637445,0.000080716134,0.00010523496,0.0000021014346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018453892,0.00013527992,0.0028423457,0.0004474825,0.0006173376,0.000044712484,0.0042881877,0.00041275748,0.00020605027,0.8771724,0.004884725,0.10876418],"study_design_scores_gemma":[0.00019824659,0.00014690965,0.0011332271,0.000062788145,0.00039948965,0.0000012852906,0.00008186141,0.5600784,0.000015575262,0.437798,0.000019321931,0.000064894695],"about_ca_topic_score_codex":0.00032094985,"about_ca_topic_score_gemma":0.00035897212,"teacher_disagreement_score":0.5596656,"about_ca_system_score_codex":0.000014668292,"about_ca_system_score_gemma":0.000027950504,"threshold_uncertainty_score":0.41179854},"labels":[],"label_agreement":null},{"id":"W2801930703","doi":"10.1002/sim.7655","title":"Quantile regression with nominated samples: An application to a bone mineral density study","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Quantile; Statistics; Quantile regression; Covariate; Sampling (signal processing); Mathematics; Simple random sample; Maxima and minima; Conditional probability distribution; Maxima; Econometrics; Population; Computer science","score_opus":0.09116800202283325,"score_gpt":0.4430228777902052,"score_spread":0.35185487576737196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801930703","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3442687,0.0000029805108,0.6547943,0.00008425475,0.0000705064,0.00052711205,0.000050301303,0.00003032832,0.00017152079],"genre_scores_gemma":[0.54262024,0.0000010364016,0.4570346,0.00010306134,0.00011763192,0.000038889862,0.000019334624,0.000015475325,0.00004976399],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982506,0.00022187486,0.00046204013,0.000400033,0.00040321122,0.00026222167],"domain_scores_gemma":[0.9976757,0.001155248,0.00014098661,0.00049027114,0.00034958313,0.00018821548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010626094,0.00018976023,0.0004594719,0.00014276287,0.00008998618,0.000012674546,0.00015892972,0.00005089637,0.0001753908],"category_scores_gemma":[0.0041873283,0.00012529673,0.0000063131415,0.00038983906,0.00025406017,0.000033603163,0.00005048505,0.0001705525,0.000012840821],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017186773,0.0025569494,0.043443173,0.00028627005,0.0000643917,0.00030510736,0.026882563,0.0000046730165,0.011087138,0.7634817,0.015361833,0.13480756],"study_design_scores_gemma":[0.006311105,0.021268174,0.25081545,0.0009262297,0.00029539698,0.00005925773,0.011121149,0.048517205,0.0008061514,0.658414,0.0004910791,0.0009747868],"about_ca_topic_score_codex":0.0007155509,"about_ca_topic_score_gemma":0.0023445413,"teacher_disagreement_score":0.20737226,"about_ca_system_score_codex":0.0000546807,"about_ca_system_score_gemma":0.000037364924,"threshold_uncertainty_score":0.51094526},"labels":[],"label_agreement":null},{"id":"W2802284801","doi":"10.1002/sim.7628","title":"Targeted maximum likelihood estimation for a binary treatment: A tutorial","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":134,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Instituto de Salud Carlos III; Canadian Institutes of Health Research; Cancer Research UK","keywords":"Computer science; Outcome (game theory); Nonparametric statistics; Contrast (vision); Propensity score matching; Code (set theory); Parametric statistics; Binary number; Estimation; Specification; Statistics; Machine learning; Artificial intelligence; Programming language; Mathematics","score_opus":0.08412398744132396,"score_gpt":0.43726232599602827,"score_spread":0.35313833855470433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802284801","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032846145,0.00004301249,0.9936074,0.00025056483,0.0006474024,0.0008557629,0.00021809136,0.00019996708,0.00089318835],"genre_scores_gemma":[0.06632053,0.00003650641,0.9320358,0.000078183184,0.0008941125,0.0002510759,0.00018681452,0.00004011645,0.00015687045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99876165,0.000044402,0.00044001365,0.00023992622,0.00020867428,0.00030532407],"domain_scores_gemma":[0.9981365,0.001135008,0.00015869693,0.0002782453,0.00021758268,0.00007392601],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037924206,0.00019326626,0.0003663975,0.0001661189,0.00007145414,0.0000076830775,0.00011311107,0.00009363888,0.00018988756],"category_scores_gemma":[0.0034552873,0.00015356664,0.000019771338,0.00019767015,0.0002476707,0.00007209341,0.000022202412,0.00009219329,0.0000120741515],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055065675,0.0004527057,0.0001593507,0.00028915956,0.00007478885,0.00006172775,0.0048281723,0.0000048881484,0.007323329,0.771125,0.062431876,0.15269832],"study_design_scores_gemma":[0.0018123838,0.0031541423,0.000066221626,0.00015550107,0.00006208035,0.0000041644325,0.00010921532,0.01039346,0.0022401768,0.9793828,0.002469064,0.00015079985],"about_ca_topic_score_codex":0.0000599916,"about_ca_topic_score_gemma":0.00012141805,"teacher_disagreement_score":0.20825778,"about_ca_system_score_codex":0.00023088453,"about_ca_system_score_gemma":0.00007590844,"threshold_uncertainty_score":0.62622654},"labels":[],"label_agreement":null},{"id":"W2804840181","doi":"10.1002/sim.7805","title":"Nonparametric analysis of dependently interval‐censored failure time data","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Estimator; Statistics; Confidence interval; Parametric statistics; Weighting; Inverse probability weighting; Econometrics; Interval (graph theory); Accelerated failure time model; Observational study; Mathematics; Computer science; Covariate; Medicine","score_opus":0.10310703289422077,"score_gpt":0.4403236091353544,"score_spread":0.33721657624113366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804840181","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006524649,0.000045110755,0.9879002,0.00016210004,0.00016663331,0.00016758338,0.0018120196,0.000022175154,0.0031995282],"genre_scores_gemma":[0.1865019,0.000022063741,0.8127641,0.00009325253,0.00011280896,0.0000036422296,0.00024012856,0.000017821854,0.00024430524],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977048,0.00023001236,0.00085378456,0.00039464288,0.0005465412,0.00027022805],"domain_scores_gemma":[0.99275327,0.005437502,0.0002913971,0.0010674137,0.0003416398,0.00010879506],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016536055,0.00017406956,0.0008879712,0.00075577374,0.000031537125,0.000009558938,0.0006772447,0.00008437627,0.0044563496],"category_scores_gemma":[0.029169703,0.00013519313,0.000029196091,0.0022071654,0.000566279,0.000043277556,0.00023244356,0.0002164219,0.000042347838],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013715294,0.00037621628,0.0068319533,0.00031708844,0.0014421738,0.00008855179,0.0017530995,0.0000041384023,0.001009213,0.8382733,0.09074835,0.05901878],"study_design_scores_gemma":[0.0015426097,0.0010024476,0.02514551,0.00035192218,0.0034763745,0.0000066190573,0.0006676119,0.3130842,0.00023501395,0.6529943,0.0010827568,0.0004106565],"about_ca_topic_score_codex":0.00025944275,"about_ca_topic_score_gemma":0.0005157918,"teacher_disagreement_score":0.31308004,"about_ca_system_score_codex":0.000044652978,"about_ca_system_score_gemma":0.000042177053,"threshold_uncertainty_score":0.9964537},"labels":[],"label_agreement":null},{"id":"W2805176315","doi":"10.1002/sim.7837","title":"A single‐index threshold Cox proportional hazard model for identifying a treatment‐sensitive subset based on multiple biomarkers","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Canadian Cancer Society","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Proportional hazards model; Estimator; Statistics; Hazard; Hazard ratio; Mathematics; Likelihood function; Computer science; Medicine; Oncology; Maximum likelihood; Biology; Confidence interval","score_opus":0.5433031768834886,"score_gpt":0.5514168099636382,"score_spread":0.008113633080149563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805176315","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043620644,0.0000073204,0.9891508,0.0005954544,0.000737206,0.0016549845,0.0025265713,0.00007275459,0.0008927981],"genre_scores_gemma":[0.34630737,0.000004327092,0.6524093,0.00040886112,0.00041374538,0.000152759,0.00008555992,0.000054298158,0.00016378851],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99642414,0.0003198065,0.001301064,0.00065948465,0.0007679061,0.000527626],"domain_scores_gemma":[0.94326353,0.055162076,0.00042320188,0.00047970618,0.00046877048,0.00020269616],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0028488995,0.0003682244,0.0009446572,0.0002669554,0.00015347262,0.00002539137,0.00018399568,0.00019252439,0.0001811615],"category_scores_gemma":[0.12200315,0.0002839303,0.000093913295,0.00028695262,0.001038013,0.00003780517,0.000034894554,0.00021276755,0.00001171482],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.026062548,0.007931798,0.016719278,0.0020862196,0.001565644,0.0009244887,0.005593231,0.0016505161,0.00834155,0.7379597,0.12180312,0.0693619],"study_design_scores_gemma":[0.0049046483,0.0013818479,0.000506392,0.00032074633,0.00013032573,0.000002262732,0.00009385498,0.522146,0.0005366532,0.46975777,0.000041373125,0.0001781438],"about_ca_topic_score_codex":0.00003367732,"about_ca_topic_score_gemma":0.0004233498,"teacher_disagreement_score":0.5204955,"about_ca_system_score_codex":0.00036068258,"about_ca_system_score_gemma":0.00019131797,"threshold_uncertainty_score":0.99996126},"labels":[],"label_agreement":null},{"id":"W2807223243","doi":"10.1002/sim.7689","title":"Regulatory assessment of drug dissolution profiles comparability via maximum deviation","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Comparability; Bioequivalence; Statistics; Standard deviation; Mathematics; Dissolution testing; Benchmark (surveying); Similarity (geometry); Computer science; Econometrics; Medicine; Drug; Pharmacology; Pharmacokinetics","score_opus":0.3097714492522006,"score_gpt":0.5680756412596896,"score_spread":0.25830419200748894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807223243","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036656212,0.00002311257,0.9589549,0.0003625201,0.0009605884,0.0006762319,0.00020662174,0.00004035415,0.0021195016],"genre_scores_gemma":[0.42221507,0.000008206198,0.5773846,0.00004024987,0.000263303,0.000021164702,0.000015195073,0.000014432539,0.000037807706],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99582857,0.0011077579,0.00166422,0.00036744002,0.00075677485,0.0002752278],"domain_scores_gemma":[0.9744878,0.023756834,0.0006129361,0.0005659462,0.00046720155,0.00010927387],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007470231,0.00018884259,0.00086888537,0.00012373172,0.00006097667,0.000004864201,0.00021791377,0.00010632037,0.0007681364],"category_scores_gemma":[0.054238692,0.000152889,0.000035058918,0.00030984124,0.0013094866,0.000041291158,0.00007440526,0.0002917557,0.0000079118845],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014894785,0.0004912255,0.03254878,0.000837889,0.00005619357,0.0000073934734,0.00067875086,0.000003679839,0.0011715889,0.92236614,0.0152961165,0.02639327],"study_design_scores_gemma":[0.0010364112,0.00030616228,0.15933853,0.00025926466,0.00007780042,0.0000011591281,0.00009419567,0.006646871,0.0004629167,0.8315724,0.00008503394,0.00011922584],"about_ca_topic_score_codex":0.000074980504,"about_ca_topic_score_gemma":0.000121273755,"teacher_disagreement_score":0.38555887,"about_ca_system_score_codex":0.00018611878,"about_ca_system_score_gemma":0.00009493681,"threshold_uncertainty_score":0.95372784},"labels":[],"label_agreement":null},{"id":"W2808396915","doi":"10.1002/sim.7841","title":"Tweedie family of generalized linear models with distribution‐free random effects for skewed longitudinal data","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Division of Mathematical Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Random effects model; Skewness; Generalized linear mixed model; Covariance; Mathematics; Econometrics; Linear model; Mixed model; Statistics; Flexibility (engineering); Population; Computer science; Medicine","score_opus":0.13676609651227098,"score_gpt":0.4275039299316327,"score_spread":0.29073783341936177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808396915","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013286258,0.00009874918,0.99106294,0.00015195007,0.00027886566,0.000732932,0.005967316,0.000025643934,0.00035295094],"genre_scores_gemma":[0.032067664,0.000043400512,0.9665942,0.00006487763,0.00040900876,0.00004902522,0.0007011164,0.00002910175,0.00004158268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979719,0.00016726417,0.0006633218,0.00040152142,0.00045876455,0.000337229],"domain_scores_gemma":[0.9908963,0.007297766,0.00024986514,0.00094500865,0.0004951079,0.000115938616],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014817311,0.00022512604,0.0008193249,0.00007304587,0.00007536646,0.00000834569,0.00055311964,0.00008020024,0.000049068276],"category_scores_gemma":[0.014594578,0.00015290757,0.000019411922,0.00025024422,0.0007870678,0.00006709118,0.00014939874,0.00015894794,0.0000014139541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010613523,0.00011690612,0.00020834236,0.00073391554,0.00008448733,0.000025821437,0.0002016929,0.0000037247762,0.00024300622,0.9573484,0.032685436,0.0072869393],"study_design_scores_gemma":[0.00903333,0.0011105074,0.0008292569,0.00050442934,0.0002645362,0.0000047785893,0.00003872141,0.12034986,0.00019070541,0.8672922,0.00021099456,0.00017063832],"about_ca_topic_score_codex":0.00016747843,"about_ca_topic_score_gemma":0.00013432113,"teacher_disagreement_score":0.12034614,"about_ca_system_score_codex":0.000035622565,"about_ca_system_score_gemma":0.00009887754,"threshold_uncertainty_score":0.9937059},"labels":[],"label_agreement":null},{"id":"W2808447433","doi":"10.1002/sim.7845","title":"Estimation for zero‐inflated beta‐binomial regression model with missing response data","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Overdispersion; Statistics; Missing data; Mathematics; Negative binomial distribution; Expectation–maximization algorithm; Count data; Zero-inflated model; Quasi-likelihood; Mean squared error; Regression analysis; Econometrics; Maximum likelihood; Poisson regression; Poisson distribution","score_opus":0.16683890694722295,"score_gpt":0.47400700736848506,"score_spread":0.3071681004212621,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808447433","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017718833,0.000017261043,0.9956458,0.0008894512,0.00016033422,0.00043023122,0.00066817383,0.00004382132,0.00037303803],"genre_scores_gemma":[0.03860993,0.000005428598,0.96071327,0.000120756384,0.00014857306,0.000017982236,0.00020523067,0.000035364388,0.00014348449],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981674,0.00021033132,0.0005524033,0.0004105507,0.00035594078,0.00030335903],"domain_scores_gemma":[0.99321556,0.005497875,0.00022817397,0.00069432345,0.0002447383,0.00011931048],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022576523,0.0002030066,0.00043015886,0.00013535462,0.00014344146,0.000023841521,0.00031455976,0.00009906702,0.00008999784],"category_scores_gemma":[0.015568512,0.00013689023,0.000008652636,0.0001998637,0.0004783393,0.00009773264,0.00008023384,0.00019176237,0.0000041151093],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005791254,0.00012489986,0.00013418036,0.00042192498,0.00004579684,0.00005650143,0.001749977,0.00004580542,0.0024010858,0.5914152,0.063818075,0.33399528],"study_design_scores_gemma":[0.0011118487,0.00042232877,0.00020115425,0.0005172975,0.00006522168,0.0000054587676,0.00002966435,0.49900147,0.00016670693,0.49825442,0.000114631206,0.00010979124],"about_ca_topic_score_codex":0.000024198831,"about_ca_topic_score_gemma":0.000038316408,"teacher_disagreement_score":0.49895567,"about_ca_system_score_codex":0.00006312259,"about_ca_system_score_gemma":0.00017722679,"threshold_uncertainty_score":0.99272376},"labels":[],"label_agreement":null},{"id":"W2808494377","doi":"10.1002/sim.7835","title":"A Bayesian finite mixture of bivariate regression model for causal mediation analyses","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Pregnancy and Medication Impact","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Hôpital du Sacré-Cœur de Montréal; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Public Health Agency","keywords":"Categorical variable; Statistics; Mixture model; Bivariate analysis; Mediation; Econometrics; Bayesian probability; Regression analysis; Outcome (game theory); Confounding; Identifiability; Mathematics","score_opus":0.07185331397151307,"score_gpt":0.4371229684999162,"score_spread":0.36526965452840315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808494377","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015434786,0.0004191665,0.99420613,0.0017759334,0.00030929985,0.00045296332,0.00025440738,0.000022907298,0.001015706],"genre_scores_gemma":[0.9183948,0.0002461077,0.07903887,0.0006428911,0.0004893803,0.000033732376,0.00048758657,0.000020885507,0.00064572284],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985485,0.000046744306,0.0005527658,0.00021880111,0.0004080016,0.00022519269],"domain_scores_gemma":[0.9983334,0.0005603094,0.00027070145,0.0003014252,0.00036451803,0.00016967423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055718987,0.0001458474,0.00046100488,0.00032096554,0.000045239165,0.0000020361533,0.000086185195,0.00012327488,0.00018715422],"category_scores_gemma":[0.005664331,0.00010027666,0.00003074281,0.00033017545,0.00031572997,0.000045074346,0.000012715024,0.00016084929,0.000002908891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009555814,0.0020387943,0.041448373,0.0074552572,0.0011646929,0.00025472307,0.07720371,0.0026606414,0.17589419,0.07754549,0.41738537,0.18739294],"study_design_scores_gemma":[0.0061046355,0.0014207808,0.010249548,0.002714036,0.00038439754,0.000012510902,0.00028727562,0.9515462,0.0027687885,0.02368246,0.0006651891,0.00016420221],"about_ca_topic_score_codex":0.000050105653,"about_ca_topic_score_gemma":0.000071008195,"teacher_disagreement_score":0.94888556,"about_ca_system_score_codex":0.00005229202,"about_ca_system_score_gemma":0.00025048235,"threshold_uncertainty_score":0.67811424},"labels":[],"label_agreement":null},{"id":"W2883076904","doi":"10.1002/sim.7896","title":"Analyzing differences between microbiome communities using mixture distributions","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Statistics; Mixture model; Poisson distribution; Mixture distribution; Mathematics; Count data; Truncation (statistics); Pairwise comparison; Sample size determination; Population; Computer science; Algorithm; Probability density function","score_opus":0.03552064600994028,"score_gpt":0.34900303886493295,"score_spread":0.3134823928549927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883076904","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8500589,0.00042885097,0.1479193,0.00023660525,0.00019230066,0.00009520787,0.00090119673,0.000006660078,0.00016099379],"genre_scores_gemma":[0.98693293,0.00016669114,0.0105421,0.00012918896,0.0005772464,0.0000018133171,0.0015533525,0.000010777683,0.00008590512],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99919015,0.00009006006,0.00025860989,0.00014564894,0.00006274575,0.00025281293],"domain_scores_gemma":[0.9994596,0.000049432692,0.00007801603,0.00023128912,0.00011562561,0.000066020155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022351895,0.00012363055,0.00021546091,0.000084042884,0.00018543964,0.000009884746,0.00016944278,0.00010092489,0.00008329685],"category_scores_gemma":[0.00008409292,0.000105330495,0.000015234528,0.0001555035,0.00058844924,0.0000018077288,0.00007679139,0.00015072698,0.0000042464194],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031980453,0.000052203482,0.2941638,0.000104812374,0.00007664819,0.000006166393,0.001178577,0.0000012574492,0.6881905,0.0016429302,0.012889396,0.0016616987],"study_design_scores_gemma":[0.003498854,0.0024410496,0.91679746,0.00094727013,0.00030575774,0.00006880744,0.0043313205,0.0005265204,0.024526402,0.00597674,0.03947766,0.0011021455],"about_ca_topic_score_codex":0.00064460986,"about_ca_topic_score_gemma":0.0011691554,"teacher_disagreement_score":0.6636641,"about_ca_system_score_codex":0.000029812649,"about_ca_system_score_gemma":0.000068468136,"threshold_uncertainty_score":0.4295253},"labels":[],"label_agreement":null},{"id":"W2884919358","doi":"10.1002/sim.7908","title":"Modeling the random effects covariance matrix for longitudinal data with covariates measurement error","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Random effects model; Statistics; Estimator; Covariance; Covariance matrix; Mathematics; Generalized linear mixed model; Computer science","score_opus":0.18409707406414916,"score_gpt":0.4458210375468594,"score_spread":0.26172396348271026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884919358","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00013384635,0.0001716444,0.99696016,0.00073804526,0.0003985577,0.0010292712,0.00035244483,0.000029265231,0.00018675257],"genre_scores_gemma":[0.08945798,0.000018236846,0.9097766,0.00013500059,0.00044164783,0.000077486686,0.000039601873,0.000030373476,0.000023067627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977476,0.00023432146,0.0005233595,0.00044626903,0.00067198754,0.0003764357],"domain_scores_gemma":[0.99182373,0.006576716,0.00014448886,0.000836948,0.00053350773,0.00008458105],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00432161,0.00022685151,0.0005389693,0.000060839542,0.00019229422,0.000031205152,0.00055293407,0.000056081193,0.000088627596],"category_scores_gemma":[0.020027293,0.00012377408,0.000013325715,0.00022058122,0.00046103846,0.000055202665,0.00009772157,0.00021940198,0.0000052165233],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00095920236,0.00008911637,0.000230428,0.00066133856,0.00011918653,0.000033987802,0.00067687815,0.00004392693,0.00008660086,0.9781699,0.00994115,0.008988265],"study_design_scores_gemma":[0.0034444104,0.0005247191,0.0002639142,0.00059531844,0.0002346265,0.000010047622,0.00010764173,0.35931712,0.000025558165,0.6351912,0.00014145294,0.00014398985],"about_ca_topic_score_codex":0.00016885911,"about_ca_topic_score_gemma":0.0005665634,"teacher_disagreement_score":0.3592732,"about_ca_system_score_codex":0.000060775616,"about_ca_system_score_gemma":0.0001258754,"threshold_uncertainty_score":0.9882274},"labels":[],"label_agreement":null},{"id":"W2886727084","doi":"10.1002/sim.7854","title":"A validation sampling approach for consistent estimation of adverse drug reaction risk with misclassified right‐censored survival data","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Carleton University; Institute of Population and Public Health; McGill University Health Centre; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; McGill University","keywords":"Estimator; Statistics; Univariate; Proportional hazards model; Unobservable; Event (particle physics); Computer science; Consistency (knowledge bases); Estimation; Econometrics; Sampling (signal processing); Survival analysis; Mathematics; Multivariate statistics; Artificial intelligence","score_opus":0.1482219059636884,"score_gpt":0.4136559518495407,"score_spread":0.2654340458858523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886727084","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048927898,0.0000049758273,0.9869097,0.00015657353,0.00010746626,0.00086289976,0.0058631706,0.000046905345,0.0011555449],"genre_scores_gemma":[0.35780644,0.0000070604656,0.63552874,0.000014121332,0.00007511607,0.00006773209,0.006419999,0.000016149392,0.00006463058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982057,0.00011594099,0.00071047567,0.00036879306,0.00041037172,0.0001887181],"domain_scores_gemma":[0.9963708,0.0019032558,0.0005414675,0.0005848228,0.0005175434,0.000082125895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010659875,0.00016241732,0.00036077632,0.00012002696,0.00014859,0.0000068619934,0.00019557549,0.00005918337,0.00009143962],"category_scores_gemma":[0.0057411822,0.00012959277,0.000015853415,0.00030839792,0.00048133577,0.00009272836,0.000033114182,0.00013781746,0.000004643541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023822447,0.000285183,0.00025891073,0.0003191305,0.000059656824,7.5923606e-7,0.0004994556,0.00033810674,0.0003706687,0.9877235,0.0069682533,0.0029381227],"study_design_scores_gemma":[0.0033219028,0.00022326126,0.008297509,0.00020476316,0.00043105154,0.000005804616,0.0012232462,0.784894,0.00048308333,0.20029561,0.00038105398,0.0002387167],"about_ca_topic_score_codex":0.00009583193,"about_ca_topic_score_gemma":0.00007427268,"teacher_disagreement_score":0.7874279,"about_ca_system_score_codex":0.00008531164,"about_ca_system_score_gemma":0.00007685643,"threshold_uncertainty_score":0.6873146},"labels":[],"label_agreement":null},{"id":"W2887614096","doi":"10.1002/sim.7693","title":"Comparing predictive abilities of longitudinal child growth models","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Child Nutrition and Water Access","field":"Nursing","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fogarty International Center; Fundação de Amparo à Pesquisa do Estado do Rio Grande do Sul; Department for International Development; Nutricia Research Foundation; British Heart Foundation; Wellcome Trust; Department for International Development, UK Government; World Health Organization; Ministério da Saúde; South African Medical Research Council; Department of Science and Technology, Ministry of Science and Technology, India; Wenner-Gren Foundation; Carolina Population Center, University of North Carolina at Chapel Hill; Andrew W. Mellon Foundation; Bill and Melinda Gates Foundation; National Institutes of Health; Indian Council of Medical Research; International Development Research Centre; United States Agency for International Development; National Science Foundation","keywords":"Estimation; Raw data; Computer science; Psychological intervention; Work (physics); Longitudinal data; Child development; Econometrics; Data science; Data mining; Psychology; Economics; Developmental psychology","score_opus":0.036968192901476814,"score_gpt":0.3174421561511075,"score_spread":0.2804739632496307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887614096","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6244585,0.0005504622,0.30423966,0.00422585,0.0030697333,0.0008212759,0.00047504067,0.000135696,0.062023766],"genre_scores_gemma":[0.99552035,0.000023507992,0.003633393,0.00018751645,0.00054576277,0.000005863202,0.00005107464,0.000014079007,0.00001844253],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99885094,0.00005634941,0.0004049298,0.00020355693,0.00028848482,0.00019572192],"domain_scores_gemma":[0.9992406,0.00021332075,0.00008805312,0.00016176928,0.00023737874,0.00005890544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025050313,0.000117469055,0.00033133794,0.00018624893,0.000071166185,0.000007200632,0.00014756038,0.00004026968,0.00011242635],"category_scores_gemma":[0.00027038628,0.000101044236,0.000015719479,0.00018957218,0.00073572586,0.000101229285,0.000039641418,0.00017723543,0.000003402608],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024246706,0.00061112695,0.7698198,0.0011920142,0.00009266187,0.000031235704,0.02789277,0.00030317288,0.00014587965,0.15723476,0.039116126,0.0011357832],"study_design_scores_gemma":[0.005387743,0.0018622308,0.47827953,0.0017120902,0.00010120554,0.000027633949,0.0011507293,0.058927007,0.003662445,0.44835815,0.00023821801,0.00029302304],"about_ca_topic_score_codex":0.0006398083,"about_ca_topic_score_gemma":0.00025832222,"teacher_disagreement_score":0.37106186,"about_ca_system_score_codex":0.000058024743,"about_ca_system_score_gemma":0.0000072884477,"threshold_uncertainty_score":0.41204643},"labels":[],"label_agreement":null},{"id":"W2888844257","doi":"10.1002/sim.7942","title":"Estimation in generalized linear models under censored covariates with an application to MIREC data","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Health Canada","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Health Canada; Ministry of Natural Resources","keywords":"Covariate; Estimator; Generalized linear model; Statistics; Econometrics; Generalized estimating equation; Computer science; Linear model; Mathematics","score_opus":0.1248335094346998,"score_gpt":0.45313467404832947,"score_spread":0.3283011646136297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888844257","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021374994,0.000008333652,0.9960465,0.0004841975,0.00007167974,0.0005005478,0.0003494917,0.00003557672,0.00036619883],"genre_scores_gemma":[0.07126544,0.000009017165,0.9277991,0.0003319199,0.00012264316,0.000043435855,0.0003797291,0.000026906813,0.000021812837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982645,0.00019048591,0.000511163,0.00044124946,0.00033765807,0.00025492933],"domain_scores_gemma":[0.99775344,0.0010696761,0.00011868368,0.0007542296,0.00017345112,0.0001305234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010591933,0.00016968766,0.0003808143,0.00016731328,0.00004609786,0.000015050452,0.00033349922,0.0000704199,0.00011569467],"category_scores_gemma":[0.0020792785,0.0001288168,0.0000037961486,0.0004309345,0.00021324768,0.0001202342,0.00006852798,0.0001527357,0.0000121926205],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016280643,0.000096417556,0.00012453007,0.00005531706,0.000008837704,0.000008844742,0.0007994958,0.00038419417,0.00017632404,0.96431655,0.0009013699,0.03296529],"study_design_scores_gemma":[0.0006054157,0.00024026088,0.0007603992,0.00009204803,0.000019383211,0.00000212549,0.00007664351,0.47977176,0.000030021833,0.518283,0.000026123082,0.00009282833],"about_ca_topic_score_codex":0.0008393061,"about_ca_topic_score_gemma":0.0022519159,"teacher_disagreement_score":0.47938755,"about_ca_system_score_codex":0.00006363025,"about_ca_system_score_gemma":0.000064212014,"threshold_uncertainty_score":0.52529967},"labels":[],"label_agreement":null},{"id":"W2890626091","doi":"10.1002/sim.7963","title":"Modeling semicontinuous longitudinal data with order constraints","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Inference; Computer science; Longitudinal data; Statistical inference; Econometrics; Statistical hypothesis testing; Joint (building); Machine learning; Statistics; Data mining; Artificial intelligence; Mathematics","score_opus":0.12914742725631273,"score_gpt":0.43149439201528045,"score_spread":0.3023469647589677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890626091","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001567368,0.000028556955,0.99187005,0.0001923183,0.00020004601,0.0001855447,0.00039982403,0.000037064056,0.0055192183],"genre_scores_gemma":[0.14817256,0.000015583537,0.851259,0.00011833729,0.00028934935,0.0000055310325,0.0000609972,0.000023339013,0.000055304594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982495,0.00010159266,0.00047740305,0.00043383482,0.00038704183,0.0003506274],"domain_scores_gemma":[0.99725956,0.0014871232,0.00009113628,0.0006945937,0.00035141403,0.00011619755],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001028352,0.00019085116,0.00044153785,0.00009426888,0.00007110909,0.000017785687,0.0003932646,0.00006241507,0.0013587085],"category_scores_gemma":[0.007461144,0.00013312898,0.000004973743,0.0002858689,0.0010919842,0.000060530827,0.00012024997,0.0002762092,0.00001822302],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008977273,0.000079950565,0.0025083679,0.00013248376,0.00004523829,0.00024370877,0.0006125865,0.0000031020609,0.00005539886,0.9135626,0.008787979,0.07387879],"study_design_scores_gemma":[0.0011520698,0.0004106777,0.00042099087,0.00051771785,0.00009156188,0.00007150813,0.0003615436,0.19385079,0.0000103940265,0.802759,0.000129988,0.00022376604],"about_ca_topic_score_codex":0.00017460146,"about_ca_topic_score_gemma":0.0006295788,"teacher_disagreement_score":0.19384769,"about_ca_system_score_codex":0.000028949486,"about_ca_system_score_gemma":0.00011383764,"threshold_uncertainty_score":0.99955416},"labels":[],"label_agreement":null},{"id":"W2893312973","doi":"10.1002/sim.7984","title":"Judgment post‐stratification in finite mixture modeling: An example in estimating the prevalence of osteoporosis","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Ranking (information retrieval); Statistics; Rank (graph theory); Small area estimation; Econometrics; Mathematics; Computer science; Expectation–maximization algorithm; Measure (data warehouse); Population; Data mining; Maximum likelihood; Artificial intelligence; Medicine","score_opus":0.05566959108421915,"score_gpt":0.3371850861906867,"score_spread":0.28151549510646756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893312973","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02086044,0.0001227652,0.9775602,0.0007628713,0.00021974463,0.000260956,0.000012783381,0.00001078702,0.00018943536],"genre_scores_gemma":[0.44578245,0.00001839784,0.5539066,0.00020718224,0.000048518636,0.000012731531,0.0000058065048,0.000004396149,0.000013925053],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99826336,0.00027892186,0.0005807219,0.00035319861,0.00030924738,0.00021456658],"domain_scores_gemma":[0.9985939,0.00047009523,0.00015286212,0.0005789096,0.00015682331,0.000047373465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021976347,0.00012240087,0.00022125745,0.00016818356,0.00004105119,0.000016820242,0.00058260374,0.000059811726,0.000015122542],"category_scores_gemma":[0.0005462344,0.000086946966,0.0000090269095,0.00047000762,0.0001606861,0.00014836097,0.000067259236,0.00023104915,8.5479047e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000722389,0.00042017526,0.0032552432,0.0009154763,0.000011392211,0.00004248682,0.11804821,0.03356989,0.0072630057,0.42541575,0.00035340223,0.41063273],"study_design_scores_gemma":[0.00032766262,0.0002561954,0.0025543277,0.00024573779,0.000005452635,0.0000018208384,0.00015202613,0.86796135,0.00015284072,0.12825863,0.000005928468,0.00007803397],"about_ca_topic_score_codex":0.0012615687,"about_ca_topic_score_gemma":0.00091503555,"teacher_disagreement_score":0.8343915,"about_ca_system_score_codex":0.000042160533,"about_ca_system_score_gemma":0.00007808986,"threshold_uncertainty_score":0.35455942},"labels":[],"label_agreement":null},{"id":"W2896981660","doi":"10.1002/sim.8008","title":"Propensity‐score matching with competing risks in survival analysis","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":147,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Statistics; Covariate; Observational study; Matching (statistics); Hazard ratio; Confounding; Sample size determination; Medicine; Absolute risk reduction; Confidence interval; Econometrics; Mathematics","score_opus":0.23846640406203207,"score_gpt":0.45839961939779816,"score_spread":0.2199332153357661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896981660","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38420707,0.000008850707,0.6120987,0.00008011199,0.000044554603,0.0002167269,0.000017417951,0.00007107168,0.0032555084],"genre_scores_gemma":[0.679157,0.000011427326,0.32061887,0.000051219322,0.00007424379,0.0000116385445,0.000021102493,0.000019138935,0.000035383302],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99836195,0.00015036904,0.0005061423,0.0002815475,0.00039681102,0.00030318016],"domain_scores_gemma":[0.99803936,0.0011553087,0.00021065355,0.000337415,0.0001971812,0.00006005298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013563909,0.00018286984,0.00063992233,0.0004041283,0.00005302934,0.000011069621,0.00018335029,0.00005705481,0.0001815781],"category_scores_gemma":[0.0015280439,0.00013422075,0.0000132893265,0.000995813,0.00039171067,0.00006452746,0.00007041612,0.00037852555,0.00000458181],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016463545,0.00015496157,0.594779,0.00023501359,0.0001877082,0.00047011403,0.0077371476,0.00012661873,0.00086593,0.3898057,0.0003330047,0.005140123],"study_design_scores_gemma":[0.0010501617,0.000599377,0.16653928,0.00085788534,0.0002909161,0.000009614103,0.0020042001,0.0027997028,0.0004367973,0.82500684,0.000037977577,0.00036726694],"about_ca_topic_score_codex":0.0012856661,"about_ca_topic_score_gemma":0.012935031,"teacher_disagreement_score":0.4352011,"about_ca_system_score_codex":0.00010829275,"about_ca_system_score_gemma":0.000036770347,"threshold_uncertainty_score":0.7218051},"labels":[],"label_agreement":null},{"id":"W2897505629","doi":"10.1002/sim.7990","title":"Methods to improve the estimation of time‐to‐event outcomes when data is de‐identified","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Ontario Institute for Cancer Research; Hamilton Health Sciences; University of Manitoba; Manitoba Health; Research Institute in Oncology and Hematology; Health Sciences Centre; CancerCare Manitoba; Cancer Care Ontario; McMaster University","funders":"","keywords":"Computer science; Identification (biology); Data set; Event (particle physics); Set (abstract data type); Estimation; Statistics; Patient confidentiality; Survival analysis; Data mining; Missing data; Confidentiality; Econometrics; Mathematics; Machine learning; Artificial intelligence","score_opus":0.0651600521362048,"score_gpt":0.43195683777357047,"score_spread":0.3667967856373657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897505629","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027472188,0.000023705108,0.93861556,0.05966119,0.00045999294,0.00032160632,0.0003494509,0.00007728258,0.00021651159],"genre_scores_gemma":[0.0036958472,0.000006225582,0.99418074,0.0017513932,0.000047120222,0.00001636042,0.000045689794,0.000009276234,0.00024736207],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981988,0.00017039098,0.00046963373,0.00046295585,0.00042858755,0.00026962074],"domain_scores_gemma":[0.98889995,0.0013830743,0.0001548491,0.009351635,0.00013916037,0.000071362316],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0037258302,0.00012733035,0.0002766781,0.00019416791,0.00006079254,0.000034198292,0.02055808,0.000054707405,0.00016358982],"category_scores_gemma":[0.103507526,0.00008686781,0.000009548984,0.0004915573,0.00025983158,0.0001676349,0.03681132,0.00017006467,0.00010468648],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000048883544,0.000017777278,0.0001377166,0.000019155887,0.00001812114,0.000003710627,0.0009228242,0.000010723774,0.00089106406,0.00327658,0.72982335,0.2648741],"study_design_scores_gemma":[0.00021390486,0.00018589264,0.0027126805,0.000078944366,0.00001763281,0.0000022077936,0.000042919397,0.5606783,0.0030910235,0.42920446,0.0036741216,0.000097889875],"about_ca_topic_score_codex":0.0004968183,"about_ca_topic_score_gemma":0.000073951574,"teacher_disagreement_score":0.7261492,"about_ca_system_score_codex":0.00007611071,"about_ca_system_score_gemma":0.000074032156,"threshold_uncertainty_score":0.98474115},"labels":[],"label_agreement":null},{"id":"W2902445064","doi":"10.1002/sim.8051","title":"Bayesian adaptive group lasso with semiparametric hidden Markov models","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute of Mental Health; Canadian Institutes of Health Research; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Covariate; Variable-order Bayesian network; Econometrics; Bayesian probability; Semiparametric regression; Prior probability; Mathematics; Lasso (programming language); Computer science; Nonparametric statistics; Bayesian inference; Artificial intelligence","score_opus":0.02237722273859513,"score_gpt":0.29250909172723244,"score_spread":0.2701318689886373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902445064","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00010036391,0.0002166664,0.97876847,0.0005405047,0.00037469144,0.00025484647,0.000022988695,0.00007246577,0.01964901],"genre_scores_gemma":[0.18205963,0.000051664912,0.8165627,0.0006715058,0.00025350522,0.000017539633,0.000007641704,0.000019854217,0.0003559585],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99774563,0.0002274581,0.00038116076,0.0005864752,0.00057984743,0.00047939742],"domain_scores_gemma":[0.99818444,0.0005834487,0.00014613781,0.00066647306,0.00021379396,0.00020571545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010873962,0.00024976337,0.0004315611,0.00041450115,0.000094952426,0.000037800488,0.00072221993,0.00009740866,0.000059788104],"category_scores_gemma":[0.00021676888,0.00018007355,0.00001761417,0.0013387272,0.00041031177,0.00025152718,0.00014450397,0.00033405644,0.00001229318],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049511942,0.00004886209,0.00014254595,0.000018275148,0.000024074492,0.00014912372,0.0014519168,0.000009691435,0.000027170945,0.7087268,0.007993979,0.281358],"study_design_scores_gemma":[0.0009991933,0.0011794298,0.0007122107,0.00014721608,0.000021546895,0.000036432757,0.00004977155,0.46077442,0.000029967348,0.53541917,0.00038470497,0.0002459493],"about_ca_topic_score_codex":0.00020110051,"about_ca_topic_score_gemma":0.00025401174,"teacher_disagreement_score":0.4607647,"about_ca_system_score_codex":0.00009264307,"about_ca_system_score_gemma":0.000089454516,"threshold_uncertainty_score":0.7343186},"labels":[],"label_agreement":null},{"id":"W2902926083","doi":"10.1002/sim.8048","title":"Using a monotone single‐index model to stabilize the propensity score in missing data problems and causal inference","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Causal inference; Propensity score matching; Inference; Missing data; Index (typography); Statistics; Monotone polygon; Computer science; Econometrics; Causal model; Mathematics; Artificial intelligence","score_opus":0.5427102071927957,"score_gpt":0.4837563441874663,"score_spread":0.0589538630053294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902926083","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15992899,0.000038081624,0.8382942,0.00040207457,0.000044168006,0.00089211826,0.00007884918,0.000051359304,0.00027013393],"genre_scores_gemma":[0.6315691,0.000017574359,0.36811656,0.00016416573,0.0000620922,0.000016220463,0.000012410615,0.000024011893,0.00001788538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998078,0.00011668192,0.00058974756,0.00046709087,0.0003758602,0.00037261503],"domain_scores_gemma":[0.997662,0.00094737276,0.00017021043,0.00089408114,0.0002192062,0.000107129155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014590839,0.00022627211,0.0004492509,0.00015964631,0.0000996256,0.000032499593,0.0004398406,0.000079599515,0.000021578759],"category_scores_gemma":[0.0072930283,0.00015626173,0.0000047272283,0.0003878123,0.0007195962,0.00019185744,0.00054739707,0.00038204962,9.455881e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008643889,0.0014559898,0.09131154,0.0028304541,0.00011203265,0.00042335354,0.07840657,0.0055215294,0.23451008,0.47285503,0.005642075,0.10606696],"study_design_scores_gemma":[0.000416172,0.00025499877,0.0010065957,0.0010776033,0.00002385539,0.000011712851,0.00024072482,0.37267357,0.00052510615,0.6235296,0.000037812162,0.00020222788],"about_ca_topic_score_codex":0.00063935854,"about_ca_topic_score_gemma":0.004915824,"teacher_disagreement_score":0.47164008,"about_ca_system_score_codex":0.00016668245,"about_ca_system_score_gemma":0.00013011499,"threshold_uncertainty_score":0.8730963},"labels":[],"label_agreement":null},{"id":"W2906741671","doi":"10.1002/sim.8075","title":"Should a propensity score model be super? The utility of ensemble procedures for causal adjustment","year":2018,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Propensity score matching; Covariate; Logistic regression; Statistics; Inverse probability weighting; Overfitting; Weighting; Regression; Matching (statistics); Mean squared error; Econometrics; Mathematics; Confounding; Computer science; Artificial intelligence; Medicine","score_opus":0.352053424871457,"score_gpt":0.4614552599099146,"score_spread":0.10940183503845757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906741671","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03792845,0.000066547014,0.9578023,0.000717934,0.00010097333,0.0016394295,0.0002672915,0.000072129515,0.0014049538],"genre_scores_gemma":[0.71152884,0.000040389456,0.2876122,0.00033202916,0.000113911585,0.00014931646,0.000022509294,0.000023288903,0.00017750659],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984712,0.000055640066,0.0005338228,0.00025788584,0.0003939316,0.00028750132],"domain_scores_gemma":[0.99778336,0.0009606837,0.00018022518,0.00047436167,0.0005441268,0.00005726732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009891925,0.00018680502,0.00044723361,0.00006447617,0.00007758097,0.000003991475,0.00025380932,0.00008410043,0.00008509209],"category_scores_gemma":[0.0056880265,0.00011361413,0.000022098746,0.0001450924,0.0008366736,0.000050803945,0.0000892793,0.0002079182,6.1175564e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032906758,0.00027674492,0.0012475343,0.0011620892,0.000043999513,0.0000064817436,0.005485426,0.000011079367,0.006251137,0.85309273,0.1263668,0.00572694],"study_design_scores_gemma":[0.0005562737,0.0007355502,0.0009763699,0.00030166106,0.00007748333,0.0000052359387,0.0003506729,0.032210447,0.011374189,0.95315444,0.00012361161,0.00013408318],"about_ca_topic_score_codex":0.00008929595,"about_ca_topic_score_gemma":0.0014791677,"teacher_disagreement_score":0.6736004,"about_ca_system_score_codex":0.000058171794,"about_ca_system_score_gemma":0.00018566572,"threshold_uncertainty_score":0.680951},"labels":[],"label_agreement":null},{"id":"W2908350920","doi":"10.1002/sim.8073","title":"Weighted causal inference methods with mismeasured covariates and misclassified outcomes","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Causal inference; Inverse probability weighting; Logistic regression; Econometrics; Computer science; Statistics; Weighting; Inference; Observational error; Regression; Estimation; Mathematics; Estimator; Artificial intelligence; Medicine","score_opus":0.1192263844432153,"score_gpt":0.4720951276343318,"score_spread":0.3528687431911165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908350920","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021505298,0.00008063695,0.9740934,0.0005481802,0.00014046257,0.0005619024,0.000057847257,0.00016704378,0.0028452307],"genre_scores_gemma":[0.14073057,0.000054381777,0.8582744,0.00016923471,0.000022188608,0.000034422235,0.000026228186,0.00003483178,0.00065373007],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99825877,0.00021541415,0.000490331,0.0003469413,0.00037618235,0.0003123894],"domain_scores_gemma":[0.9942502,0.0048211515,0.00021052854,0.0004117168,0.00019702029,0.000109380264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010253247,0.00027822106,0.0007241584,0.00017856013,0.00003642367,0.000015124726,0.0001691058,0.00011383705,0.0003188261],"category_scores_gemma":[0.0031876734,0.00018497772,0.000010848578,0.00024136719,0.0003150186,0.00008465518,0.000058671012,0.00038293944,0.0000065166964],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094895244,0.00007129945,0.057178196,0.00027195993,0.000075679316,0.000053268024,0.0012055368,0.0000018743847,0.0059905313,0.92565906,0.0010032993,0.008394423],"study_design_scores_gemma":[0.0018175808,0.00056055083,0.025049895,0.00041570625,0.00007948749,0.0000134714855,0.00038647806,0.001647307,0.0014873203,0.96785986,0.00035188123,0.00033044835],"about_ca_topic_score_codex":0.00010122991,"about_ca_topic_score_gemma":0.00016276025,"teacher_disagreement_score":0.11922528,"about_ca_system_score_codex":0.000067623936,"about_ca_system_score_gemma":0.00008154057,"threshold_uncertainty_score":0.7543173},"labels":[],"label_agreement":null},{"id":"W2910522615","doi":"10.1002/sim.8503","title":"Propensity scores using missingness pattern information: a practical guide","year":2020,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Healthcare Policy and Management","field":"Economics, Econometrics and Finance","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Health and Social Care Research and Development Division; Engineering and Physical Sciences Research Council; Economic and Social Research Council; Chief Scientist Office, Scottish Government Health and Social Care Directorate; Medical Research Council Canada; London School of Hygiene and Tropical Medicine; Medical Research Council; Public Health Agency; Department of Health and Social Care; Scottish Government; British Heart Foundation; Wellcome Trust","keywords":"Missing data; Propensity score matching; Confounding; Health records; Computer science; Statistics; Econometrics; Psychology; Medicine; Health care; Mathematics; Machine learning","score_opus":0.2291836310970289,"score_gpt":0.40090395501963755,"score_spread":0.17172032392260864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910522615","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011321569,0.00040751178,0.9417778,0.043369003,0.001563212,0.0007717444,0.0010722148,0.000038691138,0.009867618],"genre_scores_gemma":[0.75729233,0.0017105405,0.21132302,0.02567371,0.0020911535,0.000116459705,0.0013820913,0.00008988221,0.00032078393],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977331,0.00005189615,0.0014134564,0.00037221544,0.00011814927,0.0003111594],"domain_scores_gemma":[0.9984753,0.00013300864,0.00073411333,0.00039367288,0.00009201914,0.00017185873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001100257,0.00022685203,0.0007630389,0.00030909595,0.00006784422,0.00007080176,0.00022627886,0.00017185934,0.00026809186],"category_scores_gemma":[0.0028476187,0.00024193109,0.000029196788,0.00016875964,0.00013423918,0.00014452953,0.00048033026,0.00075384317,0.00013730148],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005837846,0.00010320195,0.017998094,0.0059077735,0.00014098802,0.0003931243,0.0073873284,0.00061930274,0.0000010745729,0.830592,0.09961852,0.037180234],"study_design_scores_gemma":[0.0016135086,0.00020698873,0.027760258,0.0013839878,0.00006253847,0.000022156659,0.00041283647,0.1366302,0.0000036316853,0.39643258,0.4346378,0.0008334939],"about_ca_topic_score_codex":0.02163764,"about_ca_topic_score_gemma":0.00042719545,"teacher_disagreement_score":0.7561602,"about_ca_system_score_codex":0.0002955469,"about_ca_system_score_gemma":0.00022291872,"threshold_uncertainty_score":0.98656636},"labels":[],"label_agreement":null},{"id":"W2916449784","doi":"10.1002/sim.8119","title":"Optimising the two‐stage randomised trial design when some participants are indifferent in their treatment preferences","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Preference; Randomized controlled trial; Treatment and control groups; Treatment effect; Medicine; Clinical trial; Research design; Psychology; Statistics; Mathematics; Surgery; Internal medicine","score_opus":0.6713702372673928,"score_gpt":0.5579903408757302,"score_spread":0.11337989639166257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916449784","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3946572,0.000324048,0.588015,0.001333184,0.003240737,0.010894246,0.0005169307,0.00008957733,0.00092903926],"genre_scores_gemma":[0.39545372,0.0003525242,0.60183066,0.0003224704,0.00068300613,0.00064897956,0.000014922848,0.00007177679,0.00062195025],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99225336,0.0037246507,0.0019547672,0.000562911,0.0007295002,0.00077479123],"domain_scores_gemma":[0.88099235,0.11749399,0.0006136296,0.0006572688,0.00007773177,0.00016500843],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009697568,0.00041301336,0.0017402796,0.00019580353,0.00007461514,0.000044056953,0.00047311242,0.0001574896,0.0012867323],"category_scores_gemma":[0.07111423,0.00021653021,0.00007460401,0.000240649,0.00038276313,0.000056292774,0.00009754873,0.00051977776,0.000026234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.31983846,0.0052274936,0.01199132,0.0011561998,0.0012254782,0.0005756513,0.038485654,0.001865853,0.00063362607,0.47314194,0.0060146274,0.13984369],"study_design_scores_gemma":[0.17984588,0.0015509615,0.00098395,0.00051618944,0.00013956652,8.3114514e-7,0.0011393154,0.0057437285,0.00019336095,0.80962133,0.000043082026,0.00022179735],"about_ca_topic_score_codex":0.00013972916,"about_ca_topic_score_gemma":0.00018073336,"teacher_disagreement_score":0.3364794,"about_ca_system_score_codex":0.00025741843,"about_ca_system_score_gemma":0.0001536184,"threshold_uncertainty_score":0.9996262},"labels":[],"label_agreement":null},{"id":"W2921476564","doi":"10.1002/sim.8132","title":"A test for the correct specification of marginal structural models","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval; The Quebec Population Health Research Network","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation du CHUM","keywords":"Marginal structural model; Inverse probability; Computer science; Estimator; Econometrics; Outcome (game theory); Confounding; Statistics; Causal model; Mathematics; Bayesian probability; Posterior probability","score_opus":0.14322652898192254,"score_gpt":0.43763620167038475,"score_spread":0.2944096726884622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921476564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004598652,0.000057962035,0.99262446,0.00015854002,0.00017922364,0.0007133747,0.00012582027,0.000027493512,0.0015144958],"genre_scores_gemma":[0.6003874,0.000040327883,0.3991096,0.000039349346,0.000064378895,0.000026648308,0.000023962057,0.000014787921,0.00029356536],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991457,0.000015809395,0.0003573952,0.000118922515,0.00021548127,0.00014668232],"domain_scores_gemma":[0.99332535,0.0060129617,0.00018821003,0.00027801655,0.0001753538,0.000020122761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006120349,0.00009182165,0.00022985524,0.00006961256,0.000019669298,0.0000025176175,0.0001649659,0.000038202903,0.00013444114],"category_scores_gemma":[0.0020250594,0.000057793222,0.000012559815,0.0001208029,0.00015138803,0.0000413263,0.000019176792,0.00013472102,0.0000015466587],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004773906,0.000014791609,0.00091203256,0.00014117188,0.0000069583366,0.000001005645,0.0006118622,0.000065456494,0.002149118,0.9845564,0.0036105237,0.007882976],"study_design_scores_gemma":[0.0004212525,0.00026725882,0.0010776997,0.00011514956,0.0000218586,0.0000033152132,0.00049166655,0.046359062,0.001115285,0.94989413,0.0001665446,0.00006680133],"about_ca_topic_score_codex":0.000027036096,"about_ca_topic_score_gemma":0.000042731343,"teacher_disagreement_score":0.5957887,"about_ca_system_score_codex":0.0000495966,"about_ca_system_score_gemma":0.000023616882,"threshold_uncertainty_score":0.24243316},"labels":[],"label_agreement":null},{"id":"W2921943956","doi":"10.1002/sim.8121","title":"Bayesian estimation of the average treatment effect on the treated using inverse weighting","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Vanderbilt University","keywords":"Confounding; Statistics; Marginal structural model; Context (archaeology); Bayesian probability; Weighting; Posterior probability; Inverse probability; Econometrics; Estimation; Sample size determination; Average treatment effect; Inverse probability weighting; Marginal likelihood; Mathematics; Computer science; Medicine; Propensity score matching; Economics","score_opus":0.06999270852247445,"score_gpt":0.4013656679853423,"score_spread":0.3313729594628678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921943956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7370871,0.000011303437,0.25857228,0.00019035139,0.000145477,0.001240707,0.00005318046,0.000052721625,0.0026469256],"genre_scores_gemma":[0.9428543,0.000008496715,0.056851145,0.000074668336,0.000023934132,0.000018939778,0.0000124568305,0.000019563124,0.00013649193],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989089,0.00021441207,0.00032339443,0.0001359486,0.00027348418,0.00014388483],"domain_scores_gemma":[0.9963242,0.002980392,0.00022911892,0.00040434444,0.000040119376,0.000021823938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053626695,0.00015751408,0.00030326823,0.00007201183,0.000050061935,0.0000042754177,0.0001413995,0.000047724843,0.00018352299],"category_scores_gemma":[0.00165445,0.00007075814,0.000023947268,0.00020861463,0.00013275207,0.000028676346,0.000027764274,0.00015312279,0.0000039565725],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002115603,0.00029823376,0.015452353,0.0006258549,0.00016799447,0.000049474405,0.007002827,0.0072336956,0.027194133,0.8987626,0.0018074131,0.04119388],"study_design_scores_gemma":[0.0016736015,0.002029034,0.0010270971,0.0018096413,0.00018508719,0.000008053805,0.00029015966,0.34909418,0.056478586,0.587155,0.000042860534,0.00020672021],"about_ca_topic_score_codex":0.00015791987,"about_ca_topic_score_gemma":0.00005813417,"teacher_disagreement_score":0.34186047,"about_ca_system_score_codex":0.00020008071,"about_ca_system_score_gemma":0.000024911935,"threshold_uncertainty_score":0.2885433},"labels":[],"label_agreement":null},{"id":"W2923835633","doi":"10.1002/sim.8120","title":"Emulating a trial of joint dynamic strategies: An application to monitoring and treatment of HIV‐positive individuals","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"HIV Research and Treatment","field":"Immunology and Microbiology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SAIT Polytechnic","funders":"National Center for Advancing Translational Sciences; National Institute of Allergy and Infectious Diseases; National Heart, Lung, and Blood Institute; Medical Research Council; Center for AIDS Research, University of Washington; National Institutes of Health","keywords":"Regimen; Observational study; Human immunodeficiency virus (HIV); Medicine; Antiretroviral therapy; Leverage (statistics); Outcome (game theory); Computer science; Internal medicine; Viral load; Immunology; Mathematics; Artificial intelligence","score_opus":0.02339519020486872,"score_gpt":0.35897860717107233,"score_spread":0.3355834169662036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923835633","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99283874,0.0002763686,0.0051515624,0.000051348998,0.000091911694,0.00091451674,0.00044368615,0.0000048781626,0.00022699952],"genre_scores_gemma":[0.99643886,0.00010357511,0.0029330864,0.0000018939364,0.000015766529,0.000048428115,0.00036963815,0.0000059787976,0.00008277619],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992399,0.00009804029,0.00029844252,0.0001619989,0.00005714395,0.00014442379],"domain_scores_gemma":[0.9994157,0.00025305274,0.00010032333,0.0001488316,0.000054695924,0.000027427766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018237438,0.0000883738,0.00031855673,0.00013340074,0.00002135064,0.0000022201048,0.000042502492,0.000050778162,0.000044732034],"category_scores_gemma":[0.00006577385,0.00006640621,0.000009457435,0.000081730024,0.00010350955,0.000025483736,0.000016778022,0.000057098983,0.00001658307],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008520111,0.0016523807,0.090051845,0.00019547483,0.00059388793,0.000018251252,0.030392662,0.00027419475,0.64392567,0.008736638,0.00005184487,0.21558706],"study_design_scores_gemma":[0.18379474,0.059679393,0.67504746,0.00088918075,0.00026942417,0.000017973365,0.026669554,0.0006469662,0.046569567,0.0056669116,0.00032279282,0.00042605272],"about_ca_topic_score_codex":0.0004904623,"about_ca_topic_score_gemma":0.000057503203,"teacher_disagreement_score":0.5973561,"about_ca_system_score_codex":0.00006560747,"about_ca_system_score_gemma":0.000049098275,"threshold_uncertainty_score":0.27079666},"labels":[],"label_agreement":null},{"id":"W2924458846","doi":"10.1002/sim.8142","title":"Randomised trials with provision for early stopping for benefit (or harm): The impact on the estimated treatment effect","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Sinai Hospital; University of Ottawa; McMaster University; Ottawa Hospital; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Early stopping; Interim; Interim analysis; Type I and type II errors; Estimation; Harm; Sample size determination; Econometrics; Meta-analysis; Statistics; Stopping time; Treatment effect; Computer science; Clinical trial; Medicine; Mathematics; Psychology; Economics; Artificial intelligence","score_opus":0.5239753487763673,"score_gpt":0.6123429647629159,"score_spread":0.08836761598654863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2924458846","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.104293816,0.00005579348,0.8605178,0.0021000204,0.0008412556,0.029951897,0.0018559393,0.000069479924,0.00031399433],"genre_scores_gemma":[0.16415986,0.00006055969,0.82911456,0.00037381414,0.0007362719,0.0043274057,0.000059598104,0.00014966412,0.0010182781],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9954565,0.0016107457,0.0014967213,0.00045337918,0.00050970865,0.00047293378],"domain_scores_gemma":[0.6042905,0.39451775,0.00050535786,0.00046843616,0.00014157806,0.0000764106],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019736053,0.00043779294,0.0021589962,0.000093363255,0.00016018665,0.00004813239,0.0003243683,0.00012756645,0.00040650688],"category_scores_gemma":[0.28169402,0.00013401412,0.00019053412,0.00022095417,0.00024775264,0.000025446432,0.00002492065,0.0002545266,0.000009611809],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.3574391,0.00091685285,0.0012609009,0.0015155596,0.0021990621,0.00004223558,0.0027573362,0.0006303307,0.0009611249,0.39896175,0.023014093,0.21030168],"study_design_scores_gemma":[0.11479622,0.032249596,0.0013914283,0.0016608526,0.0011984989,0.000004341015,0.00017563716,0.025180845,0.00094485807,0.8218828,0.00019521198,0.00031974493],"about_ca_topic_score_codex":0.00007772278,"about_ca_topic_score_gemma":0.000016681932,"teacher_disagreement_score":0.42292103,"about_ca_system_score_codex":0.00019781891,"about_ca_system_score_gemma":0.00011971475,"threshold_uncertainty_score":0.7243566},"labels":[],"label_agreement":null},{"id":"W2938511274","doi":"10.1002/sim.8162","title":"One‐step validation method for surrogate endpoints using data from multiple randomized cancer clinical trials with failure‐time endpoints","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Secrétariat Général pour les Affaires Régionales, Etat en Région Aquitaine; Institute of Cancer Research; Institut National de la Santé et de la Recherche Médicale; Institut National Du Cancer; Association pour la Recherche sur le Cancer","keywords":"Surrogate endpoint; Context (archaeology); Estimator; Statistics; Clinical trial; Computer science; Random effects model; Medicine; Mathematics; Meta-analysis; Internal medicine","score_opus":0.5056720796718315,"score_gpt":0.5934294578687577,"score_spread":0.0877573781969262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2938511274","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008674682,0.00006543881,0.98321193,0.0002588361,0.00036523913,0.0037530356,0.0034531339,0.000117483716,0.00010018657],"genre_scores_gemma":[0.009027208,0.00014624234,0.98827046,0.00014100746,0.0003703814,0.00017962439,0.0016350873,0.000081272316,0.000148707],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99316514,0.0027091394,0.0023809366,0.0007614055,0.00059596414,0.0003874288],"domain_scores_gemma":[0.9275372,0.06955206,0.0013660586,0.0010782535,0.00034269594,0.00012370858],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022163842,0.00033612957,0.002905911,0.00016992536,0.00004933805,0.000025383879,0.0005118045,0.00020562031,0.0011935224],"category_scores_gemma":[0.0743396,0.0002497468,0.00007389974,0.00019030688,0.00027239785,0.0002342483,0.00016969896,0.000428399,0.000017897644],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.32549828,0.0028162913,0.012474903,0.0038952997,0.007217983,0.00017332606,0.0064442195,0.0010041313,0.13839394,0.22446536,0.07344032,0.20417595],"study_design_scores_gemma":[0.14817172,0.00033913465,0.00006276125,0.0017789834,0.0012984836,0.000003050709,0.00024917175,0.33452493,0.005741051,0.50684845,0.00047788772,0.00050436164],"about_ca_topic_score_codex":0.0007644644,"about_ca_topic_score_gemma":0.00075253565,"teacher_disagreement_score":0.3335208,"about_ca_system_score_codex":0.00013887166,"about_ca_system_score_gemma":0.00019030483,"threshold_uncertainty_score":0.99999547},"labels":[],"label_agreement":null},{"id":"W2939964754","doi":"10.1002/sim.8155","title":"Score tests based on a finite mixture model of Markov processes under intermittent observation","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Systemic Lupus Erythematosus Research","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Confidence interval; Psoriatic arthritis; Mixture model; Permutation (music); Statistics; Estimator; Markov chain; Medicine; Arthritis; Mathematics; Computer science; Internal medicine","score_opus":0.059281321664442596,"score_gpt":0.34591616981542134,"score_spread":0.2866348481509787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2939964754","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7938103,0.00043260914,0.18752049,0.0041479324,0.00051024416,0.0028183872,0.00028328635,0.00007000284,0.010406744],"genre_scores_gemma":[0.98114735,0.00006894388,0.014376995,0.0010343178,0.00008094169,0.000043360924,0.00021491061,0.000040928848,0.0029922645],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779797,0.00006469165,0.0005781947,0.00031738685,0.00097095623,0.00027077916],"domain_scores_gemma":[0.9972579,0.0013916993,0.0001834736,0.00048457773,0.00057069503,0.00011164512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006037791,0.00018988297,0.0005635511,0.00037757805,0.000016489552,0.0000045863076,0.00015456139,0.00011128971,0.00021954806],"category_scores_gemma":[0.0035480522,0.00013695392,0.00002400375,0.00052288244,0.00014977949,0.00003437657,0.000032854514,0.000344341,0.000021087639],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019213038,0.0006999871,0.91532594,0.023980714,0.00009642689,0.00015005562,0.0029819321,0.014372376,0.009461578,0.00561601,0.021243121,0.004150583],"study_design_scores_gemma":[0.009983723,0.0022153633,0.032306798,0.019509193,0.000105398845,0.000117118245,0.0012278048,0.9264618,0.00057256,0.0070934254,0.00012280751,0.0002839816],"about_ca_topic_score_codex":0.0000408289,"about_ca_topic_score_gemma":0.000057072124,"teacher_disagreement_score":0.91208947,"about_ca_system_score_codex":0.00017293102,"about_ca_system_score_gemma":0.00050690403,"threshold_uncertainty_score":0.5584819},"labels":[],"label_agreement":null},{"id":"W2940434429","doi":"10.1002/sim.8152","title":"Quantile regression and empirical likelihood for the analysis of longitudinal data with monotone missing responses due to dropout, with applications to quality of life measurements from clinical trials","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Missing data; Estimator; Quantile; Dropout (neural networks); Quantile regression; Statistics; Econometrics; Skewness; Regression analysis; Regression; Computer science; Mathematics; Machine learning","score_opus":0.6491396043007869,"score_gpt":0.6197232317086139,"score_spread":0.029416372592173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940434429","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12141884,0.000092118695,0.8740094,0.00083135715,0.00003576424,0.0011603868,0.0024297638,0.000005251877,0.00001714803],"genre_scores_gemma":[0.36023623,0.000014998553,0.6394586,0.00011754286,0.000040588086,0.00004767804,0.0000658864,0.000010900925,0.000007574881],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99606365,0.0011099991,0.0015954662,0.0004527945,0.0006105712,0.00016750304],"domain_scores_gemma":[0.9430308,0.054789126,0.00064898847,0.0009485901,0.0003961639,0.00018634473],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012657557,0.00015354832,0.0015580108,0.00016315831,0.00004878459,0.000011041108,0.000321946,0.000059433634,0.00008013061],"category_scores_gemma":[0.06763857,0.00007759405,0.000029814248,0.00059780886,0.00024740616,0.000023804478,0.00011324108,0.00014576751,6.3646655e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014436897,0.00079947204,0.83117217,0.0006523125,0.0025314423,0.0000047993867,0.0020597635,0.000035643,0.0016250565,0.034519285,0.0038804417,0.10828269],"study_design_scores_gemma":[0.0041938014,0.0020838617,0.903644,0.0010480282,0.0038867206,8.594026e-7,0.0015726956,0.021609955,0.00018223876,0.061296806,0.0001948834,0.00028615398],"about_ca_topic_score_codex":0.0004607073,"about_ca_topic_score_gemma":0.0006439625,"teacher_disagreement_score":0.23881738,"about_ca_system_score_codex":0.00001704036,"about_ca_system_score_gemma":0.00016521761,"threshold_uncertainty_score":0.9402151},"labels":[],"label_agreement":null},{"id":"W2946394381","doi":"10.1002/sim.8170","title":"Partitioning of time trends in prevalence and mortality of lung cancer","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Global Cancer Incidence and Screening","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Aging","funders":"National Institute on Aging; Shandong Academy of Sciences","keywords":"Lung cancer; Incidence (geometry); Medicine; Mortality rate; Demography; Epidemiology; Relative survival; Adenocarcinoma; Cancer; Disease; Stage (stratigraphy); Internal medicine; Cancer registry; Biology","score_opus":0.04763779418145317,"score_gpt":0.41391364758910515,"score_spread":0.366275853407652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946394381","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9943601,0.001870187,0.00035181467,0.00014598832,0.000067880814,0.00013415648,0.000085942476,0.000003693948,0.002980258],"genre_scores_gemma":[0.99766046,0.00054388866,0.0012707056,0.00007950543,0.000030320882,0.000006449701,0.00002191054,0.000004891452,0.00038185593],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990386,0.000027715008,0.0003778565,0.00014228963,0.00028661368,0.00012693826],"domain_scores_gemma":[0.99952036,0.000103969665,0.00011865198,0.00013586426,0.00007649331,0.00004468758],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004204542,0.000069402035,0.00036305832,0.00014288977,0.000005676978,8.5638607e-7,0.0000421239,0.00003515388,0.0012032123],"category_scores_gemma":[0.0001846401,0.000058843074,0.000009824569,0.00027262286,0.00014933976,0.00003583008,0.000018927934,0.000116050585,7.8491905e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007445717,0.000018056462,0.99302197,0.0006508877,0.000014699005,0.000017814345,0.0005582901,0.0000630909,0.0012775258,0.0008991454,0.0006489615,0.0027550794],"study_design_scores_gemma":[0.0012660698,0.00024721836,0.989019,0.00229096,0.00007322835,0.0000038594744,0.00009852607,0.0062598535,0.00020483077,0.00046641735,0.0000206912,0.000049339083],"about_ca_topic_score_codex":0.0022365062,"about_ca_topic_score_gemma":0.00045502436,"teacher_disagreement_score":0.006196763,"about_ca_system_score_codex":0.000050228016,"about_ca_system_score_gemma":0.000049965216,"threshold_uncertainty_score":0.99970984},"labels":[],"label_agreement":null},{"id":"W2946435821","doi":"10.1002/sim.8203","title":"Adjusting for differential misclassification in matched case‐control studies utilizing health administrative data","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; Nova Scotia Health Authority; Dalhousie University; Vancouver Coastal Health; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; National Multiple Sclerosis Society","keywords":"Bayesian probability; Observational study; Bayes' theorem; Computer science; Disease; Leverage (statistics); Econometrics; Differential (mechanical device); Data mining; Medicine; Statistics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.3835311399523762,"score_gpt":0.535968901803228,"score_spread":0.15243776185085178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946435821","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041610193,0.0003155049,0.9909575,0.001062073,0.0004275844,0.0011713438,0.0016475236,0.000023711695,0.00023374468],"genre_scores_gemma":[0.4308092,0.00006013615,0.5687115,0.00010492867,0.00010381635,0.00005218435,0.00010108201,0.000018384299,0.000038785103],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975316,0.00034542932,0.0009831759,0.0004868275,0.00026137332,0.00039161925],"domain_scores_gemma":[0.9863762,0.012513923,0.00035796268,0.0005203632,0.00014158369,0.000089944646],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020860573,0.00020997052,0.00086189306,0.0001383008,0.000069857895,0.000014492459,0.00024304561,0.00006602389,0.00012850718],"category_scores_gemma":[0.0145741785,0.00016845975,0.000014269662,0.00019064407,0.00016750698,0.000061894505,0.00006860992,0.00027708066,0.000003048969],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001406016,0.00014552262,0.002491485,0.0020945943,0.00008862541,0.00018458153,0.0041450444,9.95426e-7,0.00020998293,0.90019196,0.0034107114,0.08689588],"study_design_scores_gemma":[0.0046737967,0.00069894857,0.0076889573,0.0014338339,0.00013608203,0.00006456286,0.01916103,0.0780553,0.000016623972,0.88769567,0.00007978759,0.00029539072],"about_ca_topic_score_codex":0.00013132583,"about_ca_topic_score_gemma":0.0010123509,"teacher_disagreement_score":0.42664817,"about_ca_system_score_codex":0.00013744486,"about_ca_system_score_gemma":0.00014048342,"threshold_uncertainty_score":0.9937265},"labels":[],"label_agreement":null},{"id":"W2946565097","doi":"10.1002/sim.8194","title":"To add or not to add a new treatment arm to a multiarm study: A decision‐theoretic framework","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"Computer science; Medicine","score_opus":0.4236848403530717,"score_gpt":0.6166050279663471,"score_spread":0.1929201876132754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946565097","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033307776,0.000013700716,0.95472115,0.0021040696,0.0021527954,0.0063413046,0.0006337072,0.00009647727,0.0006290244],"genre_scores_gemma":[0.047696985,0.000016948741,0.94425577,0.004505618,0.00078068225,0.00031537763,0.000004783242,0.000116755815,0.002307088],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99372256,0.00077187055,0.0021225496,0.0011514005,0.0014106992,0.0008209266],"domain_scores_gemma":[0.8612483,0.13563636,0.00021679426,0.0014284104,0.00023843274,0.0012316823],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004049385,0.0005806576,0.0020760985,0.00047325005,0.00006637943,0.00004389648,0.0007096394,0.00022996463,0.010892377],"category_scores_gemma":[0.39021152,0.0003916332,0.0000754164,0.0012711139,0.00012144474,0.000023959854,0.00032964122,0.00052827207,0.0014876922],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009840446,0.00287344,0.0012699275,0.00019849003,0.00027533757,0.00072722294,0.021452654,0.00012687546,0.000097388,0.49247324,0.09580829,0.3748567],"study_design_scores_gemma":[0.0066314046,0.018038059,0.0027396688,0.0017141544,0.00030086038,0.0000066963853,0.0019678304,0.00025419498,0.0000674001,0.96392506,0.0038124563,0.0005421871],"about_ca_topic_score_codex":0.0002949155,"about_ca_topic_score_gemma":0.00079945213,"teacher_disagreement_score":0.47145185,"about_ca_system_score_codex":0.00046446722,"about_ca_system_score_gemma":0.00026368373,"threshold_uncertainty_score":0.99985355},"labels":[],"label_agreement":null},{"id":"W2948643372","doi":"10.1002/sim.8213","title":"Analysis of clustered failure time data with cure fraction using copula","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Center for Advancing Translational Sciences; Assam Science Technology and Environment Council","keywords":"Akaike information criterion; Jackknife resampling; Copula (linguistics); Estimator; Statistics; Logistic regression; Computer science; Econometrics; Mathematics","score_opus":0.031513655357949436,"score_gpt":0.3467253180189006,"score_spread":0.3152116626609512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948643372","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026526374,0.0000598202,0.99631387,0.000272144,0.00009826401,0.00012747948,0.00008669375,0.000012280995,0.0003767848],"genre_scores_gemma":[0.07387659,0.00001213327,0.92566127,0.00012668814,0.000034775232,6.6509597e-7,0.00016315866,0.0000068427985,0.00011790857],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99876344,0.0001206149,0.00028583242,0.00034725107,0.0003386194,0.00014424349],"domain_scores_gemma":[0.99841154,0.00023868261,0.00019162952,0.0010091641,0.00010019581,0.000048807102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007128662,0.00010411702,0.00043717862,0.00030938498,0.00002004735,0.000012344858,0.00057324884,0.00005215284,0.00013822489],"category_scores_gemma":[0.00009336372,0.00007536704,0.000011957483,0.0010510342,0.00006150533,0.00018652607,0.00014530368,0.00016340277,0.000004392963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004031484,0.0006039049,0.10582017,0.0010249593,0.004029477,0.00045635633,0.0089379,0.01663907,0.024007222,0.438534,0.040405273,0.35913852],"study_design_scores_gemma":[0.00049526506,0.00010996743,0.002431474,0.00010093814,0.00028536958,0.0000048341526,0.000036177425,0.9910197,0.000019732728,0.0049781143,0.0004210394,0.00009738205],"about_ca_topic_score_codex":0.00021651264,"about_ca_topic_score_gemma":0.00012851438,"teacher_disagreement_score":0.9743806,"about_ca_system_score_codex":0.000035329565,"about_ca_system_score_gemma":0.000056510566,"threshold_uncertainty_score":0.30733788},"labels":[],"label_agreement":null},{"id":"W2950576350","doi":"10.1002/sim.8180","title":"Four papers on child growth modelling","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Child Nutrition and Water Access","field":"Nursing","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Child development; Resource (disambiguation); Quarter (Canadian coin); Child health; Task (project management); Work (physics); Global health; Psychology; Medicine; Pediatrics; Environmental health; Developmental psychology; Computer science; Public health; Geography; Engineering; Nursing","score_opus":0.020261413899094544,"score_gpt":0.2850264011441614,"score_spread":0.26476498724506686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950576350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44849703,0.00055705424,0.062247768,0.061960638,0.011856136,0.0021887352,0.00037565903,0.00036096727,0.411956],"genre_scores_gemma":[0.99233747,0.000067538334,0.0030732441,0.0038423636,0.00035320382,0.000004100151,0.00007701638,0.000024103309,0.00022094461],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989762,0.00004312183,0.00024770305,0.00022707596,0.0002930007,0.00021294],"domain_scores_gemma":[0.99944836,0.00022048055,0.000050174353,0.00017297496,0.000041052317,0.00006693541],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018410386,0.00012316387,0.00021977472,0.00016585355,0.000047744546,0.0000113568185,0.00012345106,0.000047772464,0.00042801752],"category_scores_gemma":[0.000107014785,0.000101493824,0.000015728681,0.00015199775,0.000054992262,0.00003614195,0.000013906127,0.00028508937,0.000097565615],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054714503,0.0015271861,0.18717727,0.0028708277,0.00016998869,0.0006638187,0.01651018,0.027102951,0.0019066052,0.501385,0.2225703,0.032644425],"study_design_scores_gemma":[0.048781715,0.0063001243,0.16269745,0.009785629,0.00027063995,0.00015605091,0.0016678583,0.22884002,0.004385343,0.41963762,0.11479227,0.002685274],"about_ca_topic_score_codex":0.00013376065,"about_ca_topic_score_gemma":0.000025920875,"teacher_disagreement_score":0.54384047,"about_ca_system_score_codex":0.000056294917,"about_ca_system_score_gemma":0.000003759251,"threshold_uncertainty_score":0.46864915},"labels":[],"label_agreement":null},{"id":"W2954707123","doi":"10.1002/sim.8281","title":"The Integrated Calibration Index (ICI) and related metrics for quantifying the calibration of logistic regression models","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":313,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; Institute for Clinical Evaluative Sciences; Institute of Health Services and Policy Research; Sunnybrook Hospital; University of Toronto","funders":"National Institute of Neurological Disorders and Stroke; National Institutes of Health; Ontario Ministry of Health and Long-Term Care; Canadian Institutes of Health Research; Patient-Centered Outcomes Research Institute; Heart and Stroke Foundation of Canada","keywords":"Calibration; Statistics; Percentile; Logistic regression; Mathematics; Range (aeronautics); Smoothing; Regression; Computer science","score_opus":0.2038005309243087,"score_gpt":0.4336053912476601,"score_spread":0.22980486032335143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954707123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005599792,0.00029573313,0.9920734,0.0005499726,0.00035810645,0.00070818095,0.00011208034,0.000015996326,0.0002867017],"genre_scores_gemma":[0.86278445,0.00024340427,0.13657966,0.00005798993,0.000029269979,0.000029818764,0.00004731016,0.000020936217,0.00020718087],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823356,0.00030634558,0.00073709124,0.00020009321,0.00033440234,0.00018848825],"domain_scores_gemma":[0.9826381,0.01647005,0.00034872987,0.00027892852,0.00022174546,0.00004242313],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021357497,0.00014565016,0.00035209281,0.000107969565,0.00012197269,0.00002416828,0.00016298474,0.000105062674,0.000041095278],"category_scores_gemma":[0.016842358,0.000069348345,0.000017018676,0.00043904112,0.00034157792,0.0000630884,0.00004171377,0.00027695124,3.1571741e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008500093,0.000020759993,0.0006365391,0.00018295905,0.000017605342,0.0000013975477,0.0007378232,0.0001689314,0.00032653366,0.9858239,0.0011072583,0.010891286],"study_design_scores_gemma":[0.0004012694,0.00013492774,0.00036562653,0.00017701289,0.000029230343,0.0000015118919,0.00059564074,0.50780976,0.000050904426,0.4903607,0.000025405892,0.00004802622],"about_ca_topic_score_codex":0.00014491552,"about_ca_topic_score_gemma":0.00007036505,"teacher_disagreement_score":0.85718465,"about_ca_system_score_codex":0.000034456585,"about_ca_system_score_gemma":0.00006078697,"threshold_uncertainty_score":0.9914392},"labels":[],"label_agreement":null},{"id":"W2955494793","doi":"10.1002/sim.8283","title":"Dependence modeling for multi‐type recurrent events via copulas","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Copula (linguistics); Inference; Multivariate statistics; Econometrics; Marginal model; Computer science; Poisson distribution; Marginal likelihood; Marginal distribution; Statistics; Mathematics; Artificial intelligence; Machine learning; Regression analysis; Random variable; Bayesian probability","score_opus":0.22345526336841892,"score_gpt":0.48588751595579366,"score_spread":0.26243225258737474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955494793","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00974178,0.0001016196,0.9877965,0.0000691092,0.0011777387,0.00065575645,0.00012663584,0.000024951401,0.00030593487],"genre_scores_gemma":[0.19938317,0.000043283595,0.8000655,0.00009225779,0.00008147809,0.000030126266,0.00003318024,0.00002592452,0.00024506822],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983216,0.00009874797,0.00058137707,0.00031619944,0.0003553135,0.00032676238],"domain_scores_gemma":[0.99697936,0.0022395507,0.00012586114,0.00028651045,0.00026265017,0.0001060827],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009017432,0.00017788775,0.00044748644,0.000088579865,0.000034576944,0.0000054472625,0.00019814956,0.00007863069,0.00044178002],"category_scores_gemma":[0.009062455,0.0001441116,0.000019930132,0.00015614841,0.00005328932,0.000029684223,0.000046112134,0.00023143653,0.00003765033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028809387,0.00037605455,0.0028724503,0.0011101991,0.000044511762,0.00001939287,0.0010820777,0.00019356939,0.0014297635,0.90909827,0.0025074766,0.08097816],"study_design_scores_gemma":[0.001012609,0.00043647812,0.00025641985,0.00029350305,0.000027543649,0.0000025654672,0.00009673125,0.48757422,0.000032069103,0.5100642,0.00007524018,0.00012840139],"about_ca_topic_score_codex":0.000070605616,"about_ca_topic_score_gemma":0.00007791055,"teacher_disagreement_score":0.48738065,"about_ca_system_score_codex":0.00007980827,"about_ca_system_score_gemma":0.000039479542,"threshold_uncertainty_score":0.9992846},"labels":[],"label_agreement":null},{"id":"W2956065293","doi":"10.1002/sim.8497","title":"Estimation of treatment effects following a sequential trial of multiple treatments","year":2020,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research","keywords":"Frequentist inference; Interim; Interim analysis; Confidence interval; Statistics; Replicate; Econometrics; Computer science; Nominal level; Bayesian probability; Mathematics; Randomized controlled trial; Medicine; Bayesian inference","score_opus":0.4719794924011268,"score_gpt":0.5884031063488133,"score_spread":0.11642361394768652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956065293","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05835096,0.000099347235,0.93060327,0.00013712098,0.00419805,0.004435637,0.0017198955,0.000050726852,0.00040499872],"genre_scores_gemma":[0.29542854,0.00010052257,0.7037044,0.000014606369,0.0003173178,0.00021752623,0.00013425988,0.000051488034,0.00003130703],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9940061,0.0014040577,0.0028322558,0.0006352446,0.0008250015,0.0002973501],"domain_scores_gemma":[0.92687887,0.070711724,0.0014663661,0.00067782175,0.000108243636,0.00015695962],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019993049,0.0004995877,0.0031624136,0.00022945054,0.000025238785,0.0000070952096,0.00031432527,0.00040617937,0.00008016587],"category_scores_gemma":[0.1952213,0.00039449192,0.00027539852,0.00023181624,0.00033172875,0.000018560146,0.00023813368,0.0004694774,0.0000031771717],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07873887,0.009448243,0.0015206366,0.030397652,0.010122814,0.0016104353,0.012011952,0.0024828934,0.0045110537,0.2695782,0.0045183874,0.5750589],"study_design_scores_gemma":[0.076310724,0.0054439497,0.00017550892,0.0022991789,0.0022433074,7.190315e-7,0.00004348997,0.021746496,0.002094751,0.8893996,0.0000065420977,0.00023574289],"about_ca_topic_score_codex":0.0004615256,"about_ca_topic_score_gemma":0.000033618562,"teacher_disagreement_score":0.61982137,"about_ca_system_score_codex":0.00041404233,"about_ca_system_score_gemma":0.0003322934,"threshold_uncertainty_score":0.9998507},"labels":[],"label_agreement":null},{"id":"W2956147361","doi":"10.1002/sim.8741","title":"Formulating causal questions and principled statistical answers","year":2020,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Lorentz Center; Medical Research Council; Vetenskapsrådet","keywords":"Causal inference; Covariate; Outcome (game theory); Computer science; Observational study; Set (abstract data type); Confounding; Variable (mathematics); Code (set theory); Statistical inference; Inference; Propensity score matching; Econometrics; Data science; Machine learning; Statistics; Artificial intelligence; Mathematics","score_opus":0.15779582121857488,"score_gpt":0.47360673047319685,"score_spread":0.31581090925462196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956147361","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021058293,0.00012000726,0.9925022,0.00094264717,0.00026779695,0.00086211617,0.001014806,0.00032277536,0.0018618025],"genre_scores_gemma":[0.13508885,0.00025226164,0.86355793,0.00019363037,0.00023013008,0.00011863205,0.00040046146,0.00007719625,0.00008088875],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99718845,0.00017377583,0.001048257,0.0006434751,0.00052911456,0.00041692235],"domain_scores_gemma":[0.9952785,0.0034119803,0.00039031974,0.00047594588,0.00018599343,0.00025727777],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007486402,0.00044975846,0.0009982962,0.0002137727,0.00007591005,0.000028612834,0.00025316334,0.00029991806,0.00017873751],"category_scores_gemma":[0.015417589,0.0004138553,0.000020601714,0.00016081573,0.0005229243,0.000052844098,0.0006034048,0.0016406201,0.000003798752],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026828158,0.000037611382,0.0007638199,0.0010288322,0.00003695592,0.00023419962,0.0013883208,0.000029959894,0.00018265912,0.98748386,0.0043160557,0.0044709146],"study_design_scores_gemma":[0.00049839006,0.00023628818,0.0016686633,0.0011126985,0.00012724631,0.000013537302,0.00022249627,0.01612188,0.000032816384,0.9792541,0.0003408405,0.0003710386],"about_ca_topic_score_codex":0.00023957875,"about_ca_topic_score_gemma":0.0003322673,"teacher_disagreement_score":0.13298301,"about_ca_system_score_codex":0.00022755709,"about_ca_system_score_gemma":0.00018712974,"threshold_uncertainty_score":0.9998313},"labels":[],"label_agreement":null},{"id":"W2961162542","doi":"10.1002/sim.8316","title":"Bayesian consensus‐based sample size criteria for binomial proportions","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Prior probability; Frequentist inference; Sample size determination; Bayesian probability; Statistics; Econometrics; Credible interval; Sample (material); Mathematics; Point estimation; Bayes' theorem; Computer science; Bayesian inference","score_opus":0.14867597247685566,"score_gpt":0.5096998485410166,"score_spread":0.3610238760641609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2961162542","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004378801,0.00003273658,0.98435307,0.0017347976,0.0015349215,0.0011719284,0.0033324847,0.000032013933,0.0034292398],"genre_scores_gemma":[0.17122051,0.0000011413039,0.82647276,0.0006797071,0.0001429389,0.00007188835,0.00009035887,0.00002108202,0.0012996077],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99690145,0.00036179228,0.000980063,0.0005252103,0.00089348515,0.00033802498],"domain_scores_gemma":[0.96624047,0.032491848,0.0002536614,0.0005356783,0.00032864572,0.00014969119],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003995045,0.00017695382,0.000523061,0.00025811672,0.000078762874,0.000051263425,0.00038808602,0.00007896664,0.023830386],"category_scores_gemma":[0.06313896,0.00013175327,0.0000441126,0.00051058445,0.00037345343,0.00004836914,0.000046192115,0.00014602064,0.0001136383],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012190522,0.00036288128,0.0161245,0.000120609635,0.000034882247,0.00007744051,0.0016199584,0.00040435718,0.06679549,0.060087457,0.81616586,0.036987484],"study_design_scores_gemma":[0.008298786,0.0027552312,0.013703851,0.00020690418,0.00005068413,0.000014831959,0.0031497169,0.3117243,0.0031270967,0.5702257,0.08605554,0.000687376],"about_ca_topic_score_codex":0.00013053072,"about_ca_topic_score_gemma":0.000048887592,"teacher_disagreement_score":0.73011035,"about_ca_system_score_codex":0.000087015665,"about_ca_system_score_gemma":0.00021115164,"threshold_uncertainty_score":0.977062},"labels":[],"label_agreement":null},{"id":"W2963325162","doi":"10.1002/sim.8327","title":"Information content of stepped‐wedge designs when treatment effect heterogeneity and/or implementation periods are present","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Health and Medical Research Council; National Medical Research Council; Medical Research Council","keywords":"Computer science; Sequence (biology); Cluster (spacecraft); Wedge (geometry); Econometrics; Treatment effect; Statistics; Data mining; Mathematics; Medicine; Biology","score_opus":0.510180498051622,"score_gpt":0.5711178178960157,"score_spread":0.060937319844393656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963325162","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49992362,0.00010992698,0.4926609,0.00040696556,0.00079237676,0.004398579,0.0012539317,0.000042664273,0.0004110158],"genre_scores_gemma":[0.33573055,0.000236001,0.6631841,0.00015550834,0.00016400695,0.00022055213,0.000082164675,0.00003299996,0.00019410254],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99689966,0.00082165556,0.0013509212,0.00020258452,0.00047060996,0.00025458637],"domain_scores_gemma":[0.97561896,0.023164615,0.00059984694,0.00033603716,0.00016276455,0.00011775295],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023928105,0.00023799301,0.0009859882,0.00013816834,0.000033118504,0.000014814202,0.00011895742,0.00009658124,0.00069016195],"category_scores_gemma":[0.01552112,0.00014942737,0.000039978408,0.00011198695,0.00019947748,0.000093941155,0.00006125105,0.00013305584,0.000013234249],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0053284634,0.00081428717,0.30568448,0.006555818,0.0008381978,0.000063874526,0.013267054,0.000021133665,0.0029635837,0.14775859,0.012010028,0.50469446],"study_design_scores_gemma":[0.053805836,0.026387058,0.25286207,0.0019811816,0.0013301319,0.000032371598,0.00951462,0.005212924,0.013801913,0.6320377,0.0020152922,0.0010188773],"about_ca_topic_score_codex":0.00025797667,"about_ca_topic_score_gemma":0.00017552232,"teacher_disagreement_score":0.5036756,"about_ca_system_score_codex":0.00015888292,"about_ca_system_score_gemma":0.000053415053,"threshold_uncertainty_score":0.99277157},"labels":[],"label_agreement":null},{"id":"W2963467474","doi":"10.1002/sim.8299","title":"Reconciling randomized trial evidence on proximal versus distal outcomes, with application to trials of influenza vaccination for healthcare workers","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Influenza Virus Research Studies","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Vancouver Coastal Health","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outcome (game theory); Medicine; Randomized controlled trial; Context (archaeology); Psychological intervention; Intervention (counseling); Health care; Clinical trial; Intensive care medicine; Surgery; Internal medicine","score_opus":0.20998245380367037,"score_gpt":0.5147954252479449,"score_spread":0.3048129714442745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963467474","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6682071,0.001812569,0.2349484,0.014403105,0.0019735459,0.07662106,0.0008363565,0.00010922194,0.0010886518],"genre_scores_gemma":[0.9543968,0.00017245131,0.04017184,0.001213579,0.0004229946,0.003151032,0.00017080501,0.000055254946,0.00024527306],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99642974,0.00041531248,0.0014816901,0.00039999964,0.00093671173,0.00033651796],"domain_scores_gemma":[0.9828636,0.015276545,0.00055684056,0.00038896245,0.0007696846,0.00014434078],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008137863,0.00022227148,0.0019929938,0.00038052053,0.000051392508,0.000007060694,0.0001239948,0.0000862172,0.000054896667],"category_scores_gemma":[0.06217639,0.00014052236,0.000085431486,0.00038325903,0.00012620472,0.000060245267,0.000031511172,0.00027199063,0.000009248752],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.96993226,0.00008543329,0.006966464,0.00086087466,0.00020007756,0.0000035550086,0.00091878395,0.0001133457,0.00020025623,0.0048880624,0.0005146046,0.015316281],"study_design_scores_gemma":[0.97846484,0.01052465,0.005185599,0.0019586962,0.00026705547,7.54311e-7,0.0007726989,0.001090886,0.00024534183,0.00077842374,0.0005409565,0.00017008149],"about_ca_topic_score_codex":0.00038981924,"about_ca_topic_score_gemma":0.00020393996,"teacher_disagreement_score":0.28618968,"about_ca_system_score_codex":0.0003899229,"about_ca_system_score_gemma":0.00035201447,"threshold_uncertainty_score":0.9457233},"labels":[],"label_agreement":null},{"id":"W2963571436","doi":"10.1002/sim.8318","title":"A new perspective on loss to follow‐up in failure time and life history studies","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Birth, Development, and Health","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Perspective (graphical); Time perspective; Computer science; Econometrics; Psychology; Mathematics; Artificial intelligence","score_opus":0.034291194211084945,"score_gpt":0.35064325690880327,"score_spread":0.3163520626977183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963571436","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76876235,0.024573669,0.0036137307,0.1348782,0.0053386465,0.0058300723,0.00014603756,0.00018506948,0.05667221],"genre_scores_gemma":[0.82648486,0.036450732,0.06892337,0.043270543,0.0013544017,0.000067459674,0.00010172392,0.00013616803,0.023210758],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9985884,0.00004621409,0.0003525617,0.00035828853,0.00036180936,0.0002927416],"domain_scores_gemma":[0.99897414,0.00029562213,0.000068731286,0.00019681588,0.00014137788,0.00032333066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004310417,0.00017968165,0.0006569852,0.0003653529,0.000021456799,0.0000019592962,0.00005951584,0.000075006195,0.0005523041],"category_scores_gemma":[0.0014617897,0.0001439659,0.000011412262,0.00019924558,0.000111023684,0.000022797603,0.00003670048,0.0003711083,0.0001697599],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011782517,0.00010978172,0.044817105,0.00058990694,0.00013613065,0.0004126606,0.08823182,0.0000037395516,0.00027152884,0.2600084,0.60127795,0.0029627185],"study_design_scores_gemma":[0.04685981,0.010342571,0.6744123,0.0075625456,0.00024952914,0.00008492693,0.062058214,0.00031698524,0.000039298044,0.12433106,0.0725994,0.0011433434],"about_ca_topic_score_codex":0.00079790334,"about_ca_topic_score_gemma":0.0017522553,"teacher_disagreement_score":0.6295952,"about_ca_system_score_codex":0.0012508251,"about_ca_system_score_gemma":0.00065613654,"threshold_uncertainty_score":0.60473424},"labels":[],"label_agreement":null},{"id":"W2963777543","doi":"10.1002/sim.8297","title":"Stein‐type shrinkage estimators in gamma regression model with application to prostate cancer data","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Statistics; Regression analysis; Mathematics; Regression; Linear regression; Proportional hazards model; Computer science; Econometrics; Applied mathematics","score_opus":0.025846596910134332,"score_gpt":0.3604758722269298,"score_spread":0.3346292753167954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963777543","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051929005,0.00015385481,0.9921081,0.001231249,0.00017342417,0.0006227888,0.00005020121,0.000028840637,0.00043864976],"genre_scores_gemma":[0.10554638,0.00007410883,0.89331734,0.00046931082,0.000032822554,0.000041284966,0.000054747576,0.000015795187,0.00044822702],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984283,0.00006725808,0.0002938221,0.0005886301,0.00035916746,0.00026282057],"domain_scores_gemma":[0.99846166,0.00011773413,0.00009689878,0.0011271529,0.00008607294,0.00011048574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077728624,0.00015401232,0.00028265637,0.00017671919,0.00002287993,0.0000188197,0.00080896623,0.00004846225,0.000011225968],"category_scores_gemma":[0.00010829876,0.000105704996,0.0000035347202,0.00062082644,0.00004451851,0.00018648389,0.0002688357,0.00021968674,0.000010957068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022908593,0.000117487725,0.019889338,0.00031334054,0.0000154753,0.00011463419,0.0064669587,0.044090874,0.0022706417,0.2791747,0.009520338,0.6377971],"study_design_scores_gemma":[0.00072629954,0.00015312263,0.0022654824,0.00043567346,0.0000056441877,0.0000024385856,0.000019511304,0.9691863,0.00004802462,0.02650551,0.00049840665,0.00015358819],"about_ca_topic_score_codex":0.00035410174,"about_ca_topic_score_gemma":0.00047062454,"teacher_disagreement_score":0.92509544,"about_ca_system_score_codex":0.000069442314,"about_ca_system_score_gemma":0.00015167761,"threshold_uncertainty_score":0.43105248},"labels":[],"label_agreement":null},{"id":"W2964523523","doi":"10.1002/sim.8286","title":"Measuring variability between clusters by subgroup: An extension of the median odds ratio","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Mount Sinai Hospital; Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre; Institute for Work & Health","funders":"Canadian Institutes of Health Research; Physicians' Services Incorporated Foundation; Heart and Stroke Foundation of Canada","keywords":"Extension (predicate logic); Odds; Odds ratio; Subgroup analysis; Statistics; Demography; Mathematics; Computer science; Confidence interval; Logistic regression; Sociology","score_opus":0.07676482540831311,"score_gpt":0.37053227655468124,"score_spread":0.29376745114636815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964523523","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04468695,0.00001247742,0.9527585,0.00042941107,0.00042856994,0.0004406896,0.00026383548,0.000016761518,0.0009628431],"genre_scores_gemma":[0.6789547,0.000006854214,0.32077587,0.00008464817,0.00008043912,0.000006297793,0.000026596541,0.000017732855,0.000046820336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99736977,0.0006982632,0.00072908035,0.00032196715,0.00062133954,0.0002595591],"domain_scores_gemma":[0.9930079,0.0057796836,0.00024358429,0.0006749248,0.0001742325,0.000119660755],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031186445,0.0001736134,0.00056273426,0.000063204185,0.000048751168,0.0000080081245,0.00032654923,0.000101484504,0.0003688161],"category_scores_gemma":[0.010146811,0.00011170593,0.000023891651,0.0002560074,0.00034730832,0.000054388704,0.000077526965,0.00034371726,0.000004366006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054071264,0.00016196664,0.07130316,0.00072032306,0.000036697773,0.0000065679174,0.002443493,0.000002728514,0.005497164,0.86880237,0.003195868,0.047775563],"study_design_scores_gemma":[0.000799647,0.00024235176,0.06622794,0.00032042828,0.00007165569,0.0000017654171,0.00026245744,0.0051554055,0.00059580244,0.9261265,0.000043129217,0.00015293971],"about_ca_topic_score_codex":0.00021027066,"about_ca_topic_score_gemma":0.00008518426,"teacher_disagreement_score":0.6342678,"about_ca_system_score_codex":0.00007894162,"about_ca_system_score_gemma":0.00005973715,"threshold_uncertainty_score":0.9981911},"labels":[],"label_agreement":null},{"id":"W2965457979","doi":"10.1002/sim.8306","title":"Untangling serially dependent underreported count data for gender‐based violence","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Intimate Partner and Family Violence","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Ministerio de Economía y Competitividad; World Health Organization","keywords":"Count data; Statistics; Computer science; Econometrics; Mathematics","score_opus":0.09538025833044142,"score_gpt":0.4139783812437226,"score_spread":0.31859812291328116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965457979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01449127,0.00048486367,0.9198254,0.00035645033,0.0049045873,0.002052392,0.0014549743,0.00012148051,0.056308612],"genre_scores_gemma":[0.9738564,0.00031671528,0.023847513,0.0007621735,0.00036011232,0.000024107756,0.00063720316,0.000019642126,0.00017613157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799705,0.00010634715,0.000432776,0.00042120708,0.0006348698,0.0004077286],"domain_scores_gemma":[0.99827975,0.0006997208,0.00015741723,0.00055024785,0.00021404169,0.000098810524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00254806,0.000129523,0.0002742149,0.0000872738,0.00016201481,0.000027745342,0.00058711227,0.00008396012,0.00038070258],"category_scores_gemma":[0.0013537612,0.0001186512,0.000012074602,0.00019533152,0.00026053374,0.000104287756,0.00006682511,0.00014816585,0.00003275938],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003943443,0.00025112773,0.051809113,0.0006566111,0.0000809071,0.00022045786,0.007889976,0.0015948572,0.0017332525,0.9015174,0.01637241,0.01747955],"study_design_scores_gemma":[0.01588726,0.0012993828,0.08900684,0.004122491,0.0004998731,0.00001472891,0.0626168,0.37916163,0.00032633587,0.37225103,0.072324894,0.0024887328],"about_ca_topic_score_codex":0.002197796,"about_ca_topic_score_gemma":0.0013079465,"teacher_disagreement_score":0.9593651,"about_ca_system_score_codex":0.00015456938,"about_ca_system_score_gemma":0.00051439815,"threshold_uncertainty_score":0.48384556},"labels":[],"label_agreement":null},{"id":"W2966416868","doi":"10.1002/sim.8690","title":"Measurement error and precision medicine: Error‐prone tailoring covariates in dynamic treatment regimes","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Precision medicine; Observational error; Context (archaeology); Accuracy and precision; Simple (philosophy); Error detection and correction","score_opus":0.1879669184940262,"score_gpt":0.4346654424349814,"score_spread":0.2466985239409552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966416868","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022346389,0.0023968427,0.96076477,0.010050589,0.00026375448,0.0018217592,0.000055414286,0.00029318966,0.0020073133],"genre_scores_gemma":[0.7302101,0.0010282397,0.2681422,0.00023247849,0.00010407578,0.000117874,0.000026383244,0.000048330283,0.00009032342],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99768335,0.00013488372,0.00077517837,0.0004409079,0.00064225873,0.000323402],"domain_scores_gemma":[0.99836516,0.0008345584,0.0002172045,0.000287465,0.00013724001,0.00015835243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010335967,0.0003074815,0.0007313319,0.0002033822,0.000042808235,0.0000067471005,0.0001576621,0.00009108647,0.0001164754],"category_scores_gemma":[0.006007818,0.00022679383,0.000013026143,0.0003204973,0.0002822428,0.0000813186,0.000071810166,0.00028313106,0.0000035865428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013315574,0.0009402325,0.012384607,0.0030857108,0.00029374025,0.0014223973,0.061173156,0.00025824338,0.03851622,0.66496325,0.019748103,0.1958828],"study_design_scores_gemma":[0.0060657347,0.004224642,0.006306378,0.0040491843,0.00018481897,0.000018938881,0.0044184714,0.021666583,0.0011974889,0.95001185,0.0012693058,0.0005866056],"about_ca_topic_score_codex":0.00024267257,"about_ca_topic_score_gemma":0.00065059465,"teacher_disagreement_score":0.70786375,"about_ca_system_score_codex":0.0004814413,"about_ca_system_score_gemma":0.00006157911,"threshold_uncertainty_score":0.92483836},"labels":[],"label_agreement":null},{"id":"W2967839411","doi":"10.1002/sim.8941","title":"Bayesian design and analysis of external pilot trials for complex interventions","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Programme Grants for Applied Research; Medical Research Council Canada; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research","keywords":"Bayesian probability; Monte Carlo method; Piecewise; Markov chain Monte Carlo; Psychological intervention; Sample size determination; Design of experiments; Sensitivity (control systems); Research design","score_opus":0.45041322823576735,"score_gpt":0.5294635819590232,"score_spread":0.07905035372325586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967839411","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000954701,0.00020826797,0.99812394,0.00015790673,0.00009702663,0.0003155295,0.0008461253,0.000007867263,0.00014783721],"genre_scores_gemma":[0.02105704,0.00007888809,0.9785833,0.000057363024,0.00004313638,0.00003489256,0.00006800356,0.000011085577,0.0000663348],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99757504,0.00071603816,0.0011236663,0.00021617625,0.00020746859,0.00016160465],"domain_scores_gemma":[0.97859925,0.02056152,0.00031285977,0.00019774193,0.0002490564,0.00007955498],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003537881,0.00011903929,0.0011779494,0.00026121965,0.00003678398,0.00001147448,0.000086974374,0.00003501511,0.0011590311],"category_scores_gemma":[0.032372475,0.00009529342,0.000079266116,0.00047058184,0.00020779045,0.000016545091,0.000031404612,0.000093172224,2.4478254e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001030177,0.00017213234,0.00059369364,0.0005622762,0.00035147692,0.000027335383,0.0002632918,0.000006707788,0.0023996688,0.95399916,0.002377688,0.039143566],"study_design_scores_gemma":[0.0012074487,0.0004857253,0.007120208,0.00040398003,0.002064009,0.0000035334726,0.00014209501,0.051430047,0.00018956319,0.9368332,0.000028071225,0.00009211308],"about_ca_topic_score_codex":0.00003112995,"about_ca_topic_score_gemma":0.00008525206,"teacher_disagreement_score":0.05142334,"about_ca_system_score_codex":0.00001998079,"about_ca_system_score_gemma":0.000043505042,"threshold_uncertainty_score":0.9997541},"labels":[],"label_agreement":null},{"id":"W2969784647","doi":"10.1002/sim.8986","title":"Incorporating partial adherence into the principal stratification analysis framework","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; Providence Health Care; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Estimator; Stratification (seeds); Principal (computer security); Computer science; Principal component analysis; Population; Clinical trial; Monte Carlo method; Statistics; Econometrics; Mathematics; Artificial intelligence; Medicine","score_opus":0.11815568465399728,"score_gpt":0.45816061350439785,"score_spread":0.34000492885040057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969784647","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009877053,0.00008768438,0.9875905,0.00073592557,0.00010754023,0.0001871475,0.000016892558,0.00007657185,0.0013206906],"genre_scores_gemma":[0.5148438,0.000033879856,0.48474476,0.00010529799,0.0000911576,0.00004551954,0.000053135685,0.000009477344,0.00007294538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99824303,0.00021343082,0.000634998,0.00028747116,0.00042649056,0.00019459626],"domain_scores_gemma":[0.99623495,0.0025342912,0.0002987005,0.0005933136,0.00027999852,0.00005873886],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009594523,0.00014966617,0.00035849685,0.000103346574,0.00010512984,0.000024066549,0.0002256524,0.00009251633,0.00035089717],"category_scores_gemma":[0.010450514,0.000106621745,0.00002688973,0.0012010515,0.0002987212,0.00006232775,0.00007161981,0.00047704412,0.000005430158],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063253183,0.000038137634,0.0028894572,0.00003793825,0.000057917405,0.00004310888,0.002900809,0.00006686141,0.00093498576,0.98541254,0.00030296357,0.0073089674],"study_design_scores_gemma":[0.000108646425,0.00007645727,0.0016745873,0.00012641461,0.00019437674,0.000002072008,0.0014600463,0.004920794,0.0017336897,0.9895154,0.00007222487,0.00011528475],"about_ca_topic_score_codex":0.00011049606,"about_ca_topic_score_gemma":0.0014331164,"teacher_disagreement_score":0.5049668,"about_ca_system_score_codex":0.000086000415,"about_ca_system_score_gemma":0.00011749256,"threshold_uncertainty_score":0.99788487},"labels":[],"label_agreement":null},{"id":"W2969865418","doi":"10.1002/sim.8345","title":"On estimands arising from misspecified semiparametric rate‐based analysis of recurrent episodic conditions","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; GlaxoSmithKline","keywords":"Estimator; Econometrics; Semiparametric model; Statistics; Asymptotic distribution; Mathematics; Medicine","score_opus":0.09883824884580657,"score_gpt":0.43573433639621634,"score_spread":0.3368960875504098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969865418","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12882087,0.0000628112,0.8658302,0.0001256729,0.00034992787,0.00025584563,0.0015522134,0.000021457345,0.002981045],"genre_scores_gemma":[0.6735045,0.000019279789,0.32584563,0.00016516431,0.00002701884,0.000009566794,0.0003595389,0.000014779137,0.000054535354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99789095,0.0002965494,0.0007950247,0.000340063,0.00044589443,0.00023150032],"domain_scores_gemma":[0.97446406,0.024461865,0.0003144462,0.00045664393,0.00017025496,0.0001327474],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009174157,0.00019268926,0.0009078229,0.00089839916,0.00003364915,0.000009739045,0.0001706825,0.000083102226,0.006650275],"category_scores_gemma":[0.01920591,0.00015615782,0.00005506087,0.0017581589,0.00020711533,0.000016137586,0.000020376669,0.0003127231,0.000021642818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017778437,0.00039368935,0.0066683907,0.00017670402,0.00039332957,0.000033975783,0.000438955,0.00063457,0.00057495723,0.9706064,0.005757142,0.0141441105],"study_design_scores_gemma":[0.0013073924,0.00062044145,0.06354767,0.00034910085,0.000914987,1.9091823e-7,0.00012418961,0.19176342,0.00019307804,0.74095756,0.000041225096,0.00018075881],"about_ca_topic_score_codex":0.00020782293,"about_ca_topic_score_gemma":0.000050831663,"teacher_disagreement_score":0.54468364,"about_ca_system_score_codex":0.00007895973,"about_ca_system_score_gemma":0.00006262361,"threshold_uncertainty_score":0.9942578},"labels":[],"label_agreement":null},{"id":"W2970007864","doi":"10.1002/sim.8344","title":"Overdispersion models for correlated multinomial data: Applications to blinding assessment","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; Public Health Ontario; University of Toronto","funders":"National Center for Advancing Translational Sciences","keywords":"Overdispersion; Statistics; Estimator; Generalized estimating equation; Multinomial distribution; Intraclass correlation; Mathematics; Gee; Econometrics; Estimating equations; Negative binomial distribution; Quasi-likelihood; Poisson distribution","score_opus":0.15022813602425147,"score_gpt":0.48922819164064546,"score_spread":0.339000055616394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970007864","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00043281986,0.000012126502,0.9936605,0.00029275226,0.0003860326,0.0016056896,0.0013971502,0.000028947665,0.002183967],"genre_scores_gemma":[0.053763464,0.00001164696,0.9452521,0.00016740386,0.00014869426,0.00012897424,0.0003048281,0.000025196345,0.00019764986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984402,0.00006669678,0.000505289,0.00042071455,0.0002960589,0.0002710416],"domain_scores_gemma":[0.9944981,0.004521148,0.00012359674,0.00060184376,0.00012949716,0.00012586633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010658015,0.0001499905,0.00039929262,0.0001369849,0.00006358331,0.000016020733,0.00033958344,0.00007522509,0.00025613513],"category_scores_gemma":[0.0017565329,0.00012513173,0.000013312312,0.00022672761,0.000058080375,0.0000695729,0.00014394443,0.00021040312,0.000022270033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046161338,0.00008665125,0.00050970446,0.00018268746,0.000015750587,0.0000029581058,0.00025930715,0.00009086749,0.0002384311,0.95680946,0.01185919,0.02989884],"study_design_scores_gemma":[0.0012301318,0.00017191454,0.00047353018,0.00016351108,0.00004864413,0.0000014677674,0.0002579583,0.35147417,0.0000057148145,0.6447801,0.0012567962,0.00013607465],"about_ca_topic_score_codex":0.00004778651,"about_ca_topic_score_gemma":0.000028685625,"teacher_disagreement_score":0.3513833,"about_ca_system_score_codex":0.00010783499,"about_ca_system_score_gemma":0.00007108526,"threshold_uncertainty_score":0.5102724},"labels":[],"label_agreement":null},{"id":"W2970526340","doi":"10.1002/sim.8354","title":"A more intuitive and modern way to compute a small‐sample confidence interval for the mean of a Poisson distribution","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"","keywords":"Poisson distribution; Link (geometry); Confidence interval; Computer science; TRACE (psycholinguistics); Computation; Sample (material); Sample size determination; Statistics; Interval (graph theory); Distribution (mathematics); Mathematics; Algorithm; Mathematical analysis","score_opus":0.0681805430217062,"score_gpt":0.40129177527727117,"score_spread":0.33311123225556494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970526340","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008885118,0.00004323778,0.9875113,0.000759921,0.00014529873,0.0007754009,0.0018284058,0.000009436514,0.00004188278],"genre_scores_gemma":[0.35847148,0.000014734645,0.64122784,0.00014288237,0.00003808828,0.00003516132,0.000039724466,0.0000101517435,0.00001992521],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99889,0.00008472463,0.00041021837,0.00021815726,0.00020255207,0.00019433821],"domain_scores_gemma":[0.9867662,0.012595588,0.00013133542,0.00021204614,0.00022067619,0.00007413516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088488497,0.00012918843,0.00041402373,0.000044466633,0.000034880024,0.000010241553,0.00015872421,0.000042565294,0.000052039337],"category_scores_gemma":[0.007970189,0.00008393175,0.0000168394,0.00012637055,0.00023603419,0.000017104698,0.000075711476,0.00014331438,0.0000010125104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117356576,0.000029485354,0.0003532829,0.0002980823,0.000023448052,0.000002656394,0.0047446038,0.0000030515948,0.00015054457,0.89245385,0.0007778158,0.101045825],"study_design_scores_gemma":[0.00075130886,0.0006250433,0.0055089463,0.0005303716,0.000056816014,0.0000037638697,0.0010678493,0.0838907,0.00010396337,0.9072684,0.000095775446,0.000097084965],"about_ca_topic_score_codex":0.00046234875,"about_ca_topic_score_gemma":0.00027381862,"teacher_disagreement_score":0.34958634,"about_ca_system_score_codex":0.000038380433,"about_ca_system_score_gemma":0.00002433545,"threshold_uncertainty_score":0.95416355},"labels":[],"label_agreement":null},{"id":"W2971381351","doi":"10.1002/sim.8320","title":"Discussion of Schuemie et al: “A plea to stop using the case‐control design in retrospective database studies”","year":2019,"lang":"en","type":"letter","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"","keywords":"Medicine; Pharmacoepidemiology; Epidemiology; Family medicine; Plea; Biostatistics; Pharmacoeconomics; Library science; Medical prescription; Internal medicine; Political science","score_opus":0.5841074927165224,"score_gpt":0.605698572106588,"score_spread":0.02159107939006555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971381351","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003376124,0.00016904966,0.72509426,0.2662786,0.0015938681,0.002474582,0.004271844,0.000018759376,0.00006526132],"genre_scores_gemma":[0.00029806356,0.00016334496,0.75574076,0.24255194,0.00084509165,0.00008659769,0.00003701317,0.00011884908,0.00015831567],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98795265,0.0063865497,0.0027452507,0.0009594022,0.0012725592,0.0006835726],"domain_scores_gemma":[0.81638724,0.18085349,0.00096880423,0.0013021504,0.0004067295,0.00008161791],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.018986924,0.000610779,0.0030399894,0.00047082294,0.00006798173,0.000015951076,0.0006405137,0.00045346978,0.00022149216],"category_scores_gemma":[0.40099514,0.00032388984,0.000080518126,0.00073654787,0.00076973834,0.000050624494,0.00033117944,0.0037961416,0.000008797886],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025402574,0.00008044598,0.00011735412,0.0008213679,0.00023519366,0.006250531,0.0012655957,0.000096845186,0.000097977674,0.015631462,0.97395825,0.0011909525],"study_design_scores_gemma":[0.0056892633,0.0011002964,0.00012922399,0.007416442,0.0009708605,0.00014581706,0.001770587,0.0050763395,0.000027345248,0.9671036,0.009856165,0.0007140861],"about_ca_topic_score_codex":0.00029404662,"about_ca_topic_score_gemma":0.000162874,"teacher_disagreement_score":0.9641021,"about_ca_system_score_codex":0.0005988748,"about_ca_system_score_gemma":0.00025391133,"threshold_uncertainty_score":0.9999213},"labels":[],"label_agreement":null},{"id":"W2973185263","doi":"10.1002/sim.8809","title":"SuRF: A new method for sparse variable selection, with application in microbiome data analysis","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Feature selection; Lasso (programming language); Ranking (information retrieval); Variable (mathematics); Selection (genetic algorithm); Microbiome; A priori and a posteriori; Interpretability","score_opus":0.028516412973631257,"score_gpt":0.3642394012441812,"score_spread":0.3357229882705499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2973185263","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015192658,0.00016913372,0.99604845,0.0013779537,0.000022184922,0.00034293998,0.00046233874,0.000005232356,0.000052495463],"genre_scores_gemma":[0.03203561,0.00009036176,0.95860165,0.0013954876,0.00026159573,0.00002015913,0.0073629273,0.000019406189,0.00021276824],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99898314,0.000050572075,0.0002758764,0.0004393273,0.00006313877,0.00018792655],"domain_scores_gemma":[0.9994023,0.000052553314,0.0000875351,0.00029108473,0.00007267306,0.00009388864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046081486,0.00010417337,0.00025836073,0.000100672085,0.0000266129,0.000005626657,0.00019147286,0.000073107236,0.000027793667],"category_scores_gemma":[0.00022224698,0.00009038166,0.000009180078,0.0007822374,0.000035171543,0.000002638055,0.000047701793,0.00008941273,0.000001447413],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004994031,0.00008503606,0.021845302,0.00022972043,0.00027087252,0.0000037262976,0.00039467277,0.0016814799,0.86234325,0.00323532,0.10565822,0.0037530211],"study_design_scores_gemma":[0.01681003,0.004038027,0.05126698,0.00016586063,0.0020323999,0.000045009718,0.00068043615,0.22955436,0.013191656,0.0049218335,0.6760165,0.001276905],"about_ca_topic_score_codex":0.0015645322,"about_ca_topic_score_gemma":0.005331622,"teacher_disagreement_score":0.84915155,"about_ca_system_score_codex":0.000021404923,"about_ca_system_score_gemma":0.00021809315,"threshold_uncertainty_score":0.3685657},"labels":[],"label_agreement":null},{"id":"W2982693598","doi":"10.1002/sim.8399","title":"A review of the use of time‐varying covariates in the Fine‐Gray subdistribution hazard competing risk regression model","year":2019,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":151,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; International Council for the Exploration of the Sea; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Covariate; Proportional hazards model; Statistics; Gray (unit); Regression analysis; Econometrics; Regression; Mathematics; Medicine","score_opus":0.27567504430334744,"score_gpt":0.4708426292700219,"score_spread":0.19516758496667447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982693598","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001976419,0.6782525,0.31793806,0.00005339064,0.00011961641,0.0011732507,0.0023118441,0.0000052042324,0.00014414909],"genre_scores_gemma":[0.000008119365,0.7926552,0.20697692,0.000067439956,0.000031098145,0.000033925888,0.00018093074,0.000023806228,0.000022532411],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.99430984,0.002422311,0.0020859013,0.00030106897,0.0006214374,0.0002594253],"domain_scores_gemma":[0.97285783,0.023993155,0.0020497034,0.00081622665,0.00024860294,0.000034458117],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0050339843,0.00036219842,0.0026210328,0.000120677694,0.000049203845,0.000008172225,0.0005708532,0.0001738443,0.00010886908],"category_scores_gemma":[0.063299075,0.00016485089,0.00013744149,0.0006725626,0.00031710122,0.000026209113,0.00015166322,0.0009437075,0.0000036976444],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001705498,0.00013646255,0.000066684384,0.3164381,0.00006626635,0.000008777268,0.00050790905,0.000038182647,0.0000023397613,0.20775151,0.013461921,0.4615048],"study_design_scores_gemma":[0.00049742666,0.0001307349,0.000033617547,0.77576447,0.0019273558,0.000013107171,0.000027967126,0.038119983,0.0000010520278,0.15772004,0.025467206,0.00029704603],"about_ca_topic_score_codex":0.000157985,"about_ca_topic_score_gemma":0.000032793785,"teacher_disagreement_score":0.46120775,"about_ca_system_score_codex":0.000090664784,"about_ca_system_score_gemma":0.00024947806,"threshold_uncertainty_score":0.94459116},"labels":[],"label_agreement":null},{"id":"W2986248248","doi":"10.1002/sim.8852","title":"Model diagnostics for censored regression via randomized survival probabilities","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Saskatchewan","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Residual; Quantile; Statistical hypothesis testing; Regression; Regression analysis; Nonlinear regression; Nonlinear system; Studentized residual; Accelerated failure time model","score_opus":0.13827593050603806,"score_gpt":0.4197208800041434,"score_spread":0.2814449494981054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2986248248","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005878285,0.000103608814,0.9941214,0.0018989173,0.00031000885,0.0012837376,0.0005569147,0.000057572113,0.0010800179],"genre_scores_gemma":[0.03751184,0.0002245947,0.96103853,0.00052169024,0.00026125784,0.0002092412,0.00006358772,0.00004197245,0.0001272713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976003,0.00037041717,0.0009062873,0.00034680002,0.00043307262,0.00034309414],"domain_scores_gemma":[0.970041,0.02903244,0.00021414612,0.00022943552,0.0002842483,0.00019875451],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017195131,0.0002518246,0.0012060049,0.000058943777,0.000063763924,0.000011737105,0.00019584339,0.00010003683,0.00017677195],"category_scores_gemma":[0.12928365,0.00017099836,0.000053040425,0.00015308344,0.0005406768,0.000027238237,0.00005603468,0.00025213434,0.0000035438165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038896452,0.00006115312,0.000059513794,0.00062763144,0.000023303586,0.0000090104795,0.0024693059,0.000043573156,0.000073728486,0.97846425,0.010381906,0.0038969852],"study_design_scores_gemma":[0.021876791,0.00015926635,0.000020730415,0.00016091786,0.00007624509,4.5054247e-7,0.00020310476,0.3720051,0.000024116105,0.60528046,0.00006855622,0.00012426115],"about_ca_topic_score_codex":0.000029323633,"about_ca_topic_score_gemma":0.000024624962,"teacher_disagreement_score":0.3731838,"about_ca_system_score_codex":0.000041142208,"about_ca_system_score_gemma":0.00006744448,"threshold_uncertainty_score":0.87805074},"labels":[],"label_agreement":null},{"id":"W2990278103","doi":"10.1002/sim.8403","title":"Joint modeling of binary response and survival for clustered data in clinical trials","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Population Health Research Institute; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Jackknife resampling; Covariate; Inference; Resampling; Sample size determination; Outcome (game theory); Statistics; Statistical inference; Computer science; Multivariate statistics; Statistical model; Survival analysis; Random effects model; Econometrics; Mathematics; Artificial intelligence; Medicine; Estimator; Meta-analysis; Internal medicine","score_opus":0.5370167228892887,"score_gpt":0.5753942456398025,"score_spread":0.03837752275051376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990278103","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05623152,0.000084176165,0.94104767,0.00035619581,0.00043016305,0.00069832,0.0010416151,0.0000067758356,0.00010355785],"genre_scores_gemma":[0.19229662,0.000100308134,0.8073738,0.00004960958,0.00007986482,0.000010274407,0.000045401786,0.000017035214,0.000027074404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99476933,0.002178319,0.0021815326,0.00038003322,0.0002750283,0.00021573747],"domain_scores_gemma":[0.94607973,0.05282848,0.00033155794,0.00057952263,0.000103699356,0.000076982724],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038275197,0.00013386903,0.0013042471,0.00016250586,0.000013556094,0.000005868253,0.00022111184,0.00010781171,0.00009780847],"category_scores_gemma":[0.16384368,0.000101000274,0.000022043481,0.00013105015,0.00017344482,0.00003795016,0.00016395956,0.00024903755,0.0000011067042],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008625605,0.0005494738,0.009411012,0.0025585569,0.00009249312,0.00007388982,0.0013604942,0.000045045614,0.0016164203,0.88539565,0.0038493816,0.08642196],"study_design_scores_gemma":[0.003364096,0.0005671111,0.006057746,0.0005083795,0.00004751692,0.0000015045359,0.00036762786,0.41022095,0.000003933613,0.5787413,0.000026792428,0.00009299673],"about_ca_topic_score_codex":0.0000712314,"about_ca_topic_score_gemma":0.00006646597,"teacher_disagreement_score":0.41017592,"about_ca_system_score_codex":0.00001979268,"about_ca_system_score_gemma":0.00010203723,"threshold_uncertainty_score":0.9902981},"labels":[],"label_agreement":null},{"id":"W2991920218","doi":"10.1002/sim.8435","title":"Assessing the prior event rate ratio method via probabilistic bias analysis on a Bayesian network","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Drug Policy Research Network; University of Toronto; University of Manitoba; Manitoba Health; Sanofi (Canada); University of Guelph","funders":"","keywords":"Confounding; Observational study; Bayesian probability; Econometrics; Robustness (evolution); Statistics; Computer science; Population; Probabilistic logic; Medicine; Mathematics; Environmental health","score_opus":0.07427757909138852,"score_gpt":0.44618420140823795,"score_spread":0.37190662231684946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991920218","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008657876,0.000038143837,0.99457127,0.0008793018,0.00047303416,0.0008551311,0.000045096334,0.000039816918,0.002232403],"genre_scores_gemma":[0.12827154,0.000012659587,0.8704575,0.00061188854,0.00025645262,0.00006144885,0.000032614225,0.000036175417,0.0002597887],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952327,0.0019873395,0.0010579999,0.0005461131,0.0006430859,0.00053274457],"domain_scores_gemma":[0.9723945,0.026076727,0.00043620914,0.00077137345,0.00018392691,0.00013724001],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0070136874,0.0003311057,0.000992168,0.00022803659,0.00016372796,0.000086452594,0.00034935208,0.00010736205,0.0014295146],"category_scores_gemma":[0.013246117,0.00019977558,0.00008071174,0.0014723729,0.0002189526,0.000063303094,0.00006800755,0.0005876995,0.00003189504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004536114,0.00010927529,0.003152491,0.00021525919,0.00025869466,0.00005095292,0.0006730256,0.0013967254,0.00006318517,0.9271232,0.0021766534,0.064735204],"study_design_scores_gemma":[0.0004994579,0.00022977954,0.016190486,0.00026118194,0.0006089461,0.000003839419,0.0001781556,0.26358736,0.000010684303,0.7181012,0.00013484279,0.00019406703],"about_ca_topic_score_codex":0.000109347544,"about_ca_topic_score_gemma":0.00017124055,"teacher_disagreement_score":0.26219064,"about_ca_system_score_codex":0.00013726458,"about_ca_system_score_gemma":0.00011398527,"threshold_uncertainty_score":0.9994833},"labels":[],"label_agreement":null},{"id":"W2992396062","doi":"10.1002/sim.8413","title":"Association measures for clustered competing risks","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; McGill University","funders":"Centre de Recherches Mathématiques","keywords":"Estimator; Multivariate statistics; Statistics; Proportional hazards model; Copula (linguistics); Expectation–maximization algorithm; Econometrics; Hazard ratio; Marginal model; Bone marrow transplantation; Sample size determination; Odds ratio; Maximization; Mathematics; Computer science; Confidence interval; Medicine; Regression analysis; Maximum likelihood; Internal medicine; Transplantation; Mathematical optimization","score_opus":0.16984392854236996,"score_gpt":0.45805928438306515,"score_spread":0.2882153558406952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992396062","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063384557,0.00003748344,0.98573905,0.0005100261,0.00064287113,0.00054086454,0.00021418213,0.000030074687,0.00594701],"genre_scores_gemma":[0.16786847,0.000022814189,0.8305832,0.00025073075,0.00019473022,0.000035045035,0.000031325664,0.000024330378,0.0009893494],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99847555,0.00017787606,0.0004891013,0.00020050752,0.00038492202,0.0002720356],"domain_scores_gemma":[0.98671436,0.01257561,0.00023658067,0.00017683589,0.00023925232,0.000057374356],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024868487,0.00012209431,0.00041321813,0.00007494265,0.000040011346,0.000011110474,0.00011719796,0.00008215073,0.00046572558],"category_scores_gemma":[0.03179846,0.000099799676,0.000018660645,0.00011473377,0.000042077158,0.000019379931,0.00002476642,0.00019797457,0.000020726802],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006366923,0.000057228066,0.020485353,0.00041210305,0.00004853564,0.000003904846,0.0011464078,0.0000093403305,0.00042703902,0.9251487,0.018794956,0.033402715],"study_design_scores_gemma":[0.0019746,0.00029537643,0.010459426,0.0002812469,0.000069686794,0.0000010548239,0.00054145127,0.019095974,0.00005986969,0.964752,0.0023026967,0.00016657767],"about_ca_topic_score_codex":0.00009321284,"about_ca_topic_score_gemma":0.000083854065,"teacher_disagreement_score":0.16153002,"about_ca_system_score_codex":0.00013382337,"about_ca_system_score_gemma":0.000029959721,"threshold_uncertainty_score":0.9763571},"labels":[],"label_agreement":null},{"id":"W2992636254","doi":"10.1002/sim.8414","title":"Optimizing interim analysis timing for Bayesian adaptive commensurate designs","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Xenon Pharmaceuticals (Canada)","funders":"Sanofi","keywords":"Interim; Bayesian probability; Interim analysis; Computer science; Adaptive design; Econometrics; Statistics; Artificial intelligence; Mathematics; Medicine; Clinical trial; Internal medicine","score_opus":0.2877791635705335,"score_gpt":0.511439466930051,"score_spread":0.22366030335951753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992636254","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002559738,0.00013877079,0.9904547,0.00034390422,0.0005359823,0.00058229617,0.00012974505,0.00002125915,0.0052336594],"genre_scores_gemma":[0.35932592,0.000006831256,0.63938487,0.0004034993,0.000042985444,0.000026890984,0.00002690749,0.000017641056,0.0007644379],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99636257,0.0005979744,0.0010529814,0.0006378673,0.0009445792,0.00040404897],"domain_scores_gemma":[0.9894605,0.0091143865,0.0003575578,0.00058020104,0.0003337502,0.00015356232],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065411557,0.00023258758,0.0009122474,0.0009215321,0.00008528848,0.0000701718,0.00061790686,0.00007901041,0.0017609482],"category_scores_gemma":[0.004335207,0.00017639162,0.000094016475,0.0016956914,0.00022014628,0.00015569023,0.00011844481,0.0002144667,0.00006585135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0049123922,0.0006406633,0.049969606,0.00017683697,0.0027075114,0.0004038732,0.06291028,0.09809724,0.12059213,0.27659974,0.08787841,0.29511133],"study_design_scores_gemma":[0.0018504706,0.0013896783,0.0019065184,0.00008957319,0.0002319694,0.000003825767,0.010346517,0.94100004,0.0015593426,0.040284317,0.0009794036,0.00035832488],"about_ca_topic_score_codex":0.00010611101,"about_ca_topic_score_gemma":0.000056453686,"teacher_disagreement_score":0.84290284,"about_ca_system_score_codex":0.00014773497,"about_ca_system_score_gemma":0.00004974074,"threshold_uncertainty_score":0.9991516},"labels":[],"label_agreement":null},{"id":"W2993745637","doi":"10.1002/sim.8419","title":"Causal inference with noisy data: Bias analysis and estimation approaches to simultaneously addressing missingness and misclassification in binary outcomes","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Missing data; Estimator; Inference; Causal inference; Computer science; Statistics; Estimation; Statistical inference; Econometrics; Binary number; Artificial intelligence; Mathematics; Machine learning","score_opus":0.43835106484182346,"score_gpt":0.46189622136305486,"score_spread":0.023545156521231403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993745637","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34406757,0.000039872793,0.6547899,0.0004369936,0.000018299688,0.00041761936,0.00006805732,0.00004475009,0.00011690544],"genre_scores_gemma":[0.6164043,0.000019410916,0.38332173,0.000036838497,0.0000066972093,0.000014050903,0.00014110075,0.000013146657,0.00004272461],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998489,0.00009799332,0.00046027612,0.00045119374,0.0003012502,0.0002002488],"domain_scores_gemma":[0.9964012,0.002725663,0.00020103701,0.0005187763,0.00006759108,0.000085748135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007350849,0.0002026343,0.0005546054,0.0005182182,0.000038929873,0.000036242687,0.00016592098,0.00007419361,0.000019274536],"category_scores_gemma":[0.0034897944,0.0001525067,0.0000049203236,0.00068964326,0.00019450224,0.00020322886,0.000111785,0.00021396684,0.0000011971075],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022229642,0.00027906316,0.81923914,0.0013891842,0.00020236496,0.0001755462,0.009297228,0.005981404,0.0016246923,0.08281299,0.000227177,0.07854892],"study_design_scores_gemma":[0.0011725515,0.0004491683,0.23300417,0.0011046678,0.00038965588,0.000013262447,0.0017481911,0.6685987,0.00012358067,0.09289869,0.000024815576,0.00047254405],"about_ca_topic_score_codex":0.00024843347,"about_ca_topic_score_gemma":0.0013018639,"teacher_disagreement_score":0.6626173,"about_ca_system_score_codex":0.00007010633,"about_ca_system_score_gemma":0.000046846533,"threshold_uncertainty_score":0.62190425},"labels":[],"label_agreement":null},{"id":"W2994663156","doi":"10.1002/sim.8416","title":"A flexible copula‐based approach for the analysis of secondary phenotypes in ascertained samples","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital; Université du Québec à Montréal; McGill University Health Centre; Lunenfeld-Tanenbaum Research Institute","funders":"Medical Research Council; Natural Sciences and Engineering Research Council of Canada; Wellcome Trust","keywords":"Copula (linguistics); Computer science; Statistics; Phenotype; Econometrics; Mathematics; Biology; Genetics","score_opus":0.024022248024884275,"score_gpt":0.3229461029495333,"score_spread":0.298923854924649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994663156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17700195,0.0010144513,0.81961524,0.00043130512,0.00011512421,0.0005127528,0.00045338253,0.0000031355128,0.00085265556],"genre_scores_gemma":[0.94716847,0.000079976504,0.050551593,0.000356698,0.000042895503,0.000044162574,0.0015111996,0.000008313493,0.0002367027],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991195,0.00008786078,0.00034552303,0.00019935887,0.000081952894,0.0001657865],"domain_scores_gemma":[0.9990248,0.0004937574,0.00013024785,0.00025088628,0.000078587,0.000021704609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008368627,0.00008524276,0.00034479974,0.00014137276,0.000020452284,0.0000016043681,0.0001350619,0.000087129585,0.00008669442],"category_scores_gemma":[0.000925033,0.00005980714,0.000043051903,0.00030602483,0.00009668115,6.4469407e-7,0.000022629349,0.00007556781,4.368843e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039377535,0.00020976017,0.80292267,0.00023081292,0.0010083035,8.666672e-7,0.0005103915,0.1457785,0.016165147,0.0077539277,0.009964212,0.015061662],"study_design_scores_gemma":[0.0030753312,0.0005491507,0.77342963,0.000021446433,0.00047308896,3.9476006e-7,0.0011808357,0.21297644,0.00054448977,0.0024512548,0.0051050507,0.00019289769],"about_ca_topic_score_codex":0.00047630555,"about_ca_topic_score_gemma":0.00073795026,"teacher_disagreement_score":0.7701665,"about_ca_system_score_codex":0.000016229274,"about_ca_system_score_gemma":0.000076404176,"threshold_uncertainty_score":0.24388643},"labels":[],"label_agreement":null},{"id":"W2995768992","doi":"10.1002/sim.8410","title":"Safety surveillance and the estimation of risk in select populations: Flexible methods to control for confounding while targeting marginal comparisons via standardization","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institutes of Health; U.S. Food and Drug Administration; Hamilton Health Sciences Foundation; National Center for Advancing Translational Sciences; U.S. Department of Health and Human Services","keywords":"Covariate; Causal inference; Confounding; Computer science; Inference; Statistics; Context (archaeology); Econometrics; Machine learning; Mathematics; Artificial intelligence","score_opus":0.07507788337893141,"score_gpt":0.472539222786533,"score_spread":0.3974613394076016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995768992","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032829049,0.000100498735,0.99453866,0.00019798243,0.00009746074,0.001394282,0.00023269306,0.000032601532,0.00012291793],"genre_scores_gemma":[0.4542689,0.000021410184,0.5455739,0.000020949494,0.000012919779,0.000038359492,0.00004815819,0.000009450818,0.0000059402523],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983531,0.00042172323,0.00069000834,0.00016678235,0.00019680735,0.00017154163],"domain_scores_gemma":[0.9910642,0.00817221,0.00036160438,0.00015941296,0.00021303871,0.000029528926],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005230301,0.000117764284,0.00054442434,0.00015811225,0.0000595177,0.000008235054,0.00008115865,0.000045683973,0.00002853169],"category_scores_gemma":[0.01230327,0.000088933266,0.000012101783,0.0003037251,0.00011824283,0.000060704617,0.000020321762,0.00016486328,3.430373e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007212511,0.000026349466,0.034991454,0.000256933,0.00001927734,3.3726843e-7,0.0015918955,0.02522703,0.0006877421,0.92537236,0.0006852843,0.010420085],"study_design_scores_gemma":[0.002845278,0.00012675002,0.008870582,0.00019946219,0.000026160955,8.1074387e-7,0.000282687,0.36605728,0.00018584997,0.6212421,0.0000737618,0.0000892472],"about_ca_topic_score_codex":0.00016585254,"about_ca_topic_score_gemma":0.0002795341,"teacher_disagreement_score":0.450986,"about_ca_system_score_codex":0.000117289725,"about_ca_system_score_gemma":0.00003179164,"threshold_uncertainty_score":0.9960165},"labels":[],"label_agreement":null},{"id":"W2995814717","doi":"10.1002/sim.9356","title":"Sample size estimation using a latent variable model for mixed outcome co‐primary, multiple primary and composite endpoints","year":2022,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council; National Institute for Health and Care Research; Medical Research Council Canada; Cancer Research UK","keywords":"Sample size determination; Clinical endpoint; Outcome (game theory); Statistics; Sample (material); Latent variable; Econometrics; Computer science; Mathematics; Clinical trial; Medicine; Physics; Internal medicine","score_opus":0.1837940103163691,"score_gpt":0.43787408768378433,"score_spread":0.2540800773674152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995814717","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045170006,0.00008965641,0.9821951,0.00010644605,0.0006223498,0.0014531559,0.010643751,0.00005567885,0.0003168858],"genre_scores_gemma":[0.010783485,0.000062103034,0.9870507,0.00037307502,0.0000852315,0.0002350656,0.0012103429,0.00007925933,0.00012073129],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99655193,0.0002908266,0.0013765364,0.00067655795,0.0006546429,0.000449482],"domain_scores_gemma":[0.97222525,0.026312718,0.0005784964,0.0005141499,0.00020349404,0.0001658691],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0023050182,0.00045138306,0.0013867094,0.00017962503,0.00018629192,0.000042437747,0.0002916677,0.00021221601,0.00027842872],"category_scores_gemma":[0.025886372,0.00042141537,0.00004726525,0.0001296564,0.00024970717,0.00003726841,0.00058830663,0.000846386,5.902194e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00097332615,0.00089929724,0.011108351,0.024053155,0.00039860496,0.000084926185,0.0047201347,0.065265186,0.0028122384,0.85492665,0.00732852,0.027429584],"study_design_scores_gemma":[0.0011257201,0.000077110424,0.0017992657,0.00027312717,0.00016856848,0.000003785926,0.000030352247,0.5251251,0.0000056083363,0.4711504,0.000019372415,0.00022161586],"about_ca_topic_score_codex":0.00053179596,"about_ca_topic_score_gemma":0.000023328183,"teacher_disagreement_score":0.4598599,"about_ca_system_score_codex":0.00052823743,"about_ca_system_score_gemma":0.00024376884,"threshold_uncertainty_score":0.99982375},"labels":[],"label_agreement":null},{"id":"W2996227145","doi":"10.1002/sim.8411","title":"Multistate analysis from cross‐sectional and auxiliary samples","year":2019,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Cross-sectional study; Statistics; Computer science; Mathematics","score_opus":0.10578371827638448,"score_gpt":0.46670829117387863,"score_spread":0.36092457289749413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996227145","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11180227,0.000109637724,0.8855963,0.000052043935,0.00021036988,0.00017037426,0.0014264523,0.000024143825,0.0006084541],"genre_scores_gemma":[0.2267425,0.00008051492,0.772223,0.000100528756,0.00008003141,0.000009743768,0.00017835037,0.000017608005,0.00056774134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983801,0.00011884303,0.00052839273,0.00040313567,0.0003325187,0.00023697465],"domain_scores_gemma":[0.993559,0.005831538,0.00012894397,0.00026655186,0.000098005214,0.00011594216],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00061772845,0.00016746362,0.0005295817,0.00017975259,0.000049969476,0.000016111911,0.0000961739,0.0000702792,0.0011284186],"category_scores_gemma":[0.0026933379,0.00013688765,0.000026692833,0.00025521612,0.00025344428,0.000053663254,0.000052942025,0.00023130505,0.000010621551],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011192436,0.000068777,0.32396486,0.0001260199,0.00028739133,0.000055701887,0.0007709841,0.00032244137,0.00043247102,0.66200554,0.0005795736,0.011274305],"study_design_scores_gemma":[0.000855599,0.000059441507,0.25714514,0.00002897248,0.00013280402,0.000001416187,0.00008429307,0.02417571,0.000010306075,0.717155,0.00022754642,0.00012378281],"about_ca_topic_score_codex":0.00062875735,"about_ca_topic_score_gemma":0.00040840346,"teacher_disagreement_score":0.114940226,"about_ca_system_score_codex":0.00004613581,"about_ca_system_score_gemma":0.000020403208,"threshold_uncertainty_score":0.9997847},"labels":[],"label_agreement":null},{"id":"W2998463403","doi":"10.1002/sim.8481","title":"A threshold‐free summary index for quantifying the capacity of covariates to yield efficient treatment rules","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Context (archaeology); Econometrics; Estimator; Index (typography); Computer science; Metric (unit); Statistics; Parametric statistics; Mathematics; Economics","score_opus":0.28486632970212217,"score_gpt":0.4353815638659449,"score_spread":0.15051523416382273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998463403","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024515169,0.00008484977,0.97012955,0.0029833824,0.00008577672,0.001115744,0.00063639076,0.000070494185,0.0003786718],"genre_scores_gemma":[0.5376779,0.000050548435,0.46145824,0.00049414916,0.00009835386,0.00015392361,0.000018695178,0.000026638234,0.00002159216],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987092,0.000037730664,0.00051202864,0.0002222205,0.0002868247,0.00023196408],"domain_scores_gemma":[0.99505097,0.0041686147,0.00016923272,0.0003851589,0.0001376046,0.00008845117],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00048963295,0.00018077524,0.0004653383,0.0000754917,0.0000549405,0.000006299252,0.0002998991,0.000057869845,0.000044665147],"category_scores_gemma":[0.009542333,0.00011234584,0.000029576213,0.00019804917,0.00019621714,0.000017629622,0.00008533753,0.00014231839,0.000001456366],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000195176,0.00014470877,0.001108311,0.00038111614,0.000053159725,0.000012253738,0.008471836,0.0003958828,0.005063947,0.9684871,0.01353932,0.0021472212],"study_design_scores_gemma":[0.0012062315,0.0020600818,0.00063430297,0.00082131283,0.0001242457,0.000002482292,0.0017136097,0.0212367,0.009749345,0.96155655,0.00064383587,0.00025131428],"about_ca_topic_score_codex":0.00020591258,"about_ca_topic_score_gemma":0.00030013896,"teacher_disagreement_score":0.5131627,"about_ca_system_score_codex":0.00008992394,"about_ca_system_score_gemma":0.000044698205,"threshold_uncertainty_score":0.9988007},"labels":[],"label_agreement":null},{"id":"W3003667353","doi":"10.1002/sim.8468","title":"A fair comparison of tree‐based and parametric methods in multiple imputation by chained equations","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Norman Cousins Center for Psychoneuroimmunology; National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; H. Lundbeck A/S; Servier; National Institute of Environmental Health Sciences; Northern California Institute for Research and Education; Alzheimer's Disease Neuroimaging Initiative; GE Healthcare; Alzheimer's Association; Fujirebio US; Pfizer; BioClinica; Biogen; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Roche; Merck; Alzheimer's Drug Discovery Foundation; Takeda Pharmaceutical Company; AbbVie; Foundation for the National Institutes of Health","keywords":"Imputation (statistics); Parametric statistics; Computer science; Nonparametric statistics; Inference; Missing data; Statistics; Econometrics; Data mining; Mathematics; Machine learning; Artificial intelligence","score_opus":0.172531786709154,"score_gpt":0.4936504161418888,"score_spread":0.32111862943273484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003667353","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015618458,0.00014270563,0.9967259,0.0008344532,0.000048157388,0.0003178741,0.00020455495,0.000018088367,0.00014641882],"genre_scores_gemma":[0.3681951,0.000007930066,0.6316184,0.00010013426,0.000013648273,0.00001614632,0.000036609203,0.000009652422,0.00000244397],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802625,0.000469231,0.0008201957,0.00024011968,0.00026095417,0.00018321826],"domain_scores_gemma":[0.9797799,0.019656315,0.00024032987,0.00012015161,0.000089625166,0.00011367229],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010044816,0.00014318909,0.0006244341,0.00022561583,0.000025729561,0.000006583331,0.00009642791,0.000071530216,0.00007547999],"category_scores_gemma":[0.045814157,0.00012348483,0.000012910166,0.00084743113,0.00021484132,0.00002557799,0.00002517456,0.00023511048,7.379943e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015398576,0.00037171706,0.026491735,0.00091808307,0.00002511327,0.00001653438,0.005177539,0.00008771336,0.0039854543,0.5178929,0.0031257153,0.44175348],"study_design_scores_gemma":[0.0016189853,0.00039261096,0.004328725,0.00010155294,0.0000337418,1.9448139e-7,0.00052769226,0.6363808,0.00042667103,0.35605982,0.000027454047,0.00010175024],"about_ca_topic_score_codex":0.00015898111,"about_ca_topic_score_gemma":0.00009988386,"teacher_disagreement_score":0.6362931,"about_ca_system_score_codex":0.00003403592,"about_ca_system_score_gemma":0.00004311226,"threshold_uncertainty_score":0.96222335},"labels":[],"label_agreement":null},{"id":"W3003781265","doi":"10.1002/sim.8487","title":"Correction to Walter SD, Turner RM, Macaskill P. Optimising the two‐stage randomised trial design when some participants are indifferent in their treatment preferences (2019). Statistics in Medicine 38, 2317‐2331","year":2020,"lang":"en","type":"erratum","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Hamilton Health Sciences; Impact","funders":"","keywords":"Citation; Order (exchange); Medicine; Library science; Psychology; Computer science","score_opus":0.5087324334082165,"score_gpt":0.5251660379332699,"score_spread":0.01643360452505338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003781265","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005822903,0.0011994843,0.90247536,0.0041658077,0.07096446,0.014412598,0.004790065,0.00014065484,0.0012692995],"genre_scores_gemma":[0.005094033,0.009010294,0.92457944,0.003304039,0.017850488,0.004219089,0.0019214067,0.0007928237,0.03322841],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97994316,0.008411633,0.0059917276,0.0018049952,0.0020692202,0.0017792725],"domain_scores_gemma":[0.8695962,0.12617068,0.002069935,0.0011918672,0.0003151775,0.00065614964],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.011351417,0.0015972807,0.0060578627,0.00092512264,0.00018018087,0.00010137026,0.0011374891,0.00082813436,0.0020205365],"category_scores_gemma":[0.22201848,0.000946366,0.00015929138,0.0008780904,0.001009893,0.0000890776,0.00031786354,0.0037231275,0.00003881999],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.054629523,0.0010123705,0.0001444936,0.0008112873,0.00047092506,0.0009094471,0.0144327525,0.00044904152,0.000015545807,0.0062733702,0.89672136,0.024129909],"study_design_scores_gemma":[0.20008029,0.007049061,0.00070685043,0.00921127,0.0012763845,0.000009584943,0.0028395085,0.021555327,0.000039149938,0.7499898,0.005859518,0.0013832273],"about_ca_topic_score_codex":0.0015782648,"about_ca_topic_score_gemma":0.0035568033,"teacher_disagreement_score":0.8908618,"about_ca_system_score_codex":0.0013824956,"about_ca_system_score_gemma":0.00080955523,"threshold_uncertainty_score":0.9996775},"labels":[],"label_agreement":null},{"id":"W3004002562","doi":"10.1002/sim.8465","title":"Bayesian hierarchical meta‐analytic methods for modeling surrogate relationships that vary across treatment classes using aggregate data","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; Medical Research Council; National Institute for Health and Care Research","keywords":"Surrogate endpoint; Bayesian probability; Computer science; Surrogate model; Surrogate data; Bayesian inference; Meta-analysis; Class (philosophy); Econometrics; Statistics; Data mining; Artificial intelligence; Machine learning; Mathematics; Medicine; Internal medicine","score_opus":0.8988886626769544,"score_gpt":0.6656536011715628,"score_spread":0.23323506150539164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004002562","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032446868,0.0006120487,0.991186,0.0030498402,0.00048003002,0.0012402026,0.0028835374,0.00009363835,0.00013023136],"genre_scores_gemma":[0.01582179,0.00031193256,0.9824257,0.00043591257,0.0005712519,0.000083078274,0.00020258616,0.00010546935,0.00004227394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99193186,0.0035981862,0.0020382237,0.0011247402,0.00057620124,0.00073076907],"domain_scores_gemma":[0.8525165,0.14519617,0.0005010422,0.0011370787,0.00018408945,0.00046513224],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.012459028,0.00049600255,0.0022963448,0.00012195722,0.0002737233,0.00005232618,0.00074002304,0.0002567014,0.0002142447],"category_scores_gemma":[0.2451172,0.00036826683,0.00015707737,0.0005248212,0.00048358543,0.00013822709,0.00032907363,0.00078363606,0.0000042718907],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021023683,0.0009072746,0.0010150166,0.0029466192,0.00997664,0.0005211566,0.007840617,0.008763543,0.0005553112,0.8215508,0.0034020569,0.14041863],"study_design_scores_gemma":[0.0015254432,0.00022354102,0.00000794793,0.000099504105,0.002820168,0.0000051000993,0.00025825086,0.50265574,0.000038548056,0.49199712,0.00018682476,0.00018183187],"about_ca_topic_score_codex":0.00010377444,"about_ca_topic_score_gemma":0.00010617853,"teacher_disagreement_score":0.4938922,"about_ca_system_score_codex":0.00017175305,"about_ca_system_score_gemma":0.00019765517,"threshold_uncertainty_score":0.9998769},"labels":[],"label_agreement":null},{"id":"W3004845713","doi":"10.1002/sim.8479","title":"Ordinal outcomes: A cumulative probability model with the log link and an assumption of proportionality","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Ordinal regression; Logit; Mathematics; Link (geometry); Ordered logit; Odds; Statistics; Logistic regression; Ordinal data; Log-linear model; Econometrics; Uniqueness; Linear model; Combinatorics","score_opus":0.1775003639773146,"score_gpt":0.44978809162532396,"score_spread":0.27228772764800935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004845713","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018451136,0.000007862179,0.9756079,0.0050434973,0.00001323361,0.00041017454,0.00018689732,0.000013624419,0.00026568],"genre_scores_gemma":[0.35161242,0.0000031969107,0.64811575,0.00019332707,0.000032732263,0.000015440553,0.000011540102,0.000006797114,0.000008772167],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986217,0.00021814449,0.00042924448,0.00023169054,0.00037078705,0.00012843823],"domain_scores_gemma":[0.9975974,0.001718342,0.00020133759,0.00018085295,0.00020683614,0.00009525441],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001016151,0.0001272172,0.0003913246,0.000022564276,0.00004162039,0.000005891089,0.00009810982,0.000042389078,0.000084897576],"category_scores_gemma":[0.004869954,0.00006560773,0.000009205278,0.00013769482,0.000629163,0.000044283963,0.000031130196,0.00023065833,3.5602227e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013292582,0.00007421281,0.016707128,0.0003830242,0.000021137857,0.0000074445556,0.002804921,0.000048840255,0.000041348616,0.96865267,0.00026010594,0.010866274],"study_design_scores_gemma":[0.0005272375,0.0004771676,0.041939862,0.0000614271,0.00005717568,0.000001534788,0.00020600547,0.11440379,0.0000072916478,0.8422399,0.000005706561,0.0000728801],"about_ca_topic_score_codex":0.00004940356,"about_ca_topic_score_gemma":0.00007842643,"teacher_disagreement_score":0.3331613,"about_ca_system_score_codex":0.000022286398,"about_ca_system_score_gemma":0.00007099486,"threshold_uncertainty_score":0.5830142},"labels":[],"label_agreement":null},{"id":"W3005876327","doi":"10.1002/sim.8484","title":"Comparing a multivariate response Bayesian random effects logistic regression model with a latent variable item response theory model for provider profiling on multiple binary indicators simultaneously","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; Institute of Health Services and Policy Research; University Health Network; University of Toronto; Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Economic and Social Research Council; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Logistic regression; Statistics; Multivariate statistics; Bayesian probability; Medicine; Multivariate analysis; Econometrics; Mathematics","score_opus":0.08760402899998009,"score_gpt":0.3791329511887469,"score_spread":0.2915289221887668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005876327","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020179743,0.000036378908,0.9759574,0.0005154976,0.00009066332,0.002649191,0.00038079478,0.00013926251,0.00005108136],"genre_scores_gemma":[0.45380592,0.000003430655,0.5454321,0.00032935833,0.000039601353,0.0002183481,0.000028406985,0.000067762274,0.00007509139],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995005,0.0018448327,0.00098412,0.00083230576,0.0006603874,0.00067334424],"domain_scores_gemma":[0.9114006,0.08716503,0.00042382008,0.00044696845,0.00019111695,0.00037247772],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004467951,0.0005465881,0.0012231144,0.00033228614,0.00022830773,0.000037009577,0.00033965945,0.00020350007,0.000016469761],"category_scores_gemma":[0.1398372,0.00036718266,0.000047715173,0.000507955,0.00037240583,0.000066101304,0.00010624926,0.0007001209,0.0000024773835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.33741498,0.00067437673,0.0011729127,0.0036056968,0.00018673386,0.00096918666,0.009883319,0.12466311,0.01225042,0.50367886,0.0009486299,0.0045517846],"study_design_scores_gemma":[0.008934878,0.0017149599,0.00016183723,0.0016330259,0.00016219648,0.0000061292576,0.00013951334,0.7076132,0.0002309857,0.27907228,0.000005054324,0.00032591086],"about_ca_topic_score_codex":0.000019324214,"about_ca_topic_score_gemma":0.000007328281,"teacher_disagreement_score":0.5829501,"about_ca_system_score_codex":0.00019251047,"about_ca_system_score_gemma":0.00038455037,"threshold_uncertainty_score":0.999878},"labels":[],"label_agreement":null},{"id":"W3006396558","doi":"10.1002/sim.8495","title":"A hierarchical testing approach for detecting safety signals in clinical trials","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Cancer Institute; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Clinical trial; Data mining; Safety monitoring; Curse of dimensionality; Class (philosophy); Artificial intelligence; Medicine; Bioinformatics","score_opus":0.8299342855077583,"score_gpt":0.649968645019091,"score_spread":0.17996564048866726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006396558","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008180633,0.00005646465,0.9924365,0.0016461937,0.00048670688,0.0022574181,0.0004674259,0.000085256346,0.0017459437],"genre_scores_gemma":[0.023281367,0.000032113483,0.9729939,0.0013777714,0.0020358453,0.00016709657,0.000019744853,0.000072890376,0.000019276467],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9817003,0.008138868,0.007718976,0.0009863504,0.0007312799,0.0007242247],"domain_scores_gemma":[0.45262548,0.5453329,0.0010276175,0.00036147644,0.00022207802,0.0004304409],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.07828288,0.00035671765,0.0033436269,0.00017468893,0.00007973493,0.000021939144,0.00045895218,0.00036139417,0.00019079213],"category_scores_gemma":[0.9464482,0.00028159335,0.00015739076,0.0008786796,0.0005528857,0.000036750538,0.00014930606,0.0015402362,0.000004855847],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0044992846,0.00087101065,0.0087572485,0.0026317849,0.00021078957,0.00023355879,0.001925873,0.00031488482,0.00068875327,0.30412826,0.010274447,0.6654641],"study_design_scores_gemma":[0.00796526,0.0012219066,0.0011654252,0.00040346675,0.00016369838,0.000004026003,0.000331703,0.13982262,0.00003100501,0.84839904,0.00019844307,0.00029339915],"about_ca_topic_score_codex":0.000024118312,"about_ca_topic_score_gemma":0.000013190388,"teacher_disagreement_score":0.8681654,"about_ca_system_score_codex":0.00008662988,"about_ca_system_score_gemma":0.0001788388,"threshold_uncertainty_score":0.99996364},"labels":[],"label_agreement":null},{"id":"W3008905790","doi":"10.1002/sim.8502","title":"Variance estimation when using propensity‐score matching with replacement with survival or time‐to‐event outcomes","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":86,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Statistics; Event data; Matching (statistics); Variance (accounting); Estimation; Event (particle physics); Survival analysis; Econometrics; Computer science; Mathematics; Covariate","score_opus":0.1810926378835545,"score_gpt":0.4193115110956037,"score_spread":0.2382188732120492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008905790","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02614024,0.0000041070466,0.9706906,0.0016741647,0.00003212603,0.0009571526,0.000036606452,0.00014880393,0.00031617505],"genre_scores_gemma":[0.06667566,0.0000026672665,0.9321376,0.0006842035,0.000047542842,0.00003817938,0.000028324986,0.000051911808,0.00033386945],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99818087,0.000096524454,0.00049058936,0.0003559478,0.00060435955,0.00027171796],"domain_scores_gemma":[0.998493,0.0006254167,0.0002578901,0.00031483723,0.00016255744,0.00014630587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005910589,0.0002562921,0.000600415,0.00007947806,0.00006486818,0.000019566165,0.00017122016,0.000042052663,0.000379664],"category_scores_gemma":[0.0016607764,0.00015472376,0.000008179937,0.00025995192,0.00010637538,0.000116137744,0.00008121676,0.00025707128,0.000014631963],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019170547,0.0016016299,0.07639881,0.008322908,0.0012905211,0.0058525237,0.10049338,0.06446856,0.017318469,0.62130725,0.036904868,0.046870537],"study_design_scores_gemma":[0.00947685,0.013915588,0.010637649,0.009708902,0.0007855804,0.00018576912,0.0026315239,0.16051297,0.00207904,0.7869579,0.00069253903,0.0024156864],"about_ca_topic_score_codex":0.000091377384,"about_ca_topic_score_gemma":0.00013987625,"teacher_disagreement_score":0.16565067,"about_ca_system_score_codex":0.00017331401,"about_ca_system_score_gemma":0.0001157486,"threshold_uncertainty_score":0.6309452},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W3008923208","doi":"10.1002/sim.8507","title":"A bootstrap semiparametric homogeneity test for the distributions of multigroup proportional data, with applications to analysis of quality of life outcomes in clinical trials","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Canadian Cancer Society","funders":"Fundamental Research Funds for the Central Universities; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Statistics; Mathematics; Homogeneity (statistics); Nonparametric statistics; Type I and type II errors; Statistical hypothesis testing; Parametric statistics; Likelihood-ratio test; Wald test; Test statistic; Null hypothesis; Empirical likelihood; Econometrics; Confidence interval","score_opus":0.8162034951521221,"score_gpt":0.6841353634128662,"score_spread":0.1320681317392559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008923208","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0073818727,0.000059511094,0.9434448,0.0022050354,0.00005509027,0.002448392,0.044384535,0.000008240609,0.000012536539],"genre_scores_gemma":[0.30048904,0.000053385713,0.69875234,0.0001389727,0.000078179255,0.00021554988,0.00025777624,0.000011122808,0.0000035998266],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9902402,0.0017146043,0.006576452,0.00048626374,0.00077666494,0.00020581191],"domain_scores_gemma":[0.5117924,0.48377645,0.002503215,0.0010629056,0.0006379201,0.00022707655],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.031074725,0.00017629849,0.003190238,0.00026588776,0.000030896048,0.0000036285774,0.0006431569,0.00011929604,0.00010096854],"category_scores_gemma":[0.775755,0.000105331295,0.00016814495,0.0028402922,0.00086390367,0.00002183645,0.0001382451,0.00030346416,4.0282364e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011173222,0.0023477306,0.6918463,0.0010112406,0.002050693,0.0000016079376,0.00024617638,0.00028918678,0.00014607434,0.2875761,0.0022454287,0.0111221],"study_design_scores_gemma":[0.004940282,0.0011002945,0.80686927,0.00011819403,0.0040588393,1.4125801e-7,0.00042537315,0.015829599,0.00006758717,0.16630661,0.00009317839,0.00019064387],"about_ca_topic_score_codex":0.00024709626,"about_ca_topic_score_gemma":0.00047291772,"teacher_disagreement_score":0.7446803,"about_ca_system_score_codex":0.000028559967,"about_ca_system_score_gemma":0.0002611533,"threshold_uncertainty_score":0.9977125},"labels":[],"label_agreement":null},{"id":"W3009924189","doi":"10.1002/sim.8517","title":"Mitigating bias from intermittent measurement of time‐dependent covariates in failure time analysis","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Estimator; Covariate; Proportional hazards model; Statistics; Regression analysis; Computer science; Regression; Linear regression; Econometrics; Mathematics","score_opus":0.12201525913244021,"score_gpt":0.36799358052698866,"score_spread":0.24597832139454845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009924189","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023910046,0.00009066219,0.97304535,0.0011763903,0.000064448235,0.00028658137,0.00066768465,0.000024194744,0.0007346611],"genre_scores_gemma":[0.46545517,0.0000144445385,0.53412896,0.00021165959,0.00007149648,0.0000121839275,0.0000638087,0.00001816007,0.000024118466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997061,0.00040683852,0.0011208679,0.00034341324,0.000825974,0.00024186294],"domain_scores_gemma":[0.99537385,0.0036764324,0.00033058546,0.0002460837,0.00023213177,0.00014093192],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016639062,0.00020330655,0.0009620816,0.00020090795,0.000018928262,0.000010273898,0.00023362078,0.00007408099,0.0027739224],"category_scores_gemma":[0.022759616,0.00016531449,0.000044481043,0.00067908515,0.00014989673,0.000023309722,0.00008611651,0.00030723427,0.000029107801],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00091585174,0.0020099154,0.11228535,0.003136649,0.005760851,0.0014914154,0.06384587,0.001887826,0.14671615,0.49512523,0.043472998,0.12335187],"study_design_scores_gemma":[0.00331118,0.0007576985,0.02619629,0.0014655512,0.0015079122,0.0000014962117,0.0019394326,0.3549984,0.0024193176,0.6067911,0.00006151552,0.0005500926],"about_ca_topic_score_codex":0.0007390728,"about_ca_topic_score_gemma":0.0003144888,"teacher_disagreement_score":0.44154513,"about_ca_system_score_codex":0.0000951394,"about_ca_system_score_gemma":0.000056574005,"threshold_uncertainty_score":0.99813765},"labels":[],"label_agreement":null},{"id":"W3010442290","doi":"10.1002/sim.8519","title":"Sample size and power calculations for open cohort longitudinal cluster randomized trials","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; National Health and Medical Research Council; Medical Research Council Canada","keywords":"Sample size determination; Statistics; Cohort; Sample (material); Sampling (signal processing); Cluster sampling; Cluster (spacecraft); Statistical power; Autocorrelation; Econometrics; Mathematics; Psychology; Demography; Computer science; Population","score_opus":0.6232407975323997,"score_gpt":0.6131850654261651,"score_spread":0.01005573210623456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010442290","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032676634,0.00006682595,0.98229223,0.008457235,0.00051314896,0.0056926985,0.001840281,0.000031710133,0.0007790916],"genre_scores_gemma":[0.010792845,0.00007436935,0.9855385,0.0025195312,0.00043893338,0.0004617998,0.000026678697,0.000044383985,0.00010299146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9930314,0.0029233736,0.0027191543,0.0005578466,0.00044147082,0.00032677766],"domain_scores_gemma":[0.33087653,0.6677544,0.00057331665,0.0002860741,0.00023587245,0.0002738225],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02782529,0.0002572004,0.0034913574,0.00005576249,0.00009159881,0.000055211043,0.0003372523,0.00014491452,0.0018694499],"category_scores_gemma":[0.9372823,0.00018176758,0.00010410559,0.0002148895,0.00063845527,0.000052836636,0.00022068324,0.00028805636,0.0000044512594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.027980588,0.00007402827,0.0011579087,0.0002854194,0.000341569,0.000018044482,0.0006465451,0.00000720816,0.000018695368,0.9004258,0.066535555,0.0025086533],"study_design_scores_gemma":[0.12014097,0.00029555606,0.0009792091,0.00012738701,0.0006954227,0.0000018627427,0.000084503255,0.0061684875,0.000006671675,0.8705961,0.00072176725,0.00018206889],"about_ca_topic_score_codex":0.00012867109,"about_ca_topic_score_gemma":0.00003078949,"teacher_disagreement_score":0.909457,"about_ca_system_score_codex":0.00005015614,"about_ca_system_score_gemma":0.00009283315,"threshold_uncertainty_score":0.999043},"labels":[],"label_agreement":null},{"id":"W3014896206","doi":"10.1002/sim.8532","title":"STRATOS guidance document on measurement error and misclassification of variables in observational epidemiology: Part 1—Basic theory and simple methods of adjustment","year":2020,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":176,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"National Institutes of Health; National Cancer Institute; Medical Research Council; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Patient-Centered Outcomes Research Institute","keywords":"Covariate; Observational error; Statistics; Computer science; Observational study; Errors-in-variables models; Econometrics; Type I and type II errors; Regression; Regression analysis; Sample size determination; Extrapolation; Calibration; Linear regression; Data mining; Mathematics","score_opus":0.3319225737265194,"score_gpt":0.49109950696514776,"score_spread":0.15917693323862836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014896206","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012924898,0.9880056,0.009210373,0.0009877735,0.00011543755,0.0009956316,0.00044953794,0.000004147426,0.00021858005],"genre_scores_gemma":[0.00009365068,0.9483869,0.050415333,0.00031805897,0.0001339674,0.00021856402,0.00040254497,0.000015987913,0.000015000777],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964949,0.0009896834,0.0015354363,0.00039138782,0.000411747,0.00017682678],"domain_scores_gemma":[0.9941573,0.0047212495,0.000638421,0.00019328189,0.00019448157,0.000095262294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005620636,0.00026076243,0.0021868977,0.00014551682,0.000022909693,0.0000010241824,0.00006731255,0.00012306092,0.00007745035],"category_scores_gemma":[0.0077897143,0.00018635228,0.00004426187,0.00022125982,0.00034893825,0.000012862931,0.000046357243,0.00027385252,3.6211335e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030403846,0.00025515346,0.0013170189,0.03205015,0.0003398315,0.00001520876,0.00013790086,0.0000033451827,0.00001560109,0.40197262,0.009904694,0.5536844],"study_design_scores_gemma":[0.0032627734,0.0017743451,0.03289328,0.04412734,0.0013240298,0.000013002389,0.00043943277,0.00010048638,0.0000052286273,0.15580934,0.7599753,0.000275393],"about_ca_topic_score_codex":0.00006651271,"about_ca_topic_score_gemma":0.000030806525,"teacher_disagreement_score":0.75007063,"about_ca_system_score_codex":0.00019990728,"about_ca_system_score_gemma":0.00020932902,"threshold_uncertainty_score":0.9325578},"labels":[],"label_agreement":null},{"id":"W3014964148","doi":"10.1002/sim.8531","title":"STRATOS guidance document on measurement error and misclassification of variables in observational epidemiology: Part 2—More complex methods of adjustment and advanced topics","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":126,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"National Institutes of Health; National Cancer Institute; Medical Research Council; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Patient-Centered Outcomes Research Institute","keywords":"Categorical variable; Covariate; Observational error; Computer science; Statistics; Imputation (statistics); Bayesian probability; Errors-in-variables models; Data mining; Bayes' theorem; Missing data; Standard error; Econometrics; Mathematics","score_opus":0.4407366589677345,"score_gpt":0.5053344638457099,"score_spread":0.0645978048779754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014964148","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022700373,0.00041221565,0.99232244,0.0042082337,0.00006896157,0.000360955,0.00014906883,0.0000053879057,0.00020271547],"genre_scores_gemma":[0.025770362,0.00017742843,0.97349715,0.00044243908,0.000040115065,0.000041373794,0.000019189325,0.0000072222756,0.000004702416],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977528,0.00057241996,0.0009838449,0.0002573072,0.00028648862,0.00014714092],"domain_scores_gemma":[0.9948582,0.0043970956,0.00034998934,0.00014974078,0.00016363272,0.000081334605],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024958136,0.00013407321,0.00062338257,0.000053927426,0.00001615632,0.0000015424205,0.00008118154,0.00005440037,0.000085160784],"category_scores_gemma":[0.018682212,0.00010740236,0.000009544581,0.0001430082,0.0002930603,0.00002130175,0.000030775314,0.00014162189,9.389895e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008547973,0.00006673723,0.0054391343,0.00074776495,0.000019127934,0.000002552469,0.0006827953,0.000017391774,0.0017954768,0.9217972,0.0009370759,0.068409234],"study_design_scores_gemma":[0.0010857461,0.00047512053,0.2315008,0.0005926762,0.000036550013,8.8154707e-7,0.0004283121,0.010852573,0.00027482744,0.75427127,0.00038450124,0.000096732845],"about_ca_topic_score_codex":0.000032879143,"about_ca_topic_score_gemma":0.000025206817,"teacher_disagreement_score":0.22606167,"about_ca_system_score_codex":0.00004880194,"about_ca_system_score_gemma":0.00005082611,"threshold_uncertainty_score":0.98958385},"labels":[],"label_agreement":null},{"id":"W3015122744","doi":"10.1002/sim.8595","title":"Graphical approaches for the control of generalized error rates","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"False discovery rate; Multiple comparisons problem; Graphical model; Context (archaeology); Word error rate; Control (management); Statistical hypothesis testing","score_opus":0.6677080684007569,"score_gpt":0.5681343876762122,"score_spread":0.09957368072454476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015122744","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002651588,0.0002264724,0.984962,0.012194999,0.00033286578,0.0011194004,0.00071468926,0.000022712022,0.00016172456],"genre_scores_gemma":[0.1551751,0.000060207083,0.84273595,0.0013259342,0.0005057311,0.0001361439,0.000008165896,0.000030326637,0.000022433838],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99723,0.0005966699,0.0012306295,0.00028617264,0.00040220452,0.00025431803],"domain_scores_gemma":[0.87514436,0.12403581,0.00030055578,0.00026449797,0.00013474168,0.00012000525],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0036815363,0.000176648,0.0009880277,0.000045066816,0.00004702329,0.00000589287,0.00034002413,0.00010813701,0.00025286718],"category_scores_gemma":[0.23973274,0.00010232095,0.000073171825,0.00027578883,0.00081856805,0.00001258582,0.000038381655,0.00030022464,0.0000017071109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005578937,0.00006979813,0.0003882257,0.0003559461,0.00011393683,0.0000061357478,0.00045049173,0.000025323216,0.0001645947,0.97513425,0.014535346,0.008198043],"study_design_scores_gemma":[0.0049969126,0.00048445302,0.00053893885,0.00006230995,0.00028033223,8.031401e-7,0.00025567345,0.06738761,0.00009565438,0.9251791,0.0006123212,0.000105839004],"about_ca_topic_score_codex":0.000014512845,"about_ca_topic_score_gemma":0.000010495848,"teacher_disagreement_score":0.2360512,"about_ca_system_score_codex":0.000012022579,"about_ca_system_score_gemma":0.000042408086,"threshold_uncertainty_score":0.7666713},"labels":[],"label_agreement":null},{"id":"W3019567365","doi":"10.1002/sim.8541","title":"Doubly robust estimation and causal inference for recurrent event data","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Jewish General Hospital","funders":"Canadian Institutes of Health Research","keywords":"Estimator; Semiparametric regression; Causal inference; Computer science; Statistics; Semiparametric model; Inference; Event (particle physics); Econometrics; Estimating equations; Mathematics; Artificial intelligence","score_opus":0.32461444492443875,"score_gpt":0.5000145513770762,"score_spread":0.17540010645263743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019567365","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006317394,0.000114425595,0.9959028,0.0019405468,0.00009781681,0.0005794767,0.0005221176,0.00009119042,0.000119929275],"genre_scores_gemma":[0.12141595,0.000143463,0.87745535,0.0002625817,0.00011955346,0.00005626127,0.00050562806,0.000022051201,0.000019176028],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99874806,0.000039242404,0.0004601297,0.00032760738,0.00023488404,0.00019009941],"domain_scores_gemma":[0.9975978,0.0016686443,0.0001625998,0.00034750908,0.000110868685,0.00011254758],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005265505,0.00015298201,0.00032019915,0.00005698646,0.00003818154,0.000011357668,0.00025021617,0.000054504162,0.00005011987],"category_scores_gemma":[0.012078391,0.00013090442,0.000005702593,0.00013275101,0.00014591617,0.00012685393,0.00016621924,0.00020381084,0.0000018179203],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001713931,0.00008302436,0.00035524604,0.001064719,0.00002469139,0.000025019632,0.0022121363,0.00028045333,0.00028031622,0.79231966,0.07204642,0.13113691],"study_design_scores_gemma":[0.00081000203,0.00070542435,0.00017475717,0.00031036543,0.00005233511,0.0000028831603,0.00014022109,0.31848297,0.00009167954,0.67795146,0.0011133961,0.0001645174],"about_ca_topic_score_codex":0.000018797355,"about_ca_topic_score_gemma":0.000102516155,"teacher_disagreement_score":0.3182025,"about_ca_system_score_codex":0.000045393193,"about_ca_system_score_gemma":0.000051443258,"threshold_uncertainty_score":0.9962433},"labels":[],"label_agreement":null},{"id":"W3019617362","doi":"10.1002/sim.8508","title":"A multiparameter regression model for interval‐censored survival data","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Irish Research Council","keywords":"Proportional hazards model; Statistics; Interval (graph theory); Weibull distribution; Survival analysis; Computer science; Regression; Parametric statistics; Accelerated failure time model; Confidence interval; Regression analysis; Parametric model; Longitudinal data; Econometrics; Mathematics; Data mining","score_opus":0.40073178722091246,"score_gpt":0.49977133220344255,"score_spread":0.09903954498253009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3019617362","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048099415,0.000039757142,0.9943336,0.0018538508,0.0002555635,0.00041358292,0.0021935469,0.000039180915,0.0003899037],"genre_scores_gemma":[0.042511683,0.000028551673,0.9561324,0.0007397436,0.00019221404,0.000026887741,0.00021415528,0.00003407112,0.00012026391],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816996,0.00014363114,0.00061738,0.00045138653,0.00033270134,0.0002849699],"domain_scores_gemma":[0.99323255,0.0057496666,0.00014962621,0.0005486002,0.00013886199,0.00018071904],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00095132034,0.00019267398,0.0005794834,0.000049408565,0.000039462026,0.0000119123,0.00049446383,0.00007597803,0.00017821754],"category_scores_gemma":[0.04698842,0.00013688486,0.000018556384,0.00013611425,0.00018463163,0.000045247685,0.00021145245,0.00025931204,0.0000060954235],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045006772,0.00012203314,0.00019736795,0.00081321824,0.000043772005,0.000040737446,0.0040590838,0.000051561354,0.000727751,0.8170334,0.121601254,0.05485977],"study_design_scores_gemma":[0.0010228468,0.00016377712,0.00006350832,0.00016694082,0.000041074003,6.4783075e-7,0.00018124658,0.63950175,0.000020497668,0.35840306,0.0003278586,0.00010679036],"about_ca_topic_score_codex":0.000026956306,"about_ca_topic_score_gemma":0.0000358152,"teacher_disagreement_score":0.6394502,"about_ca_system_score_codex":0.000024380293,"about_ca_system_score_gemma":0.000043945634,"threshold_uncertainty_score":0.9610392},"labels":[],"label_agreement":null},{"id":"W3021389985","doi":"10.1002/sim.8560","title":"A tractable method to account for high‐dimensional nonignorable missing data in intensive longitudinal data","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute","keywords":"Missing data; Covariate; Computer science; Curse of dimensionality; Multinomial distribution; Outcome (game theory); Econometrics; Data mining; Statistics; Mathematics; Machine learning","score_opus":0.2896584364384498,"score_gpt":0.49417319198457804,"score_spread":0.20451475554612825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021389985","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001433714,0.000076903394,0.98483515,0.008521522,0.00023177246,0.0006387321,0.005385363,0.000019975294,0.00014720915],"genre_scores_gemma":[0.006278378,0.000009149527,0.9896504,0.0027298755,0.00027968318,0.000026375179,0.0009612209,0.000038949336,0.000025965233],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970191,0.00022742826,0.0008676392,0.0009062939,0.00049865484,0.0004808621],"domain_scores_gemma":[0.9878293,0.01033201,0.00017488233,0.001065642,0.00032595,0.0002721908],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030645714,0.0002531978,0.00084547687,0.00014584819,0.00006881145,0.000036427176,0.001016069,0.0000876191,0.00039853744],"category_scores_gemma":[0.053358134,0.00021236062,0.000010218546,0.00049182156,0.00011661017,0.00017272985,0.00062989106,0.00040872095,0.0000097595985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006501466,0.00021606155,0.00091323047,0.0009803532,0.000075069955,0.00051478983,0.0016272172,0.000038280054,0.0017761561,0.6009934,0.24843013,0.14378516],"study_design_scores_gemma":[0.0018028468,0.00040521458,0.0013269287,0.0006327593,0.0001294094,0.000016059525,0.0005560642,0.21486373,0.00010584694,0.7777353,0.002114314,0.00031151652],"about_ca_topic_score_codex":0.0006905206,"about_ca_topic_score_gemma":0.00037287653,"teacher_disagreement_score":0.24631582,"about_ca_system_score_codex":0.000075246026,"about_ca_system_score_gemma":0.00021191011,"threshold_uncertainty_score":0.95461583},"labels":[],"label_agreement":null},{"id":"W3022690991","doi":"10.1002/sim.8552","title":"Statistical properties of minimal sufficient balance and minimization as methods for controlling baseline covariate imbalance at the design stage of sequential clinical trials","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Center for Advancing Translational Sciences; National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Neurological Disorders and Stroke; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of General Medical Sciences","keywords":"Covariate; Randomness; Minification; Baseline (sea); Computer science; Statistics; Type I and type II errors; Balance (ability); Mathematical optimization; Mathematics; Econometrics; Medicine","score_opus":0.7238147778658908,"score_gpt":0.6262184680458172,"score_spread":0.09759630982007361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022690991","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026605448,0.0005227058,0.98973155,0.0016064568,0.0005687471,0.0024867903,0.0023741738,0.000020659747,0.000028397528],"genre_scores_gemma":[0.03597388,0.00038131562,0.96252567,0.000497505,0.0003629176,0.00009902833,0.000027675367,0.00004432573,0.000087714354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97687715,0.015383214,0.005941861,0.00068476994,0.00068832247,0.000424685],"domain_scores_gemma":[0.70601207,0.291193,0.0017412541,0.00033411762,0.00051460596,0.00020492858],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.059862334,0.00030628883,0.0028342188,0.00007136246,0.000077894016,0.000013927836,0.00030805578,0.00020295243,0.00037581133],"category_scores_gemma":[0.7289109,0.00019044073,0.0001083129,0.00027018943,0.0016751151,0.000029979825,0.00014281286,0.00037933793,0.0000013538885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03709179,0.000992804,0.001894428,0.006310393,0.0009153264,0.00005039363,0.0040407134,0.0012931331,0.046821836,0.83277357,0.012793556,0.05502208],"study_design_scores_gemma":[0.016877208,0.00433187,0.00039252988,0.0007607579,0.0012337136,0.0000053063445,0.00073277927,0.62252367,0.011309867,0.34056556,0.00085616094,0.0004105814],"about_ca_topic_score_codex":0.0000306396,"about_ca_topic_score_gemma":0.0000059501344,"teacher_disagreement_score":0.66904855,"about_ca_system_score_codex":0.000043544263,"about_ca_system_score_gemma":0.0002322096,"threshold_uncertainty_score":0.96806955},"labels":[],"label_agreement":null},{"id":"W3023339592","doi":"10.1002/sim.8557","title":"Point and interval estimation in two‐stage adaptive designs with time to event data and biomarker‐driven subpopulation selection","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; Medical Research Council; National Institutes of Health; Medical Research Council Canada","keywords":"Estimator; Stage (stratigraphy); Event (particle physics); Population; Statistics; Categorical variable; Interval (graph theory); Hazard ratio; Computer science; Confidence interval; Estimation; Selection (genetic algorithm); Interval estimation; Proportional hazards model; Mathematics; Medicine; Artificial intelligence; Biology","score_opus":0.5202491863090454,"score_gpt":0.5605198589785412,"score_spread":0.0402706726694958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023339592","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016104696,0.000014500228,0.9810173,0.0015248948,0.00004936016,0.0008375586,0.00034028245,0.00002857447,0.00008282265],"genre_scores_gemma":[0.22159629,0.000009146815,0.77801,0.00021593775,0.00005422208,0.000017746708,0.00005007816,0.000021939906,0.00002460288],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760205,0.000604624,0.0007835781,0.00048691218,0.00032919642,0.00019361431],"domain_scores_gemma":[0.9888368,0.01047811,0.00020429505,0.00021815527,0.00007951867,0.00018312364],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024023647,0.00017833394,0.0005552427,0.00013787992,0.000032094737,0.000017269562,0.00013769142,0.00005510081,0.00019652222],"category_scores_gemma":[0.048976418,0.00014441097,0.000005994646,0.00037870056,0.00016578352,0.00009400631,0.00015446653,0.000241262,0.0000077275035],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013038122,0.00089890155,0.05557501,0.0026338124,0.0005145124,0.0006724216,0.018147133,0.004313083,0.0059569557,0.29323792,0.02675914,0.578253],"study_design_scores_gemma":[0.0024729818,0.0011429616,0.014550734,0.00046727524,0.000087376,0.0000071945565,0.00019999567,0.7764539,0.000026439237,0.2043874,0.000030783136,0.00017294986],"about_ca_topic_score_codex":0.0001439128,"about_ca_topic_score_gemma":0.0004163724,"teacher_disagreement_score":0.7721408,"about_ca_system_score_codex":0.00007972905,"about_ca_system_score_gemma":0.000037300186,"threshold_uncertainty_score":0.95903444},"labels":[],"label_agreement":null},{"id":"W3025024871","doi":"10.1002/sim.8555","title":"One‐stage individual participant data meta‐analysis models for continuous and binary outcomes: Comparison of treatment coding options and estimation methods","year":2020,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; Medical Research Council; National Institute for Health and Care Research","keywords":"Restricted maximum likelihood; Statistics; Random effects model; Meta-analysis; Confidence interval; Mathematics; Estimation; Mixed model; Maximum likelihood; Variance (accounting); Covariate; Standard error; Binary number; Medicine","score_opus":0.9611799200684782,"score_gpt":0.7025338956772175,"score_spread":0.2586460243912607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025024871","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.6308206e-7,0.5113975,0.48315164,0.000096536445,0.00003916615,0.0011891862,0.004103861,0.0000019874412,0.000019491974],"genre_scores_gemma":[0.0001036496,0.5253285,0.47262457,0.000018357843,0.000016157666,0.00019743349,0.0015254495,0.000014709026,0.00017112879],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.974801,0.009271599,0.012376625,0.0013546164,0.0019444188,0.00025171915],"domain_scores_gemma":[0.9515811,0.03752808,0.0076592728,0.0026361498,0.0003805521,0.00021484216],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06322819,0.0005615185,0.027060093,0.001064468,0.00010284771,0.00018532448,0.0010947371,0.00014181115,0.00045095937],"category_scores_gemma":[0.03527312,0.00026673145,0.001084747,0.0016104676,0.00024120884,0.000134265,0.00033728013,0.00019732204,0.0000049798296],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000467523,0.00011267308,0.00009664629,0.005937419,0.13789712,0.000005399063,0.0021520543,0.0009870129,1.3744948e-7,0.0153890345,0.0012972073,0.8361206],"study_design_scores_gemma":[0.00022830852,0.0002074892,0.000025205163,0.00034623855,0.5160398,0.0000011601674,0.00065578055,0.41809916,2.7974393e-8,0.0036812923,0.060560144,0.0001554197],"about_ca_topic_score_codex":0.00009015322,"about_ca_topic_score_gemma":0.00014143008,"teacher_disagreement_score":0.8359652,"about_ca_system_score_codex":0.000035689656,"about_ca_system_score_gemma":0.00015066993,"threshold_uncertainty_score":0.9999785},"labels":[],"label_agreement":null},{"id":"W3028357212","doi":"10.1002/sim.8868","title":"The optimal design of clinical trials with potential biomarker effects: A novel computational approach","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Western Canada Research Grid; Compute Canada","keywords":"Computer science; Scalability; Smoothing; Curse of dimensionality; Personalized medicine; Clinical trial; Software; Data mining; Machine learning; Bioinformatics","score_opus":0.6846230401092185,"score_gpt":0.6258049677645551,"score_spread":0.05881807234466341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028357212","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00036123124,0.00015689149,0.9965329,0.00041538596,0.0009163604,0.0009427323,0.00026003332,0.000022332773,0.0003921047],"genre_scores_gemma":[0.010540942,0.00009384639,0.98858744,0.0001496233,0.00039443077,0.00006452635,0.000029391786,0.000040125506,0.00009969593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9847517,0.008915124,0.0042207763,0.0005461058,0.001183843,0.00038244398],"domain_scores_gemma":[0.6370342,0.36092296,0.0009693226,0.0004093405,0.0005237242,0.00014046098],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.045852892,0.0002600168,0.002132037,0.00007999762,0.00009830914,0.00002442552,0.0003226184,0.00020208147,0.00012724796],"category_scores_gemma":[0.5446955,0.00014551367,0.00011535524,0.00046950905,0.0014403674,0.000025450448,0.000103731545,0.0005834949,0.0000026660803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0048005427,0.0020645792,0.00061391527,0.00091895135,0.0013098449,0.00044347547,0.00031395914,0.0044371225,0.000436142,0.887408,0.020289378,0.07696406],"study_design_scores_gemma":[0.010758587,0.0008464757,0.0040357225,0.00041492222,0.0006122966,0.000050449515,0.00027157695,0.15804403,0.0000658034,0.8246024,0.00008015383,0.00021755185],"about_ca_topic_score_codex":0.0000101224405,"about_ca_topic_score_gemma":0.0000026747668,"teacher_disagreement_score":0.49884263,"about_ca_system_score_codex":0.000031782987,"about_ca_system_score_gemma":0.00041954056,"threshold_uncertainty_score":0.98249525},"labels":[],"label_agreement":null},{"id":"W3032046824","doi":"10.1002/sim.8757","title":"Analysis of time‐to‐event for observational studies: Guidance to the use of intensity models","year":2020,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Waterloo","funders":"Canadian Institutes of Health Research; National Cancer Institute; National Institutes of Health; Javna Agencija za Raziskovalno Dejavnost RS; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Censoring (clinical trials); Covariate; Event (particle physics); Hazard; Computer science; Proportional hazards model; Observational study; Econometrics; Regression analysis; Goodness of fit; Software; Statistics; Data mining; Machine learning; Mathematics","score_opus":0.6177402007733431,"score_gpt":0.5192164900705176,"score_spread":0.0985237107028255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032046824","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011636779,0.000078544836,0.98656976,0.003927367,0.00021610578,0.0009959856,0.007001859,0.000008854222,0.000037852074],"genre_scores_gemma":[0.009816251,0.00006705502,0.988304,0.0012516878,0.00008942168,0.00014140322,0.00016516699,0.000020665559,0.00014435325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972499,0.00018225421,0.0013859331,0.0004039238,0.000591868,0.00018612684],"domain_scores_gemma":[0.9822912,0.014716687,0.00055236614,0.00059252244,0.0017414185,0.00010577758],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016642461,0.00023315233,0.0016817418,0.00023604283,0.000028541403,0.000006022822,0.00039655887,0.00008563635,0.00011485085],"category_scores_gemma":[0.07862178,0.00015872365,0.00009557071,0.0007088427,0.00020793255,0.0000142867575,0.00049909356,0.00027730272,0.0000020790696],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034192938,0.00014413954,0.00035582852,0.0022172427,0.0026854237,0.0000066900416,0.009230257,0.08586116,0.00012691997,0.739746,0.15189265,0.007391778],"study_design_scores_gemma":[0.00015373122,0.00020473279,0.0022445712,0.0006921696,0.0012138218,9.964941e-8,0.00016982251,0.4193717,0.000018096624,0.575486,0.0003300585,0.000115202565],"about_ca_topic_score_codex":0.00017732983,"about_ca_topic_score_gemma":0.00013704668,"teacher_disagreement_score":0.33351052,"about_ca_system_score_codex":0.00009413021,"about_ca_system_score_gemma":0.00011432549,"threshold_uncertainty_score":0.9291394},"labels":[],"label_agreement":null},{"id":"W3034503810","doi":"10.1002/sim.8570","title":"Graphical calibration curves and the integrated calibration index (ICI) for survival models","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":214,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"National Center for Advancing Translational Sciences; Canadian Institutes of Health Research; National Institutes of Health; Ontario Ministry of Health and Long-Term Care; Georgia Clinical and Translational Science Alliance; Heart and Stroke Foundation of Canada; Institute for Clinical Evaluative Sciences; Patient-Centered Outcomes Research Institute; Vanderbilt Institute for Clinical and Translational Research; Vanderbilt University","keywords":"Calibration; Context (archaeology); Statistics; Proportional hazards model; Percentile; Regression analysis; Mathematics; Survival analysis; Regression; Computer science","score_opus":0.32714729481711025,"score_gpt":0.4229108498472749,"score_spread":0.09576355503016465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034503810","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013531754,0.0020680723,0.8168408,0.17739543,0.000299575,0.0009614534,0.0007553028,0.000023805733,0.00030237678],"genre_scores_gemma":[0.92394584,0.0020251493,0.01082599,0.061120436,0.0007563854,0.0002930639,0.0008644723,0.000048040853,0.00012060436],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99659115,0.00039227237,0.002336865,0.00035870713,0.000112813155,0.00020817101],"domain_scores_gemma":[0.9958757,0.0030210542,0.00072210183,0.00017669165,0.000070793394,0.0001336347],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009051238,0.0001448755,0.0008060008,0.00012824456,0.000106600855,0.000031454467,0.00014853831,0.000095009185,0.0001060255],"category_scores_gemma":[0.010565605,0.00012442734,0.000028116277,0.00025178603,0.00031366598,0.0002460732,0.000025987616,0.00022085149,0.000006032262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010528415,0.000014651512,0.005006091,0.00048086263,0.000025465555,6.066991e-7,0.0025692217,0.0005958277,0.0000013089596,0.94673085,0.04436165,0.00010818567],"study_design_scores_gemma":[0.0022486513,0.000088644076,0.0016855203,0.000109159584,0.000009262071,6.591613e-7,0.0008061171,0.7407881,4.2360372e-7,0.25231546,0.0018385866,0.00010941742],"about_ca_topic_score_codex":0.0011112399,"about_ca_topic_score_gemma":0.0005280912,"teacher_disagreement_score":0.9225927,"about_ca_system_score_codex":0.00007029159,"about_ca_system_score_gemma":0.00008302548,"threshold_uncertainty_score":0.9977688},"labels":[],"label_agreement":null},{"id":"W3038020972","doi":"10.1002/sim.8657","title":"Constructing inverse probability weights for institutional comparisons in healthcare","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; Institute for Clinical Evaluative Sciences; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Health care; Inverse; Inverse probability; Computer science; Statistics; Econometrics; Mathematics; Bayesian probability; Posterior probability; Political science","score_opus":0.4797407362015364,"score_gpt":0.46809264349482754,"score_spread":0.011648092706708857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038020972","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07899799,0.0014359165,0.4272835,0.47808415,0.0016548008,0.003351055,0.005282067,0.000071096954,0.0038394108],"genre_scores_gemma":[0.7320685,0.00006411024,0.24073026,0.025686553,0.00064232684,0.00021832343,0.0005280291,0.000026216845,0.000035721452],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955205,0.00020800083,0.0033525974,0.0004840678,0.00009649676,0.0003383881],"domain_scores_gemma":[0.9968353,0.0017946466,0.00087526906,0.00019537406,0.00008211374,0.00021727629],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070223925,0.00014687906,0.00097078376,0.00022152811,0.00010278845,0.000011933437,0.00016920669,0.00009973025,0.00018061868],"category_scores_gemma":[0.0150667755,0.00017765032,0.000028123775,0.00027400724,0.0002906539,0.00013080136,0.000025461008,0.0002918067,0.00009325163],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002244092,0.000028090562,0.25096646,0.0006744154,0.000007858611,0.0000023345785,0.0015963212,0.00013744945,3.0399295e-7,0.7282931,0.018085718,0.0001855109],"study_design_scores_gemma":[0.006287982,0.00039451616,0.07310221,0.00047931663,0.000009108616,0.0000069811704,0.0047549866,0.1781326,0.0000026251332,0.68616086,0.05015052,0.0005182623],"about_ca_topic_score_codex":0.0024700244,"about_ca_topic_score_gemma":0.0060488204,"teacher_disagreement_score":0.65307045,"about_ca_system_score_codex":0.0007974726,"about_ca_system_score_gemma":0.0003009249,"threshold_uncertainty_score":0.99322975},"labels":[],"label_agreement":null},{"id":"W3043139790","doi":"10.1002/sim.8584","title":"A general method for elicitation, imputation, and sensitivity analysis for incomplete repeated binary data","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR School for Primary Care Research; Medical Research Council Canada; Medical Research Council; National Institute for Health and Care Research","keywords":"Pooling; Missing data; Imputation (statistics); Expert opinion; Expert elicitation; Statistics; Computer science; Econometrics; Medicine; Artificial intelligence; Mathematics","score_opus":0.16647558434536588,"score_gpt":0.4701183694083897,"score_spread":0.3036427850630238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043139790","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00049158203,0.00003406872,0.99072707,0.0028365634,0.00006329616,0.00067022245,0.0051134075,0.000033985805,0.000029805355],"genre_scores_gemma":[0.0067867944,0.000017449682,0.99052775,0.0008749524,0.00019667653,0.000051135015,0.0015078981,0.000023500292,0.000013830377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802446,0.00035294157,0.00064851734,0.00052998966,0.00021250725,0.00023158884],"domain_scores_gemma":[0.9847528,0.014198947,0.00021519934,0.0003277966,0.0003579563,0.00014732871],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024234776,0.00017429185,0.0006749653,0.0001632336,0.00009624848,0.000020090683,0.00011650292,0.00006236985,0.000034517176],"category_scores_gemma":[0.031766657,0.00014870844,0.000026346603,0.0006075058,0.00013482019,0.000058515532,0.00008703173,0.00011644418,4.1123738e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029247956,0.000058201287,0.0014417857,0.0008464456,0.00047193898,0.00004815944,0.0022426446,0.00010091897,0.0015631783,0.8765605,0.02460223,0.09177153],"study_design_scores_gemma":[0.00079197035,0.0002125323,0.003179785,0.00002205461,0.00052351406,0.0000025514564,0.00012743578,0.5330555,0.000013215978,0.461645,0.0003212644,0.000105155304],"about_ca_topic_score_codex":0.00014558714,"about_ca_topic_score_gemma":0.00016631516,"teacher_disagreement_score":0.5329546,"about_ca_system_score_codex":0.000022967515,"about_ca_system_score_gemma":0.000050609277,"threshold_uncertainty_score":0.97638917},"labels":[],"label_agreement":null},{"id":"W3044494018","doi":"10.1002/sim.8592","title":"Design and sample size considerations for valuation studies of multi‐attribute utility instruments","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Statistics; Valuation (finance); Mean squared error; Econometrics; Gaussian; Correlation; Mathematics; Sample size determination; Regression analysis; Value (mathematics); Economics","score_opus":0.7317871135772142,"score_gpt":0.5185467643539607,"score_spread":0.2132403492232534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044494018","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016174097,0.0016470334,0.94303775,0.034883667,0.0002900135,0.0014775293,0.0024522496,0.000015262112,0.00002237225],"genre_scores_gemma":[0.50695956,0.00040227853,0.48843333,0.003979069,0.00007787129,0.00009564282,0.000026265832,0.000011203185,0.000014761961],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966091,0.00027359466,0.0025447642,0.00031900938,0.00008015225,0.0001733663],"domain_scores_gemma":[0.97289646,0.025613891,0.0010412418,0.00016145717,0.00018256449,0.00010436327],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00887497,0.0001159317,0.0008435454,0.00009421835,0.00009938045,0.000009005784,0.00006130787,0.00005490677,0.00021862189],"category_scores_gemma":[0.18974015,0.00013398331,0.000016568762,0.00010881163,0.00020413905,0.000099975754,0.00002667138,0.0000843587,0.00001237711],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015493121,0.00037778512,0.31775802,0.0057276073,0.0006846021,0.0000030274223,0.087467626,0.0020647817,0.00008231802,0.42872074,0.15350968,0.0034488803],"study_design_scores_gemma":[0.0046167406,0.00049985974,0.04228449,0.00013567536,0.00003539688,0.0000010338342,0.0034119226,0.3436692,0.000021834088,0.6042909,0.0008135143,0.0002194308],"about_ca_topic_score_codex":0.00024380241,"about_ca_topic_score_gemma":0.00008331278,"teacher_disagreement_score":0.49078548,"about_ca_system_score_codex":0.00011133316,"about_ca_system_score_gemma":0.00006309346,"threshold_uncertainty_score":0.817085},"labels":[],"label_agreement":null},{"id":"W3045859451","doi":"10.1002/sim.8662","title":"A bivariate autoregressive Poisson model and its application to asthma‐related emergency room visits","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bivariate analysis; Autoregressive model; Statistics; Poisson regression; Poisson distribution; Overdispersion; Estimator; Bayesian probability; Series (stratigraphy); Econometrics; Time series; Computer science; Mathematics; Count data; Medicine","score_opus":0.019389079551677096,"score_gpt":0.3185714517097249,"score_spread":0.29918237215804777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045859451","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006849227,0.0004558893,0.9880719,0.009632043,0.00016747805,0.000335996,0.00003166839,0.000060762653,0.0005593321],"genre_scores_gemma":[0.3218775,0.000107283326,0.6765626,0.0011665572,0.00008523262,0.000026362488,0.000013367428,0.000014272592,0.0001467801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855506,0.00008800785,0.00037658788,0.00047819613,0.00027290656,0.0002292522],"domain_scores_gemma":[0.9991878,0.0000754785,0.00011192435,0.00022431707,0.000114018905,0.00028644162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037855632,0.00015867063,0.00027309087,0.00010200402,0.000053791555,0.000012682012,0.0003530858,0.000071913724,0.00001985545],"category_scores_gemma":[0.0004167179,0.00013377276,0.00001106935,0.00046785074,0.000010877597,0.0001017467,0.00015739142,0.0002071905,0.000016193002],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014580841,0.000018239076,0.000038420025,0.000048075686,0.000010810324,0.000030588053,0.0068605663,0.0013166611,0.0040047723,0.8760555,0.0026285117,0.10897328],"study_design_scores_gemma":[0.00034364845,0.00014356173,0.0009584309,0.00003819198,0.0000073896567,0.000003087785,0.000008486368,0.7806776,0.0000589485,0.21742798,0.00021461825,0.00011804834],"about_ca_topic_score_codex":0.000023062878,"about_ca_topic_score_gemma":0.000013238434,"teacher_disagreement_score":0.77936095,"about_ca_system_score_codex":0.000024506911,"about_ca_system_score_gemma":0.00003910825,"threshold_uncertainty_score":0.54550946},"labels":[],"label_agreement":null},{"id":"W3081371020","doi":"10.1002/sim.8715","title":"A tutorial on dealing with time‐varying eligibility for treatment: Comparing the risk of major bleeding with direct‐acting oral anticoagulant<scp>s</scp> vs warfarin","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; McGill University; McGill University Health Centre; Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research","keywords":"Contraindication; Covariate; Weighting; Warfarin; Computer science; Medicine; Statistics; Econometrics; Mathematics; Internal medicine; Atrial fibrillation; Alternative medicine","score_opus":0.25340054521848643,"score_gpt":0.4219089152046647,"score_spread":0.1685083699861783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081371020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8366815,0.00062334264,0.1413979,0.006787037,0.00066097925,0.0029566365,0.0014274928,0.00009204854,0.009373103],"genre_scores_gemma":[0.97403014,0.000066931956,0.02428842,0.0008112078,0.0005807453,0.000066086184,0.00006946177,0.000044088447,0.00004292307],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99651396,0.00020850488,0.0021808876,0.0005396649,0.00016408529,0.00039291577],"domain_scores_gemma":[0.9890943,0.008478394,0.0018795182,0.00031233075,0.00009192366,0.00014353769],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007221701,0.00025042618,0.001474876,0.00015979582,0.00023915812,0.000032991727,0.00019782156,0.000068456524,0.00002763429],"category_scores_gemma":[0.010399444,0.00018965043,0.00004240876,0.00023039772,0.00016178693,0.00010160472,0.00002719578,0.00019824188,0.000022503114],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009839127,0.00023413717,0.8448077,0.0016109279,0.00081784773,0.000015295234,0.032993827,0.019093672,0.000033122004,0.09462758,0.0036237491,0.0011582347],"study_design_scores_gemma":[0.02574917,0.007933482,0.058841005,0.0021857857,0.0005798813,0.0000117554555,0.008563706,0.8659299,0.00027097418,0.015281608,0.013947057,0.00070566154],"about_ca_topic_score_codex":0.0034027824,"about_ca_topic_score_gemma":0.000463697,"teacher_disagreement_score":0.84683627,"about_ca_system_score_codex":0.00034461985,"about_ca_system_score_gemma":0.00009457471,"threshold_uncertainty_score":0.99793637},"labels":[],"label_agreement":null},{"id":"W3081450496","doi":"10.1002/sim.8727","title":"Statistical inference for missing data mechanisms","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Inference; Statistical inference; Computer science; Statistics; Econometrics; Data mining; Artificial intelligence; Machine learning; Mathematics","score_opus":0.33318924658330423,"score_gpt":0.5021841392437316,"score_spread":0.1689948926604274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081450496","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000031989304,0.00004028346,0.99140304,0.0032070493,0.00023935136,0.00042259286,0.0034668657,0.00005471144,0.001134123],"genre_scores_gemma":[0.0232184,0.000023526598,0.97462106,0.001464656,0.00022985064,0.000024980713,0.00034637743,0.0000358016,0.000035366505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997743,0.00015970482,0.0007299557,0.00054724317,0.00042180548,0.00039827314],"domain_scores_gemma":[0.9846238,0.014254762,0.00014933525,0.0005218603,0.00014994916,0.0003002839],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011754328,0.00022128447,0.0006019918,0.000058458696,0.00007374557,0.000024893907,0.0005773802,0.0000825757,0.0010868595],"category_scores_gemma":[0.08485656,0.00018205207,0.000011474625,0.00021376832,0.0002568774,0.0000560988,0.00019554172,0.00030452845,0.000013724522],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054206357,0.00003481052,0.00004547028,0.00032443088,0.000013136467,0.000036892256,0.00042990706,9.704311e-7,0.00030273185,0.914613,0.032254886,0.051889542],"study_design_scores_gemma":[0.0009794828,0.00042917213,0.00029037605,0.00014029435,0.00007058204,0.0000024048836,0.00022589497,0.10193962,0.000046509922,0.89366573,0.0020159339,0.0001939759],"about_ca_topic_score_codex":0.000044131066,"about_ca_topic_score_gemma":0.000025135987,"teacher_disagreement_score":0.10193865,"about_ca_system_score_codex":0.00003132977,"about_ca_system_score_gemma":0.00011512224,"threshold_uncertainty_score":0.9998263},"labels":[],"label_agreement":null},{"id":"W3081944489","doi":"10.1002/sim.8710","title":"Impact of discretization of the timeline for longitudinal causal inference methods","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hôpital du Sacré-Cœur de Montréal; Université de Montréal; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Timeline; Causal inference; Inference; Computer science; Econometrics; Discretization; Statistics; Mathematics; Artificial intelligence","score_opus":0.22839864773798854,"score_gpt":0.5624154422413042,"score_spread":0.3340167945033157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081944489","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048893294,0.000032365773,0.9937842,0.0003659722,0.000043814023,0.00041090974,0.00027945245,0.000021387757,0.00017257073],"genre_scores_gemma":[0.4437044,0.000019807349,0.5561584,0.000021652291,0.000037835318,0.000012686959,0.00002232188,0.0000115283265,0.000011364791],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99883294,0.00011060901,0.00057527045,0.00014004334,0.00021000665,0.00013112338],"domain_scores_gemma":[0.99659026,0.0024698914,0.0003686776,0.00022789095,0.0002967483,0.000046533976],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0005818945,0.00012150456,0.00042249472,0.000049412687,0.000017198461,0.0000016098173,0.00019789881,0.000049925748,0.00008791131],"category_scores_gemma":[0.018601522,0.00007324496,0.000037999005,0.0003061277,0.00027957352,0.000036625035,0.000057887126,0.00014527433,1.7861827e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000148924,0.00008793036,0.022656498,0.00062257063,0.00006000714,0.0000018287922,0.0020817777,0.00027207527,0.025721297,0.936116,0.0036527053,0.008578401],"study_design_scores_gemma":[0.0007419555,0.0012495191,0.0154228825,0.00034820152,0.00010375082,0.0000013089598,0.00011097589,0.022169765,0.010664768,0.9490315,0.000032170712,0.00012322172],"about_ca_topic_score_codex":0.00006180794,"about_ca_topic_score_gemma":0.00002658,"teacher_disagreement_score":0.43881506,"about_ca_system_score_codex":0.000042692624,"about_ca_system_score_gemma":0.00008388684,"threshold_uncertainty_score":0.9896652},"labels":[],"label_agreement":null},{"id":"W3082894717","doi":"10.1002/sim.8722","title":"Multiply robust estimation of causal quantile treatment effects","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Roche (Canada)","funders":"","keywords":"Quantile; Causal inference; Estimator; Propensity score matching; Econometrics; Statistics; Inverse probability weighting; Empirical likelihood; Weighting; Average treatment effect; Inference; Computer science; Estimation; Mathematics; Artificial intelligence; Medicine; Economics","score_opus":0.1383377641491244,"score_gpt":0.4358404304734299,"score_spread":0.2975026663243055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3082894717","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014555597,0.000059240123,0.98388314,0.00033506204,0.000072757684,0.00047266923,0.000065534114,0.00010799976,0.00044799145],"genre_scores_gemma":[0.4549971,0.000047201785,0.544736,0.00007122596,0.000042474494,0.000029602108,0.00003628318,0.000017214516,0.000022892584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989106,0.00006624249,0.00044263207,0.0001794728,0.00024049738,0.00016055163],"domain_scores_gemma":[0.9976616,0.0018190348,0.00018153641,0.00018354294,0.000072628354,0.00008165655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016789226,0.00015788947,0.00044944743,0.00007453049,0.00001839943,0.0000025233626,0.000092827584,0.00005560828,0.000078782774],"category_scores_gemma":[0.0046438915,0.00012410898,0.000015266229,0.00018398037,0.00014451898,0.000044774468,0.000023869672,0.00011673,0.000005808932],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019234898,0.00045369918,0.0018824175,0.0020197812,0.00008911126,0.0002892744,0.010243546,0.0038105578,0.013267986,0.8748778,0.012337448,0.08053602],"study_design_scores_gemma":[0.003835686,0.0051033385,0.0018120997,0.0009502524,0.00020288002,0.000007568421,0.0005647121,0.26775646,0.03662734,0.6825323,0.00021168431,0.00039567988],"about_ca_topic_score_codex":0.000097410084,"about_ca_topic_score_gemma":0.000052217514,"teacher_disagreement_score":0.4404415,"about_ca_system_score_codex":0.00008980677,"about_ca_system_score_gemma":0.000034116874,"threshold_uncertainty_score":0.5559507},"labels":[],"label_agreement":null},{"id":"W3085834915","doi":"10.1002/sim.8688","title":"Genetic association studies with bivariate mixed responses subject to measurement error and misclassification","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bivariate analysis; Univariate; Covariate; Trait; Statistics; Computer science; Pleiotropy; Econometrics; Association (psychology); Binary number; Mathematics; Multivariate statistics; Psychology; Genetics; Biology; Phenotype; Gene","score_opus":0.059095089833382373,"score_gpt":0.31206555386596074,"score_spread":0.2529704640325784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3085834915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7433842,0.002713459,0.24395886,0.008759597,0.00024845902,0.0005776486,0.00008068409,0.000015773736,0.00026135176],"genre_scores_gemma":[0.9003608,0.00016407747,0.09809152,0.0009328017,0.000208134,0.000032877473,0.000022963135,0.000015446727,0.00017136213],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99888426,0.00012976483,0.00022900448,0.0003005526,0.0002960785,0.00016036387],"domain_scores_gemma":[0.9993703,0.000089025954,0.00009076231,0.00013272194,0.00021147088,0.00010577024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038290818,0.00012666112,0.00018560982,0.000038381724,0.000044005363,0.0000064565897,0.000078488396,0.000054811295,0.000008341732],"category_scores_gemma":[0.002637811,0.00010038361,0.0000068400404,0.00011687325,0.00007837725,0.0000012001159,0.000035866746,0.00007297935,0.0000032009095],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0058860616,0.00031301298,0.27297142,0.00091458875,0.0014212315,0.000037391183,0.023278482,0.0035937289,0.44915348,0.016153866,0.18646942,0.03980732],"study_design_scores_gemma":[0.0019528045,0.003328205,0.97969294,0.00010898419,0.0001247717,0.000004609641,0.0015580648,0.00014301545,0.0026690802,0.0020535537,0.008084968,0.00027898492],"about_ca_topic_score_codex":0.00001798663,"about_ca_topic_score_gemma":0.00017789793,"teacher_disagreement_score":0.70672154,"about_ca_system_score_codex":0.0000426725,"about_ca_system_score_gemma":0.000068487854,"threshold_uncertainty_score":0.40935245},"labels":[],"label_agreement":null},{"id":"W3086774075","doi":"10.1002/sim.8738","title":"Meta‐analysis of quantile intervals from different studies with an application to a pulmonary tuberculosis data","year":2020,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Quantile; Confidence interval; Statistics; Coverage probability; CDF-based nonparametric confidence interval; Meta-analysis; Random effects model; Estimator; Mathematics; Robust confidence intervals; Confidence distribution; Econometrics; Medicine; Internal medicine","score_opus":0.3857157534275251,"score_gpt":0.5229027888145859,"score_spread":0.13718703538706073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086774075","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.3264245e-7,0.44985995,0.5389854,0.00007230147,0.00003500089,0.0005747917,0.010434566,0.000014826321,0.000022662853],"genre_scores_gemma":[0.000012139776,0.52811885,0.4695064,0.000044268618,0.00006144907,0.00019633387,0.0020180652,0.000037346374,0.000005153087],"study_design_codex":"design_other","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9955394,0.0008252591,0.0017198675,0.0010033591,0.000662325,0.0002497655],"domain_scores_gemma":[0.984786,0.012304444,0.0007681412,0.0017297927,0.00019654093,0.00021510654],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00095822575,0.00057516806,0.008097781,0.0004977659,0.00003225359,0.000013933594,0.0009943201,0.00013079908,0.0003203433],"category_scores_gemma":[0.0037827992,0.00032867325,0.0001827024,0.0012993729,0.0002575423,0.0000458182,0.00041619365,0.00039724153,0.000005177375],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036959016,0.0002211947,0.000011630806,0.0116228135,0.10897233,0.00007661259,0.0006873305,4.580116e-7,8.3244544e-7,0.07264325,0.00066816487,0.8050584],"study_design_scores_gemma":[0.00016803308,0.0005926433,0.000045845292,0.005154283,0.7455062,0.0000035936143,0.0004848267,0.0049334727,6.1208635e-7,0.22389743,0.018678512,0.000534543],"about_ca_topic_score_codex":0.00044090993,"about_ca_topic_score_gemma":0.00096216216,"teacher_disagreement_score":0.8045239,"about_ca_system_score_codex":0.00007480509,"about_ca_system_score_gemma":0.00006958947,"threshold_uncertainty_score":0.99991655},"labels":[],"label_agreement":null},{"id":"W3087039075","doi":"10.1002/sim.8752","title":"Bayesian estimation of multivariate Gaussian Markov random fields with constraint","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Multivariate statistics; Deviance information criterion; Computer science; Bayesian probability; Prior probability; Bayesian hierarchical modeling; Markov chain Monte Carlo; Copula (linguistics); Mathematics; Statistics; Bayesian inference; Artificial intelligence; Econometrics","score_opus":0.025308784439702175,"score_gpt":0.2580846507327724,"score_spread":0.23277586629307026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087039075","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016177793,0.00011372527,0.9895659,0.0024388563,0.00006775433,0.00012384201,0.0005983465,0.000007982861,0.0054658283],"genre_scores_gemma":[0.9482674,0.00005968585,0.050938245,0.00038465476,0.00005497465,0.000005365412,0.0002431571,0.000007815304,0.000038680628],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990809,0.000018252686,0.0005373467,0.00019579766,0.00005104158,0.00011667794],"domain_scores_gemma":[0.99934965,0.00017542261,0.00024238043,0.00013404067,0.000022432869,0.00007604529],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028167272,0.00009291937,0.00045016187,0.00010985194,0.000020703897,0.0000063146654,0.00010028705,0.000044162603,0.0012181485],"category_scores_gemma":[0.0006245403,0.00007870475,0.00001722827,0.00024942274,0.0001319505,0.000041507003,0.000014754596,0.0001175652,0.000015795493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011075219,0.00017797129,0.086751066,0.000684668,0.00045064514,0.00020706197,0.011346759,0.016333682,0.00006225591,0.8100444,0.007693978,0.06513997],"study_design_scores_gemma":[0.006063207,0.00052902714,0.021287803,0.0001308134,0.0000619813,0.0000034186032,0.00035544074,0.9264279,0.000031075993,0.04376578,0.0010951041,0.00024842884],"about_ca_topic_score_codex":0.0015922297,"about_ca_topic_score_gemma":0.00025175387,"teacher_disagreement_score":0.9466497,"about_ca_system_score_codex":0.000014119795,"about_ca_system_score_gemma":0.000014554613,"threshold_uncertainty_score":0.9996949},"labels":[],"label_agreement":null},{"id":"W3087499679","doi":"10.1002/sim.8735","title":"Finite sample variance estimation for optimal dynamic treatment regimes of survival outcomes","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Jewish General Hospital; McGill University","funders":"","keywords":"Estimator; Nuisance parameter; Confidence interval; Delta method; Variance (accounting); Statistics; Mathematics; Sample size determination; Econometrics; Computer science; Applied mathematics","score_opus":0.13053276575746314,"score_gpt":0.442096167453149,"score_spread":0.31156340169568586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087499679","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008128917,0.000031996224,0.9954885,0.0013053135,0.00017664777,0.00039237246,0.0015664222,0.000022390748,0.00020344589],"genre_scores_gemma":[0.07249692,0.000040661704,0.9270774,0.00010751118,0.000038889495,0.000043569333,0.000097297154,0.00001887414,0.00007889115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986957,0.000093261755,0.00057200564,0.0002190961,0.00022889132,0.0001910979],"domain_scores_gemma":[0.9789798,0.020436615,0.00020105085,0.00017831835,0.000116475465,0.000087692504],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.000394567,0.00016397753,0.00065497064,0.000050412564,0.00003084598,0.00000520531,0.00011424117,0.000048839192,0.00016695751],"category_scores_gemma":[0.039221544,0.00012175624,0.0000287252,0.0001426487,0.00015136,0.000022112576,0.000020094802,0.000079641075,0.0000020374723],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012289328,0.00010399659,0.00087794696,0.00042184608,0.000053660722,0.000008250856,0.0020617112,0.0006531389,0.00006402743,0.9528053,0.0005422004,0.042285062],"study_design_scores_gemma":[0.001508208,0.00096867996,0.0020555847,0.00008423693,0.00008740358,2.9509323e-7,0.00022883355,0.47728908,0.00004135111,0.5174693,0.00016006528,0.00010696687],"about_ca_topic_score_codex":0.000109040455,"about_ca_topic_score_gemma":0.00002866144,"teacher_disagreement_score":0.47663596,"about_ca_system_score_codex":0.000052422296,"about_ca_system_score_gemma":0.000054544438,"threshold_uncertainty_score":0.9688715},"labels":[],"label_agreement":null},{"id":"W3089031369","doi":"10.1002/sim.8744","title":"Comparing Kaplan‐Meier curves with the probability of agreement","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada","keywords":"Nonparametric statistics; Similarity (geometry); Statistics; Confidence interval; Computer science; Reliability (semiconductor); Coverage probability; Point estimation; Mathematics; Sample size determination; Contrast (vision); Econometrics; Artificial intelligence","score_opus":0.1459445148099727,"score_gpt":0.39587051930710915,"score_spread":0.24992600449713645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089031369","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002373548,0.00012075337,0.9884682,0.0049612727,0.000039057635,0.00038420595,0.00007509264,0.00001218018,0.00356568],"genre_scores_gemma":[0.22680926,0.00004494302,0.7722721,0.00075605384,0.00006016596,0.000019611303,0.0000094096595,0.000009942034,0.000018512203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99867076,0.00017774221,0.00041466107,0.0001775594,0.00039547656,0.0001638042],"domain_scores_gemma":[0.9968285,0.0026050217,0.00015733422,0.00021789258,0.000113608185,0.00007764707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078446727,0.00011884003,0.0004291022,0.00001967848,0.000029971334,0.0000038380913,0.0001893729,0.000021649488,0.00038327734],"category_scores_gemma":[0.0040744296,0.000062327446,0.000010101763,0.00021125442,0.00043167316,0.000014912448,0.00004558536,0.00021669122,0.0000026162227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008657372,0.000072206945,0.011885251,0.0018972174,0.000032848668,0.000022348078,0.0019946815,0.000003998439,0.00007741092,0.9542421,0.023730293,0.0059550493],"study_design_scores_gemma":[0.0010233726,0.0007232727,0.02542411,0.0011548903,0.00012208243,0.000003711029,0.0005376989,0.0057411646,0.00008931935,0.9645109,0.00051523023,0.00015420695],"about_ca_topic_score_codex":0.00006184854,"about_ca_topic_score_gemma":0.00011838253,"teacher_disagreement_score":0.22443572,"about_ca_system_score_codex":0.000018493974,"about_ca_system_score_gemma":0.00003816631,"threshold_uncertainty_score":0.48777673},"labels":[],"label_agreement":null},{"id":"W3092385491","doi":"10.1002/sim.8764","title":"The effect of a constraint on the maximum number of controls matched to each treated subject on the performance of full matching on the propensity score when estimating risk differences","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Matching (statistics); Observational study; Calipers; Constraint (computer-aided design); Statistics; Mathematics; Average treatment effect; Econometrics; Medicine","score_opus":0.09042720693450075,"score_gpt":0.3650431871051201,"score_spread":0.2746159801706194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092385491","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94325155,0.00000800638,0.05084564,0.0030306135,0.000043836077,0.0019243074,0.00014214954,0.000036837195,0.0007170584],"genre_scores_gemma":[0.98470354,0.000020057914,0.014771525,0.0003115615,0.00003770612,0.00011688391,0.0000042602883,0.000024305886,0.000010170214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972691,0.0008317699,0.0007621628,0.00022546186,0.0006540654,0.00025746907],"domain_scores_gemma":[0.9734361,0.025051797,0.0007456525,0.0005541221,0.000156063,0.000056219287],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002976065,0.0002836324,0.00075902545,0.00003725373,0.00017872412,0.000014244804,0.00054709805,0.00005936608,0.00008729621],"category_scores_gemma":[0.016697058,0.00010147599,0.00004544322,0.00022328911,0.0008113193,0.000022317618,0.00009049935,0.0006916947,0.0000042785305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005154565,0.00025463814,0.04942407,0.0015714526,0.0004564724,0.000027875734,0.033189066,0.0005378201,0.025323585,0.85125405,0.003298048,0.029508347],"study_design_scores_gemma":[0.0026698047,0.016575456,0.01109361,0.008672591,0.00045209634,0.000015542082,0.005641029,0.048944917,0.090592064,0.81481755,0.000011645239,0.0005136946],"about_ca_topic_score_codex":0.00019554925,"about_ca_topic_score_gemma":0.000059635226,"teacher_disagreement_score":0.06526848,"about_ca_system_score_codex":0.000047351798,"about_ca_system_score_gemma":0.00004334094,"threshold_uncertainty_score":0.99158573},"labels":[],"label_agreement":null},{"id":"W3093256252","doi":"10.1002/sim.8772","title":"Selection models for efficient two‐phase design of family studies","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Simple random sample; Copula (linguistics); Selection (genetic algorithm); Computer science; Sampling (signal processing); Sampling design; Statistics; Sample size determination; Robustness (evolution); Econometrics; Stratified sampling; Mathematics; Machine learning; Biology; Medicine; Population","score_opus":0.3913889358246923,"score_gpt":0.5107849811338429,"score_spread":0.11939604530915054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093256252","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012312523,0.00020452823,0.9972379,0.00025875855,0.00013726806,0.00054748746,0.00019310736,0.000022364355,0.00016733943],"genre_scores_gemma":[0.13944297,0.00006796119,0.86009204,0.00022491542,0.000091685615,0.000046624977,0.0000057702146,0.000015997832,0.000012052743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862945,0.00014455587,0.00057030964,0.00020633165,0.0002626573,0.00018666743],"domain_scores_gemma":[0.9927732,0.0065568904,0.0001584244,0.000095119074,0.00033594482,0.000080473066],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009147257,0.00013152008,0.00052074663,0.00006469184,0.00003532427,0.000002785675,0.00009345434,0.0000327766,0.000028306398],"category_scores_gemma":[0.015063268,0.00010125914,0.000015851238,0.00023551127,0.00018666792,0.0000132013,0.000023856954,0.00011862793,9.484416e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026097745,0.00017516587,0.000005832966,0.0006080052,0.00005026912,0.0000062271392,0.003704841,0.0062713386,0.0027428956,0.96352065,0.008600579,0.014053249],"study_design_scores_gemma":[0.0016314419,0.0010667987,0.000005055233,0.000096850505,0.000054893786,4.5264548e-7,0.00056804245,0.5131712,0.00026668058,0.48306447,0.000014551186,0.000059557748],"about_ca_topic_score_codex":0.0000141349965,"about_ca_topic_score_gemma":0.0000023414166,"teacher_disagreement_score":0.5068999,"about_ca_system_score_codex":0.00003705439,"about_ca_system_score_gemma":0.000047756213,"threshold_uncertainty_score":0.99323326},"labels":[],"label_agreement":null},{"id":"W3094519324","doi":"10.1002/sim.8786","title":"Spline‐based accelerated failure time model","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Parametric statistics; Accelerated failure time model; Covariate; Computer science; Spline (mechanical); Proportional hazards model; Parametric model; Semiparametric model; Hazard; Statistics; Mathematics; Engineering; Structural engineering","score_opus":0.4405836122262447,"score_gpt":0.4606245123093229,"score_spread":0.020040900083078184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094519324","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0086400965,0.0006682863,0.7225605,0.2583623,0.00029666352,0.0008085398,0.0021207167,0.00011087548,0.006431985],"genre_scores_gemma":[0.55764,0.00010617059,0.2724466,0.16510637,0.0014291609,0.00012630157,0.0012830088,0.00013835012,0.0017240227],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995833,0.00014084807,0.0030439745,0.0005015917,0.0001281463,0.0003524872],"domain_scores_gemma":[0.99752146,0.00089895376,0.00091066124,0.00030951388,0.00008236105,0.00027706503],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0050314325,0.00019686838,0.0010208321,0.0002295535,0.00007170472,0.000023369672,0.0002745705,0.00012183024,0.00270906],"category_scores_gemma":[0.008195807,0.00023196849,0.00003014297,0.00033626746,0.00011557329,0.00013030958,0.000032674885,0.00029283986,0.0025117777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047111054,0.00007831754,0.006241875,0.0005480666,0.000040597268,0.000016937489,0.0030979256,0.022305917,0.00006659376,0.21060295,0.75674903,0.00020465208],"study_design_scores_gemma":[0.0017092238,0.00012207523,0.0010808777,0.00007912226,0.0000066446178,6.210913e-7,0.00021858764,0.9520653,0.000004493795,0.029567558,0.014907521,0.00023795791],"about_ca_topic_score_codex":0.00019727513,"about_ca_topic_score_gemma":0.000077483775,"teacher_disagreement_score":0.9297594,"about_ca_system_score_codex":0.00023282589,"about_ca_system_score_gemma":0.00017983349,"threshold_uncertainty_score":0.9982649},"labels":[],"label_agreement":null},{"id":"W3094834023","doi":"10.1002/sim.8766","title":"Minimum sample size for external validation of a clinical prediction model with a continuous outcome","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Body Composition Measurement Techniques","field":"Medicine","cited_by":198,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; National Institute for Health and Care Research; NIHR School for Primary Care Research; NIHR Oxford Biomedical Research Centre; Medical Research Council Canada; Wellcome Trust; British Heart Foundation; Cancer Research UK","keywords":"Sample size determination; Variance (accounting); Statistics; Outcome (game theory); Calibration; Sample (material); Range (aeronautics); Cross-validation; Computer science; Mathematics; Econometrics","score_opus":0.1267781237050936,"score_gpt":0.4179327851487913,"score_spread":0.2911546614436977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094834023","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072996974,0.000022850763,0.9229719,0.0022397575,0.000090462796,0.0009973532,0.0004181762,0.000073404735,0.00018913676],"genre_scores_gemma":[0.5756824,0.0000147655055,0.42314833,0.0007786499,0.00020106528,0.000040219944,0.00008925958,0.000016709604,0.0000286205],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979071,0.00006187077,0.0010985472,0.00026023504,0.00052044395,0.00015180098],"domain_scores_gemma":[0.9977784,0.0011613731,0.00031720957,0.00017795846,0.00041574473,0.00014929594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095445925,0.00013312604,0.00065996643,0.00006954536,0.000021260865,0.000003554953,0.000078042336,0.00008117453,0.000058719925],"category_scores_gemma":[0.0063151745,0.00010329283,0.00003975919,0.00014386018,0.00018086331,0.00003836704,0.00001566293,0.00022758578,8.446909e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008982861,0.000733621,0.90745026,0.0016547646,0.00019595146,0.00006388431,0.0017998925,0.00047601465,0.03539501,0.0080134515,0.026497263,0.008737004],"study_design_scores_gemma":[0.04521101,0.027647719,0.1683954,0.0028940123,0.0016675766,0.000049834995,0.0005895269,0.71122324,0.009123559,0.03158278,0.0010533343,0.0005619964],"about_ca_topic_score_codex":0.00002606805,"about_ca_topic_score_gemma":0.0000044272933,"teacher_disagreement_score":0.73905486,"about_ca_system_score_codex":0.000039509086,"about_ca_system_score_gemma":0.000112042,"threshold_uncertainty_score":0.756031},"labels":[],"label_agreement":null},{"id":"W3101173445","doi":"10.1002/sim.8798","title":"Functional principal component analysis for longitudinal data with informative dropout","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Functional principal component analysis; Missing data; Principal component analysis; Dropout (neural networks); Functional data analysis; Covariance; Computer science; Orthonormal basis; Statistics; Regression; Mathematics; Artificial intelligence; Machine learning","score_opus":0.2706996628872454,"score_gpt":0.43814257808506935,"score_spread":0.16744291519782395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101173445","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001120104,0.000016582175,0.9946976,0.0010391274,0.00007568412,0.0003287672,0.001998957,0.000025199653,0.0006980002],"genre_scores_gemma":[0.20292372,0.000008681866,0.7955373,0.00037613927,0.00016020183,0.000028078957,0.0009143317,0.0000133169315,0.000038266124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983436,0.000070923714,0.00055249577,0.00032638392,0.00047125996,0.0002353687],"domain_scores_gemma":[0.9954531,0.003604335,0.00019094265,0.0003668601,0.00021632446,0.00016844584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071154704,0.00017008597,0.0005589111,0.000115454735,0.000065274886,0.000014254377,0.00027538487,0.000039128787,0.0006343726],"category_scores_gemma":[0.006530442,0.0001169931,0.000019192154,0.00050925807,0.00026153986,0.000066888366,0.000120901015,0.00021629086,0.0000070979127],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039280343,0.00007660021,0.012732727,0.00031537478,0.00050300575,0.000029901958,0.001573023,0.00012343781,0.000009577165,0.96765864,0.013504648,0.003080287],"study_design_scores_gemma":[0.0035043638,0.0013683866,0.08191985,0.00013910283,0.0015752219,0.0000071269797,0.0013738779,0.6182558,0.000016258931,0.28950697,0.0019399401,0.00039313166],"about_ca_topic_score_codex":0.000051035702,"about_ca_topic_score_gemma":0.00012659852,"teacher_disagreement_score":0.67815167,"about_ca_system_score_codex":0.0000391512,"about_ca_system_score_gemma":0.0000731801,"threshold_uncertainty_score":0.78180206},"labels":[],"label_agreement":null},{"id":"W3105488458","doi":"10.1002/sim.8816","title":"Survival analysis under the Cox proportional hazards model with pooled covariates","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Statistics; Proportional hazards model; Estimator; Pooling; Accelerated failure time model; Mathematics; Hazard ratio; Confounding; Econometrics; Survival analysis; Random effects model; Medicine; Computer science; Confidence interval; Meta-analysis; Internal medicine","score_opus":0.09750907629122232,"score_gpt":0.4004200705843978,"score_spread":0.3029109942931755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105488458","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020644728,0.00002325715,0.98947287,0.0063009635,0.000054199958,0.00020959163,0.00030639765,0.000029338751,0.001538917],"genre_scores_gemma":[0.385792,0.0000133995645,0.6127497,0.0011375534,0.00009557815,0.000020306177,0.000053045496,0.000017636035,0.00012082378],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981213,0.00019538323,0.0004944725,0.00027318162,0.0006812386,0.00023441068],"domain_scores_gemma":[0.9963459,0.002891669,0.00016249687,0.00023388916,0.00023207607,0.00013397065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093385606,0.00017510056,0.0005296887,0.00007153809,0.000077829056,0.000017331087,0.00020178924,0.00004853283,0.0007505894],"category_scores_gemma":[0.0039488403,0.000093765935,0.000026704522,0.0007255181,0.0004011704,0.000020949994,0.000042567535,0.00030645213,0.000005546712],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008655573,0.000042714324,0.0010065504,0.000054282347,0.00029713174,0.000025602129,0.00080178917,0.0025997644,0.000036764995,0.99182105,0.0024579915,0.00076982734],"study_design_scores_gemma":[0.0005396757,0.00016218722,0.0045167436,0.000024267205,0.00066204806,0.0000013124255,0.00056043675,0.44593534,0.000007026273,0.547463,0.000023650931,0.00010433496],"about_ca_topic_score_codex":0.0001072278,"about_ca_topic_score_gemma":0.0001931666,"teacher_disagreement_score":0.44435805,"about_ca_system_score_codex":0.000033604414,"about_ca_system_score_gemma":0.00015759532,"threshold_uncertainty_score":0.8218428},"labels":[],"label_agreement":null},{"id":"W3105768632","doi":"10.1002/sim.8857","title":"Conflating marginal and conditional treatment effects: Comments on “Assessing the performance of population adjustment methods for anchored indirect comparisons: A simulation study”","year":2021,"lang":"en","type":"letter","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Engineering and Physical Sciences Research Council; Canadian Institutes of Health Research","keywords":"Inference; Marginal structural model; Econometrics; Marginal model; Population; Treatment effect; Causal inference; Statistics; Statistical inference; Computer science; Medicine; Mathematics; Artificial intelligence; Regression analysis","score_opus":0.20791701651492495,"score_gpt":0.5391972190249351,"score_spread":0.33128020251001017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105768632","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02528937,0.0003842018,0.96296674,0.0058144634,0.00035282562,0.004723327,0.0003471894,0.000060958606,0.000060907598],"genre_scores_gemma":[0.18205452,0.00009191077,0.8029771,0.0094282,0.0006415521,0.0008756803,0.0038023205,0.0000752354,0.000053495223],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974228,0.0007680154,0.0008253289,0.00034141663,0.00041099553,0.00023145271],"domain_scores_gemma":[0.98069483,0.01800657,0.0007814912,0.0002969542,0.00019428408,0.000025869942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010877764,0.00034088234,0.0009486122,0.00020366881,0.0001325741,0.000019531008,0.0001035343,0.00018078536,0.000018182782],"category_scores_gemma":[0.0019445051,0.00023784324,0.00003045747,0.00014120349,0.00015554996,0.00006168625,0.000037915375,0.0005548222,1.0353288e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010546495,0.004808819,0.08587468,0.024750289,0.0039051115,0.00037986287,0.023584625,0.012282152,0.0012377454,0.04536187,0.30217376,0.49458644],"study_design_scores_gemma":[0.0149786165,0.016785337,0.10890929,0.01372209,0.0032113432,0.000023688348,0.003086333,0.5508689,0.0014174073,0.27462867,0.010790476,0.0015778415],"about_ca_topic_score_codex":0.000054585234,"about_ca_topic_score_gemma":0.000015864274,"teacher_disagreement_score":0.53858674,"about_ca_system_score_codex":0.00040386253,"about_ca_system_score_gemma":0.000042861626,"threshold_uncertainty_score":0.96989655},"labels":[],"label_agreement":null},{"id":"W3112861306","doi":"10.1002/sim.8847","title":"An overview and critique of the use of cumulative sum methods with surgical learning curve data","year":2020,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Healthcare Operations and Scheduling Optimization","field":"Health Professions","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal; Hôpital Maisonneuve-Rosemont","funders":"","keywords":"CUSUM; Computer science; Learning curve; Focus (optics); Statistics; Econometrics; Machine learning; Mathematics","score_opus":0.5748082015241052,"score_gpt":0.6488662788855685,"score_spread":0.0740580773614633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112861306","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000038931557,0.8295722,0.16732793,0.0004966802,0.00015821068,0.0012715242,0.001107622,0.000009040835,0.00005290393],"genre_scores_gemma":[0.000009566764,0.7779016,0.2207187,0.00009287796,0.0000713302,0.000024362835,0.0011027831,0.000027088598,0.00005169597],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99066395,0.0072818445,0.001274615,0.00033641487,0.00026423417,0.00017894755],"domain_scores_gemma":[0.9899045,0.008305767,0.00071969215,0.00058015145,0.00038159787,0.000108248125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028436054,0.00019864948,0.0015650884,0.000097500146,0.00017223794,0.0000041986223,0.00025919554,0.0002264517,0.000098979006],"category_scores_gemma":[0.0076524722,0.00010910181,0.000018206576,0.0005114007,0.00025617308,0.00008815723,0.00016944687,0.0013841179,4.2802588e-7],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040304738,0.000060954986,0.0024555845,0.06468039,0.00010521403,0.000034588906,0.005346023,0.00043692207,1.3360814e-7,0.042025976,0.00119582,0.88361806],"study_design_scores_gemma":[0.00044659714,0.00028772,0.0001843211,0.042596597,0.0003405709,0.0000052518453,0.00055970455,0.029664323,2.5388537e-8,0.00014566512,0.9256358,0.00013339448],"about_ca_topic_score_codex":0.001175043,"about_ca_topic_score_gemma":0.00058349036,"teacher_disagreement_score":0.92444,"about_ca_system_score_codex":0.000052109972,"about_ca_system_score_gemma":0.0010949541,"threshold_uncertainty_score":0.9161277},"labels":[],"label_agreement":null},{"id":"W3112901974","doi":"10.1002/sim.8848","title":"Mean comparisons and power calculations to ensure reproducibility in preclinical drug discovery","year":2020,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Animal testing and alternatives","field":"Veterinary","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Reproducibility; Sample size determination; Statistical power; Statistics; Computer science; Power analysis; Statistical hypothesis testing; Power (physics); Sample (material); Multiple comparisons problem; Data mining; False discovery rate; Reliability engineering; Mathematics; Algorithm; Chemistry","score_opus":0.25756195579739644,"score_gpt":0.48454320906766907,"score_spread":0.22698125327027263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112901974","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96819645,0.00018656456,0.020623859,0.008330415,0.00013568891,0.00028010271,0.00020677698,0.000038642003,0.0020015137],"genre_scores_gemma":[0.98042375,0.000007882827,0.01860543,0.00069788884,0.00012999837,0.000007059466,0.000024873021,0.0000114381355,0.000091709706],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99835384,0.00017555241,0.0004548524,0.00067653647,0.00018079104,0.00015840518],"domain_scores_gemma":[0.9980942,0.0013400519,0.00006389179,0.000332885,0.00004047711,0.00012851834],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010194088,0.00011048165,0.0003133833,0.00005142399,0.000034392688,0.000010715993,0.00009848484,0.000026500249,0.000059782287],"category_scores_gemma":[0.013002968,0.000092868286,0.000010545594,0.00020368912,0.00017738821,0.000047771584,0.00010605481,0.00031047862,0.000009086447],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007108901,0.00022356058,0.92273337,0.00012325333,0.00002402355,0.00040281075,0.025681416,0.00013314739,0.00087477476,0.021779135,0.025319623,0.0019940052],"study_design_scores_gemma":[0.00075725646,0.0009893201,0.98588926,0.00019697082,0.000014098233,0.000007365448,0.0016811963,0.005168814,0.000008033847,0.0038792968,0.0012631674,0.00014523405],"about_ca_topic_score_codex":0.00043111804,"about_ca_topic_score_gemma":0.0004091747,"teacher_disagreement_score":0.06315588,"about_ca_system_score_codex":0.000026605592,"about_ca_system_score_gemma":0.000024376606,"threshold_uncertainty_score":0.9953109},"labels":[],"label_agreement":null},{"id":"W3120069145","doi":"10.1002/sim.10199","title":"Estimating causes of maternal death in data‐sparse contexts","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Global Maternal and Child Health","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"World Health Organization","keywords":"Multinomial distribution; Data quality; Computer science; Missing data; Bayesian probability; Population; Quality (philosophy); Resource allocation; Econometrics; Environmental health; Medicine; Machine learning; Artificial intelligence; Business; Economics","score_opus":0.05196058672600602,"score_gpt":0.4003532393911025,"score_spread":0.3483926526650965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120069145","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9707752,0.0038003428,0.01744454,0.0025335527,0.0014630974,0.00045207338,0.0008998113,0.00005682546,0.0025745449],"genre_scores_gemma":[0.9746931,0.00023562532,0.023948314,0.0004491186,0.0002697301,0.000003462157,0.0001473452,0.00001550541,0.0002377872],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986364,0.000034215394,0.0005510005,0.0002369486,0.00031573023,0.00022568004],"domain_scores_gemma":[0.99933326,0.00020105003,0.000058055863,0.0002654867,0.000045625544,0.00009653504],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005029638,0.00011635443,0.00040516944,0.00018201125,0.000012104353,0.0000056946396,0.0001327331,0.000042440737,0.0002211155],"category_scores_gemma":[0.00044935237,0.00008444388,0.000008398682,0.00017917094,0.00010108102,0.000044216456,0.000068333946,0.00025830365,0.000018438328],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003271823,0.00019836621,0.85114527,0.0067796856,0.0000870825,0.0071918704,0.0019352899,0.00007885088,0.00073639286,0.07536176,0.018237935,0.03792032],"study_design_scores_gemma":[0.0026751591,0.00050146,0.90477204,0.012270479,0.00012397661,0.00035135087,0.0002009419,0.053983178,0.00010201147,0.022320399,0.002544289,0.00015471583],"about_ca_topic_score_codex":0.0029597536,"about_ca_topic_score_gemma":0.00073206745,"teacher_disagreement_score":0.05390433,"about_ca_system_score_codex":0.000068245834,"about_ca_system_score_gemma":0.00012162917,"threshold_uncertainty_score":0.4474282},"labels":[],"label_agreement":null},{"id":"W3124976303","doi":"10.1002/sim.8863","title":"Spatial modeling of individual‐level infectious disease transmission: Tuberculosis data in Manitoba, Canada","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Infectious disease (medical specialty); Tuberculosis; Infectivity; Statistics; Demography; Demographics; Maximization; Transmission (telecommunications); Population; Estimation; Econometrics; Computer science; Medicine; Disease; Environmental health; Geography; Immunology; Mathematics; Internal medicine","score_opus":0.2830997507269963,"score_gpt":0.4096805293144711,"score_spread":0.1265807785874748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124976303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08965184,0.0017705795,0.8986549,0.0049363594,0.0004075628,0.0004541239,0.0036545824,0.00002892285,0.000441163],"genre_scores_gemma":[0.96963286,0.0006305294,0.028397625,0.0007589542,0.00011158428,0.00001628525,0.00041751814,0.000017923618,0.000016718144],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99761003,0.00024730267,0.0008613877,0.000394859,0.0006112351,0.00027517276],"domain_scores_gemma":[0.99498785,0.0040705744,0.00012082267,0.0005500792,0.00012865875,0.0001420246],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011310044,0.0001800466,0.0006496761,0.00008271164,0.000046662746,0.000003997831,0.0003341365,0.000057211088,0.00019845403],"category_scores_gemma":[0.02180003,0.00014553715,0.00001635521,0.00031148666,0.000105125786,0.000032430922,0.00029886843,0.00030792126,4.7462757e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003168999,0.001450518,0.69766176,0.0066925935,0.000562257,0.0052238833,0.0044247103,0.012751634,0.00011968692,0.051738087,0.08335395,0.13570403],"study_design_scores_gemma":[0.003038579,0.00011400047,0.21473159,0.0015268315,0.0003983694,0.000008134153,0.0015413818,0.28440464,0.000018028815,0.4926718,0.0010571887,0.00048948906],"about_ca_topic_score_codex":0.50182503,"about_ca_topic_score_gemma":0.91562927,"teacher_disagreement_score":0.87998104,"about_ca_system_score_codex":0.00021296571,"about_ca_system_score_gemma":0.0005613,"threshold_uncertainty_score":0.98643976},"labels":[],"label_agreement":null},{"id":"W3125785889","doi":"10.1002/sim.1577","title":"The roles of birth inputs and outputs in predicting health, behaviour and test scores in early childhood","year":2003,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Birth, Development, and Health","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Early childhood; Developmental psychology; Birth weight; Predictive value; Psychology; Test (biology); Structural equation modeling; Child development; Medicine; Pregnancy; Statistics; Mathematics","score_opus":0.01593232426620633,"score_gpt":0.3052187598674422,"score_spread":0.28928643560123585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125785889","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99170464,0.0044830972,0.00022142423,0.0024563556,0.00011480502,0.00057518604,0.000050352483,0.000010598188,0.0003835483],"genre_scores_gemma":[0.9581361,0.037516657,0.0036600924,0.00058725156,0.000040333456,0.00001388978,0.00001356146,0.00001692916,0.000015190545],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99824655,0.00011239909,0.00074121077,0.00024239511,0.00029839674,0.00035907392],"domain_scores_gemma":[0.99869967,0.00074439053,0.00018218571,0.00015239093,0.000054773107,0.00016659113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015655623,0.00014751355,0.00048262608,0.00028464265,0.00007649596,0.00000658318,0.000053673448,0.00007123489,0.0000050888057],"category_scores_gemma":[0.0023350157,0.000104426654,0.000005988519,0.00029985944,0.00029366434,0.00002851972,0.000025957288,0.00045262714,3.666607e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030131108,0.000111692316,0.95753646,0.00026499777,0.000005183244,0.000041521802,0.013440798,2.9536153e-7,0.000018416116,0.021321207,0.00012027585,0.0071090385],"study_design_scores_gemma":[0.0035069732,0.00076296786,0.98248994,0.0012877667,0.000009414668,0.000034865403,0.0021556045,0.00003822116,0.000025423547,0.009570469,0.000043933505,0.00007442757],"about_ca_topic_score_codex":0.00094608084,"about_ca_topic_score_gemma":0.0129995905,"teacher_disagreement_score":0.03356854,"about_ca_system_score_codex":0.00007459268,"about_ca_system_score_gemma":0.0003939146,"threshold_uncertainty_score":0.72540766},"labels":[],"label_agreement":null},{"id":"W3125937508","doi":"10.1002/sim.8879","title":"Multiple imputation strategies for a bounded outcome variable in a competing risks analysis","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Bristol; Medical Research Council; Royal Society; NHS Blood and Transplant; Medical Research Council Canada; Wellcome Trust","keywords":"Imputation (statistics); Statistics; Missing data; Cumulative distribution function; Econometrics; Cumulative incidence; Mathematics; Regression analysis; Confidence interval; Computer science; Probability density function","score_opus":0.14089669959972412,"score_gpt":0.4712305057681186,"score_spread":0.3303338061683945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125937508","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00410117,0.000045400004,0.99385434,0.00014963596,0.00014735405,0.000267673,0.00034908688,0.000022876893,0.0010624601],"genre_scores_gemma":[0.20439309,0.000008359884,0.79522693,0.00009226266,0.000048650778,0.000050107006,0.00013344396,0.000014024616,0.000033099965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99795014,0.00026119538,0.00088276697,0.0003186391,0.00026597126,0.00032131086],"domain_scores_gemma":[0.98746014,0.011810014,0.00019094793,0.0002197642,0.00025098532,0.00006813681],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016045417,0.00016253655,0.0007205691,0.00026888173,0.00006122287,0.000045680532,0.00010448306,0.00007974263,0.0002785315],"category_scores_gemma":[0.02119903,0.00014466126,0.00003563529,0.0010512942,0.00011294373,0.000051979066,0.000033296128,0.00023249033,0.0000013405414],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033870474,0.00009483864,0.032320734,0.00034471133,0.000085603075,0.000071611976,0.0010976859,0.00015262762,0.00013812252,0.96071565,0.00016469962,0.00477985],"study_design_scores_gemma":[0.0013589808,0.00006772001,0.0148922,0.000109228116,0.0002497171,0.0000024291433,0.0026161205,0.14652953,0.000012446473,0.83398557,0.00004362064,0.00013244883],"about_ca_topic_score_codex":0.0006681103,"about_ca_topic_score_gemma":0.0029408464,"teacher_disagreement_score":0.20029192,"about_ca_system_score_codex":0.000092019596,"about_ca_system_score_gemma":0.000158998,"threshold_uncertainty_score":0.9870458},"labels":[],"label_agreement":null},{"id":"W3134342065","doi":"10.1002/sim.8922","title":"uTPI: A utility‐based toxicity probability interval design for phase I/II dose‐finding trials","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute; National Institutes of Health","keywords":"Maximum tolerated dose; Confidence interval; Clinical trial; Toxicity; Parametric statistics; Computer science; Medicine; Clinical study design; Optimal design; Interval (graph theory); Statistics; Mathematics; Machine learning; Internal medicine","score_opus":0.8161295342178478,"score_gpt":0.6464013638722923,"score_spread":0.16972817034555554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134342065","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004259951,0.00007497799,0.98721325,0.0015183463,0.0015810947,0.0028658214,0.0020031652,0.000094236915,0.0003891443],"genre_scores_gemma":[0.0342875,0.000016417274,0.96387166,0.00055966125,0.00060302333,0.00036751849,0.000064702865,0.000058774902,0.00017072354],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9875488,0.006127494,0.0038640224,0.0009507215,0.000816349,0.00069255556],"domain_scores_gemma":[0.7319252,0.26553187,0.0007782212,0.00084455585,0.0006309847,0.00028917924],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042760212,0.00042899934,0.0028199053,0.0001663469,0.00018557032,0.00003368394,0.0003952579,0.000299996,0.0022849943],"category_scores_gemma":[0.78428996,0.00034797296,0.00021347406,0.00056064106,0.00067211187,0.000051714447,0.00015943358,0.0006250103,0.000004648573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007650217,0.0076645636,0.00029276084,0.003913257,0.00043185693,0.00045449368,0.0016814333,0.000035548932,0.0060388944,0.6786689,0.06544595,0.22772211],"study_design_scores_gemma":[0.0154341655,0.0024642008,0.00006725569,0.00064499857,0.00040325843,0.0000050135877,0.0001494943,0.022434251,0.0059623946,0.951409,0.0007109344,0.00031502167],"about_ca_topic_score_codex":0.000014571951,"about_ca_topic_score_gemma":0.00004298498,"teacher_disagreement_score":0.7415297,"about_ca_system_score_codex":0.00022276696,"about_ca_system_score_gemma":0.00052526494,"threshold_uncertainty_score":0.99989724},"labels":[],"label_agreement":null},{"id":"W3135053972","doi":"10.1002/sim.8906","title":"The impact of adjusting for pure predictors of exposure, mediator, and outcome on the variance of natural direct and indirect effect estimators","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal; Université Laval","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Estimator; Confounding; Outcome (game theory); Mediation; Inverse probability weighting; Variance (accounting); Weighting; Econometrics; Mathematics; Linear regression; Regression analysis; Medicine; Economics","score_opus":0.05564411871493614,"score_gpt":0.42065357746469295,"score_spread":0.3650094587497568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135053972","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9782513,0.0016052483,0.018395577,0.00009682756,0.00021224952,0.0007941514,0.00037901834,0.00002958842,0.00023604235],"genre_scores_gemma":[0.9729033,0.00021214566,0.026760086,0.0000088983425,0.000034162364,0.000035407407,0.000010340495,0.000018972185,0.000016656746],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986122,0.00018041862,0.0005995249,0.00015708654,0.00027973484,0.00017098573],"domain_scores_gemma":[0.9782064,0.020857023,0.0004383598,0.00026847646,0.00019110362,0.000038656675],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015876191,0.00016686223,0.0006143028,0.000065265915,0.000050326682,0.0000041513485,0.00012795244,0.0000633686,0.0000061596875],"category_scores_gemma":[0.031428788,0.00008272867,0.000032895015,0.00019929503,0.0004951141,0.000029237324,0.000055623965,0.00022245804,2.105641e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063301966,0.0001838515,0.5842794,0.004236121,0.00051077816,0.00004051386,0.005905292,0.00007277153,0.019920332,0.35830322,0.0040520024,0.02186266],"study_design_scores_gemma":[0.003508002,0.0056302007,0.24449791,0.0036559443,0.00055931025,0.000030516097,0.0013629596,0.0050231796,0.07819267,0.65708286,0.000023137742,0.00043332524],"about_ca_topic_score_codex":0.000022128615,"about_ca_topic_score_gemma":0.000036769226,"teacher_disagreement_score":0.33978152,"about_ca_system_score_codex":0.000033985423,"about_ca_system_score_gemma":0.00005532143,"threshold_uncertainty_score":0.97672987},"labels":[],"label_agreement":null},{"id":"W3141196614","doi":"10.1002/sim.8966","title":"Multiparameter one‐sided tests for nonlinear mixed effects models with censored responses","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nonlinear system; Statistical hypothesis testing; Computer science; Econometrics; Mathematics; Statistics; Physics","score_opus":0.10619714876143097,"score_gpt":0.42130522307059237,"score_spread":0.31510807430916143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3141196614","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038468863,0.00009301038,0.9936759,0.00033665381,0.00027776064,0.0006341378,0.00071514456,0.000044955566,0.00037555743],"genre_scores_gemma":[0.010706242,0.000036032703,0.9882284,0.00027933848,0.00013180717,0.00009867289,0.0001034771,0.000052570635,0.00036349057],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99776274,0.00038691465,0.00056304457,0.00043644823,0.00042580022,0.0004250401],"domain_scores_gemma":[0.96591717,0.0328975,0.0001484697,0.0004288866,0.00045264466,0.0001553249],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.000748852,0.00025716622,0.00074748945,0.00012235447,0.00006286166,0.000022155476,0.00014305352,0.00010718912,0.000088038985],"category_scores_gemma":[0.043714695,0.0001944154,0.000028485834,0.00029376842,0.00028359916,0.00004474185,0.000041158306,0.00026527856,0.0000042363404],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006082511,0.00029662828,0.00026483432,0.0008689137,0.000076335724,0.00043470977,0.00060972123,0.000009496184,0.0016083355,0.9718833,0.0056136576,0.017725803],"study_design_scores_gemma":[0.0035330213,0.00072919007,0.0014922958,0.001120265,0.0001763632,0.00002367895,0.00015610084,0.03400567,0.0031148489,0.95522994,0.00014149271,0.0002771127],"about_ca_topic_score_codex":0.000029575727,"about_ca_topic_score_gemma":0.00017189655,"teacher_disagreement_score":0.042965844,"about_ca_system_score_codex":0.000054193184,"about_ca_system_score_gemma":0.00013408314,"threshold_uncertainty_score":0.9643405},"labels":[],"label_agreement":null},{"id":"W3152465836","doi":"10.1002/sim.8949","title":"Optimizing subgroup selection in two‐stage adaptive enrichment and umbrella designs","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Horizon 2020 Framework Programme; H2020 Marie Skłodowska-Curie Actions; Innovative Medicines Initiative; Medical Research Council Canada; National Institute for Health and Care Research; Springworks Therapeutics; Medical Research Council; European Federation of Pharmaceutical Industries and Associations","keywords":"Type I and type II errors; Computer science; Selection (genetic algorithm); Word error rate; Population; Subgroup analysis; Adaptive design; Interim analysis; Bayesian probability; Multiple comparisons problem; Clinical trial; Statistics; Mathematical optimization; Medicine; Mathematics; Machine learning; Artificial intelligence; Internal medicine; Confidence interval","score_opus":0.4502326642966361,"score_gpt":0.553600628135857,"score_spread":0.10336796383922087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152465836","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005563106,0.00028549787,0.9909262,0.00025997005,0.00038263225,0.00041985294,0.00008895138,0.000032180917,0.002041613],"genre_scores_gemma":[0.0699938,0.000363665,0.92877394,0.00022850266,0.00018845516,0.00003676326,0.0000068237023,0.000033070595,0.00037496677],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99635726,0.0011575263,0.001105011,0.0005066892,0.00044831473,0.00042520536],"domain_scores_gemma":[0.95999897,0.039295007,0.00021022375,0.00019646283,0.00015663663,0.00014272961],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004309305,0.00022486948,0.0008096652,0.000171437,0.00005620758,0.000017832172,0.00010680057,0.00010233665,0.00054771424],"category_scores_gemma":[0.0633664,0.00020580603,0.000021678034,0.00055388646,0.00026252843,0.000036780908,0.00010338508,0.0005676767,0.0000046506925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024269575,0.00031227697,0.004044248,0.00033945678,0.00006161452,0.0008143724,0.0020133054,0.00015771571,0.002209064,0.9682703,0.0020075787,0.019527398],"study_design_scores_gemma":[0.004001283,0.00036814142,0.0030827164,0.0005148454,0.00008531522,0.000019210578,0.0010796132,0.014545921,0.0005297356,0.9753933,0.00012834033,0.0002515709],"about_ca_topic_score_codex":0.00015874607,"about_ca_topic_score_gemma":0.00072433945,"teacher_disagreement_score":0.0644307,"about_ca_system_score_codex":0.0001935947,"about_ca_system_score_gemma":0.000102586615,"threshold_uncertainty_score":0.9445233},"labels":[],"label_agreement":null},{"id":"W3153092758","doi":"10.1002/sim.8991","title":"Computing the polytomous discrimination index","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian VIGOUR Centre; University of Alberta","funders":"Canadian Institutes of Health Research","keywords":"Polytomous Rasch model; Categorical variable; Outcome (game theory); Ranking (information retrieval); Pairwise comparison; Computer science; Statistics; Index (typography); Econometrics; Mathematics; Data mining; Artificial intelligence; Item response theory; Psychometrics","score_opus":0.4309870051715288,"score_gpt":0.5813675000711929,"score_spread":0.15038049489966404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153092758","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017563967,0.00011217736,0.9872806,0.003605525,0.0011753871,0.00023333728,0.000079105186,0.000039238876,0.005718208],"genre_scores_gemma":[0.22473183,0.00005258107,0.77321035,0.0008883252,0.00060260587,0.000008849042,0.000013048507,0.000028243227,0.0004641673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969151,0.00096368464,0.0009484464,0.00029659088,0.00058645586,0.0002897023],"domain_scores_gemma":[0.93126714,0.06779366,0.00021556648,0.00042560755,0.00021933166,0.00007868739],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038159566,0.00015388135,0.0005133603,0.000062837345,0.000098164004,0.000019908148,0.00023311326,0.000090235786,0.00061453873],"category_scores_gemma":[0.21079598,0.00009953028,0.000029011748,0.0004067745,0.00041522237,0.000020184798,0.0001244089,0.0004978186,0.0000125891875],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022308293,0.00009574076,0.0013037911,0.00012606865,0.00002510893,0.00020699235,0.00094506715,0.000007543986,0.00007713386,0.91124594,0.013741715,0.0722026],"study_design_scores_gemma":[0.001014772,0.00006817349,0.010178843,0.00022460353,0.0000691511,0.00002042001,0.0009029141,0.0055730497,0.000095638796,0.981312,0.00042482704,0.00011564297],"about_ca_topic_score_codex":0.000049396756,"about_ca_topic_score_gemma":0.00014606383,"teacher_disagreement_score":0.22297543,"about_ca_system_score_codex":0.00006790626,"about_ca_system_score_gemma":0.000081348,"threshold_uncertainty_score":0.7958518},"labels":[],"label_agreement":null},{"id":"W3156818063","doi":"10.1002/sim.9002","title":"Semiparametric recurrent event vs time‐to‐first‐event analyses in randomized trials: Estimands and model misspecification","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Censoring (clinical trials); Estimator; Econometrics; Proportional hazards model; Event (particle physics); Semiparametric regression; Semiparametric model; Sample size determination; Statistics; Computer science; Mathematics","score_opus":0.30399888459233215,"score_gpt":0.5326979569422585,"score_spread":0.22869907234992637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156818063","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003815863,0.0014107932,0.9918494,0.001226928,0.00007717582,0.0009881365,0.00006836508,0.00006078296,0.0005025406],"genre_scores_gemma":[0.13555504,0.0024497283,0.8606334,0.00016395761,0.000081312166,0.00030468294,0.00014226652,0.000039902323,0.00062972563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964209,0.00072037335,0.001681793,0.0004277986,0.000478294,0.0002708236],"domain_scores_gemma":[0.9866794,0.012141098,0.00041551885,0.00038879926,0.0002468486,0.0001283497],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0054805605,0.00025064594,0.0018828658,0.0006453616,0.000036962756,0.00001727634,0.00013771617,0.00009578299,0.00027705438],"category_scores_gemma":[0.08024328,0.00020095248,0.000059778347,0.00094594236,0.00015526098,0.000054029457,0.0000762885,0.00030292873,0.000009950275],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03741564,0.0027353552,0.00034586567,0.002212513,0.0005808708,0.0006603278,0.012861336,0.023880748,0.010500276,0.60433817,0.112186484,0.19228242],"study_design_scores_gemma":[0.020518325,0.00017684058,0.0000861115,0.0008595826,0.00020592134,0.0000072104904,0.00012864865,0.2976755,0.0010106025,0.6789537,0.00015035545,0.00022720179],"about_ca_topic_score_codex":0.000029329492,"about_ca_topic_score_gemma":0.00008249181,"teacher_disagreement_score":0.27379477,"about_ca_system_score_codex":0.0002436914,"about_ca_system_score_gemma":0.000097486314,"threshold_uncertainty_score":0.92750424},"labels":[],"label_agreement":null},{"id":"W3157155409","doi":"10.1002/sim.8997","title":"Using generalized linear models to implement g‐estimation for survival data with time‐varying confounding","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Bijzonder Onderzoeksfonds UGent; Medical Research Council Canada; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research; UK Research and Innovation","keywords":"Confounding; Computer science; Estimation; Weighting; Statistics; Marginal structural model; Software; Proportional hazards model; Econometrics; Observational study; Data mining; Mathematics; Medicine","score_opus":0.4354915215451955,"score_gpt":0.5352801309584877,"score_spread":0.0997886094132922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157155409","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022770013,0.000024028246,0.995827,0.00022172165,0.00010033067,0.0006215482,0.0005584478,0.00007587828,0.00029402066],"genre_scores_gemma":[0.010191941,0.000016613496,0.98828804,0.0001675238,0.0001254355,0.00004064142,0.0010201257,0.000044280216,0.000105388695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984041,0.00007242177,0.0005140862,0.0003523128,0.00036251935,0.0002945558],"domain_scores_gemma":[0.99761903,0.001236371,0.00015583588,0.00058862375,0.0003140868,0.00008607056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010309445,0.00017375189,0.0004386701,0.000111114634,0.00007971234,0.000017258775,0.00021437573,0.000042939777,0.00011714786],"category_scores_gemma":[0.0021455605,0.00014956793,0.000008400108,0.00023604688,0.000048626993,0.00015784804,0.0001618599,0.00012395807,0.000001469926],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014365016,0.00007493454,0.000049591887,0.0004015744,0.00007235792,0.00009083813,0.0014201811,0.01624356,0.015792659,0.9560856,0.0042845663,0.0053404905],"study_design_scores_gemma":[0.00082023395,0.00011142361,0.0000018057476,0.0003296491,0.00006479972,0.000008970192,0.00017464045,0.60636,0.0012841203,0.3905263,0.00017597376,0.00014208526],"about_ca_topic_score_codex":0.000093852985,"about_ca_topic_score_gemma":0.00016304274,"teacher_disagreement_score":0.59011644,"about_ca_system_score_codex":0.0001597454,"about_ca_system_score_gemma":0.00014629192,"threshold_uncertainty_score":0.6099203},"labels":[],"label_agreement":null},{"id":"W3157346880","doi":"10.1002/sim.8944","title":"Comment on Ellenberg and Morris: The role of statisticians in vaccine surveillance","year":2021,"lang":"en","type":"letter","venue":"Statistics in Medicine","topic":"Vaccine Coverage and Hesitancy","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Pandemic; Vaccine trial; Vaccination; Medicine; Observational study; Scope (computer science); Vaccine efficacy; Coronavirus disease 2019 (COVID-19); Virology; Computer science; Disease","score_opus":0.01695799143974529,"score_gpt":0.30909520132909285,"score_spread":0.29213720988934755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157346880","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00049137144,0.0057423566,0.0012431258,0.9824893,0.00058218685,0.00052425265,0.00065386697,0.000011757286,0.008261819],"genre_scores_gemma":[0.07456395,0.024909765,0.002338092,0.8905447,0.0045776446,0.00008268271,0.0009639018,0.00009313905,0.0019260985],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973983,0.0006598046,0.00060192903,0.00031751982,0.00064352615,0.00037891456],"domain_scores_gemma":[0.99610883,0.003143432,0.00025048398,0.00031705937,0.00013499409,0.00004522669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011723163,0.00021557057,0.000662159,0.00017407845,0.00011055773,0.00001653181,0.00028737372,0.00022550789,0.00048034024],"category_scores_gemma":[0.0015869488,0.00016188061,0.0000191966,0.00033078413,0.0000998788,0.00002136524,0.000053844265,0.001101842,0.0000033536046],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019245057,0.000033918095,0.019493038,0.00010884697,0.0000215104,0.00048036504,0.0068979515,0.000005476432,0.0000015648432,0.017445303,0.9499592,0.0055335592],"study_design_scores_gemma":[0.0008512377,0.00018454932,0.020997612,0.00062966254,0.000030605366,0.0000016065367,0.004550098,0.000099528974,0.0000018758491,0.029294798,0.94315845,0.00019995624],"about_ca_topic_score_codex":0.009422117,"about_ca_topic_score_gemma":0.029002694,"teacher_disagreement_score":0.09194454,"about_ca_system_score_codex":0.00014783177,"about_ca_system_score_gemma":0.00017195757,"threshold_uncertainty_score":0.9971742},"labels":[],"label_agreement":null},{"id":"W3158038957","doi":"10.1002/sim.8958","title":"Contamination: How much can an individually randomized trial tolerate?","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Patient Safety and Medication Errors","field":"Health Professions","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital","funders":"Collaboration for Leadership in Applied Health Research and Care - Greater Manchester; National Institute for Health and Care Research","keywords":"Randomized controlled trial; Contamination; Statistics; Computer science; Medicine; Mathematics; Biology; Internal medicine; Ecology","score_opus":0.08878237919998472,"score_gpt":0.4545213410230711,"score_spread":0.3657389618230864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158038957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20966299,0.00068639877,0.5483179,0.1726997,0.019496167,0.008713284,0.0012122968,0.00024721585,0.038964026],"genre_scores_gemma":[0.9722073,0.00027807304,0.008299325,0.006074028,0.001125294,0.00050538284,0.0030605928,0.000025961934,0.008424006],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"randomized_trial","domain_scores_codex":[0.99581444,0.0021436883,0.0008124274,0.0002883719,0.0005902227,0.00035086524],"domain_scores_gemma":[0.99575603,0.0028003703,0.00041392777,0.00030915573,0.00049418665,0.00022631574],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002934253,0.00014950857,0.0007168844,0.00015212552,0.00026555502,0.0000014470723,0.00014359086,0.00017082834,0.0018247525],"category_scores_gemma":[0.011967825,0.00012076869,0.00002417527,0.0003279323,0.00028166067,0.0000689271,0.00004034894,0.0006374375,0.00002355502],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.2502264,0.0007912193,0.0077037825,0.00064565806,0.00021277824,0.0004772583,0.11667427,0.000025453473,0.00016416692,0.5150698,0.09480063,0.013208565],"study_design_scores_gemma":[0.94208026,0.0003301908,0.0055251,0.00042100658,0.00010561763,0.0000028229822,0.015588082,0.00081879913,0.000016232905,0.014703108,0.02022696,0.00018181522],"about_ca_topic_score_codex":0.00013769013,"about_ca_topic_score_gemma":0.0020085918,"teacher_disagreement_score":0.76254433,"about_ca_system_score_codex":0.00013357497,"about_ca_system_score_gemma":0.00093665876,"threshold_uncertainty_score":0.9990877},"labels":[],"label_agreement":null},{"id":"W3158999510","doi":"10.1002/sim.8918","title":"Confidence interval estimation for treatment effects in cluster randomization trials based on ranks","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Confidence interval; Statistics; Estimator; Restricted randomization; Coverage probability; Randomization; Cluster randomised controlled trial; Mathematics; Interval estimation; Cluster (spacecraft); Computer science; Randomized controlled trial; Medicine","score_opus":0.09668797906989537,"score_gpt":0.46362505929020326,"score_spread":0.3669370802203079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158999510","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023247763,0.000044374163,0.99679565,0.00066679163,0.00044807806,0.00128524,0.00013959115,0.000015953081,0.00037183028],"genre_scores_gemma":[0.051055484,0.000025998654,0.9478731,0.00039660998,0.00009744756,0.00031778068,0.00014324253,0.000019573552,0.0000707691],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997158,0.0011653245,0.00092301716,0.00028621036,0.00026043743,0.0002069966],"domain_scores_gemma":[0.94654125,0.05283954,0.00020922671,0.00021184147,0.00013907191,0.000059098355],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00309159,0.00018597482,0.0010105448,0.00016191375,0.00003166959,0.000018962832,0.00006797762,0.000086689615,0.00021089993],"category_scores_gemma":[0.094826125,0.00013525721,0.000043428692,0.00020005213,0.0000855141,0.000027716816,0.000009821211,0.00009630752,0.0000029238765],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018060395,0.00028324983,0.00012275891,0.00066348497,0.000023517656,0.00009036692,0.0005985417,0.00039769663,0.00012386912,0.8616064,0.0017643286,0.13251972],"study_design_scores_gemma":[0.01796102,0.00055892667,0.00029455082,0.000887378,0.00008742895,0.0000016431222,0.000038044083,0.34350932,0.0005186866,0.6360186,0.000031303367,0.00009309591],"about_ca_topic_score_codex":0.000035742127,"about_ca_topic_score_gemma":0.00013498623,"teacher_disagreement_score":0.34311163,"about_ca_system_score_codex":0.00016967976,"about_ca_system_score_gemma":0.00011134588,"threshold_uncertainty_score":0.9127985},"labels":[],"label_agreement":null},{"id":"W3159307809","doi":"10.1002/sim.9593","title":"Dose finding studies for therapies with late‐onset toxicities: A comparison study of designs","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council Canada; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research","keywords":"Maximum tolerated dose; Medicine; Clinical trial; Early stopping; Confidence interval; Set (abstract data type); Toxicity; Interval (graph theory); Computer science; Statistics; Oncology; Mathematics; Internal medicine; Machine learning","score_opus":0.7531072275672495,"score_gpt":0.6337813978697665,"score_spread":0.11932582969748295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159307809","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38044393,0.00042580595,0.6132714,0.00038555104,0.00077476026,0.0032722794,0.0012232007,0.0000571174,0.00014595967],"genre_scores_gemma":[0.4860441,0.00002120566,0.513218,0.00007408069,0.00006203168,0.00042554294,0.000006376627,0.000031514835,0.000117155345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99587137,0.0012619467,0.0014561395,0.00034586608,0.00075415196,0.0003105204],"domain_scores_gemma":[0.8945138,0.104342915,0.0005451295,0.0003429955,0.000198761,0.000056406752],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00495545,0.00022986456,0.0014729573,0.00020507365,0.00019365852,0.000006439983,0.0002927654,0.000038629478,0.0002863553],"category_scores_gemma":[0.0516793,0.00016606583,0.000028742621,0.0003928278,0.00046761698,0.000019768104,0.00013661993,0.00037839537,4.074529e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010327777,0.009777225,0.047557782,0.003968431,0.0038729294,0.0004985912,0.35886082,0.0014766025,0.00035662472,0.4739273,0.064258456,0.025117472],"study_design_scores_gemma":[0.0072840624,0.011105066,0.0014786583,0.00023130445,0.0003424721,0.0000041295384,0.1212131,0.0010049857,0.00003786096,0.85696834,0.00012044146,0.00020958215],"about_ca_topic_score_codex":0.000052341766,"about_ca_topic_score_gemma":0.00017827358,"teacher_disagreement_score":0.38304105,"about_ca_system_score_codex":0.000119415745,"about_ca_system_score_gemma":0.00006453939,"threshold_uncertainty_score":0.9563088},"labels":[],"label_agreement":null},{"id":"W3159320036","doi":"10.1002/sim.9000","title":"Score tests for scale effects, with application to genomic analysis","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Toronto; University of Waterloo; Ontario Institute for Cancer Research","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Statistics; Mathematics; Type I and type II errors; Permutation (music); Scale (ratio); Gaussian; Applied mathematics","score_opus":0.24350483640801132,"score_gpt":0.5516258013485317,"score_spread":0.3081209649405203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159320036","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0098336255,0.000052730178,0.98740244,0.00067646167,0.00018464272,0.0010948705,0.00037417188,0.00003599307,0.00034506863],"genre_scores_gemma":[0.028015349,0.000018479439,0.9704478,0.0005735064,0.000279175,0.00035525163,0.00006687421,0.000039250295,0.00020431726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976738,0.00030180826,0.0007977134,0.0005289817,0.00038777024,0.00030990996],"domain_scores_gemma":[0.94478166,0.053918704,0.00018442246,0.0005859075,0.00033773057,0.0001916031],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0020543342,0.00019165628,0.0009906305,0.00020469769,0.00005276336,0.000013703415,0.00018987633,0.000092161245,0.00012328199],"category_scores_gemma":[0.07830169,0.00014890124,0.000048939986,0.0012251183,0.0001666364,0.000014365998,0.000055960078,0.00018841105,0.000011996218],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084075035,0.0007978883,0.0422677,0.0027031726,0.0013882603,0.00023984323,0.0013897127,0.00030869155,0.0082898075,0.679282,0.025160179,0.23733202],"study_design_scores_gemma":[0.002142477,0.0005333531,0.034376867,0.00022880318,0.0016028706,0.0000039628617,0.0000899203,0.002437699,0.00088265655,0.9569789,0.0004894605,0.00023303609],"about_ca_topic_score_codex":0.000030912153,"about_ca_topic_score_gemma":0.00067783345,"teacher_disagreement_score":0.2776969,"about_ca_system_score_codex":0.00010363583,"about_ca_system_score_gemma":0.000084486186,"threshold_uncertainty_score":0.92946213},"labels":[],"label_agreement":null},{"id":"W3161655502","doi":"10.1002/sim.9023","title":"Fine‐Gray subdistribution hazard models to simultaneously estimate the absolute risk of different event types: Cumulative total failure probability may exceed 1","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Covariate; Hazard; Cumulative incidence; Statistics; Hazard ratio; Proportional hazards model; Event (particle physics); Mathematics; Confidence interval","score_opus":0.1656706911041427,"score_gpt":0.42450913207225904,"score_spread":0.25883844096811637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161655502","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51501215,0.0006111966,0.45404068,0.02177214,0.00058739114,0.0013238277,0.00615021,0.000027154552,0.00047525868],"genre_scores_gemma":[0.9832871,0.000056652658,0.015207709,0.0005138211,0.00015463779,0.0000847079,0.0003750536,0.000023067736,0.00029724932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951498,0.0005316672,0.003191941,0.0005350134,0.00021209469,0.0003794908],"domain_scores_gemma":[0.994462,0.0031230466,0.0013479991,0.0006013198,0.00030000732,0.00016561101],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0073212422,0.0002317651,0.0010901308,0.00013928335,0.00012808233,0.000020876783,0.00021175663,0.000109099055,0.00040963944],"category_scores_gemma":[0.015060679,0.0002023349,0.00006456511,0.00030948556,0.00018754297,0.00009217657,0.00008655357,0.00030681677,0.00009542184],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014524253,0.00043315947,0.042682406,0.001070956,0.0002693311,0.000022225733,0.013600693,0.26040772,0.000022623835,0.65285784,0.027376123,0.0011116955],"study_design_scores_gemma":[0.0014078482,0.00029008993,0.07822025,0.00033424544,0.000052267536,0.0000090304,0.0011777371,0.44982377,0.000020129462,0.46725318,0.0010799315,0.00033153704],"about_ca_topic_score_codex":0.001526683,"about_ca_topic_score_gemma":0.005898933,"teacher_disagreement_score":0.46827495,"about_ca_system_score_codex":0.0006360494,"about_ca_system_score_gemma":0.0001610592,"threshold_uncertainty_score":0.9932359},"labels":[],"label_agreement":null},{"id":"W3173746581","doi":"10.1002/sim.9109","title":"Bayesian variable selection with a pleiotropic loss function in Mendelian randomization","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; National Cancer Institute; National Institutes of Health; National Institute for Health and Care Research; Medical Research Council Canada; NIHR Cambridge Biomedical Research Centre; British Heart Foundation; Wellcome Trust","keywords":"Mendelian randomization; Pleiotropy; Selection (genetic algorithm); Inference; Context (archaeology); Computer science; Statistics; Genetics; Biology; Mathematics; Genetic variants; Machine learning; Artificial intelligence; Phenotype; Gene","score_opus":0.006242120170021306,"score_gpt":0.25977184954295146,"score_spread":0.25352972937293017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173746581","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04580613,0.00022841714,0.9521781,0.00039571957,0.00016392258,0.000138706,0.000017084261,0.0000051449974,0.0010667698],"genre_scores_gemma":[0.9224901,0.00028890677,0.07504132,0.00042776257,0.0002145121,0.00003384895,0.0008103684,0.000015197089,0.0006779874],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989771,0.00019040096,0.00028846404,0.00025391398,0.0000988079,0.00019129828],"domain_scores_gemma":[0.99956703,0.000051768977,0.00008418982,0.00012143009,0.00013733156,0.00003823706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039862978,0.00009674123,0.00021364405,0.00007776907,0.000037881313,0.000004371027,0.00003880087,0.00011078529,0.00013067364],"category_scores_gemma":[0.00067936536,0.000083959494,0.000008842483,0.00032159523,0.000049533803,0.000002219583,0.00001600642,0.00010869658,0.0000016471383],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014172376,0.00028153832,0.8632981,0.00011604658,0.00018160838,0.00009227447,0.00036959094,0.03819542,0.04896386,0.02387345,0.016521318,0.006689539],"study_design_scores_gemma":[0.050065294,0.0039317156,0.75751,0.00039998716,0.00031051706,0.00025350053,0.0017512036,0.08764689,0.0031180733,0.058962908,0.034941696,0.0011081898],"about_ca_topic_score_codex":0.000196011,"about_ca_topic_score_gemma":0.0030018236,"teacher_disagreement_score":0.87713677,"about_ca_system_score_codex":0.000047355625,"about_ca_system_score_gemma":0.00013352622,"threshold_uncertainty_score":0.3423769},"labels":[],"label_agreement":null},{"id":"W3176979971","doi":"10.1002/sim.9097","title":"Estimation of diagnostic test accuracy: A “Rule of Three” for data with repeated observations but without a gold standard","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Multinomial distribution; Statistics; Computer science; Goodness of fit; Gold standard (test); Degrees of freedom (physics and chemistry); Test (biology); Mathematics","score_opus":0.1483904432595583,"score_gpt":0.4300721741808364,"score_spread":0.2816817309212781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176979971","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00521742,0.00008142912,0.9862501,0.0003501914,0.00007146655,0.00051228027,0.0073131057,0.000018004026,0.00018599736],"genre_scores_gemma":[0.077751726,0.00006021506,0.92131966,0.000035324636,0.00003278736,0.000045359648,0.00069053576,0.000024394789,0.00004001864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99810296,0.00008941894,0.00086484617,0.00031403537,0.0004318391,0.00019690994],"domain_scores_gemma":[0.9438755,0.054136287,0.00044601443,0.00076530426,0.0007086646,0.0000682295],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00094351295,0.00016046582,0.0006611815,0.00007921649,0.00003302827,0.000009136387,0.0002545649,0.00005999057,0.000089742476],"category_scores_gemma":[0.28164598,0.00012293065,0.000013513448,0.0004142095,0.00031759345,0.000076496086,0.00008401642,0.00014737115,3.826189e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022687491,0.0003795773,0.026619311,0.0025273035,0.00010593844,0.000075670825,0.0005685714,0.000035771787,0.0012505625,0.84825814,0.005848593,0.1141037],"study_design_scores_gemma":[0.002119111,0.0007269184,0.011959009,0.002032338,0.0003525664,0.00001278425,0.00025523934,0.08675032,0.0010952413,0.8944342,0.00009399552,0.00016823657],"about_ca_topic_score_codex":0.00015528162,"about_ca_topic_score_gemma":0.0006788134,"teacher_disagreement_score":0.28070247,"about_ca_system_score_codex":0.00003455729,"about_ca_system_score_gemma":0.00031719287,"threshold_uncertainty_score":0.724405},"labels":[],"label_agreement":null},{"id":"W3179584355","doi":"10.1002/sim.9126","title":"Fitting marginal models in small samples: A simulation study of marginalized multilevel models and generalized estimating equations","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Heart, Lung, and Blood Institute","keywords":"Marginal model; Generalized estimating equation; Gee; Inference; Econometrics; Estimating equations; Sample size determination; Statistics; Multilevel model; Statistical inference; Cluster (spacecraft); Random effects model; Sample (material); Population; Mathematics; Computer science; Regression analysis; Meta-analysis; Estimator; Physics; Demography; Artificial intelligence","score_opus":0.3026635934558983,"score_gpt":0.45129308017905495,"score_spread":0.14862948672315662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3179584355","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07066629,0.0000780465,0.9284127,0.00005982342,0.00007698976,0.00044659022,0.00011905318,0.000015615688,0.00012491609],"genre_scores_gemma":[0.41477263,0.000010576028,0.5850958,0.000022424912,0.00002651184,0.000027722344,0.00001584331,0.000014831567,0.000013648566],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99741083,0.0005356548,0.0010847003,0.00036735355,0.00033469006,0.00026679432],"domain_scores_gemma":[0.9883376,0.010659635,0.00035678773,0.00026052498,0.0003058016,0.00007967518],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014021639,0.00020203578,0.0007500482,0.0002189932,0.00006234825,0.000017011704,0.000102172846,0.000070174974,0.00008152552],"category_scores_gemma":[0.013719096,0.00018652935,0.000015156441,0.0003397636,0.00011853219,0.00007878198,0.00008158689,0.00025223134,2.3165241e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008730748,0.0006160947,0.00280952,0.00058381184,0.000035660778,0.00014715923,0.010639998,0.09153012,0.00012584215,0.86394334,0.000023697092,0.02945742],"study_design_scores_gemma":[0.0020252692,0.00007239218,0.0016168496,0.0003622856,0.000041824205,0.000001909781,0.0014785061,0.5097762,0.000003179199,0.48453492,2.8355734e-7,0.00008641673],"about_ca_topic_score_codex":0.00078154035,"about_ca_topic_score_gemma":0.0009657663,"teacher_disagreement_score":0.41824606,"about_ca_system_score_codex":0.00005932411,"about_ca_system_score_gemma":0.000076532495,"threshold_uncertainty_score":0.9945888},"labels":[],"label_agreement":null},{"id":"W3185479023","doi":"10.1002/sim.9135","title":"Optimal design of cluster randomized trials allowing unequal allocation of clusters and unequal cluster size between arms","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"Cluster (spacecraft); Variance (accounting); Range (aeronautics); Sample size determination; Statistics; Cluster size; Statistical power; Computer science; Cluster randomised controlled trial; Mathematics; Randomized controlled trial; Medicine; Physics; Engineering","score_opus":0.22106253953040395,"score_gpt":0.4884150912243174,"score_spread":0.2673525516939135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185479023","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039210126,0.00057652366,0.95733166,0.0009852832,0.0005004678,0.0010376105,0.000100382196,0.000009714085,0.00024824025],"genre_scores_gemma":[0.4206701,0.00008418675,0.57873636,0.00019276026,0.0000998234,0.00002211764,0.000025301733,0.000018892646,0.00015047519],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9816263,0.011239006,0.0041480656,0.00065386045,0.0019872047,0.0003455794],"domain_scores_gemma":[0.87781143,0.11973431,0.0011934576,0.0004900986,0.00061232154,0.00015837656],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05531043,0.00029121464,0.0030768882,0.0003744228,0.00004789658,0.00004081473,0.00040385616,0.0001723701,0.00040434068],"category_scores_gemma":[0.1583154,0.00020576896,0.0001352701,0.00077494857,0.00097196415,0.0001808963,0.00022282662,0.00026019374,0.000004518288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.18573023,0.0010612546,0.005711845,0.0009010863,0.002102235,0.00038706104,0.079064146,0.24713546,0.21769576,0.028692367,0.01788786,0.21363069],"study_design_scores_gemma":[0.36121807,0.0020899472,0.0027903288,0.0011492411,0.0012117794,0.000020472497,0.020609662,0.46953467,0.046792272,0.09347388,0.00012670808,0.0009829566],"about_ca_topic_score_codex":0.000100039964,"about_ca_topic_score_gemma":0.000008223641,"teacher_disagreement_score":0.38145998,"about_ca_system_score_codex":0.00006407774,"about_ca_system_score_gemma":0.00020772731,"threshold_uncertainty_score":0.9727567},"labels":[],"label_agreement":null},{"id":"W3189430776","doi":"10.1002/sim.9141","title":"Estimating adjusted risk differences by multiply‐imputing missing control binary potential outcomes following propensity score‐matching","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Statistics; Imputation (statistics); Missing data; Confidence interval; Matching (statistics); Mean squared error; Absolute risk reduction; Regression; Mathematics; Econometrics; Medicine","score_opus":0.0927472377061911,"score_gpt":0.39244463014258196,"score_spread":0.2996973924363909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189430776","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41623697,0.00014778331,0.5824531,0.0001666746,0.00035285283,0.00029245604,0.00007000127,0.00018561193,0.0000945954],"genre_scores_gemma":[0.5691907,0.000010603368,0.43047303,0.00011192243,0.00006646486,0.000013888258,0.000042087766,0.00003633087,0.0000549993],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99658054,0.00050112786,0.001087779,0.0005530868,0.00069256127,0.0005849258],"domain_scores_gemma":[0.9946833,0.0039177802,0.0005935268,0.00042580583,0.00022530589,0.00015424012],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001470033,0.00040678107,0.0011314962,0.00014607901,0.00034346138,0.00005968255,0.00026333483,0.00014547621,0.00007844404],"category_scores_gemma":[0.017317304,0.00033271482,0.000075139666,0.00030178743,0.00020341312,0.00018470164,0.0001701676,0.0008405148,0.0000032764692],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012466473,0.00075487694,0.7542516,0.001441243,0.00063079677,0.004698739,0.010366712,0.0013601466,0.101,0.015125105,0.0028981275,0.107348],"study_design_scores_gemma":[0.005219074,0.00033431582,0.09462126,0.0037429444,0.00057393184,0.000054970882,0.0021583345,0.1799359,0.0013243932,0.71099097,0.0000075699213,0.0010363336],"about_ca_topic_score_codex":0.0003825322,"about_ca_topic_score_gemma":0.00008958747,"teacher_disagreement_score":0.69586587,"about_ca_system_score_codex":0.00015309267,"about_ca_system_score_gemma":0.00011154616,"threshold_uncertainty_score":0.9999125},"labels":[],"label_agreement":null},{"id":"W3191796027","doi":"10.1002/sim.9133","title":"Testing and correcting for weak and pleiotropic instruments in two‐sample multivariable Mendelian randomization","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":630,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; Wellcome Trust","keywords":"Mendelian randomization; Statistics; Pleiotropy; Test statistic; Instrumental variable; Statistic; Mathematics; Econometrics; Sample size determination; Resampling; Statistical hypothesis testing; Biology; Genetics; Genetic variants","score_opus":0.021971664813142743,"score_gpt":0.32767985268335337,"score_spread":0.30570818787021065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191796027","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7063362,0.00040522285,0.29217207,0.0002590891,0.0002076209,0.000259456,0.000081142585,0.0000033432048,0.00027586505],"genre_scores_gemma":[0.79545593,0.00016410719,0.20380954,0.00013606832,0.00008218998,0.00002483041,0.00024496898,0.000008150273,0.00007421497],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99920654,0.00009280526,0.00027426236,0.00022000667,0.00004374765,0.00016265322],"domain_scores_gemma":[0.9990808,0.0006423067,0.00008234581,0.000073696625,0.00008518641,0.000035674086],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004909669,0.000077156896,0.00020200551,0.000043371154,0.000051874107,0.0000053810304,0.000025959738,0.000051441086,0.000007084159],"category_scores_gemma":[0.011961055,0.00007413078,0.0000052325713,0.000094561285,0.000049342652,0.0000017177583,0.00004218733,0.00006118504,8.456791e-8],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073505376,0.000027907288,0.9256311,0.00005383932,0.000019722573,0.0000022808679,0.00020267931,0.0005628993,0.030972695,0.00074400083,0.0005314591,0.041177914],"study_design_scores_gemma":[0.04575028,0.0007945669,0.72375757,0.00036162132,0.00010345485,0.00006235721,0.0032867142,0.17937817,0.0032194632,0.03961495,0.0031117562,0.0005590969],"about_ca_topic_score_codex":0.0005883351,"about_ca_topic_score_gemma":0.0011294867,"teacher_disagreement_score":0.20187353,"about_ca_system_score_codex":0.000017436312,"about_ca_system_score_gemma":0.000044349144,"threshold_uncertainty_score":0.9963616},"labels":[],"label_agreement":null},{"id":"W3193216897","doi":"10.1002/sim.9151","title":"Estimating the marginal effect of a continuous exposure on an ordinal outcome using data subject to covariate‐driven treatment and visit processes","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Covariate; Marginal structural model; Outcome (game theory); Confounding; Causal inference; Econometrics; Inference; Statistics; Odds; Generalization; Computer science; Inverse probability weighting; Mathematics; Logistic regression; Artificial intelligence; Propensity score matching","score_opus":0.18254403681751505,"score_gpt":0.48358799182642537,"score_spread":0.30104395500891035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193216897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4769054,0.0000951122,0.52183944,0.00014217653,0.00007214857,0.00053174264,0.00028565785,0.000041722866,0.0000866365],"genre_scores_gemma":[0.511941,0.000013131306,0.48781025,0.00004681184,0.000065431064,0.000013975407,0.00007031513,0.000019909303,0.000019167814],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99853104,0.00022866907,0.00045727342,0.00032603985,0.00025675245,0.00020021897],"domain_scores_gemma":[0.995956,0.0030051698,0.00019235224,0.0006168436,0.00016227433,0.00006735526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084145187,0.000204739,0.00058426283,0.00008049243,0.00006625619,0.000017506056,0.00022199869,0.000044600696,0.000032232114],"category_scores_gemma":[0.00802841,0.00012486277,0.00000815766,0.00025700874,0.00013208705,0.000071851624,0.00012496812,0.00015491802,4.842209e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003091979,0.0020281337,0.37697673,0.01276327,0.00082126464,0.0038692858,0.029512897,0.0049102837,0.043856896,0.20844813,0.0017848113,0.31193632],"study_design_scores_gemma":[0.020480681,0.07203456,0.020389775,0.01647539,0.0037210807,0.0013032315,0.006185708,0.27382204,0.04360831,0.5386402,0.0005478123,0.0027911959],"about_ca_topic_score_codex":0.00015253862,"about_ca_topic_score_gemma":0.00023125244,"teacher_disagreement_score":0.35658696,"about_ca_system_score_codex":0.00008545669,"about_ca_system_score_gemma":0.000093377486,"threshold_uncertainty_score":0.96113366},"labels":[],"label_agreement":null},{"id":"W3193380525","doi":"10.1002/sim.9167","title":"A Bayesian nonparametric approach to dynamic item‐response modeling: An application to the GUSTO cohort study","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute","funders":"Medical Research Council; National Medical Research Council; National Research Foundation Singapore; Singapore Institute for Clinical Sciences; National University Health System; National Research Foundation","keywords":"Nonparametric statistics; Respondent; Cluster analysis; Item response theory; Bayesian probability; Cohort; Computer science; Econometrics; Statistics; Psychology; Machine learning; Psychometrics; Mathematics; Artificial intelligence","score_opus":0.05233594052253809,"score_gpt":0.4136245242099736,"score_spread":0.3612885836874355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193380525","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018344192,0.000027756227,0.9776547,0.00084079494,0.00015621654,0.0020166605,0.00014075958,0.00004680172,0.00077211607],"genre_scores_gemma":[0.41866747,0.000004376742,0.58033055,0.00040661695,0.000060550672,0.00036931224,0.000033247034,0.000029907633,0.000098013545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99622875,0.0010517538,0.0007921131,0.00072113104,0.00079543394,0.0004108325],"domain_scores_gemma":[0.9936052,0.0044881143,0.00010323666,0.0010934223,0.0003779195,0.00033209688],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004115271,0.00026962988,0.00061122014,0.00033256665,0.00013672633,0.00004783016,0.0004615573,0.000079889185,0.00008589489],"category_scores_gemma":[0.024088489,0.00019491672,0.000021689466,0.0018714684,0.000075824595,0.000036153244,0.00013051621,0.00037785427,0.00002435221],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013435241,0.005116418,0.018075725,0.0004006897,0.00021323172,0.00033492577,0.025151685,0.0053704483,0.0007551494,0.7286405,0.0074886126,0.2071091],"study_design_scores_gemma":[0.00063572085,0.0006692969,0.024413662,0.000059407295,0.00013384069,0.000019041649,0.0037253092,0.69728976,0.000005168192,0.27261844,0.00015228153,0.0002780443],"about_ca_topic_score_codex":0.00020837662,"about_ca_topic_score_gemma":0.00044623335,"teacher_disagreement_score":0.6919193,"about_ca_system_score_codex":0.00018529668,"about_ca_system_score_gemma":0.00013512436,"threshold_uncertainty_score":0.98413205},"labels":[],"label_agreement":null},{"id":"W3194048807","doi":"10.1002/sim.9159","title":"A Bayesian approach for estimating typhoid fever incidence from large‐scale facility‐based passive surveillance data","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Salmonella and Campylobacter epidemiology","field":"Agricultural and Biological Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Infection and Immunity","funders":"Public Health Research Programme; Government of the United Kingdom; Department of Health and Social Care; Wellcome Trust; National Institute for Health and Care Research; Bill and Melinda Gates Foundation","keywords":"Typhoid fever; Incidence (geometry); Medicine; Credible interval; Blood culture; Population; Environmental health; Demography; Confidence interval; Virology; Internal medicine; Biology; Mathematics","score_opus":0.05473443333751478,"score_gpt":0.31792407375043935,"score_spread":0.2631896404129246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194048807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10332932,0.0003757116,0.8807936,0.0018379599,0.0003666539,0.00028797245,0.012811512,0.00003604654,0.00016125664],"genre_scores_gemma":[0.648267,0.000029584813,0.32576737,0.0013949533,0.0004892908,0.000038640137,0.023941977,0.0000018457597,0.000069349706],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981858,0.00026752593,0.00040700208,0.000603314,0.0001919919,0.00034437713],"domain_scores_gemma":[0.9962582,0.0031467741,0.00013493183,0.00023023739,0.00013231351,0.0000975145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008434135,0.0001511803,0.00043263272,0.00000969331,0.00010547225,0.000014038614,0.00039083482,0.000100418416,0.0004533419],"category_scores_gemma":[0.003793317,0.00006733127,0.00002174602,0.00023827457,0.00012538792,0.000046981535,0.0001398297,0.00017033909,0.000004849528],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023225317,0.00054318283,0.7168742,0.00020539915,0.000079068835,0.0002661656,0.0011865958,0.0005569296,0.027654199,0.000685353,0.059414178,0.1923025],"study_design_scores_gemma":[0.0013092903,0.00020011577,0.3964065,0.00010235464,0.000037589245,0.000013624465,0.0020039543,0.5816263,0.0001575184,0.010639843,0.0070926934,0.0004102156],"about_ca_topic_score_codex":0.00073798955,"about_ca_topic_score_gemma":0.004046641,"teacher_disagreement_score":0.58106935,"about_ca_system_score_codex":0.000029994886,"about_ca_system_score_gemma":0.000035623092,"threshold_uncertainty_score":0.4963776},"labels":[],"label_agreement":null},{"id":"W3196973804","doi":"10.1002/sim.3967","title":"Correction","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Toronto Metropolitan University","funders":"","keywords":"Regret; Statistics; Confidence interval; Proofreading; Estimator; Mathematics; Computer science; Medicine","score_opus":0.04686030747778479,"score_gpt":0.41881745912163143,"score_spread":0.37195715164384663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196973804","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010110625,0.0000055173773,0.9702048,0.00023930245,0.003272121,0.00010020222,0.00002788614,0.000035146317,0.025103975],"genre_scores_gemma":[0.043393455,0.000009763473,0.95550126,0.00012467641,0.00029101007,0.000011424922,0.000008260275,0.000013890033,0.0006462898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990863,0.000060435883,0.0003052176,0.00015746916,0.00021220074,0.00017836831],"domain_scores_gemma":[0.99604,0.0035347503,0.00006825893,0.00020153211,0.00007816451,0.000077299075],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006843979,0.00009688828,0.0002273794,0.000089571666,0.00003608711,0.000006796423,0.00010082625,0.00006483458,0.0019861376],"category_scores_gemma":[0.016067112,0.000074877855,0.0000081725375,0.0001707401,0.00020879948,0.000020593994,0.000017612474,0.00047192123,0.000022761193],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069857624,0.00002761265,0.0010092369,0.000022844013,0.000002507697,0.00002397878,0.00017464663,3.2079736e-8,0.00072038925,0.8425486,0.05924948,0.096213676],"study_design_scores_gemma":[0.00032861097,0.00008685501,0.008341813,0.000057578945,0.000014133407,0.000015727526,0.00007326027,0.0027493362,0.000098687706,0.9858448,0.0023005262,0.00008865817],"about_ca_topic_score_codex":0.000087828186,"about_ca_topic_score_gemma":0.0004176855,"teacher_disagreement_score":0.1432962,"about_ca_system_score_codex":0.000014852794,"about_ca_system_score_gemma":0.000027033077,"threshold_uncertainty_score":0.99892616},"labels":[],"label_agreement":null},{"id":"W3199775394","doi":"10.1002/sim.9176","title":"Informing power and sample size calculations when using inverse probability of treatment weighting using the propensity score","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Institute of Health Services and Policy Research; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Propensity score matching; Observational study; Weighting; Statistics; Sample size determination; Average treatment effect; Mathematics; Statistic; Homogeneity (statistics); Econometrics; Inverse probability weighting; Medicine","score_opus":0.27352121820347886,"score_gpt":0.4268053675944418,"score_spread":0.15328414939096296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199775394","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63930464,0.000026281967,0.35993525,0.00007913205,0.00003506697,0.00039145316,0.00005888864,0.000021099531,0.00014819007],"genre_scores_gemma":[0.290549,0.000014624262,0.70934844,0.00003697678,0.000017523382,0.000005775519,0.0000054238035,0.000010136671,0.000012101364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989145,0.00009439327,0.0004721341,0.00016735637,0.00018598136,0.00016564339],"domain_scores_gemma":[0.99612314,0.0030766635,0.00021925052,0.00030342554,0.00023473619,0.00004278134],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00049333076,0.00013290162,0.0003440573,0.00004193483,0.00010841875,0.000008280972,0.000058331796,0.000047212954,0.00008505109],"category_scores_gemma":[0.01181668,0.000087307366,0.000015532449,0.0001764449,0.00034126337,0.00008483298,0.0000903637,0.00013510644,6.9712264e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101631354,0.00046269153,0.22899422,0.001458148,0.000218146,0.00017017948,0.050822597,0.0011626554,0.055536192,0.64835405,0.0002575677,0.012461916],"study_design_scores_gemma":[0.0004726545,0.00014009097,0.002041729,0.00050167285,0.00010731443,0.000029021057,0.0012506566,0.01713863,0.0031151262,0.9750288,0.000047408208,0.00012689961],"about_ca_topic_score_codex":0.0008862511,"about_ca_topic_score_gemma":0.0010572418,"teacher_disagreement_score":0.34941316,"about_ca_system_score_codex":0.00027655053,"about_ca_system_score_gemma":0.0001861297,"threshold_uncertainty_score":0.9965072},"labels":[],"label_agreement":null},{"id":"W3200775649","doi":"10.1002/sim.9562","title":"Network meta‐analysis of rare events using penalized likelihood regression","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Horizon 2020 Framework Programme; Medical Research Council Canada","keywords":"Overdispersion; Rare events; Statistics; Computer science; Econometrics; Multiplicative function; Likelihood function; Meta-analysis; Mathematics; Maximum likelihood; Count data; Poisson distribution; Medicine","score_opus":0.1664385312629363,"score_gpt":0.44900875208886887,"score_spread":0.2825702208259325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200775649","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010898164,0.0008646831,0.99630976,0.00014549242,0.00021592034,0.00023992885,0.00068088394,0.00001599568,0.00043754582],"genre_scores_gemma":[0.058352694,0.000035588713,0.94115466,0.00017529476,0.00006179259,0.00003863715,0.00008548473,0.000023156641,0.00007271349],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968565,0.0009103265,0.0008501197,0.00028541137,0.0007768194,0.00032081697],"domain_scores_gemma":[0.9947579,0.004188814,0.0004548753,0.00037974794,0.00012539967,0.00009324611],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021942751,0.00018997327,0.0014981511,0.0003323194,0.00013827617,0.0000036165743,0.00025528416,0.000041804913,0.0072982833],"category_scores_gemma":[0.0025528504,0.0001400299,0.00013186887,0.0015402837,0.000117299496,0.000021350725,0.000174254,0.00032555466,6.04087e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023576211,0.00031535418,0.0028716538,0.0003661624,0.022591542,0.00020781014,0.0015753388,0.00075024896,0.0003286007,0.9554864,0.009844467,0.0054266215],"study_design_scores_gemma":[0.00060814916,0.00016033862,0.0014432891,0.00005622446,0.049438793,0.0000046224955,0.00029574527,0.01726309,0.0000061777346,0.9304811,0.00009827819,0.0001442072],"about_ca_topic_score_codex":0.00021646143,"about_ca_topic_score_gemma":0.00007648458,"teacher_disagreement_score":0.05726288,"about_ca_system_score_codex":0.000072905124,"about_ca_system_score_gemma":0.00006726431,"threshold_uncertainty_score":0.9936092},"labels":[],"label_agreement":null},{"id":"W3203445629","doi":"10.1002/sim.9718","title":"Causal inference in survival analysis using longitudinal observational data: Sequential trials and marginal structural models","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; Norges Forskningsråd; UK Research and Innovation","keywords":"Marginal structural model; Causal inference; Censoring (clinical trials); Observational study; Inverse probability; Econometrics; Computer science; Confounding; Inference; Statistics; Inverse probability weighting; Propensity score matching; Mathematics; Artificial intelligence; Bayesian probability","score_opus":0.7073736049282677,"score_gpt":0.5705797811041333,"score_spread":0.1367938238241344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203445629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24767403,0.00004575757,0.7505701,0.00012610527,0.00017927511,0.0002800882,0.0009895056,0.000082205195,0.00005292067],"genre_scores_gemma":[0.7270468,0.00012839466,0.27141932,0.00002097382,0.00015583813,0.000014460527,0.0011592152,0.000021357559,0.00003364898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99695253,0.0003843319,0.0011318417,0.0004999684,0.00065166986,0.00037966174],"domain_scores_gemma":[0.9931491,0.005783044,0.0003308528,0.00048393232,0.00016535996,0.00008769291],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004174677,0.00024656198,0.0011087147,0.0007512901,0.000065037435,0.000029606785,0.00032157614,0.00010565278,0.00015450518],"category_scores_gemma":[0.010837155,0.00021329035,0.000023995035,0.0015556748,0.00030651884,0.0003812445,0.0003036279,0.00037010535,9.670483e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014343491,0.000034387773,0.13504769,0.0002164611,0.00031099853,0.00037380782,0.0009862526,0.013103762,0.0008635785,0.8466038,0.0005921561,0.0017236749],"study_design_scores_gemma":[0.00053960714,0.00003869819,0.03018978,0.00008903783,0.00024117329,0.0000031221323,0.00017541413,0.4083308,0.000011053978,0.56023115,0.0000033789806,0.00014674877],"about_ca_topic_score_codex":0.00089562876,"about_ca_topic_score_gemma":0.003204427,"teacher_disagreement_score":0.47937277,"about_ca_system_score_codex":0.0001443739,"about_ca_system_score_gemma":0.00014277278,"threshold_uncertainty_score":0.997495},"labels":[],"label_agreement":null},{"id":"W3204069683","doi":"10.1002/sim.9203","title":"A comparison of methods for analyzing a binary composite endpoint with partially observed components in randomized controlled trials","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; Medical Research Council; National Institute for Health and Care Research; NHS Blood and Transplant","keywords":"Composite number; Binary number; Randomized controlled trial; Statistics; Computer science; Mathematics; Medicine; Algorithm; Internal medicine; Arithmetic","score_opus":0.28725368993790196,"score_gpt":0.5240229339826206,"score_spread":0.2367692440447186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204069683","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0053616553,0.00096313294,0.99057585,0.00032753617,0.00020598008,0.0022053744,0.0001881844,0.000015735961,0.00015654443],"genre_scores_gemma":[0.077822894,0.00009518515,0.921505,0.00005295404,0.000048709968,0.0003254972,0.00010268868,0.000025929525,0.000021188016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98713905,0.00788242,0.0038975698,0.00037305418,0.0003506155,0.000357316],"domain_scores_gemma":[0.87716776,0.12080667,0.0012257124,0.00028630276,0.00041140738,0.00010213206],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022373272,0.0002995539,0.008993173,0.00028803668,0.000042889296,0.000017851882,0.00016741625,0.00009975775,0.00019510476],"category_scores_gemma":[0.10978552,0.00018776036,0.00020661534,0.00044176835,0.00039142233,0.000029287205,0.0000388453,0.00029752657,3.217254e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.17177309,0.0010865524,0.0050875717,0.0014340921,0.0010019863,0.00013667314,0.0026301013,0.00007310936,0.023430955,0.77056485,0.0003654383,0.022415573],"study_design_scores_gemma":[0.29577821,0.00040586048,0.001723135,0.0015137099,0.001124182,0.0000035800626,0.00039056496,0.10392596,0.0017388997,0.59316164,0.000019185987,0.00021505245],"about_ca_topic_score_codex":0.000091386,"about_ca_topic_score_gemma":0.00017302544,"teacher_disagreement_score":0.17740321,"about_ca_system_score_codex":0.000058591402,"about_ca_system_score_gemma":0.00015773768,"threshold_uncertainty_score":0.8977131},"labels":[],"label_agreement":null},{"id":"W3204449925","doi":"10.1002/sim.9211","title":"Two‐phase sample selection strategies for design and analysis in post‐genome‐wide association fine‐mapping studies","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto; University Health Network","funders":"National Heart, Lung, and Blood Institute; Canadian Institutes of Health Research; Terveyden ja hyvinvoinnin laitos; Oulun Yliopisto; Government of Ontario; Broad Institute; Compute Canada; University of Toronto; Ontario Institute for Cancer Research","keywords":"Selection (genetic algorithm); Sample (material); Computer science; Sample size determination; Genome-wide association study; Genetic association; Association (psychology); Statistics; Biology; Genetics; Mathematics; Artificial intelligence; Psychology; Single-nucleotide polymorphism; Genotype; Chromatography","score_opus":0.029815570153603213,"score_gpt":0.33703081872226015,"score_spread":0.30721524856865695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204449925","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17930399,0.001691101,0.8183485,0.00024323331,0.00008025454,0.00017220108,0.00011837719,0.0000035202834,0.000038803348],"genre_scores_gemma":[0.50586987,0.00032922384,0.49249062,0.00023070349,0.00013031374,0.000042031857,0.000749976,0.000010477733,0.00014679992],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990523,0.00011685358,0.00028234732,0.00026348542,0.00010463981,0.00018037831],"domain_scores_gemma":[0.99882394,0.00070177426,0.00009603343,0.00009306459,0.00025168632,0.000033508302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000485299,0.000109672925,0.000258375,0.00011664154,0.000050073686,0.000011436845,0.000044616558,0.000066897475,0.000016969465],"category_scores_gemma":[0.002782444,0.0001066375,0.000019337998,0.00030704594,0.000053490625,0.0000031814639,0.000024952056,0.000075854616,1.7399108e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014300862,0.0012713348,0.38462266,0.0010200551,0.0075554755,0.000038074715,0.020314053,0.18270083,0.2586886,0.089315064,0.013586131,0.039457656],"study_design_scores_gemma":[0.015151413,0.004520885,0.6764227,0.0001541,0.0014736615,0.000009306868,0.019965325,0.010474555,0.004136752,0.2631853,0.003574398,0.0009315746],"about_ca_topic_score_codex":0.00006746128,"about_ca_topic_score_gemma":0.0016428304,"teacher_disagreement_score":0.32656586,"about_ca_system_score_codex":0.000047094167,"about_ca_system_score_gemma":0.00012522069,"threshold_uncertainty_score":0.4348551},"labels":[],"label_agreement":null},{"id":"W3205527824","doi":"10.1002/sim.9225","title":"Bayesian consensus clustering for multivariate longitudinal data","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Liver Disease Diagnosis and Treatment","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Queen's University","funders":"","keywords":"Cluster analysis; Multivariate statistics; Computer science; Data mining; Fuzzy clustering; Bayesian probability; CURE data clustering algorithm; Correlation clustering; Consensus clustering; Clustering high-dimensional data; Artificial intelligence; Machine learning","score_opus":0.09591034766605583,"score_gpt":0.3992369993620657,"score_spread":0.30332665169600986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205527824","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.025690591,0.006178168,0.92677253,0.021010008,0.0023056373,0.0027144304,0.0097943265,0.00012303233,0.005411296],"genre_scores_gemma":[0.8134419,0.00029734246,0.1799679,0.0008239534,0.00043710295,0.00006304692,0.004472421,0.0000346151,0.00046172945],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99875814,0.000036810936,0.00032819106,0.0004122862,0.000224989,0.0002396124],"domain_scores_gemma":[0.9983355,0.000675556,0.00006117724,0.00058560685,0.00017085465,0.00017131356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023634522,0.00014013155,0.00038662707,0.000067024695,0.000049228107,0.000008443128,0.00008676588,0.000041544543,0.00034474573],"category_scores_gemma":[0.0013619061,0.00011370526,0.00002090954,0.00012408935,0.00010089343,0.00001922089,0.000103234575,0.00010146344,0.000007282991],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022117214,0.00387341,0.5645339,0.003651578,0.0020716172,0.029554002,0.0021732245,0.00015400571,0.0017440483,0.031183366,0.24249847,0.116350636],"study_design_scores_gemma":[0.033891845,0.0012650994,0.75584227,0.0025480527,0.002496426,0.0003961675,0.0014450663,0.17786787,0.0003919582,0.007225646,0.016100546,0.0005290644],"about_ca_topic_score_codex":0.00022352247,"about_ca_topic_score_gemma":0.00044826008,"teacher_disagreement_score":0.7877513,"about_ca_system_score_codex":0.000078295285,"about_ca_system_score_gemma":0.0001816487,"threshold_uncertainty_score":0.4636766},"labels":[],"label_agreement":null},{"id":"W3210129212","doi":"10.1002/sim.9246","title":"Weighted generalized estimating equations and unified estimation for longitudinal data with nonmonotone missing data patterns","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Missing data; Estimator; Covariate; Generalized estimating equation; Estimating equations; Computer science; Statistics; Mathematics","score_opus":0.22131465097394634,"score_gpt":0.4628701982297937,"score_spread":0.24155554725584735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210129212","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006213225,0.00008845728,0.9942839,0.0009892373,0.00014815519,0.00036070234,0.0034032871,0.00002920488,0.00007574348],"genre_scores_gemma":[0.0088065425,0.000026738977,0.98581797,0.000082748695,0.00014327382,0.000022561651,0.0050412132,0.000029472461,0.000029478551],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980709,0.00016305722,0.00058763265,0.0006020953,0.00031447044,0.0002618698],"domain_scores_gemma":[0.9908352,0.0074987067,0.00021753818,0.0011182291,0.0002194439,0.000110902336],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012303316,0.00019076251,0.00046846215,0.00008467794,0.00015281892,0.000060957304,0.0003357474,0.000057368856,0.00013882494],"category_scores_gemma":[0.017063348,0.00015191534,0.0000052945784,0.00022557475,0.00017673831,0.00016215374,0.00025023177,0.00018025076,6.8156226e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007807689,0.00012164723,0.0017239999,0.0009626677,0.00008132248,0.00016042842,0.00045847587,0.000021470927,0.00016842097,0.7551112,0.002568188,0.23854406],"study_design_scores_gemma":[0.0011127286,0.000066915054,0.0009638664,0.00048128713,0.00016124497,0.00001999485,0.00009009681,0.5923117,0.000021227097,0.40461493,0.000033129203,0.00012291543],"about_ca_topic_score_codex":0.00014333856,"about_ca_topic_score_gemma":0.00043542372,"teacher_disagreement_score":0.5922902,"about_ca_system_score_codex":0.000030868174,"about_ca_system_score_gemma":0.0001499372,"threshold_uncertainty_score":0.99121636},"labels":[],"label_agreement":null},{"id":"W3212678746","doi":"10.1002/sim.9233","title":"Estimation of standard deviations and inverse‐variance weights from an observed range","year":2021,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Statistics; Standard deviation; Standard error; Contrast (vision); Variance (accounting); Mathematics; Sample size determination; Inverse; Range (aeronautics); Mean squared error; Population variance; Sample (material); Econometrics; Population; Computer science; Medicine","score_opus":0.6336011764395778,"score_gpt":0.6039632280292192,"score_spread":0.029637948410358605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212678746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004337767,0.47093943,0.5229176,0.000044989807,0.0005350604,0.0006640032,0.0047619725,0.000020824962,0.0001117543],"genre_scores_gemma":[0.0000010145725,0.48812672,0.51124924,0.00003069328,0.00017753588,0.000040788746,0.0003096709,0.00003756952,0.000026773927],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99333274,0.0023360401,0.0027418758,0.0006288719,0.0006995628,0.00026091546],"domain_scores_gemma":[0.91774905,0.07987754,0.0011965248,0.00072473305,0.0002593885,0.00019275644],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0035134472,0.00043812828,0.004462377,0.00020413299,0.000053664302,0.000020855072,0.00030256517,0.00043347772,0.0007171771],"category_scores_gemma":[0.15988487,0.00034613747,0.00009396333,0.0005005224,0.0004871917,0.000064561915,0.0001078139,0.0006597833,0.000004194544],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018104976,0.00007389076,0.000012081857,0.009223619,0.0001431722,0.00007425913,0.00023741207,9.270612e-7,1.10178725e-7,0.30784768,0.0021914307,0.68017733],"study_design_scores_gemma":[0.0013096915,0.00022162935,0.000037084996,0.029232424,0.0020466547,0.0000052775963,0.000054649958,0.0011918935,5.9957273e-7,0.92777085,0.037816964,0.00031227022],"about_ca_topic_score_codex":0.00011960338,"about_ca_topic_score_gemma":0.00020582258,"teacher_disagreement_score":0.67986506,"about_ca_system_score_codex":0.00014374446,"about_ca_system_score_gemma":0.00036280075,"threshold_uncertainty_score":0.9998991},"labels":[],"label_agreement":null},{"id":"W3216992363","doi":"10.1002/sim.9259","title":"Using fractional polynomials and restricted cubic splines to model non‐proportional hazards or time‐varying covariate effects in the Cox regression model","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Health Network; Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences; Heart and Stroke Foundation of Canada","keywords":"Covariate; Proportional hazards model; Mathematics; Statistics; Regression; Regression analysis; Applied mathematics; Econometrics","score_opus":0.16597718893485655,"score_gpt":0.48343134940256793,"score_spread":0.31745416046771135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216992363","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01734204,0.000069042915,0.98091763,0.00064054935,0.00012131988,0.0004483223,0.00023798317,0.000014823008,0.00020829533],"genre_scores_gemma":[0.04942383,0.00006154269,0.9492955,0.0006171115,0.00012906521,0.0000402955,0.00006337038,0.000031316067,0.00033792673],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977832,0.00026016147,0.0006804693,0.0003944832,0.0005705064,0.00031116992],"domain_scores_gemma":[0.99437404,0.0048537767,0.0001804432,0.0002583277,0.00021086188,0.00012253055],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010151956,0.00022840369,0.00055565557,0.00017006492,0.00013507737,0.00002009289,0.00011619362,0.00010516851,0.000050634902],"category_scores_gemma":[0.010721598,0.00014547724,0.000017911854,0.00039366074,0.0001233535,0.000075820935,0.000087601526,0.00037945618,0.0000015166681],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014999053,0.00059476565,0.00017330098,0.001111535,0.00007738042,0.0018742622,0.0038362523,0.31737694,0.05581267,0.5882601,0.009005663,0.020377235],"study_design_scores_gemma":[0.0008035098,0.000053924137,0.00015280642,0.00040603176,0.00004178796,0.000031980922,0.000046507794,0.57655257,0.00009856888,0.4217014,0.0000075318353,0.000103336875],"about_ca_topic_score_codex":0.000045959736,"about_ca_topic_score_gemma":0.00004200691,"teacher_disagreement_score":0.25917566,"about_ca_system_score_codex":0.000102156555,"about_ca_system_score_gemma":0.00032243275,"threshold_uncertainty_score":0.9976115},"labels":[],"label_agreement":null},{"id":"W4200422816","doi":"10.1002/sim.9270","title":"Methods to assess evidence consistency in <scp>dose‐response</scp> model based network <scp>meta‐analysis</scp>","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Mental Health Research Topics","field":"Psychology","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; Department of Health and Social Care; University of Bristol; National Institute for Health and Care Research; University Hospitals Bristol NHS Foundation Trust; Pfizer","keywords":"Consistency (knowledge bases); Function (biology); Meta-analysis; Computer science; Node (physics); Mathematics; Medicine; Artificial intelligence; Biology","score_opus":0.34084893848496445,"score_gpt":0.5589487149081261,"score_spread":0.2180997764231617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200422816","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012707082,0.013771771,0.96120584,0.003064711,0.0010839929,0.0011805494,0.00030525163,0.00005947515,0.0066213463],"genre_scores_gemma":[0.083965585,0.00047324598,0.8898868,0.009761687,0.00034312927,0.00063114817,0.00021114021,0.00009560112,0.01463164],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9869652,0.0076089175,0.0015644798,0.0011322415,0.0012324868,0.0014966866],"domain_scores_gemma":[0.9451988,0.051990543,0.00028094827,0.0013204586,0.00048467334,0.00072463433],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014749747,0.00043494816,0.0018159715,0.000959917,0.00014551253,0.00003935629,0.0006562092,0.00028311388,0.0011176036],"category_scores_gemma":[0.042643037,0.00040582396,0.0001722145,0.0042237663,0.00037197725,0.000081134145,0.00023819643,0.0012423439,0.00010021529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011158836,0.002790337,0.081587225,0.003151823,0.023424566,0.017534744,0.029280843,0.16346742,0.0029047276,0.18100485,0.46120444,0.032533135],"study_design_scores_gemma":[0.009732348,0.0032113853,0.27960292,0.0015965838,0.027750704,0.0001032739,0.017408708,0.5348151,0.00065905985,0.08819191,0.036289543,0.00063845573],"about_ca_topic_score_codex":0.00064573024,"about_ca_topic_score_gemma":0.0022741056,"teacher_disagreement_score":0.4249149,"about_ca_system_score_codex":0.0003879218,"about_ca_system_score_gemma":0.0010403472,"threshold_uncertainty_score":0.99983937},"labels":[],"label_agreement":null},{"id":"W4200447663","doi":"10.1002/sim.9285","title":"Ranked set sampling in finite populations with bivariate responses: An application to an osteoporosis study","year":2021,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bivariate analysis; Statistics; Univariate; Estimator; Mathematics; Sampling (signal processing); Sampling design; Poisson distribution; Sample size determination; Poisson regression; Population; Econometrics; Multivariate statistics; Computer science; Medicine","score_opus":0.2533609540721423,"score_gpt":0.5232595687678369,"score_spread":0.26989861469569454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200447663","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09494869,0.000010763784,0.9034974,0.00020668523,0.00006862732,0.0007798974,0.00037867518,0.00003437082,0.000074911695],"genre_scores_gemma":[0.33921212,0.000004133162,0.6602195,0.00014277193,0.0000424624,0.00012179507,0.0001838203,0.000029009816,0.00004442288],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99755126,0.00059480517,0.0006804495,0.00050676113,0.000381277,0.0002854303],"domain_scores_gemma":[0.99615836,0.0026963572,0.00012656843,0.00059259066,0.00023132119,0.00019477929],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014895458,0.00019368598,0.0004900925,0.00023419314,0.000088619236,0.000018812352,0.00013699758,0.000054997177,0.000060632243],"category_scores_gemma":[0.006058837,0.00016484926,0.0000080521795,0.000696565,0.00006425646,0.000098781136,0.00004278868,0.0002495499,0.000002365409],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013413331,0.0020358257,0.014830912,0.00021925484,0.000052279465,0.00045693267,0.049779233,0.014838223,0.00198619,0.86447924,0.000105578925,0.049875006],"study_design_scores_gemma":[0.002834297,0.0014291472,0.03045903,0.00019966168,0.00009863907,0.0000075511093,0.011796515,0.03347313,0.000022093656,0.9192941,0.000080368045,0.00030546717],"about_ca_topic_score_codex":0.00038161667,"about_ca_topic_score_gemma":0.009136799,"teacher_disagreement_score":0.24426343,"about_ca_system_score_codex":0.00009029983,"about_ca_system_score_gemma":0.000081193575,"threshold_uncertainty_score":0.7253431},"labels":[],"label_agreement":null},{"id":"W4200631872","doi":"10.1002/sim.9439","title":"Using principal stratification in analysis of clinical trials","year":2022,"lang":"en","type":"preprint","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bayer (Canada)","funders":"","keywords":"Principal (computer security); Computer science; Variety (cybernetics); Observational study; Set (abstract data type); Addendum; Key (lock); Data science; Stratification (seeds); Management science; Machine learning; Risk analysis (engineering); Artificial intelligence; Mathematics; Engineering; Statistics; Medicine; Programming language; Biology","score_opus":0.9143698492728977,"score_gpt":0.7492055652700645,"score_spread":0.16516428400283312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200631872","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030293917,0.00015175325,0.9579756,0.0002059761,0.003484231,0.0020059228,0.004324238,0.000032446093,0.0015259158],"genre_scores_gemma":[0.053052306,0.00033794748,0.94554174,0.0000650581,0.00049228943,0.00011717025,0.00027836757,0.000052822532,0.00006227599],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95695114,0.02266446,0.016767139,0.0013154163,0.0018188283,0.0004829932],"domain_scores_gemma":[0.7335626,0.25951988,0.0051143304,0.0013434016,0.00029161855,0.00016821177],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12264726,0.00042691518,0.007768412,0.0015097834,0.00003562956,0.000014772293,0.00076434074,0.0006518047,0.004294911],"category_scores_gemma":[0.7008931,0.00037392715,0.00043501623,0.0018262134,0.0006704637,0.000020543275,0.0006515215,0.002806242,0.0000010372654],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009830398,0.0016429914,0.057725206,0.0021521833,0.0035271037,0.00023446692,0.0015250212,0.009093306,0.00008156372,0.88359594,0.0014669601,0.037972186],"study_design_scores_gemma":[0.0019199917,0.00018625666,0.027375618,0.0004769447,0.004826011,4.1539963e-7,0.00033710495,0.0903461,0.0000062512195,0.87420225,0.00004852608,0.00027450008],"about_ca_topic_score_codex":0.0006187393,"about_ca_topic_score_gemma":0.0005772582,"teacher_disagreement_score":0.5782458,"about_ca_system_score_codex":0.00028832172,"about_ca_system_score_gemma":0.00062505685,"threshold_uncertainty_score":0.99987125},"labels":[],"label_agreement":null},{"id":"W4205106986","doi":"10.1002/sim.8607","title":"Issue Information","year":2021,"lang":"en","type":"paratext","venue":"Statistics in Medicine","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institutes of Health","keywords":"Computer science; Citation; Information retrieval; Library science","score_opus":0.023449971841725304,"score_gpt":0.3298981782937842,"score_spread":0.3064482064520589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205106986","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000062749896,0.0013306605,0.25136244,0.00021413017,0.035718054,0.00031287136,0.00068198494,0.00009968416,0.7102174],"genre_scores_gemma":[0.0023999682,0.024770131,0.02353834,0.0028720382,0.02073751,0.0002217871,0.08390285,0.00024205669,0.8413153],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989256,0.000039374416,0.0004539762,0.0000915856,0.00033743063,0.00015201041],"domain_scores_gemma":[0.99953765,0.00006594071,0.00005652857,0.00017760183,0.000109998386,0.00005229571],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00022612771,0.00016958459,0.0003036611,0.00025979523,0.000023164212,0.00001912059,0.000084975,0.00018200756,0.37564665],"category_scores_gemma":[0.00016931127,0.00017079161,0.000012393651,0.00015215698,0.00005092178,0.00008687812,0.000012001485,0.00040620205,0.107536145],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011808255,0.0000026977436,0.0000010318483,0.000397195,0.000010382346,0.0000030713315,0.0012168459,0.0066995723,0.000024745135,0.00003887266,0.97864187,0.012962539],"study_design_scores_gemma":[0.0003623881,0.000022919738,0.00024770605,0.00033194383,0.000017415909,0.0000016940223,0.00034892117,0.015788738,0.0000050229996,0.0001336911,0.98257875,0.00016082273],"about_ca_topic_score_codex":0.0000053205235,"about_ca_topic_score_gemma":0.00004937478,"teacher_disagreement_score":0.2681105,"about_ca_system_score_codex":0.00019260467,"about_ca_system_score_gemma":0.00004788055,"threshold_uncertainty_score":0.89315873},"labels":[],"label_agreement":null},{"id":"W4205333182","doi":"10.1002/sim.9320","title":"Profile‐likelihood Bayesian model averaging for two‐sample summary data Mendelian randomization in the presence of horizontal pleiotropy","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; Medical Research Council; University of Bristol; University of Exeter; Bureau for Economic Growth, Education, and Environment, United States Agency for International Development","keywords":"Mendelian randomization; Posterior probability; Bayesian probability; Computer science; Pleiotropy; Econometrics; Sample size determination; Bayesian inference; Statistics; Mathematics; Artificial intelligence; Biology; Genetic variants; Genetics","score_opus":0.02507433636254932,"score_gpt":0.3259323980784495,"score_spread":0.3008580617159002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205333182","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016375454,0.0003272628,0.9788685,0.0008631028,0.00015269882,0.00066880195,0.0025407374,0.0000025133818,0.00020093877],"genre_scores_gemma":[0.9029718,0.00016677966,0.08853544,0.00030275053,0.00011876277,0.00017925254,0.007670412,0.000013784224,0.000040995048],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856895,0.00031051753,0.0004287896,0.00028621993,0.0001821845,0.00022333626],"domain_scores_gemma":[0.9988846,0.0004549497,0.00016440423,0.00041472877,0.0000557289,0.00002554548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020993138,0.0000958024,0.00023608711,0.00007025278,0.00009155505,0.0000028686584,0.00042959178,0.00003852503,0.000023606875],"category_scores_gemma":[0.0020974337,0.00007720918,0.00001682078,0.00013643329,0.000075502125,0.000003057108,0.00019878328,0.00013019278,8.767035e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004337022,0.001149188,0.153272,0.00049525476,0.00037072622,0.000029348785,0.009055636,0.26719683,0.09957591,0.038653433,0.37850803,0.04735662],"study_design_scores_gemma":[0.0067944536,0.000522581,0.0019298552,0.00002285866,0.000041417392,0.000004396574,0.0016918961,0.96806884,0.00013302293,0.018985888,0.0016614146,0.00014337861],"about_ca_topic_score_codex":0.00048449374,"about_ca_topic_score_gemma":0.0007503878,"teacher_disagreement_score":0.89033306,"about_ca_system_score_codex":0.000029095352,"about_ca_system_score_gemma":0.00012022553,"threshold_uncertainty_score":0.3148499},"labels":[],"label_agreement":null},{"id":"W4206399182","doi":"10.1002/sim.8615","title":"Issue Information","year":2021,"lang":"en","type":"paratext","venue":"Statistics in Medicine","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institutes of Health","keywords":"Computer science; Citation; Information retrieval; World Wide Web","score_opus":0.023449971841725304,"score_gpt":0.3298981782937842,"score_spread":0.3064482064520589,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206399182","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000062749896,0.0013306605,0.25136244,0.00021413017,0.035718054,0.00031287136,0.00068198494,0.00009968416,0.7102174],"genre_scores_gemma":[0.0023999682,0.024770131,0.02353834,0.0028720382,0.02073751,0.0002217871,0.08390285,0.00024205669,0.8413153],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989256,0.000039374416,0.0004539762,0.0000915856,0.00033743063,0.00015201041],"domain_scores_gemma":[0.99953765,0.00006594071,0.00005652857,0.00017760183,0.000109998386,0.00005229571],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00022612771,0.00016958459,0.0003036611,0.00025979523,0.000023164212,0.00001912059,0.000084975,0.00018200756,0.37564665],"category_scores_gemma":[0.00016931127,0.00017079161,0.000012393651,0.00015215698,0.00005092178,0.00008687812,0.000012001485,0.00040620205,0.107536145],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011808255,0.0000026977436,0.0000010318483,0.000397195,0.000010382346,0.0000030713315,0.0012168459,0.0066995723,0.000024745135,0.00003887266,0.97864187,0.012962539],"study_design_scores_gemma":[0.0003623881,0.000022919738,0.00024770605,0.00033194383,0.000017415909,0.0000016940223,0.00034892117,0.015788738,0.0000050229996,0.0001336911,0.98257875,0.00016082273],"about_ca_topic_score_codex":0.0000053205235,"about_ca_topic_score_gemma":0.00004937478,"teacher_disagreement_score":0.2681105,"about_ca_system_score_codex":0.00019260467,"about_ca_system_score_gemma":0.00004788055,"threshold_uncertainty_score":0.89315873},"labels":[],"label_agreement":null},{"id":"W4206839457","doi":"10.1002/sim.7888","title":"Issue Information","year":2019,"lang":"en","type":"paratext","venue":"Statistics in Medicine","topic":"Diverse Scientific and Economic Studies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institutes of Health","keywords":"Computer science; Statistics; Mathematics","score_opus":0.0312994404200627,"score_gpt":0.2620493222487607,"score_spread":0.23074988182869802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206839457","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000047715366,0.0025677057,0.009278106,0.00032088044,0.042981923,0.0002614975,0.009570515,0.000007871264,0.93500674],"genre_scores_gemma":[0.00021899455,0.0032098019,0.0012363952,0.0008129823,0.0005335878,0.000018136978,0.001617332,0.000017732938,0.992335],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982848,0.000008522121,0.0010155691,0.00033477193,0.000057151887,0.00029914753],"domain_scores_gemma":[0.99884,0.00011128699,0.0005924495,0.00035558967,0.000046517715,0.000054183492],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006535346,0.00021877998,0.0008658475,0.00059052603,0.000046087374,0.00004035056,0.00028049396,0.00017406496,0.18577208],"category_scores_gemma":[0.00032951692,0.00023221252,0.000033295193,0.00018661006,0.0001806775,0.0001857846,0.00009483718,0.00029689816,0.6776106],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005292246,0.000008283414,0.00011396384,0.00016600278,0.000033714507,0.0000011763918,0.0010116115,0.00009106934,3.5064566e-8,0.06328193,0.93461597,0.0006709375],"study_design_scores_gemma":[0.00066477794,0.000047277084,0.00017296379,0.0001059998,0.0000058969736,5.4173694e-7,0.0005489261,0.0005851708,2.2105144e-7,0.004875947,0.9927576,0.00023465019],"about_ca_topic_score_codex":0.0006237751,"about_ca_topic_score_gemma":0.000017029633,"teacher_disagreement_score":0.49183849,"about_ca_system_score_codex":0.00019443639,"about_ca_system_score_gemma":0.00003447095,"threshold_uncertainty_score":0.9469352},"labels":[],"label_agreement":null},{"id":"W4206897392","doi":"10.1002/sim.9317","title":"Response adaptive intervention allocation in stepped‐wedge cluster randomized trials","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"Intervention (counseling); Randomized controlled trial; Cluster (spacecraft); Adaptability; Computer science; Medicine; Cluster randomised controlled trial; Research design; Risk analysis (engineering); Reliability engineering; Operations management; Statistics; Mathematics; Engineering; Nursing; Surgery","score_opus":0.5051541458839005,"score_gpt":0.5887984476152415,"score_spread":0.08364430173134096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206897392","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00686227,0.00019316676,0.98349184,0.0025279596,0.001994271,0.003753854,0.00046033037,0.000046553403,0.00066975545],"genre_scores_gemma":[0.124927826,0.00007358928,0.8715321,0.00072386774,0.0002638263,0.0014241533,0.000050053306,0.000061539875,0.0009430399],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9300193,0.061969593,0.00556605,0.00067045365,0.0012759751,0.00049860886],"domain_scores_gemma":[0.63574773,0.3626168,0.0009962231,0.00039841377,0.00014424296,0.00009654431],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.14169292,0.00026041837,0.00270409,0.00054335,0.00008313631,0.000013107983,0.00033408494,0.00011403248,0.0030642226],"category_scores_gemma":[0.68957555,0.00021413251,0.00015772019,0.0006173889,0.000451469,0.00004751842,0.00022465452,0.0008388166,0.000014662091],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.45750085,0.0007589312,0.00008295803,0.00018272034,0.00016105929,0.00019044879,0.0028527586,0.00013490274,0.00013608228,0.47978234,0.02920063,0.02901633],"study_design_scores_gemma":[0.17626363,0.0006208569,0.00028772093,0.0002644007,0.000178215,0.0000051652482,0.0012244068,0.007475678,0.000019577843,0.81316304,0.00032167707,0.00017561625],"about_ca_topic_score_codex":0.00013864432,"about_ca_topic_score_gemma":0.00011759516,"teacher_disagreement_score":0.5478826,"about_ca_system_score_codex":0.00045323966,"about_ca_system_score_gemma":0.00010403233,"threshold_uncertainty_score":0.99784714},"labels":[],"label_agreement":null},{"id":"W4210609813","doi":"10.1002/sim.9318","title":"Preserving data privacy when using multi‐site data to estimate individualized treatment rules","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Pooling; Robustness (evolution); Data mining; Covariate; Regression; Context (archaeology); Confidentiality; Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.5117738302480719,"score_gpt":0.5546970299518682,"score_spread":0.04292319970379632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210609813","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018249333,0.0001912817,0.9669385,0.0005098828,0.00018353586,0.0011078332,0.012419345,0.00021761621,0.00018270465],"genre_scores_gemma":[0.004022254,0.0000434904,0.9900901,0.00016328445,0.00008012776,0.000086198816,0.005258516,0.0000639212,0.00019214285],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973347,0.00021183505,0.00069005135,0.0007042029,0.00064403453,0.00041516722],"domain_scores_gemma":[0.9949835,0.0013752969,0.0002616292,0.0031769793,0.00006692959,0.00013565901],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015452466,0.00027868745,0.0005721751,0.0002570359,0.0002000146,0.000027049618,0.0020565954,0.0000401921,0.00074019714],"category_scores_gemma":[0.006414182,0.0002459992,0.000009034956,0.00025219328,0.00010463068,0.00025320917,0.005207267,0.00030129333,0.000006290182],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083430856,0.0042567947,0.034812562,0.0021475167,0.0010015042,0.0032181386,0.097135544,0.0029113346,0.021259818,0.3288509,0.33390132,0.16967027],"study_design_scores_gemma":[0.0041168146,0.000856064,0.00134198,0.00067482464,0.00044820094,0.00006203958,0.001336235,0.31494668,0.00022137638,0.63328147,0.0419124,0.0008019256],"about_ca_topic_score_codex":0.0010445119,"about_ca_topic_score_gemma":0.000587451,"teacher_disagreement_score":0.31203532,"about_ca_system_score_codex":0.00038367196,"about_ca_system_score_gemma":0.00012680831,"threshold_uncertainty_score":0.9999992},"labels":[],"label_agreement":null},{"id":"W4214682600","doi":"10.1002/sim.8233","title":"Issue Information","year":2020,"lang":"en","type":"paratext","venue":"Statistics in Medicine","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Citation; Information retrieval; Library science","score_opus":0.026466283137171996,"score_gpt":0.32556839600590054,"score_spread":0.29910211286872856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214682600","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019745605,0.000463199,0.31873867,0.00061510847,0.024520861,0.00041536137,0.00085293106,0.00015307541,0.65422106],"genre_scores_gemma":[0.010754853,0.03512528,0.05291173,0.0152618345,0.065277405,0.0005365023,0.13573594,0.0006806443,0.6837158],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989638,0.00002994883,0.00045008055,0.00008966076,0.00032726405,0.00013925605],"domain_scores_gemma":[0.99962366,0.00005534566,0.000060686136,0.0001278937,0.00006011502,0.00007228003],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015794249,0.0001751958,0.000299258,0.00021603762,0.000020650765,0.000014613786,0.00010489384,0.00015672582,0.24040782],"category_scores_gemma":[0.00016784665,0.00017227567,0.000011105992,0.00014275832,0.000052461473,0.000088002475,0.000011431958,0.00044083863,0.24197179],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026081782,0.0000015848478,7.852774e-7,0.00041996266,0.000008985471,0.0000017583873,0.0018322587,0.005575742,0.000020003507,0.000041691197,0.98066914,0.011425482],"study_design_scores_gemma":[0.00037040314,0.00004307523,0.0001608226,0.00017031268,0.00001649474,6.7834844e-7,0.00020009172,0.037248243,0.0000026169448,0.00018586451,0.9614482,0.00015321067],"about_ca_topic_score_codex":0.0000038150133,"about_ca_topic_score_gemma":0.000017786568,"teacher_disagreement_score":0.26582694,"about_ca_system_score_codex":0.00015381213,"about_ca_system_score_gemma":0.000031653148,"threshold_uncertainty_score":0.7602865},"labels":[],"label_agreement":null},{"id":"W4220708167","doi":"10.1002/sim.9049","title":"Issue Information","year":2022,"lang":"en","type":"paratext","venue":"Statistics in Medicine","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science","score_opus":0.022882675844517697,"score_gpt":0.3267985601856628,"score_spread":0.3039158843411451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220708167","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000047304704,0.00062007934,0.09803207,0.00018345691,0.03956136,0.0004428341,0.0013369649,0.00012826225,0.8596477],"genre_scores_gemma":[0.0020490398,0.013462325,0.009373216,0.0028219754,0.013188544,0.0005648679,0.08115395,0.00025652687,0.87712955],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99883336,0.00004821866,0.0004449503,0.000087302695,0.0004325324,0.00015364077],"domain_scores_gemma":[0.9996015,0.00007066705,0.00006652031,0.00016966645,0.000045909364,0.000045728844],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00032472445,0.00016371632,0.00026471613,0.00037207134,0.00004480391,0.000011957555,0.00012279549,0.000108357206,0.75545573],"category_scores_gemma":[0.00010980821,0.00016970163,0.000011422526,0.00016021715,0.000047995567,0.000084367806,0.000019857089,0.0005406686,0.11886545],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002402147,0.0000028464083,9.917277e-7,0.00025854155,0.000008355024,0.000001661884,0.00154477,0.02058995,0.000008191029,0.000048593727,0.9648386,0.012695056],"study_design_scores_gemma":[0.00036539644,0.00004672989,0.00017896907,0.00007366303,0.000014624115,0.0000012712233,0.000383272,0.0182923,7.7841935e-7,0.00018599704,0.980303,0.00015400058],"about_ca_topic_score_codex":0.000007835934,"about_ca_topic_score_gemma":0.000022683178,"teacher_disagreement_score":0.63659024,"about_ca_system_score_codex":0.0003357609,"about_ca_system_score_gemma":0.000035823778,"threshold_uncertainty_score":0.8818206},"labels":[],"label_agreement":null},{"id":"W4220757114","doi":"10.1002/sim.9367","title":"A mixture distribution approach for assessing genetic impact from twin study","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Statistics; Restricted maximum likelihood; Estimator; Bivariate analysis; Consistency (knowledge bases); Inference; Dizygotic twins; Twin study; Econometrics; Correlation; Monozygotic twin; Genetic correlation; Mathematics; Maximum likelihood; Computer science; Heritability; Biology; Genetics; Genetic variation; Artificial intelligence; Medicine","score_opus":0.030329456089655076,"score_gpt":0.36346358413950375,"score_spread":0.33313412804984865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220757114","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005371678,0.00027918955,0.9924501,0.00017033736,0.00037508877,0.00063827407,0.0005763793,0.000032840944,0.00010609926],"genre_scores_gemma":[0.3926799,0.0000016220184,0.606663,0.0001096602,0.000114967756,0.00010396786,0.00029675642,0.000008576048,0.000021550437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981066,0.00041566,0.0003346236,0.0004467289,0.0004206757,0.00027573053],"domain_scores_gemma":[0.9988337,0.00047230412,0.00012181412,0.00042538287,0.00006135173,0.00008543855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011756247,0.00015629269,0.00031921017,0.00008627432,0.00019830027,0.000050803246,0.00052924646,0.00003276969,0.000040206596],"category_scores_gemma":[0.00027719222,0.00012647096,0.000029148925,0.0004164773,0.00004439497,0.00007646305,0.00018859375,0.00031269406,2.87506e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012157487,0.0017450479,0.012475393,0.0000937853,0.00017258854,0.00032688593,0.015039884,0.0034852438,0.0006736428,0.11030881,0.04834224,0.8072149],"study_design_scores_gemma":[0.0025181011,0.0009926836,0.042208843,0.000019203451,0.00006469938,0.000017543929,0.0007752505,0.69253457,0.00001510431,0.260007,0.00056786026,0.0002791818],"about_ca_topic_score_codex":0.00030364783,"about_ca_topic_score_gemma":0.000010274074,"teacher_disagreement_score":0.8069357,"about_ca_system_score_codex":0.00018126534,"about_ca_system_score_gemma":0.00010326944,"threshold_uncertainty_score":0.5157336},"labels":[],"label_agreement":null},{"id":"W4220980829","doi":"10.1002/sim.9299","title":"Sensitivity to missing not at random dropout in clinical trials: Use and interpretation of the trimmed means estimator","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Health Technology Assessment Programme; Medical Research Council; Medical Research Council Canada; University of Exeter; University of Bristol; Department of Health and Social Care; Elizabeth Blackwell Institute for Health Research, University of Bristol; University Hospitals Bristol NHS Foundation Trust; UK Research and Innovation; National Institute for Health and Care Research; Cancer Research UK; Wellcome Trust","keywords":"Estimator; Missing data; Statistics; Dropout (neural networks); Randomized controlled trial; Mathematics; Econometrics; Sensitivity (control systems); Imputation (statistics); Medicine; Computer science; Internal medicine","score_opus":0.20896445576742714,"score_gpt":0.5020260976696712,"score_spread":0.29306164190224404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220980829","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05815848,0.0000191349,0.93908954,0.0012297097,0.0004297127,0.0006150429,0.000378157,0.00000801605,0.000072193456],"genre_scores_gemma":[0.54727113,0.000009411688,0.45231634,0.00030464114,0.000032036987,0.00002047101,0.0000062057134,0.000011994359,0.000027747958],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99202687,0.0055181053,0.001555974,0.00026921474,0.00044558028,0.00018426769],"domain_scores_gemma":[0.936992,0.062199652,0.0003898896,0.00025095037,0.000073523624,0.00009397428],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016687283,0.00013563209,0.0009867894,0.0001293794,0.000092278824,0.000011036797,0.00010475411,0.00004771057,0.00011869832],"category_scores_gemma":[0.19584647,0.00009249546,0.00004132465,0.00025894208,0.00029705043,0.000028156737,0.00019038323,0.00040034205,5.27995e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006431876,0.00048617527,0.050149165,0.00057173683,0.000094028204,0.0002735619,0.010464079,0.000094515155,0.003355929,0.43830293,0.007681605,0.4820944],"study_design_scores_gemma":[0.008626631,0.0004978773,0.06907446,0.0007235364,0.00021605229,0.00003139036,0.00090866006,0.2866336,0.00022998589,0.6326577,0.00015706157,0.00024305213],"about_ca_topic_score_codex":0.00022522346,"about_ca_topic_score_gemma":0.0003486165,"teacher_disagreement_score":0.48911268,"about_ca_system_score_codex":0.00011327939,"about_ca_system_score_gemma":0.000076830605,"threshold_uncertainty_score":0.8109273},"labels":[],"label_agreement":null},{"id":"W4221004841","doi":"10.1002/sim.9364","title":"Assessing complier average causal effects from longitudinal trials with multiple endpoints and treatment noncompliance: An application to a study of Arthritis Health Journal","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Research Canada; Simon Fraser University","funders":"National Cancer Institute; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Econometrics; Medicine; Clinical trial; Arthritis; Internal medicine; Economics","score_opus":0.19042324253128365,"score_gpt":0.49042503604727183,"score_spread":0.3000017935159882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221004841","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4423274,0.00008701205,0.5561706,0.000059558613,0.000049569422,0.0011435171,0.00012997843,0.000022528251,0.00000984962],"genre_scores_gemma":[0.7146567,0.000048164376,0.28488842,0.00004816499,0.00006330235,0.00022636761,0.00004629995,0.00002020987,0.000002384287],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973174,0.0007850514,0.0008549802,0.00031669057,0.00050612236,0.000219811],"domain_scores_gemma":[0.9959835,0.0028297657,0.0006327836,0.0002921132,0.00009631267,0.00016554493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018025095,0.000199066,0.0010076044,0.00017305302,0.00022613308,0.00002253016,0.000120506025,0.000021629758,0.000060978207],"category_scores_gemma":[0.0008876904,0.00015462363,0.000011448372,0.0002019429,0.00008014182,0.00009580535,0.000063863685,0.00027841487,2.7915698e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017824507,0.006795337,0.10802416,0.00029209102,0.0004269247,0.0010502422,0.053241193,0.0012787423,0.008076456,0.013195454,0.0007855359,0.80505145],"study_design_scores_gemma":[0.041278176,0.077840045,0.33386344,0.0023504503,0.0004117771,0.00043126647,0.035399813,0.009346949,0.0020933484,0.49575916,0.00016177217,0.0010638103],"about_ca_topic_score_codex":0.0008284311,"about_ca_topic_score_gemma":0.0016308579,"teacher_disagreement_score":0.8039876,"about_ca_system_score_codex":0.00036607945,"about_ca_system_score_gemma":0.00008964897,"threshold_uncertainty_score":0.63053685},"labels":[],"label_agreement":null},{"id":"W4221129397","doi":"10.1002/sim.9386","title":"Multiply robust subgroup analysis based on a single‐index threshold linear marginal model for longitudinal data with dropouts","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Natural Science Foundation of China","keywords":"Longitudinal data; Statistics; Index (typography); Mathematics; Single-index model; Linear model; Marginal model; Subgroup analysis; Econometrics; Computer science; Applied mathematics; Regression analysis; Data mining","score_opus":0.22592500866140303,"score_gpt":0.4120618597321267,"score_spread":0.1861368510707237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221129397","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001185702,0.000017927496,0.99229383,0.00042291664,0.00010552946,0.000517685,0.0049936245,0.000037277856,0.0004254978],"genre_scores_gemma":[0.36970422,0.0000022573538,0.6290219,0.00024692362,0.00007192019,0.000086460335,0.0006845037,0.00003459761,0.00014721954],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705374,0.00015733553,0.0006258719,0.00072315964,0.000992545,0.0004473188],"domain_scores_gemma":[0.9937482,0.0045981524,0.00024477378,0.0010726391,0.00018391968,0.00015232597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018749093,0.000293053,0.000756815,0.00041104306,0.00021204924,0.000019239786,0.0006084273,0.000052151685,0.0006254678],"category_scores_gemma":[0.0039763786,0.00022675503,0.000038770326,0.0008475802,0.00026794092,0.000041261836,0.00018590644,0.00050044735,0.000001064323],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032218688,0.0019420197,0.028727263,0.0006439752,0.000601469,0.00044682572,0.00091895845,0.4937172,0.00005472371,0.44976124,0.013696691,0.00626776],"study_design_scores_gemma":[0.0023702986,0.0012283506,0.0016099846,0.000082030376,0.0007131814,0.0000038459257,0.00022276596,0.9242535,0.000002487595,0.06918858,0.00006681264,0.00025815316],"about_ca_topic_score_codex":0.0001243992,"about_ca_topic_score_gemma":0.00055559777,"teacher_disagreement_score":0.4305363,"about_ca_system_score_codex":0.00016731735,"about_ca_system_score_gemma":0.00013542763,"threshold_uncertainty_score":0.9246802},"labels":[],"label_agreement":null},{"id":"W4224718928","doi":"10.1002/sim.9417","title":"Variable selection in semiparametric regression models for longitudinal data with informative observation times","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Semiparametric regression; Covariate; Estimator; Regression; Semiparametric model; Regression analysis; Statistics; Feature selection; Econometrics; Outcome (game theory); Flexibility (engineering); Computer science; Mathematics; Artificial intelligence","score_opus":0.20494563651052067,"score_gpt":0.43039976701503624,"score_spread":0.22545413050451557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224718928","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011249104,0.000041388575,0.99625176,0.00011740776,0.00009969272,0.0005509285,0.0007180879,0.000020907499,0.0010749372],"genre_scores_gemma":[0.033141956,0.000011545235,0.96587867,0.00009049483,0.00004057039,0.00016583219,0.00045322522,0.000017462191,0.00020022874],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983074,0.00017353444,0.0005311555,0.00028597962,0.0004572824,0.0002446382],"domain_scores_gemma":[0.9946539,0.0046462063,0.0002345838,0.00026188974,0.00015681698,0.00004664994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021221119,0.0001431862,0.0003640677,0.00030183847,0.00012274453,0.000011479831,0.0002597138,0.000039430066,0.00029964437],"category_scores_gemma":[0.0066867503,0.00010758023,0.000005364964,0.0011428671,0.000072987685,0.0001883562,0.00013906414,0.00035369274,5.293373e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023597834,0.00010345848,0.0016764728,0.00021144238,0.000014533155,0.0000066003845,0.0009738543,0.0029794348,0.0000128609645,0.97579205,0.011699217,0.0062941196],"study_design_scores_gemma":[0.0008073915,0.00039603264,0.0011082552,0.00012087302,0.000023809433,0.000005353889,0.0004472151,0.45583016,0.0000043604814,0.54100204,0.00017301086,0.00008148323],"about_ca_topic_score_codex":0.00027696366,"about_ca_topic_score_gemma":0.00009511008,"teacher_disagreement_score":0.45285073,"about_ca_system_score_codex":0.0001849413,"about_ca_system_score_gemma":0.00012980617,"threshold_uncertainty_score":0.8005148},"labels":[],"label_agreement":null},{"id":"W4228997420","doi":"10.1002/sim.9429","title":"Analyzing cohort studies with interval‐censored data: A new model‐based linear rank‐type test","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"","keywords":"Statistics; Nonparametric statistics; Test statistic; Interval (graph theory); Hazard ratio; Mathematics; Hazard; Confidence interval; Rank (graph theory); Statistical hypothesis testing; Computer science; Econometrics","score_opus":0.21045099987993063,"score_gpt":0.4656520468827665,"score_spread":0.25520104700283586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4228997420","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012410146,0.0003104245,0.9955652,0.000776184,0.00024529628,0.0003826196,0.00090863416,0.000053525633,0.0005171261],"genre_scores_gemma":[0.040283,0.0001487812,0.9581182,0.00044759034,0.00014284882,0.000033035773,0.00023035968,0.00004551075,0.00055067433],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976054,0.00023257177,0.0006743138,0.0005003596,0.00064708607,0.0003402603],"domain_scores_gemma":[0.9912008,0.0073838183,0.00022111215,0.00080156414,0.00024848673,0.00014420677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017906959,0.00024845288,0.0007798951,0.000176019,0.00015080742,0.000010620636,0.00049749174,0.000032882017,0.0004631022],"category_scores_gemma":[0.02456269,0.0001845493,0.000013702073,0.00060141843,0.00030550527,0.000043787386,0.00032088114,0.0005443775,0.0000035542346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013900048,0.0010346181,0.034019765,0.0014997715,0.001094585,0.0012276206,0.0066814353,0.011059397,0.00039930048,0.58356225,0.3158699,0.04216137],"study_design_scores_gemma":[0.0022293013,0.0012229095,0.0006378667,0.00034535883,0.00044862903,0.000012398899,0.0010986351,0.7240219,0.000014775487,0.26885942,0.0008011307,0.00030767772],"about_ca_topic_score_codex":0.00017731663,"about_ca_topic_score_gemma":0.00016066688,"teacher_disagreement_score":0.7129625,"about_ca_system_score_codex":0.00013792663,"about_ca_system_score_gemma":0.00027040308,"threshold_uncertainty_score":0.98365384},"labels":[],"label_agreement":null},{"id":"W4231258378","doi":"10.1002/sim.822.abs","title":"Simultaneous modelling of operative mortality and long‐term survival after coronary artery bypass surgery","year":2001,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Simon Fraser University; University of Alberta","funders":"","keywords":"Covariate; Poisson regression; Proportional hazards model; Coronary artery bypass surgery; Medicine; Survival analysis; Accelerated failure time model; Bypass surgery; Term (time); Regression analysis; Poisson distribution; Artery; Surgery; Cardiology; Statistics; Mathematics; Population","score_opus":0.05708445331418451,"score_gpt":0.3571871711612406,"score_spread":0.3001027178470561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231258378","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9316966,0.0006443003,0.06363841,0.0001888245,0.00071369205,0.0003146134,0.00013333382,0.000025517418,0.0026446912],"genre_scores_gemma":[0.9946089,0.0036378372,0.0010961279,0.00013713456,0.0002116472,0.000021339229,0.000040719493,0.000015769141,0.00023057296],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99754655,0.0003765399,0.0006024066,0.00033214843,0.0007549229,0.00038745103],"domain_scores_gemma":[0.99784374,0.0014330067,0.00015669336,0.00024031916,0.00019841126,0.00012781774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001840415,0.00018252042,0.00050871633,0.00019339038,0.00013715237,0.000020729722,0.00014775946,0.00008142521,0.00021800368],"category_scores_gemma":[0.00043046416,0.00016935945,0.00003389168,0.00036057003,0.0012297973,0.00011333295,0.000050441307,0.00019306746,0.0000026325038],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000100649915,0.00010250884,0.9807883,0.000084329076,0.00009122435,0.0014582858,0.005903666,0.001138125,0.0000033417634,0.004482243,0.00013380355,0.0057135043],"study_design_scores_gemma":[0.0005859006,0.00008404817,0.98604333,0.00019854597,0.00010693055,0.000005279531,0.0023886417,0.0049001058,0.0000014809984,0.005113437,0.00030510954,0.00026719397],"about_ca_topic_score_codex":0.0039510163,"about_ca_topic_score_gemma":0.01950405,"teacher_disagreement_score":0.06291224,"about_ca_system_score_codex":0.00006886684,"about_ca_system_score_gemma":0.00007768479,"threshold_uncertainty_score":0.99838746},"labels":[],"label_agreement":null},{"id":"W4232296411","doi":"10.1002/sim.3571","title":"Correction","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Delphi Technique in Research","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children","funders":"","keywords":"Regret; Acknowledgement; Spirometry; Statistics; Psychology; Asthma; Medicine; Computer science; Mathematics; Internal medicine","score_opus":0.09469270781760097,"score_gpt":0.5091439785365464,"score_spread":0.4144512707189454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232296411","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014588151,0.00013251771,0.19217816,0.023646483,0.0022153705,0.00042636433,0.000008745175,0.0001832638,0.7797503],"genre_scores_gemma":[0.9756533,0.00039572432,0.014240902,0.00065820187,0.00048089845,0.000008019095,0.0000094760235,0.0000053306085,0.008548147],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99897766,0.0001165176,0.00014170771,0.00009808342,0.00046669974,0.00019935214],"domain_scores_gemma":[0.9992972,0.00042965714,0.000027264437,0.00009280125,0.00008789661,0.00006520387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014312342,0.00003945996,0.00008931151,0.000131637,0.00009410942,0.000008319372,0.00013962219,0.00004574564,0.0005357687],"category_scores_gemma":[0.0041447813,0.000036410514,0.000004639339,0.0003687246,0.0002755691,0.000033342116,0.000006892494,0.00019267006,0.000024485247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008586529,0.00002557405,0.0010663129,0.0000021394915,8.860098e-7,0.00004636428,0.00383891,0.0000023974205,0.000090209105,0.23747395,0.55015284,0.20729187],"study_design_scores_gemma":[0.0006094975,0.0005677426,0.055248894,0.00019999851,0.000007845247,0.000003775457,0.008221853,0.0015288634,0.0000830036,0.64294785,0.2903849,0.00019579707],"about_ca_topic_score_codex":0.0020296255,"about_ca_topic_score_gemma":0.0019757284,"teacher_disagreement_score":0.97419447,"about_ca_system_score_codex":0.00012462401,"about_ca_system_score_gemma":0.00007579722,"threshold_uncertainty_score":0.58662915},"labels":[],"label_agreement":null},{"id":"W4232817067","doi":"10.1002/sim.8559","title":"Authors' response","year":2020,"lang":"en","type":"letter","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"","keywords":"Library science; Lien; The arts; Citation; Sociology; Political science; Law; Computer science","score_opus":0.37558666727407897,"score_gpt":0.47380113509376554,"score_spread":0.09821446781968657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232817067","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039407063,0.0018408133,0.031101568,0.955344,0.0028539044,0.0007072243,0.0042153466,0.000066546425,0.0038311991],"genre_scores_gemma":[0.00022572617,0.0002227979,0.016144803,0.96679443,0.007045243,0.000106576,0.001277276,0.000118926444,0.008064231],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9900886,0.0014024838,0.006550984,0.001008623,0.00027766294,0.0006716697],"domain_scores_gemma":[0.98821026,0.007853132,0.0028401508,0.00079253665,0.00008159818,0.00022229571],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.02044385,0.00042806816,0.0024557267,0.0008405502,0.000106899795,0.00004016477,0.0005843319,0.0006833586,0.0032601643],"category_scores_gemma":[0.048798125,0.00052595686,0.0000712915,0.00036461296,0.00031124646,0.00010328936,0.00008273551,0.002409121,0.0047857044],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004596472,0.000011371439,0.0005459032,0.00073614396,0.000043720534,0.0003358991,0.0017788246,0.000004996319,3.2099538e-7,0.023960374,0.97247374,0.00006272876],"study_design_scores_gemma":[0.00080438424,0.00019094459,0.0011315614,0.00033408028,0.000013572452,0.000008249717,0.00021395733,0.0012370327,1.1343607e-7,0.110277064,0.8853807,0.00040833687],"about_ca_topic_score_codex":0.0008427582,"about_ca_topic_score_gemma":0.000071892806,"teacher_disagreement_score":0.08709305,"about_ca_system_score_codex":0.000932002,"about_ca_system_score_gemma":0.00031719502,"threshold_uncertainty_score":0.99989235},"labels":[],"label_agreement":null},{"id":"W4234921364","doi":"10.1002/sim.2781","title":"The performance of different propensity score methods for estimating marginal odds ratios","year":2006,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":244,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences","keywords":"Propensity score matching; Covariate; Statistics; Odds ratio; Odds; Estimator; Matching (statistics); Medicine; Mathematics; Logistic regression","score_opus":0.16363719544178307,"score_gpt":0.47372662365848633,"score_spread":0.31008942821670327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234921364","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052861143,0.00005312101,0.9456895,0.00013756694,0.00014367163,0.00071046146,0.000021087702,0.000042779775,0.00034065865],"genre_scores_gemma":[0.14389014,0.00002468122,0.8556389,0.000017510474,0.000103859005,0.00010504983,0.000020776673,0.000018213663,0.00018084158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998661,0.00011053021,0.0006178968,0.00015586543,0.00021950259,0.00023523546],"domain_scores_gemma":[0.99544847,0.003698763,0.00031565502,0.0002784863,0.00023152708,0.00002707009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014405828,0.00015330553,0.00039560627,0.00005870846,0.00011969706,0.0000078638295,0.00018791013,0.00004498881,0.000016752208],"category_scores_gemma":[0.0033466113,0.00009087888,0.000017414486,0.00011442308,0.00033339852,0.00004524119,0.000048911057,0.00019157064,2.6925795e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091860435,0.00007759775,0.0044587837,0.00073018565,0.000013911304,0.0000028436052,0.00026054203,0.00006668358,0.0061830566,0.91013944,0.0030943756,0.074880704],"study_design_scores_gemma":[0.0005251256,0.0005000319,0.004005472,0.00044439881,0.000043036955,0.000004917463,0.00005520105,0.11044669,0.013352848,0.8703821,0.000110871915,0.0001293549],"about_ca_topic_score_codex":0.000030006197,"about_ca_topic_score_gemma":0.00008847591,"teacher_disagreement_score":0.11038001,"about_ca_system_score_codex":0.00007043953,"about_ca_system_score_gemma":0.000034654855,"threshold_uncertainty_score":0.4006448},"labels":[],"label_agreement":null},{"id":"W4240995029","doi":"10.1002/sim.8237","title":"Issue Information","year":2020,"lang":"en","type":"paratext","venue":"Statistics in Medicine","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Information retrieval; Citation; Library science","score_opus":0.026466283137171996,"score_gpt":0.32556839600590054,"score_spread":0.29910211286872856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240995029","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019745605,0.000463199,0.31873867,0.00061510847,0.024520861,0.00041536137,0.00085293106,0.00015307541,0.65422106],"genre_scores_gemma":[0.010754853,0.03512528,0.05291173,0.0152618345,0.065277405,0.0005365023,0.13573594,0.0006806443,0.6837158],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989638,0.00002994883,0.00045008055,0.00008966076,0.00032726405,0.00013925605],"domain_scores_gemma":[0.99962366,0.00005534566,0.000060686136,0.0001278937,0.00006011502,0.00007228003],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015794249,0.0001751958,0.000299258,0.00021603762,0.000020650765,0.000014613786,0.00010489384,0.00015672582,0.24040782],"category_scores_gemma":[0.00016784665,0.00017227567,0.000011105992,0.00014275832,0.000052461473,0.000088002475,0.000011431958,0.00044083863,0.24197179],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026081782,0.0000015848478,7.852774e-7,0.00041996266,0.000008985471,0.0000017583873,0.0018322587,0.005575742,0.000020003507,0.000041691197,0.98066914,0.011425482],"study_design_scores_gemma":[0.00037040314,0.00004307523,0.0001608226,0.00017031268,0.00001649474,6.7834844e-7,0.00020009172,0.037248243,0.0000026169448,0.00018586451,0.9614482,0.00015321067],"about_ca_topic_score_codex":0.0000038150133,"about_ca_topic_score_gemma":0.000017786568,"teacher_disagreement_score":0.26582694,"about_ca_system_score_codex":0.00015381213,"about_ca_system_score_gemma":0.000031653148,"threshold_uncertainty_score":0.7602865},"labels":[],"label_agreement":null},{"id":"W4244582227","doi":"10.1002/sim.2880","title":"Authors' reply","year":2007,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Healthcare Policy and Management","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; University of Toronto","funders":"","keywords":"Biostatistics; Library science; Public health; Medical school; Health care; Medicine; Political science; Medical education; Nursing","score_opus":0.06658054735097424,"score_gpt":0.3524056193680195,"score_spread":0.28582507201704527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244582227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020328031,0.0010336572,0.7424325,0.022988582,0.0016686318,0.00027010124,0.0001651902,0.000041803036,0.22936675],"genre_scores_gemma":[0.95041317,0.000402214,0.031535715,0.010650676,0.00062881614,0.000010809461,0.000048816048,0.00002483269,0.0062849615],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987616,0.000009613588,0.0006681806,0.00021366762,0.00004273523,0.00030423366],"domain_scores_gemma":[0.99935913,0.0001545057,0.00013709159,0.00022392518,0.000017783914,0.00010758734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026795007,0.00007682733,0.000244848,0.00030411634,0.000034551795,0.000005024384,0.0001082934,0.000041389714,0.0005179259],"category_scores_gemma":[0.0010339756,0.00008205339,0.00001053318,0.00023675991,0.00007368832,0.000028187304,0.00002690481,0.00016374736,0.0002419599],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000686617,0.000016478745,0.0057986625,0.00003859246,0.0000053422427,0.000045256867,0.0007128179,0.0000021249862,8.110145e-7,0.95311236,0.03209975,0.008160917],"study_design_scores_gemma":[0.00041279194,0.00008431705,0.045707207,0.000025460322,0.000001609481,0.0000015605482,0.00015278425,0.00026638433,0.000002868026,0.3581222,0.5951336,0.00008922868],"about_ca_topic_score_codex":0.005490766,"about_ca_topic_score_gemma":0.0009787566,"teacher_disagreement_score":0.94838035,"about_ca_system_score_codex":0.00009786426,"about_ca_system_score_gemma":0.000009449859,"threshold_uncertainty_score":0.83004326},"labels":[],"label_agreement":null},{"id":"W4245910571","doi":"10.1002/sim.6278","title":"Correction","year":2014,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Smoothing; Multivariate statistics; Bayesian probability; Statistics; Data mining; B-spline; Artificial intelligence; Mathematics; Machine learning","score_opus":0.08967552808242954,"score_gpt":0.4643787968405947,"score_spread":0.3747032687581652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245910571","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015759777,0.000013938522,0.9745362,0.00017607328,0.0010845974,0.00009513325,0.000014247227,0.00003570486,0.023886502],"genre_scores_gemma":[0.04485133,0.000022076209,0.9526985,0.0002350096,0.00022699742,0.000012404848,0.000010980257,0.000018935285,0.0019237187],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99901617,0.00012853432,0.00030414652,0.0001689811,0.00020095691,0.0001812342],"domain_scores_gemma":[0.9954787,0.0041416003,0.00007020219,0.00017658585,0.00006205913,0.00007088282],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008230332,0.000096991884,0.00026264746,0.000071089285,0.000034774086,0.0000030110941,0.0000691724,0.000040165076,0.00022420917],"category_scores_gemma":[0.014416309,0.000076503326,0.0000081550925,0.00011490336,0.00012084712,0.000022314065,0.00001645376,0.00018686998,0.000010427754],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009993867,0.000021086136,0.000070635084,0.000030903644,0.0000024676526,0.000005715985,0.00018272462,0.00001553514,0.000061511106,0.8513914,0.03313663,0.11507145],"study_design_scores_gemma":[0.00046028025,0.00014782061,0.0004728621,0.000087151115,0.000014296275,0.0000045446013,0.000066701155,0.0442369,0.00002679408,0.9481177,0.006281742,0.00008322912],"about_ca_topic_score_codex":0.00002865714,"about_ca_topic_score_gemma":0.00006775658,"teacher_disagreement_score":0.11498822,"about_ca_system_score_codex":0.000034276705,"about_ca_system_score_gemma":0.000009533165,"threshold_uncertainty_score":0.9938857},"labels":[],"label_agreement":null},{"id":"W4248104173","doi":"10.1002/sim.3486","title":"Correction","year":2009,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"","keywords":"Inflation (cosmology); Sample size determination; Computer science; Statistics; Mathematics; Applied mathematics; Physics; Theoretical physics","score_opus":0.4513497466859385,"score_gpt":0.6047742542354313,"score_spread":0.15342450754949277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248104173","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000387168,0.000031150536,0.96260697,0.0013520622,0.0031978136,0.0002535539,0.000033647422,0.00007792044,0.032059737],"genre_scores_gemma":[0.031075671,0.000058885802,0.9659629,0.00090348016,0.0006032037,0.0000075822945,0.0000048110724,0.000015442996,0.0013680292],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796355,0.00034222077,0.00081110105,0.0002475206,0.0003857774,0.00024981642],"domain_scores_gemma":[0.96447575,0.034891866,0.00015313269,0.00028234778,0.000093034934,0.00010386584],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026257958,0.00013803742,0.00052461453,0.00011637856,0.00003473858,0.000006479632,0.0001481196,0.0000966019,0.0009646682],"category_scores_gemma":[0.20617773,0.000109671215,0.000020263207,0.00029231637,0.00017535723,0.000022763074,0.000014876112,0.00037204562,0.000031239775],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052117888,0.00009545128,0.00018589383,0.000019340036,0.000006106393,0.000054458866,0.0001536737,0.0000015296939,0.000082748855,0.63935256,0.21446794,0.14552815],"study_design_scores_gemma":[0.000989412,0.0004688373,0.0067631565,0.0001674776,0.000034174835,0.0000072230287,0.000062858046,0.0014379077,0.000052741678,0.9887634,0.0011395273,0.00011326562],"about_ca_topic_score_codex":0.00001713375,"about_ca_topic_score_gemma":0.000018012084,"teacher_disagreement_score":0.34941083,"about_ca_system_score_codex":0.0000652879,"about_ca_system_score_gemma":0.000026483827,"threshold_uncertainty_score":0.99994856},"labels":[],"label_agreement":null},{"id":"W4252029050","doi":"10.1002/sim.3909","title":"Construction of confidence limits about effect measures: A general approach—Reply","year":2010,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Biostatistics; Epidemiology; Library science; Citation; Confidence interval; Medicine; History; Demography; Family medicine; Sociology; Computer science; Pathology","score_opus":0.29723315980429194,"score_gpt":0.5271650463082589,"score_spread":0.22993188650396695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252029050","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020056635,0.00006622626,0.9700155,0.0001637144,0.0023067319,0.00077503436,0.00022921653,0.000054178876,0.0063327504],"genre_scores_gemma":[0.045084935,0.00008545792,0.95390105,0.00016441332,0.0005770487,0.00005108431,0.000009055275,0.000034739212,0.000092186994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99593455,0.00092505274,0.0015374377,0.00043635684,0.00082555047,0.00034105356],"domain_scores_gemma":[0.9493467,0.049035672,0.0005275797,0.0005974815,0.00031988125,0.0001726419],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0075377757,0.00025864973,0.0011836697,0.0001708126,0.00004627736,0.000010317403,0.00032440867,0.00020628146,0.0003679782],"category_scores_gemma":[0.28135228,0.00019737467,0.000054101376,0.00032563097,0.0015608694,0.00003473605,0.000045309233,0.00088407635,0.000007085677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019081637,0.000109794375,0.001945098,0.0005381455,0.00005424176,0.000025164163,0.00027520067,0.0000023482473,0.005816514,0.9357249,0.0039578914,0.05135986],"study_design_scores_gemma":[0.0025039518,0.0005715628,0.0023114237,0.00030243237,0.00017375464,0.000036845566,0.00007023711,0.0015314105,0.0022741123,0.98964596,0.00037535102,0.00020293774],"about_ca_topic_score_codex":0.000113674476,"about_ca_topic_score_gemma":0.000047229085,"teacher_disagreement_score":0.27381453,"about_ca_system_score_codex":0.00003091735,"about_ca_system_score_gemma":0.0000960438,"threshold_uncertainty_score":0.80487055},"labels":[],"label_agreement":null},{"id":"W4252233634","doi":"10.1002/sim.8229","title":"Issue Information","year":2020,"lang":"en","type":"paratext","venue":"Statistics in Medicine","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Citation; Information retrieval; World Wide Web","score_opus":0.026466283137171996,"score_gpt":0.32556839600590054,"score_spread":0.29910211286872856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252233634","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019745605,0.000463199,0.31873867,0.00061510847,0.024520861,0.00041536137,0.00085293106,0.00015307541,0.65422106],"genre_scores_gemma":[0.010754853,0.03512528,0.05291173,0.0152618345,0.065277405,0.0005365023,0.13573594,0.0006806443,0.6837158],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989638,0.00002994883,0.00045008055,0.00008966076,0.00032726405,0.00013925605],"domain_scores_gemma":[0.99962366,0.00005534566,0.000060686136,0.0001278937,0.00006011502,0.00007228003],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015794249,0.0001751958,0.000299258,0.00021603762,0.000020650765,0.000014613786,0.00010489384,0.00015672582,0.24040782],"category_scores_gemma":[0.00016784665,0.00017227567,0.000011105992,0.00014275832,0.000052461473,0.000088002475,0.000011431958,0.00044083863,0.24197179],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026081782,0.0000015848478,7.852774e-7,0.00041996266,0.000008985471,0.0000017583873,0.0018322587,0.005575742,0.000020003507,0.000041691197,0.98066914,0.011425482],"study_design_scores_gemma":[0.00037040314,0.00004307523,0.0001608226,0.00017031268,0.00001649474,6.7834844e-7,0.00020009172,0.037248243,0.0000026169448,0.00018586451,0.9614482,0.00015321067],"about_ca_topic_score_codex":0.0000038150133,"about_ca_topic_score_gemma":0.000017786568,"teacher_disagreement_score":0.26582694,"about_ca_system_score_codex":0.00015381213,"about_ca_system_score_gemma":0.000031653148,"threshold_uncertainty_score":0.7602865},"labels":[],"label_agreement":null},{"id":"W4252992953","doi":"10.1002/(sici)1097-0258(20000415)19:7<975::aid-sim381>3.3.co;2-0","title":"A robust mixed linear model analysis for longitudinal data","year":2000,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Okanagan University College; University of British Columbia","funders":"","keywords":"Mixed model; Random effects model; Generalized linear mixed model; Bayesian probability; Autocorrelation; Computer science; Longitudinal data; Linear model; Statistics; Econometrics; Linear regression; Robust regression; Mathematics; Data mining; Medicine","score_opus":0.3914669943620445,"score_gpt":0.473223682916968,"score_spread":0.08175668855492346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252992953","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014269665,0.000049778075,0.9933729,0.00027132503,0.00008241545,0.00026309644,0.0030366248,0.000028200022,0.0014686739],"genre_scores_gemma":[0.024275161,0.000082478924,0.97386557,0.000121523204,0.00015389803,0.00002894076,0.0005435876,0.000023261557,0.0009055947],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981184,0.00009116212,0.0006371672,0.00047635922,0.00034742386,0.0003295139],"domain_scores_gemma":[0.9948667,0.003909335,0.00010042399,0.0008587729,0.00013982113,0.0001249279],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014833233,0.00018403147,0.0006511802,0.00017371571,0.00006494428,0.000010973531,0.00044898028,0.000073116935,0.0019477345],"category_scores_gemma":[0.00834349,0.00014573132,0.00003087441,0.00053771713,0.00020513327,0.00004321222,0.00006303677,0.00019812096,0.000009502471],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020343688,0.000263595,0.0024541516,0.00032557355,0.00045289198,0.000051493775,0.00055998453,0.00926734,0.000016283317,0.8687808,0.046586987,0.07103747],"study_design_scores_gemma":[0.000544034,0.00008664198,0.0011872472,0.000040144114,0.0005037255,0.0000012258831,0.000038479448,0.63212305,0.0000020887312,0.36512688,0.00023793949,0.000108542656],"about_ca_topic_score_codex":0.00012221346,"about_ca_topic_score_gemma":0.00039411095,"teacher_disagreement_score":0.6228557,"about_ca_system_score_codex":0.000033847347,"about_ca_system_score_gemma":0.000055445922,"threshold_uncertainty_score":0.9989646},"labels":[],"label_agreement":null},{"id":"W4254487627","doi":"10.1002/sim.8864","title":"Editorial","year":2020,"lang":"en","type":"editorial","venue":"Statistics in Medicine","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science","score_opus":0.012351039779580427,"score_gpt":0.34109523348290754,"score_spread":0.32874419370332714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254487627","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.826478e-8,0.00027548472,0.0019555301,0.00020497864,0.9753617,0.00038994526,0.01656436,0.00017353502,0.005074379],"genre_scores_gemma":[0.0000022465179,0.0002154666,0.005334772,0.00005761219,0.9787717,0.0000480582,0.014494825,0.00035293572,0.0007224123],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924447,0.00027340776,0.0011531035,0.00089147594,0.004585151,0.00065218855],"domain_scores_gemma":[0.99214303,0.0055740564,0.0005316866,0.00061612995,0.0007753105,0.00035978173],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity","insufficient_payload"],"category_scores_codex":[0.0014595006,0.00065853674,0.0015194936,0.00041939857,0.00005617563,0.000028924002,0.0008257832,0.0013510904,0.0010863683],"category_scores_gemma":[0.069271944,0.0006021895,0.000041233227,0.0006924752,0.00059862604,0.000048220354,0.00018504294,0.0042464226,0.003628365],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002680755,0.00003559707,0.000007468254,0.00029126552,0.000055900768,0.00031590273,0.0004998617,0.000002285573,0.000032014785,0.0012411297,0.99688613,0.0003643351],"study_design_scores_gemma":[0.0034107615,0.00051733555,0.0000058888913,0.00055814185,0.00019610925,5.009863e-7,0.000064937085,0.000063456835,9.703857e-7,0.009596501,0.9850973,0.00048808512],"about_ca_topic_score_codex":0.0007009457,"about_ca_topic_score_gemma":0.00048360365,"teacher_disagreement_score":0.06781244,"about_ca_system_score_codex":0.00063236774,"about_ca_system_score_gemma":0.0011118628,"threshold_uncertainty_score":0.99994534},"labels":[],"label_agreement":null},{"id":"W4254597931","doi":"10.1002/sim.8247","title":"Issue Information","year":2020,"lang":"en","type":"paratext","venue":"Statistics in Medicine","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institutes of Health","keywords":"Computer science; Citation; Information retrieval; Library science","score_opus":0.026466283137171996,"score_gpt":0.32556839600590054,"score_spread":0.29910211286872856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254597931","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019745605,0.000463199,0.31873867,0.00061510847,0.024520861,0.00041536137,0.00085293106,0.00015307541,0.65422106],"genre_scores_gemma":[0.010754853,0.03512528,0.05291173,0.0152618345,0.065277405,0.0005365023,0.13573594,0.0006806443,0.6837158],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989638,0.00002994883,0.00045008055,0.00008966076,0.00032726405,0.00013925605],"domain_scores_gemma":[0.99962366,0.00005534566,0.000060686136,0.0001278937,0.00006011502,0.00007228003],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00015794249,0.0001751958,0.000299258,0.00021603762,0.000020650765,0.000014613786,0.00010489384,0.00015672582,0.24040782],"category_scores_gemma":[0.00016784665,0.00017227567,0.000011105992,0.00014275832,0.000052461473,0.000088002475,0.000011431958,0.00044083863,0.24197179],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026081782,0.0000015848478,7.852774e-7,0.00041996266,0.000008985471,0.0000017583873,0.0018322587,0.005575742,0.000020003507,0.000041691197,0.98066914,0.011425482],"study_design_scores_gemma":[0.00037040314,0.00004307523,0.0001608226,0.00017031268,0.00001649474,6.7834844e-7,0.00020009172,0.037248243,0.0000026169448,0.00018586451,0.9614482,0.00015321067],"about_ca_topic_score_codex":0.0000038150133,"about_ca_topic_score_gemma":0.000017786568,"teacher_disagreement_score":0.26582694,"about_ca_system_score_codex":0.00015381213,"about_ca_system_score_gemma":0.000031653148,"threshold_uncertainty_score":0.7602865},"labels":[],"label_agreement":null},{"id":"W4280491254","doi":"10.1002/sim.9431","title":"The impact of methodological choices when developing predictive models using urinary metabolite data","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Canada Foundation for Innovation; National Institute of Diabetes and Digestive and Kidney Diseases; Kidney Foundation of Canada","keywords":"Metabolomics; Computer science; Generalizability theory; Database normalization; Normalization (sociology); Linear discriminant analysis; Metabolite; Urinary system; Data mining; Computational biology; Bioinformatics; Medicine; Artificial intelligence; Biology; Internal medicine; Pattern recognition (psychology); Statistics; Mathematics","score_opus":0.18211004271361309,"score_gpt":0.43133334131057005,"score_spread":0.24922329859695697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280491254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12655823,0.024178615,0.84480774,0.00028838796,0.00046285044,0.00041417906,0.0024003927,0.000007960295,0.00088166137],"genre_scores_gemma":[0.8007097,0.00624492,0.19159028,0.00011475739,0.00029478938,0.000036416088,0.0008362486,0.000025750092,0.00014714383],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983321,0.0004276109,0.00038808596,0.00033897738,0.00026080932,0.00025244386],"domain_scores_gemma":[0.9987772,0.00035992303,0.00020965883,0.0005230554,0.00009064667,0.000039502633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002115351,0.00014538031,0.00036008714,0.00007877368,0.00022489694,0.0000057739935,0.0005689985,0.00003635898,0.000034009616],"category_scores_gemma":[0.0012328811,0.000091512506,0.000032288095,0.00018309541,0.00026665864,0.0000051786124,0.0011317725,0.00019361053,6.9129385e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00577574,0.0011218287,0.04601461,0.00036296042,0.0071846107,0.00022661198,0.0051198616,0.09850494,0.50018907,0.24804357,0.053550556,0.03390566],"study_design_scores_gemma":[0.0061878106,0.007807205,0.07745075,0.00009998683,0.0007704371,0.0002435218,0.0067160088,0.3791884,0.003992851,0.47057685,0.045637697,0.0013284845],"about_ca_topic_score_codex":0.0003361354,"about_ca_topic_score_gemma":0.000020456873,"teacher_disagreement_score":0.6741515,"about_ca_system_score_codex":0.00004772411,"about_ca_system_score_gemma":0.00015225391,"threshold_uncertainty_score":0.37317717},"labels":[],"label_agreement":null},{"id":"W4280543579","doi":"10.1002/sim.9433","title":"Dynamic prediction with time‐dependent marker in survival analysis using supervised functional principal component analysis","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Division of Cancer Prevention, National Cancer Institute","keywords":"Principal component analysis; Computer science; Functional principal component analysis; Event (particle physics); Artificial intelligence; Independent component analysis; Data mining; Machine learning; Pattern recognition (psychology); Feature (linguistics)","score_opus":0.05897852154404278,"score_gpt":0.35533086880594217,"score_spread":0.2963523472618994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280543579","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19204348,0.000023255501,0.806112,0.00006517516,0.0001571145,0.00022903841,0.0009787377,0.000021868424,0.00036933864],"genre_scores_gemma":[0.71061033,0.000009688471,0.28836796,0.000045086497,0.000030821502,0.000053087708,0.0006379688,0.000022830678,0.00022222493],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964273,0.0007787248,0.0008080161,0.00045693663,0.0011962934,0.00033273047],"domain_scores_gemma":[0.9969829,0.00223039,0.00020281551,0.00034550155,0.00012958725,0.00010884841],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025237182,0.00022076414,0.00084253825,0.0011290557,0.0001365399,0.000014479088,0.00016481934,0.000046930567,0.0066513848],"category_scores_gemma":[0.0009364889,0.00018576355,0.00005942222,0.0028253328,0.00015827444,0.000035340086,0.00011740279,0.00047142437,0.0000022033694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017830647,0.0016415371,0.6276764,0.00028964845,0.0067811697,0.0007830635,0.003181584,0.24879713,0.0011728784,0.10290193,0.00040346858,0.0045880796],"study_design_scores_gemma":[0.0011122237,0.0001863278,0.26017013,0.000019635585,0.0021879866,0.000005352667,0.00061968336,0.71873623,9.86604e-7,0.016802683,0.00001067948,0.00014807886],"about_ca_topic_score_codex":0.00067510054,"about_ca_topic_score_gemma":0.0012636875,"teacher_disagreement_score":0.51856685,"about_ca_system_score_codex":0.0005221286,"about_ca_system_score_gemma":0.000091958966,"threshold_uncertainty_score":0.9942567},"labels":[],"label_agreement":null},{"id":"W4281251350","doi":"10.1002/sim.9441","title":"The polytomous discrimination index for prediction involving multistate processes under intermittent observation","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Polytomous Rasch model; Multinomial logistic regression; Context (archaeology); Econometrics; Computer science; Logistic regression; Index (typography); Time horizon; Statistics; Machine learning; Mathematics; Item response theory; Psychometrics; Mathematical optimization","score_opus":0.1312956431616157,"score_gpt":0.40548558923975936,"score_spread":0.2741899460781436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281251350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004737131,0.00016045454,0.99134874,0.0012400806,0.00090580666,0.00068252825,0.0007307416,0.000040062823,0.00015442955],"genre_scores_gemma":[0.7580779,0.00020187807,0.23815598,0.00047937228,0.00026271562,0.0010814022,0.00038003456,0.000054285203,0.0013064411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99826103,0.00019978087,0.0005854674,0.00023281586,0.0004708315,0.00025004614],"domain_scores_gemma":[0.99388635,0.00535566,0.00024232893,0.00018977102,0.00027731486,0.000048551687],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001443991,0.00013716763,0.00021465447,0.000095734285,0.00044897042,0.000026873524,0.00019659166,0.000030180376,0.00006663085],"category_scores_gemma":[0.01336339,0.0000982078,0.000014409921,0.00029044776,0.00016832109,0.000053559324,0.000082976345,0.00026120487,4.689448e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013391595,0.00010557401,0.0018947233,0.00043777114,0.000021700052,0.0000057847524,0.0026667402,0.00013897002,0.00014781096,0.912854,0.007902377,0.07369061],"study_design_scores_gemma":[0.00091616175,0.0003941935,0.021808444,0.00011365651,0.00004459351,0.0000050791355,0.0045543686,0.08664857,0.00001914207,0.8844951,0.0008900465,0.00011068449],"about_ca_topic_score_codex":0.00011692749,"about_ca_topic_score_gemma":0.00040080925,"teacher_disagreement_score":0.7533408,"about_ca_system_score_codex":0.0002234295,"about_ca_system_score_gemma":0.00009144898,"threshold_uncertainty_score":0.9949475},"labels":[],"label_agreement":null},{"id":"W4281383153","doi":"10.1002/sim.9442","title":"A classification for complex imbalanced data in disease screening and early diagnosis","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.1130163235397242,"score_gpt":0.3732825950494658,"score_spread":0.26026627150974163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281383153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015647751,0.00015334939,0.99163955,0.0045328443,0.000081787075,0.0005435731,0.0013770836,0.00006998813,0.000037062553],"genre_scores_gemma":[0.5261646,0.00010674974,0.47141877,0.00040832913,0.00003047299,0.00061782764,0.001226231,0.000009662618,0.000017343547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9984828,0.00011646597,0.00037249902,0.0005070894,0.0003208923,0.00020024955],"domain_scores_gemma":[0.998078,0.00068435393,0.00014529134,0.00096653786,0.00004765983,0.00007816916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010105371,0.00009939364,0.00019506172,0.00024397328,0.00011555596,0.000030560765,0.0010675507,0.000016619399,0.000019790961],"category_scores_gemma":[0.0010276878,0.0001034553,0.0000054298853,0.0004477252,0.00011221447,0.0002306793,0.0005856226,0.00017226789,4.5351288e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010718198,0.0002057926,0.3139416,0.00014000267,0.000011070015,0.000051317536,0.0016049107,0.000039233488,0.00084624445,0.46369943,0.04675098,0.1726022],"study_design_scores_gemma":[0.00083691836,0.00010009321,0.6462744,0.000038985916,0.0000055757296,0.0000013626975,0.00010627684,0.31756383,0.0000040620444,0.02267299,0.012285032,0.00011046623],"about_ca_topic_score_codex":0.00013229622,"about_ca_topic_score_gemma":0.000048514947,"teacher_disagreement_score":0.52459985,"about_ca_system_score_codex":0.00007822986,"about_ca_system_score_gemma":0.000050393,"threshold_uncertainty_score":0.4218785},"labels":[],"label_agreement":null},{"id":"W4283706657","doi":"10.1002/sim.9509","title":"Augmented weighting estimators for the additive rates model under multivariate recurrent event data with missing event type","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"Fundamental Research Funds for the Central Universities; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Inverse probability weighting; Missing data; Multivariate statistics; Estimator; Event (particle physics); Nonparametric statistics; Computer science; Inverse probability; Statistics; Weighting; Econometrics; Data mining; Mathematics; Medicine; Bayesian probability","score_opus":0.19762742846424525,"score_gpt":0.47804157139208986,"score_spread":0.2804141429278446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283706657","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039468566,0.00017770898,0.9947296,0.0010877622,0.00040541176,0.00069926144,0.0023760027,0.000023427529,0.00010618635],"genre_scores_gemma":[0.09479117,0.000032966604,0.9039957,0.00026744098,0.00009107086,0.00015359304,0.0004855728,0.000043494583,0.00013902133],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99797845,0.00025362833,0.0005438285,0.0003873242,0.0005134998,0.00032327298],"domain_scores_gemma":[0.98677343,0.012185609,0.00027285446,0.0005106334,0.00017389069,0.000083564744],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0018874089,0.00020433486,0.00036375126,0.00007047531,0.00035765264,0.000016581353,0.00042098208,0.000026079395,0.0004060262],"category_scores_gemma":[0.009925543,0.00012491569,0.000013602749,0.0002582889,0.00018150729,0.000035438316,0.00027953432,0.00038745377,9.7306e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006298426,0.00035130169,0.00007687463,0.00024459301,0.00020515735,0.00003296502,0.0028238127,0.00841579,0.00015305307,0.8685734,0.028744036,0.089749165],"study_design_scores_gemma":[0.0008684715,0.00033822408,0.00021492876,0.00020009904,0.00012876806,0.000004588501,0.001140003,0.66235554,0.000012447015,0.33417147,0.00044461054,0.00012085982],"about_ca_topic_score_codex":0.000112980975,"about_ca_topic_score_gemma":0.00005245103,"teacher_disagreement_score":0.6539397,"about_ca_system_score_codex":0.00015978345,"about_ca_system_score_gemma":0.0001926753,"threshold_uncertainty_score":0.9984143},"labels":[],"label_agreement":null},{"id":"W4283804698","doi":"10.1002/sim.9512","title":"Unified estimation for Cox regression model with nonmonotone missing at random covariates","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; University of Regina","funders":"","keywords":"Covariate; Estimator; Missing data; Computer science; Proportional hazards model; Imputation (statistics); Statistics; Mathematics; Econometrics","score_opus":0.06925157385471965,"score_gpt":0.40727885511625317,"score_spread":0.33802728126153353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283804698","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007080977,0.000043165368,0.9966494,0.00070665835,0.00013581608,0.00067500933,0.00047337907,0.000035595483,0.00057292223],"genre_scores_gemma":[0.028048245,0.000010524864,0.9709262,0.00015944662,0.000037464648,0.00020060802,0.00018022153,0.000033312903,0.00040396847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998309,0.0002022507,0.00049565383,0.000282914,0.0004471057,0.00026306967],"domain_scores_gemma":[0.9933346,0.005981041,0.00024514584,0.0002407975,0.0001109251,0.00008751727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013760342,0.00018154194,0.0004911874,0.00012095806,0.00032282417,0.000011870461,0.0001396146,0.000041361334,0.0003562085],"category_scores_gemma":[0.004336566,0.00012992612,0.000016013175,0.0002043003,0.00016957824,0.000031378553,0.00007134474,0.00022728214,9.705894e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019008,0.00011869392,0.00009799824,0.00034062588,0.000026212118,0.000049091832,0.0016911677,0.0021771605,0.00074332516,0.95125645,0.01188704,0.02971145],"study_design_scores_gemma":[0.0029415784,0.0002563371,0.000041292602,0.00013535225,0.000055209654,0.0000095710275,0.00012061731,0.4660567,0.0000713846,0.53013676,0.00007584432,0.00009935607],"about_ca_topic_score_codex":0.00003815096,"about_ca_topic_score_gemma":0.000025204472,"teacher_disagreement_score":0.46387956,"about_ca_system_score_codex":0.00017735513,"about_ca_system_score_gemma":0.00009134193,"threshold_uncertainty_score":0.5298233},"labels":[],"label_agreement":null},{"id":"W4284892632","doi":"10.1002/sim.9516","title":"Adaptive response‐dependent two‐phase designs: Some results on robustness and efficiency","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Robustness (evolution); Computer science; Covariate; Biomarker; Statistics; Quantile; Data mining; Econometrics; Machine learning; Mathematics","score_opus":0.47951310210464493,"score_gpt":0.5641417443802038,"score_spread":0.08462864227555889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284892632","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020550413,0.00015878893,0.97024137,0.0021232413,0.0015481272,0.0013061285,0.0030590761,0.00008811114,0.0009247683],"genre_scores_gemma":[0.19403577,0.0000599021,0.8039847,0.00068261544,0.000407656,0.00019172473,0.000021406131,0.000066376444,0.00054984004],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9915539,0.004394959,0.0015577064,0.000729125,0.0012766104,0.00048771166],"domain_scores_gemma":[0.87082314,0.12793444,0.00039778292,0.00053742377,0.0001051975,0.00020202712],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.017854398,0.00030041908,0.000915795,0.00032937454,0.00025037577,0.000015156791,0.00037583153,0.00007854436,0.00049741234],"category_scores_gemma":[0.20920189,0.00025528733,0.000030446912,0.00041708344,0.0005827091,0.0000350045,0.00025980666,0.000950941,0.000006549994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.028781122,0.0015192179,0.000016244787,0.00011123127,0.00006795173,0.0015960038,0.0016834853,0.0017582623,0.00041919973,0.9112333,0.017816674,0.03499732],"study_design_scores_gemma":[0.01752474,0.0069037527,0.00015609594,0.0001927243,0.000106958854,0.000026779991,0.0010484307,0.017749755,0.000103238795,0.9556704,0.0002004824,0.00031664674],"about_ca_topic_score_codex":0.000036916266,"about_ca_topic_score_gemma":0.000010173346,"teacher_disagreement_score":0.1913475,"about_ca_system_score_codex":0.00026842472,"about_ca_system_score_gemma":0.00013893182,"threshold_uncertainty_score":0.9999899},"labels":[],"label_agreement":null},{"id":"W4285592479","doi":"10.1002/sim.9519","title":"Bootstrap vs asymptotic variance estimation when using propensity score weighting with continuous and binary outcomes","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research; Ministerio de Sanidad, Consumo y Bienestar Social; Heart and Stroke Foundation of Canada","keywords":"Statistics; Mathematics; Propensity score matching; Estimator; Confidence interval; Weighting; Average treatment effect; Sample size determination; Delta method; Matching (statistics); Inverse probability weighting; Medicine","score_opus":0.14787825533505633,"score_gpt":0.3957896493172065,"score_spread":0.24791139398215017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285592479","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33297634,0.000050932646,0.6656471,0.00028543442,0.000078108766,0.0005626747,0.000045978853,0.00011229491,0.00024115418],"genre_scores_gemma":[0.5051744,0.000006616423,0.49450678,0.00012390128,0.000017971055,0.00003227016,0.000020393803,0.000024806515,0.00009283909],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99852407,0.0001244224,0.00041325839,0.00027555088,0.00041804241,0.00024465227],"domain_scores_gemma":[0.99853635,0.0007808087,0.00028098727,0.000247961,0.00009567216,0.0000582057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000694133,0.00019157429,0.00049419265,0.00014078352,0.0001948712,0.000014046187,0.0001289051,0.00003408095,0.00011584432],"category_scores_gemma":[0.0011358759,0.0001504879,0.000007973684,0.00017562018,0.00024289348,0.00011414218,0.00013452648,0.0003871026,4.2146362e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004805666,0.00040156662,0.21443677,0.0012376822,0.00013624031,0.001537475,0.00844783,0.0021523386,0.0040352335,0.745907,0.0027553698,0.018471906],"study_design_scores_gemma":[0.0015743407,0.0011609311,0.02967658,0.0006655706,0.00014007391,0.00018347445,0.00070867507,0.05199682,0.00010448136,0.9133447,0.000055158045,0.0003891854],"about_ca_topic_score_codex":0.00013406375,"about_ca_topic_score_gemma":0.000047537425,"teacher_disagreement_score":0.18476018,"about_ca_system_score_codex":0.00016401625,"about_ca_system_score_gemma":0.00006731817,"threshold_uncertainty_score":0.6136719},"labels":[],"label_agreement":null},{"id":"W4285732379","doi":"10.1002/sim.9520","title":"Bayesian unanchored additive models for component network meta‐analysis","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Notation; Component (thermodynamics); Bayesian probability; Bayesian network; Statistical model; Additive model; Contrast (vision); Econometrics; Machine learning; Data mining; Artificial intelligence; Mathematics","score_opus":0.6624841692767993,"score_gpt":0.5228154949789899,"score_spread":0.13966867429780938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285732379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000040214534,0.003277775,0.9884768,0.001440329,0.0003657377,0.0010614425,0.0020178182,0.0000043488226,0.003315514],"genre_scores_gemma":[0.65587807,0.00012833838,0.32565042,0.0026214845,0.00041323382,0.0016807397,0.0015707508,0.000041067582,0.012015874],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9769994,0.008348349,0.0076141125,0.0010348287,0.0056025498,0.00040074307],"domain_scores_gemma":[0.9773252,0.016372152,0.003222053,0.0021398205,0.0007708435,0.000169939],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09884307,0.0003040988,0.0068797083,0.0007785135,0.00032038393,0.00009499879,0.0013781952,0.000036156005,0.047469016],"category_scores_gemma":[0.012202616,0.00015771003,0.0016495225,0.004032909,0.0001251968,0.00006690641,0.00019048393,0.0002527213,0.000041805393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027134649,0.000058574104,0.00034863668,0.000021607257,0.033371814,0.000024471847,0.0010261334,0.28500858,0.0000011023036,0.1276578,0.5491991,0.0032550644],"study_design_scores_gemma":[0.0002961732,0.00009684689,0.00033152936,0.00000333119,0.05145791,0.0000017678868,0.000988863,0.59237874,1.7845471e-7,0.3031551,0.05116047,0.00012911875],"about_ca_topic_score_codex":0.00009555194,"about_ca_topic_score_gemma":0.000387837,"teacher_disagreement_score":0.6628264,"about_ca_system_score_codex":0.000083569306,"about_ca_system_score_gemma":0.000058829588,"threshold_uncertainty_score":0.996118},"labels":[],"label_agreement":null},{"id":"W4286209045","doi":"10.1002/sim.9529","title":"Modeling and forecasting of at home activity in older adults using passive sensor technology","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Context-Aware Activity Recognition Systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council","keywords":"Categorical variable; Quarter (Canadian coin); Life expectancy; Computer science; Gerontology; Medicine; Machine learning; Geography; Environmental health","score_opus":0.04229577504528906,"score_gpt":0.2954046475400237,"score_spread":0.2531088724947347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286209045","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5992325,0.000072420895,0.40011808,0.00019254013,0.0001468086,0.00016707466,0.000032946085,0.000014757201,0.00002286604],"genre_scores_gemma":[0.9787287,0.000008640454,0.021164764,0.000029361965,0.000019698497,0.000024803978,0.0000036991169,0.000008624847,0.000011706509],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861276,0.00015392952,0.00037805512,0.00032950888,0.00031461637,0.00021114122],"domain_scores_gemma":[0.9989327,0.0005161031,0.0001948673,0.00021903998,0.000101067795,0.00003621927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005343977,0.000107933396,0.0003627437,0.0005460492,0.00008859437,0.0000056229537,0.0001947697,0.00004325063,0.000017299835],"category_scores_gemma":[0.00043848233,0.00011165926,0.000009600963,0.00066280493,0.00009440531,0.000101852645,0.00047958863,0.00029148968,2.8694046e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032399734,0.0004044898,0.07868604,0.0008298113,0.000062347484,0.0010570863,0.02264273,0.027708827,0.016766954,0.007909752,0.00009887606,0.8435091],"study_design_scores_gemma":[0.0014259183,0.00010939672,0.0019643656,0.00025922502,0.0000042975994,0.00011275433,0.001357477,0.9922757,0.00015994914,0.00221283,0.000005742375,0.00011231716],"about_ca_topic_score_codex":0.0009002698,"about_ca_topic_score_gemma":0.0006851398,"teacher_disagreement_score":0.9645669,"about_ca_system_score_codex":0.00021864212,"about_ca_system_score_gemma":0.000050840215,"threshold_uncertainty_score":0.45533326},"labels":[],"label_agreement":null},{"id":"W4290033699","doi":"10.1002/sim.9538","title":"Calculating the power to examine treatment‐covariate interactions when planning an individual participant data meta‐analysis of randomized trials with a binary outcome","year":2022,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Oxford Biomedical Research Centre; Medical Research Council; National Institute for Health and Care Research; Medical Research Council Canada; Cancer Research UK","keywords":"Covariate; Statistics; Outcome (game theory); Variance (accounting); Econometrics; Logistic regression; Computer science; Statistical power; Wald test; Binary data; Type I and type II errors; Binary number; Mathematics; Statistical hypothesis testing","score_opus":0.9718818217885831,"score_gpt":0.689846894753815,"score_spread":0.28203492703476807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290033699","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010728074,0.9061121,0.08246865,0.0002648503,0.00033795348,0.0046976423,0.0058059283,0.0000054338893,0.00029673232],"genre_scores_gemma":[0.0019233993,0.7837577,0.18131565,0.0008451549,0.00048581173,0.0063662673,0.019422999,0.00021881965,0.00566422],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.8607869,0.09780747,0.032350365,0.0018561643,0.006757235,0.00044183215],"domain_scores_gemma":[0.7373343,0.22802259,0.024485085,0.009331601,0.00053193595,0.00029445768],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3724203,0.0008209047,0.057465553,0.0028079713,0.00020666572,0.00029009476,0.0036698317,0.00008448625,0.03770846],"category_scores_gemma":[0.25615868,0.00025512127,0.0038066187,0.0051099462,0.00023371165,0.00015604301,0.0006205459,0.00049054273,0.000031096213],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008965443,0.00028097435,0.00009731725,0.0009798178,0.8472862,0.00017542244,0.016396936,0.0025810886,1.3346595e-7,0.0023302902,0.00586966,0.123105615],"study_design_scores_gemma":[0.0035835425,0.00021885424,0.000022595945,0.00039329662,0.720587,0.000008433483,0.0022753633,0.006143756,3.967755e-9,0.00026796735,0.26629868,0.00020049105],"about_ca_topic_score_codex":0.0005076853,"about_ca_topic_score_gemma":0.0006192297,"teacher_disagreement_score":0.26042902,"about_ca_system_score_codex":0.00006675786,"about_ca_system_score_gemma":0.0002580931,"threshold_uncertainty_score":0.9999901},"labels":[],"label_agreement":null},{"id":"W4290034027","doi":"10.1002/sim.9547","title":"Use of copula to model within‐study association in bivariate meta‐analysis of binomial data at the aggregate level: A Bayesian approach and application to surrogate endpoint evaluation","year":2022,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Chronic Myeloid Leukemia Treatments","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; University of Leicester","keywords":"Bivariate analysis; Copula (linguistics); Statistics; Beta-binomial distribution; Econometrics; Random effects model; Continuity correction; Surrogate endpoint; Binomial distribution; Bayesian probability; Computer science; Meta-analysis; Mathematics; Negative binomial distribution; Medicine; Internal medicine; Poisson distribution","score_opus":0.3400497914709901,"score_gpt":0.44790679767266445,"score_spread":0.10785700620167432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290034027","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024480275,0.81178963,0.12699585,0.0005957882,0.00029092346,0.031312123,0.026368404,0.000038158214,0.00016109513],"genre_scores_gemma":[0.014858722,0.885783,0.055104684,0.00023716604,0.00010943585,0.004080218,0.03896767,0.00018908482,0.0006699761],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99372536,0.0011711939,0.001959684,0.0009292956,0.0019438168,0.00027063294],"domain_scores_gemma":[0.9947256,0.0017033267,0.0015404444,0.0016287756,0.00026766528,0.0001341913],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008825699,0.00042251337,0.0038522508,0.0013212254,0.000057362107,0.000009715062,0.00037840553,0.00014661565,0.0001334809],"category_scores_gemma":[0.004706685,0.00028578134,0.00013928952,0.0025851675,0.00007333513,0.000054018838,0.0005518876,0.00044431517,0.0000015970955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016499831,0.00313858,0.0038118456,0.016935807,0.19592868,0.00009317787,0.025707945,0.107948765,0.000020195348,0.0013882263,0.0031866836,0.6401901],"study_design_scores_gemma":[0.0034493832,0.00053103303,0.0014186653,0.000790813,0.44134036,0.00000712927,0.00038982322,0.54447716,0.0000010726777,0.00012266301,0.0071471552,0.00032472756],"about_ca_topic_score_codex":0.0062331874,"about_ca_topic_score_gemma":0.009967044,"teacher_disagreement_score":0.6398654,"about_ca_system_score_codex":0.0041725044,"about_ca_system_score_gemma":0.0009673203,"threshold_uncertainty_score":0.9999594},"labels":[],"label_agreement":null},{"id":"W4297271369","doi":"10.1002/sim.9549","title":"Substantive model compatible multilevel multiple imputation: A joint modeling approach","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"Imputation (statistics); Covariate; Computer science; Missing data; Statistics; Multilevel model; Data mining; Econometrics; Mathematics; Machine learning","score_opus":0.19222843533564607,"score_gpt":0.40369911782895407,"score_spread":0.211470682493308,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297271369","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002831384,0.000055773307,0.99348396,0.000111200156,0.000184646,0.0004971752,0.00082220265,0.000060412745,0.0019532468],"genre_scores_gemma":[0.39718363,0.000007539683,0.6023919,0.000103530656,0.00003896441,0.000110656074,0.00008617226,0.000026698443,0.000050930576],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972637,0.00031762547,0.0008321603,0.00043622954,0.0007470924,0.0004031673],"domain_scores_gemma":[0.9972144,0.0019637188,0.0002008868,0.00031132443,0.00018304566,0.0001266684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001423575,0.0002436402,0.0006207364,0.00023701812,0.00025666834,0.00001446371,0.00023968966,0.00004810179,0.00033985017],"category_scores_gemma":[0.0035638844,0.00021997729,0.0000318068,0.0003644724,0.00016359625,0.000048850903,0.00015872395,0.0006092664,0.0000029311188],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007705263,0.00029500423,0.00026635826,0.00019963272,0.00002592047,0.00005143929,0.005834157,0.05819359,0.00013349376,0.92311615,0.002712295,0.009094879],"study_design_scores_gemma":[0.00087629387,0.000083799285,0.0000735455,0.000031585583,0.00002253018,0.0000076246224,0.0012459693,0.5253115,0.0000056126996,0.47220495,0.0000054331645,0.00013112355],"about_ca_topic_score_codex":0.00018545125,"about_ca_topic_score_gemma":0.000029763212,"teacher_disagreement_score":0.46711794,"about_ca_system_score_codex":0.00019530032,"about_ca_system_score_gemma":0.000117295414,"threshold_uncertainty_score":0.8970414},"labels":[],"label_agreement":null},{"id":"W4309515696","doi":"10.1002/sim.9608","title":"Double robust estimation of optimal partially adaptive treatment strategies: An application to breast cancer treatment using hormonal therapy","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre hospitalier de l'Université Laval; McGill University; Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Breast cancer; Covariate; Computer science; Robustness (evolution); Ordinary least squares; Confounding; Estimation; Econometrics; Statistics; Machine learning; Cancer; Medicine; Mathematics; Internal medicine","score_opus":0.49093574846171567,"score_gpt":0.5630733962666775,"score_spread":0.07213764780496185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309515696","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05428284,0.00006395499,0.9413937,0.00026069683,0.00023265333,0.0014746889,0.0021489977,0.00003094326,0.00011156199],"genre_scores_gemma":[0.2638878,0.00008577951,0.73499894,0.00004624073,0.00019166034,0.0006789896,0.000052978514,0.00003410027,0.000023525812],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99714124,0.0005094956,0.0010239594,0.00043894627,0.00059579336,0.00029053574],"domain_scores_gemma":[0.9944042,0.0044678976,0.00040551336,0.00039597778,0.00016045714,0.00016594787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012533945,0.00026479614,0.00077513396,0.00015250187,0.0001279392,0.000013227942,0.0001886311,0.000060538463,0.00077922887],"category_scores_gemma":[0.00057722395,0.00020809405,0.000040241932,0.00037522538,0.00018271265,0.00006483473,0.00004369058,0.00014422277,0.0000013755965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040630577,0.0017809811,0.00024481176,0.000044599903,0.00021170087,0.000028998948,0.004400384,0.5283531,0.0014419648,0.2326953,0.00016795512,0.22656713],"study_design_scores_gemma":[0.00972643,0.0097067375,0.0020828699,0.000100890924,0.00033102863,0.00001810611,0.0033816008,0.5561154,0.0005555306,0.4174855,0.00011850849,0.00037742328],"about_ca_topic_score_codex":0.00261504,"about_ca_topic_score_gemma":0.00034172006,"teacher_disagreement_score":0.22618972,"about_ca_system_score_codex":0.00091856404,"about_ca_system_score_gemma":0.00038299663,"threshold_uncertainty_score":0.8532009},"labels":[],"label_agreement":null},{"id":"W4309699570","doi":"10.1002/sim.9611","title":"Measures of explained variation under the mixture cure model for survival data","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Variation (astronomy); Statistics; Regression; Residual; Regression analysis; Computer science; Econometrics; Mathematics; Algorithm","score_opus":0.32615973814007776,"score_gpt":0.4525609731484041,"score_spread":0.12640123500832634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309699570","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016939781,0.00007690795,0.9933906,0.0015527409,0.0003556755,0.0003836837,0.0037434695,0.000011198747,0.00031628655],"genre_scores_gemma":[0.17951252,0.00003339029,0.81936955,0.00028303312,0.00012520696,0.00009183481,0.00033043648,0.000025028214,0.00022896932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99823314,0.00031965825,0.00047364866,0.00022678477,0.00057377154,0.00017302402],"domain_scores_gemma":[0.99189866,0.007123093,0.00019609263,0.00059022073,0.00015614134,0.000035814115],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032350696,0.00011374935,0.00032719588,0.00005644028,0.00012933846,0.0000049718396,0.00050895254,0.000034573262,0.00023464441],"category_scores_gemma":[0.008655717,0.00007534791,0.000013075243,0.00018487946,0.0001359419,0.000023501603,0.00018560163,0.0002612578,2.2565042e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006888748,0.00006159153,0.000023151722,0.00010013934,0.000025842293,0.0000015411855,0.0017896788,0.00082356314,0.00017455328,0.9709026,0.023416923,0.0026115181],"study_design_scores_gemma":[0.0004916755,0.0000909694,0.00021252298,0.000018405131,0.000057240562,9.4688147e-7,0.0009644191,0.39905408,0.0000034184382,0.59877664,0.00027610225,0.00005359048],"about_ca_topic_score_codex":0.00007635685,"about_ca_topic_score_gemma":0.00013120606,"teacher_disagreement_score":0.3982305,"about_ca_system_score_codex":0.000039795505,"about_ca_system_score_gemma":0.00010089493,"threshold_uncertainty_score":0.9996948},"labels":[],"label_agreement":null},{"id":"W4309915237","doi":"10.1002/sim.9071","title":"Issue Information","year":2022,"lang":"en","type":"paratext","venue":"Statistics in Medicine","topic":"Transportation Systems and Logistics","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Citation; Information retrieval; Library science","score_opus":0.013242268203910631,"score_gpt":0.2767656958766696,"score_spread":0.263523427672759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309915237","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000988718,0.0022824728,0.4763838,0.00008611737,0.024102094,0.00042351327,0.007017002,0.00010837158,0.48958674],"genre_scores_gemma":[0.056150027,0.034946293,0.056599952,0.0032197246,0.011612821,0.0013622246,0.22695185,0.000755465,0.60840166],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998655,0.000023911756,0.0006705003,0.000094797244,0.0003706934,0.00018505211],"domain_scores_gemma":[0.99948275,0.00012660497,0.00009413087,0.00018940994,0.000053474963,0.000053637737],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00020461848,0.00019780685,0.00040274585,0.0003032227,0.00003282611,0.000010536064,0.00014734917,0.00012835757,0.040759567],"category_scores_gemma":[0.00006394122,0.00019360264,0.000013609938,0.00022556868,0.00005254416,0.000055404627,0.000008678953,0.0005496504,0.0033191654],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027696326,0.000002875013,0.000010383729,0.0007357581,0.000017493414,0.000013256401,0.0010721894,0.029322784,0.0000014020119,0.0023525867,0.96205884,0.004409679],"study_design_scores_gemma":[0.00037292286,0.000044108812,0.00023346039,0.0001213223,0.000019316327,0.0000023082684,0.00043669896,0.0029336954,9.242388e-7,0.00017935979,0.99547386,0.00018200374],"about_ca_topic_score_codex":0.00023894766,"about_ca_topic_score_gemma":0.00007773716,"teacher_disagreement_score":0.41978386,"about_ca_system_score_codex":0.00013837736,"about_ca_system_score_gemma":0.000040496678,"threshold_uncertainty_score":0.99745685},"labels":[],"label_agreement":null},{"id":"W4309915763","doi":"10.1002/sim.9606","title":"Adjusting for treatment selection in phase II/III clinical trials with time to event data","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Novartis Pharma; Medical Research Council Canada","keywords":"Estimator; Statistics; Selection (genetic algorithm); Stage (stratigraphy); U-statistic; Selection bias; Mean squared error; Variance (accounting); Clinical trial; Efficiency; Mathematics; Computer science; Econometrics; Medicine; Internal medicine; Artificial intelligence","score_opus":0.7994143033413676,"score_gpt":0.7010730436421652,"score_spread":0.09834125969920249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309915763","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004870047,0.00004050052,0.984468,0.0015367627,0.0006722309,0.0038790165,0.0041894712,0.000052955096,0.00029102463],"genre_scores_gemma":[0.0065692863,0.000027742499,0.98986155,0.00041781648,0.00086632505,0.0007584002,0.00026025067,0.00005903432,0.0011795816],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99000746,0.0041332887,0.003801552,0.0008694791,0.0007044677,0.0004837702],"domain_scores_gemma":[0.8385807,0.15973525,0.0007392354,0.0006085682,0.000116553274,0.00021968907],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047501598,0.00027477366,0.002209684,0.0002515072,0.00018042649,0.000010203353,0.0004653473,0.000090498084,0.0027829483],"category_scores_gemma":[0.35633132,0.000202912,0.000054481632,0.0006145911,0.00014351522,0.000034950597,0.0003247148,0.00039679176,0.000007432436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013149278,0.0064427773,0.00040859173,0.00021911928,0.00036429404,0.00020457627,0.0013435886,0.000437915,0.00028878884,0.040687636,0.16381422,0.7726392],"study_design_scores_gemma":[0.073405504,0.04793291,0.0002624679,0.0005798244,0.0012770395,0.000027203883,0.0008743675,0.113228515,0.000052076306,0.7361036,0.0255865,0.0006700129],"about_ca_topic_score_codex":0.000107045904,"about_ca_topic_score_gemma":0.00019296714,"teacher_disagreement_score":0.7719692,"about_ca_system_score_codex":0.00041115782,"about_ca_system_score_gemma":0.00026967115,"threshold_uncertainty_score":0.99812865},"labels":[],"label_agreement":null},{"id":"W4310022099","doi":"10.1002/sim.9594","title":"Practical implementation of the partial ordering continual reassessment method in a Phase I combination‐schedule dose‐finding trial","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council Canada; Department of Health and Social Care; Merck KGaA; Medical Research Council; National Institute for Health and Care Research","keywords":"Computer science; Dosing; Maximum tolerated dose; Schedule; Scheduling (production processes); A priori and a posteriori; Operations research; Medical physics; Clinical trial; Risk analysis (engineering); Management science; Medicine; Mathematical optimization; Mathematics","score_opus":0.5226493986877256,"score_gpt":0.6801128053508417,"score_spread":0.1574634066631161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310022099","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060858168,0.000010399538,0.93093526,0.0027153024,0.0022289276,0.0023616913,0.00047538689,0.000022013815,0.00039284307],"genre_scores_gemma":[0.3067176,0.0000051728402,0.69267106,0.00010757657,0.0001464739,0.00028619394,0.000017067254,0.00002268563,0.00002615538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99185556,0.0041313353,0.002147627,0.00036531276,0.0011549343,0.0003452045],"domain_scores_gemma":[0.9529894,0.04561841,0.0008477711,0.00035611406,0.00011490174,0.00007338851],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.014838845,0.00017878032,0.0008287188,0.00018241891,0.00012435629,0.000011190436,0.0002744354,0.00006381106,0.0017777642],"category_scores_gemma":[0.08419108,0.00014218003,0.00005133248,0.00066347694,0.00020845018,0.000049438277,0.00028151774,0.0007814003,6.985808e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0051807794,0.0017388735,0.0012223278,0.00014073377,0.000068397574,0.0000664651,0.0019641244,0.000028080538,0.00047931046,0.9476533,0.0037025942,0.03775505],"study_design_scores_gemma":[0.11769586,0.002377749,0.0017965706,0.00011154986,0.00020393687,0.0000111157615,0.00603362,0.0058824075,0.00058112195,0.8646617,0.0004416514,0.0002027034],"about_ca_topic_score_codex":0.00020167751,"about_ca_topic_score_gemma":0.00013730723,"teacher_disagreement_score":0.24585943,"about_ca_system_score_codex":0.00028803034,"about_ca_system_score_gemma":0.00029845024,"threshold_uncertainty_score":0.9991347},"labels":[],"label_agreement":null},{"id":"W4310462658","doi":"10.1002/sim.9618","title":"A nonparametric simultaneous confidence band for biomarker effect on the restricted mean survival time","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Cancer Society; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biomarker; Censoring (clinical trials); Confidence interval; Statistics; Proportional hazards model; Breast cancer; Nonparametric statistics; Survival analysis; Oncology; Smoothing; Sample size determination; Medicine; Econometrics; Mathematics; Internal medicine; Cancer; Biology","score_opus":0.2991692867616709,"score_gpt":0.5212572817545618,"score_spread":0.22208799499289084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310462658","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018372145,0.00011968297,0.95870656,0.0029144706,0.0035111024,0.0059297597,0.0041027153,0.00016955317,0.0061739995],"genre_scores_gemma":[0.4147325,0.00004041961,0.5796731,0.0015001354,0.0006174221,0.0010978075,0.000092067035,0.00016983617,0.0020767371],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99319726,0.0034427026,0.0011717849,0.0005290807,0.0011815826,0.00047759854],"domain_scores_gemma":[0.578089,0.42097047,0.00026794936,0.00045996305,0.00012007306,0.000092562586],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011730382,0.00029265773,0.0010015428,0.0002760601,0.00027296945,0.000020311696,0.00058599946,0.00009331149,0.002396707],"category_scores_gemma":[0.5590194,0.00018942221,0.000068743975,0.0012000784,0.00047391633,0.000012042155,0.00012204959,0.0007146594,0.000026658305],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004391609,0.00059066084,0.00020285606,0.00044801825,0.00028712148,0.0006338484,0.00065847836,0.00019538125,0.001550429,0.8196012,0.12672426,0.044716135],"study_design_scores_gemma":[0.0037462479,0.0041419007,0.00025134062,0.00013001463,0.0002107788,0.000010875125,0.0001372412,0.026325416,0.00012675408,0.9631118,0.0015437185,0.00026388955],"about_ca_topic_score_codex":0.000052570867,"about_ca_topic_score_gemma":0.00001254544,"teacher_disagreement_score":0.547289,"about_ca_system_score_codex":0.00017974817,"about_ca_system_score_gemma":0.00007984268,"threshold_uncertainty_score":0.99851525},"labels":[],"label_agreement":null},{"id":"W4310566398","doi":"10.1002/sim.9605","title":"Point estimation for adaptive trial designs I: A methodological review","year":2022,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council; National Institute for Health and Care Research; Medical Research Council Canada; Department of Health and Social Care; Cancer Research UK; Health and Care Research Wales","keywords":"Estimator; Computer science; Estimation; Type I and type II errors; Point estimation; Point (geometry); Contrast (vision); Set (abstract data type); Econometrics; Statistics; Artificial intelligence; Mathematics","score_opus":0.9563494966257471,"score_gpt":0.7322871607745378,"score_spread":0.22406233585120927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310566398","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.0958632e-9,0.48299348,0.5069911,0.000099774115,0.0012302574,0.007038091,0.0012783484,0.000043404325,0.0003255577],"genre_scores_gemma":[1.5075861e-9,0.4989441,0.4967474,0.00023479915,0.00046098902,0.003247237,0.00017936868,0.00007606356,0.0001100399],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97788954,0.013765913,0.005443167,0.001123923,0.0011301286,0.00064734236],"domain_scores_gemma":[0.5717872,0.42524847,0.0018967566,0.00073647196,0.00014252464,0.00018859073],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04316554,0.00081176154,0.009406961,0.00033608204,0.00013118256,0.000014350118,0.00079817243,0.00050462235,0.0052671293],"category_scores_gemma":[0.75426865,0.00056774676,0.00054484955,0.000814416,0.00048389158,0.000032567008,0.00024580187,0.0017048809,0.000018694029],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012181841,0.000131013,4.397882e-9,0.051359635,0.00012385815,0.000049852777,0.000019826084,2.7359877e-7,6.346444e-9,0.2590469,0.042817567,0.64523286],"study_design_scores_gemma":[0.0068177297,0.0023312839,2.1030896e-8,0.03373432,0.0032682014,0.00001667119,0.000014563743,0.00016939583,1.8429853e-8,0.57573503,0.3775855,0.00032727738],"about_ca_topic_score_codex":0.000010210643,"about_ca_topic_score_gemma":0.000003994642,"teacher_disagreement_score":0.7111031,"about_ca_system_score_codex":0.0005504522,"about_ca_system_score_gemma":0.0005204607,"threshold_uncertainty_score":0.9996774},"labels":[{"model":"gemma","categories":["metaresearch"],"domain":"methods","study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4311277361","doi":"10.1002/sim.9629","title":"Consistent inverse probability of treatment weighted estimation of the average treatment effect with mismeasured time‐dependent confounders","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"National Natural Science Foundation of China","keywords":"Observational error; Computer science; Confounding; Inverse probability; Inverse; Statistics; Function (biology); Estimation; Econometrics; Algorithm; Mathematics; Bayesian probability","score_opus":0.0685040974191771,"score_gpt":0.3618328318137441,"score_spread":0.29332873439456697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311277361","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6733039,0.00009503561,0.31396735,0.0006080114,0.0002646837,0.0077569718,0.0010376851,0.00015695355,0.0028094288],"genre_scores_gemma":[0.9041243,0.000013732936,0.09516802,0.000021328715,0.0000072109515,0.00030457808,0.00007573489,0.000020530726,0.0002645219],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806887,0.00046608955,0.0005531592,0.00021977947,0.0005304121,0.00016167015],"domain_scores_gemma":[0.9973994,0.0015010234,0.00044340256,0.000496142,0.000115967174,0.000044052387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006678597,0.00021990015,0.00060073717,0.00009149074,0.00007354111,0.0000022385384,0.00013644683,0.00003474984,0.00032965827],"category_scores_gemma":[0.0006194586,0.00012113158,0.000039544513,0.00021459095,0.00044350445,0.000024117518,0.00004533308,0.00012792437,6.6438423e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006809243,0.009135941,0.037920237,0.004307691,0.0028445316,0.00043053745,0.04765132,0.06507106,0.033716206,0.7046112,0.004601763,0.08290026],"study_design_scores_gemma":[0.012106175,0.026093002,0.0013583573,0.00061583694,0.0009807457,0.000063331325,0.0009915568,0.048932206,0.03908321,0.86917055,0.0001512736,0.00045373803],"about_ca_topic_score_codex":0.0004118293,"about_ca_topic_score_gemma":0.00034518752,"teacher_disagreement_score":0.23082045,"about_ca_system_score_codex":0.0013665337,"about_ca_system_score_gemma":0.00023672594,"threshold_uncertainty_score":0.49396026},"labels":[],"label_agreement":null},{"id":"W4311277378","doi":"10.1002/sim.9621","title":"An exact regression‐based approach for the estimation of natural direct and indirect effects with a binary outcome and a continuous mediator","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Outcome (game theory); Binary number; Regression; Estimation; Econometrics; Statistics; Regression analysis; Computer science; Natural (archaeology); Mathematics; Mathematical economics; Economics; Biology","score_opus":0.035421275230070264,"score_gpt":0.38196971108714584,"score_spread":0.34654843585707557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311277378","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022959813,0.00037685363,0.97523606,0.00011670219,0.000106490814,0.00085978274,0.00026151128,0.000019128325,0.000063646905],"genre_scores_gemma":[0.46936053,0.0000057991156,0.5303715,0.000048515303,0.00001638745,0.00014410079,0.0000335534,0.000011990379,0.0000076170295],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985964,0.00034227216,0.00033448217,0.0002286944,0.0003363291,0.00016182766],"domain_scores_gemma":[0.98700804,0.012461907,0.00021003255,0.0001999776,0.00005540601,0.00006462561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001370916,0.00015117956,0.000501439,0.000117253076,0.00014376068,0.000009527548,0.00011341679,0.00002985021,0.00002166159],"category_scores_gemma":[0.0050017266,0.00008166362,0.000010270852,0.00019396779,0.00033244904,0.000027181552,0.000037750982,0.00022526024,2.0611921e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030556044,0.0010637242,0.053422567,0.00819393,0.00026368638,0.00022075367,0.009288424,0.0003074213,0.0018816838,0.4046449,0.00442025,0.51323706],"study_design_scores_gemma":[0.0053092674,0.0041497494,0.034158662,0.00038250012,0.00043500346,0.000034652126,0.001563076,0.79816985,0.00024482486,0.155193,0.00003375412,0.00032566968],"about_ca_topic_score_codex":0.000030388523,"about_ca_topic_score_gemma":0.0000086053815,"teacher_disagreement_score":0.7978624,"about_ca_system_score_codex":0.000026224394,"about_ca_system_score_gemma":0.000039895087,"threshold_uncertainty_score":0.5987895},"labels":[],"label_agreement":null},{"id":"W4312118888","doi":"10.1002/sim.9632","title":"Power analyses for stepped wedge designs with multivariate continuous outcomes","year":2022,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Center for Advancing Translational Sciences; National Institute on Aging","keywords":"Multivariate statistics; Univariate; Statistics; Multivariate analysis; Estimator; Sample size determination; Multivariate normal distribution; Computer science; Linear model; Econometrics; Mathematics","score_opus":0.6093308194721376,"score_gpt":0.6148700768653204,"score_spread":0.005539257393182728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312118888","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018423229,0.000040560113,0.9917019,0.00072034635,0.0008802857,0.0016538429,0.0016867286,0.00007133446,0.0014027001],"genre_scores_gemma":[0.059853703,0.000005403467,0.9375214,0.0005865249,0.00010557887,0.00048187698,0.00003040109,0.00007130974,0.001343794],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99588156,0.0011006737,0.001278966,0.00048709018,0.0007701073,0.0004815875],"domain_scores_gemma":[0.9012395,0.09749831,0.00044109364,0.00047002634,0.00020590649,0.0001451221],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0047632405,0.0002987371,0.0014187661,0.00021292732,0.00018588228,0.000014376648,0.00037046484,0.000070345435,0.0022982806],"category_scores_gemma":[0.11262077,0.0002091385,0.00006414561,0.00040247195,0.00036315052,0.000026325342,0.00013066636,0.0004869053,0.000004909634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024630378,0.001011924,0.0073954635,0.00035047712,0.0006958051,0.00042086776,0.002336048,0.00011453378,0.0007626586,0.9140432,0.06377,0.006636009],"study_design_scores_gemma":[0.009952517,0.0021672715,0.0040215,0.00008936273,0.00038565724,0.000009001601,0.0015108917,0.0013740329,0.000057318197,0.9784821,0.001604317,0.00034601917],"about_ca_topic_score_codex":0.00008324609,"about_ca_topic_score_gemma":0.000035722944,"teacher_disagreement_score":0.107857525,"about_ca_system_score_codex":0.00013570636,"about_ca_system_score_gemma":0.000101848,"threshold_uncertainty_score":0.9986138},"labels":[],"label_agreement":null},{"id":"W4312132984","doi":"10.1002/sim.9451","title":"Issue Information","year":2022,"lang":"en","type":"paratext","venue":"Statistics in Medicine","topic":"Human auditory perception and evaluation","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Citation; Information retrieval; Library science; World Wide Web","score_opus":0.022882675844517697,"score_gpt":0.3267985601856628,"score_spread":0.3039158843411451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312132984","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000047304704,0.00062007934,0.09803207,0.00018345691,0.03956136,0.0004428341,0.0013369649,0.00012826225,0.8596477],"genre_scores_gemma":[0.0020490398,0.013462325,0.009373216,0.0028219754,0.013188544,0.0005648679,0.08115395,0.00025652687,0.87712955],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99883336,0.00004821866,0.0004449503,0.000087302695,0.0004325324,0.00015364077],"domain_scores_gemma":[0.9996015,0.00007066705,0.00006652031,0.00016966645,0.000045909364,0.000045728844],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00032472445,0.00016371632,0.00026471613,0.00037207134,0.00004480391,0.000011957555,0.00012279549,0.000108357206,0.75545573],"category_scores_gemma":[0.00010980821,0.00016970163,0.000011422526,0.00016021715,0.000047995567,0.000084367806,0.000019857089,0.0005406686,0.11886545],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002402147,0.0000028464083,9.917277e-7,0.00025854155,0.000008355024,0.000001661884,0.00154477,0.02058995,0.000008191029,0.000048593727,0.9648386,0.012695056],"study_design_scores_gemma":[0.00036539644,0.00004672989,0.00017896907,0.00007366303,0.000014624115,0.0000012712233,0.000383272,0.0182923,7.7841935e-7,0.00018599704,0.980303,0.00015400058],"about_ca_topic_score_codex":0.000007835934,"about_ca_topic_score_gemma":0.000022683178,"teacher_disagreement_score":0.63659024,"about_ca_system_score_codex":0.0003357609,"about_ca_system_score_gemma":0.000035823778,"threshold_uncertainty_score":0.8818206},"labels":[],"label_agreement":null},{"id":"W4317359118","doi":"10.1002/sim.9650","title":"Practical strategies for operationalizing optimal allocation in stratified cluster‐based outcome‐dependent sampling designs","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Environmental Health Sciences; National Institutes of Health; Grand Challenges Canada; Harvard T.H. Chan School of Public Health; Government of the United Kingdom; Bill and Melinda Gates Foundation; National Heart, Lung, and Blood Institute; United States Agency for International Development","keywords":"Computer science; Statistics; Sampling design; Covariate; Sampling (signal processing); Sample size determination; Cluster sampling; Inverse probability weighting; Outcome (game theory); Weighting; Missing data; Stratified sampling; Adaptive sampling; Mathematical optimization; Mathematics; Estimator; Filter (signal processing); Population; Monte Carlo method","score_opus":0.3702937272011516,"score_gpt":0.5299317334396962,"score_spread":0.15963800623854463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317359118","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015280364,0.0000070879064,0.9954178,0.001518401,0.00024106939,0.000756046,0.00017698911,0.000057448025,0.00029716818],"genre_scores_gemma":[0.11099511,0.0000072698044,0.8882411,0.00020159989,0.00010607906,0.00019477317,0.00018158567,0.000026904667,0.000045580207],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99761033,0.00026139332,0.00095170207,0.00034633698,0.00045021504,0.00038002746],"domain_scores_gemma":[0.98580825,0.013569977,0.0001529112,0.00020364409,0.00017949258,0.000085726955],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002859913,0.00019795449,0.00044417699,0.00027720755,0.00008540005,0.00006538367,0.00013365915,0.00010756679,0.00014268565],"category_scores_gemma":[0.014290114,0.00017229664,0.000020260324,0.00037802462,0.00013393759,0.000114726856,0.0000279884,0.00029702403,0.0000075223766],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113637,0.000082502076,0.00048584712,0.0003305124,0.000010436725,0.000041410487,0.00058865955,0.001193934,0.00056714943,0.9921469,0.0017340966,0.0027049105],"study_design_scores_gemma":[0.001492995,0.00025452825,0.0018039155,0.00019392128,0.00003221912,0.000003144958,0.002142471,0.29595608,0.000051239836,0.69786865,0.000028667562,0.00017215837],"about_ca_topic_score_codex":0.00007477292,"about_ca_topic_score_gemma":0.0006200386,"teacher_disagreement_score":0.29476213,"about_ca_system_score_codex":0.000112181675,"about_ca_system_score_gemma":0.00030695752,"threshold_uncertainty_score":0.99401295},"labels":[],"label_agreement":null},{"id":"W4317869010","doi":"10.1002/sim.9666","title":"Two‐phase designs with current status data","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Current (fluid); Phase (matter); Computer science; Statistics; Econometrics; Mathematics; Physics; Thermodynamics","score_opus":0.5036974145021728,"score_gpt":0.6117296971940839,"score_spread":0.10803228269191112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317869010","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005069629,0.0009102339,0.98700774,0.00040628968,0.0012119298,0.00045301457,0.0012201361,0.0000931062,0.0036279187],"genre_scores_gemma":[0.093087524,0.00057821075,0.90346503,0.00029733544,0.00036775318,0.00004422246,0.0010198551,0.000060213984,0.0010798682],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99504834,0.0006010839,0.00081599836,0.0007968413,0.0021830767,0.0005546756],"domain_scores_gemma":[0.9924915,0.0053190254,0.00020418165,0.0015018594,0.00020087294,0.00028260038],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0074989665,0.000208487,0.0004837239,0.0006016292,0.00008807986,0.00006657415,0.0012558027,0.000032118707,0.0010874065],"category_scores_gemma":[0.011915169,0.00013227419,0.000011122579,0.0024489474,0.0005104751,0.00022109796,0.00041703027,0.00030263083,0.0004586357],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004192258,0.00025976208,0.005574651,0.000023748962,0.00002336635,0.00069193257,0.0024397892,0.00041654354,0.0028958274,0.029259542,0.29515538,0.66284025],"study_design_scores_gemma":[0.025738787,0.0049873055,0.01961633,0.0006117888,0.00013979955,0.00005591789,0.015037183,0.41575345,0.00095890096,0.29893425,0.21683505,0.0013312433],"about_ca_topic_score_codex":0.0001540818,"about_ca_topic_score_gemma":0.000115721195,"teacher_disagreement_score":0.661509,"about_ca_system_score_codex":0.00007645118,"about_ca_system_score_gemma":0.00019664111,"threshold_uncertainty_score":0.9998257},"labels":[],"label_agreement":null},{"id":"W4318024824","doi":"10.1002/sim.9658","title":"Propensity score matching after multiple imputation when a confounder has missing data","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"Propensity score matching; Causal inference; Missing data; Imputation (statistics); Confounding; Statistics; Observational study; Average treatment effect; Matching (statistics); Estimator; Computer science; Confidence interval; Inference; Covariate; Econometrics; Mathematics; Artificial intelligence","score_opus":0.4066710686130003,"score_gpt":0.46171335322110957,"score_spread":0.05504228460810928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318024824","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03081481,0.000036582045,0.9666271,0.00090032764,0.00018831898,0.00050565973,0.00020679642,0.00036261443,0.0003577975],"genre_scores_gemma":[0.4986424,0.000025084715,0.50017637,0.00027088466,0.00011129465,0.000033723463,0.00052229007,0.000043378102,0.00017454204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983574,0.00009351783,0.00049065636,0.00035856312,0.00039615744,0.0003036839],"domain_scores_gemma":[0.997313,0.0016609111,0.00016378322,0.0006535743,0.00013361021,0.00007508329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001178013,0.00018000689,0.0003605257,0.00017856449,0.00009070049,0.000040220126,0.0002963105,0.000073516945,0.0001458393],"category_scores_gemma":[0.005262186,0.00015061391,0.000008978387,0.00024666882,0.00026349328,0.0002205848,0.00028221568,0.00031219484,0.000025650128],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067127903,0.00044040222,0.06816714,0.0042719417,0.00023815034,0.00408502,0.05490792,0.00018369795,0.015710454,0.346765,0.31710684,0.18745214],"study_design_scores_gemma":[0.00053006934,0.00006250145,0.012466019,0.00062072626,0.000033540473,0.0000110972605,0.000401085,0.011507642,0.000107716834,0.9736603,0.00041766115,0.00018167018],"about_ca_topic_score_codex":0.00023226977,"about_ca_topic_score_gemma":0.00048550582,"teacher_disagreement_score":0.62689525,"about_ca_system_score_codex":0.000094762465,"about_ca_system_score_gemma":0.00008239574,"threshold_uncertainty_score":0.6299708},"labels":[],"label_agreement":null},{"id":"W4318067345","doi":"10.1002/sim.9665","title":"Measuring the performance of prediction models to personalize treatment choice","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; ZonMw; European Commission; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Computer science; Covariate; Calibration; Machine learning; Baseline (sea); Outcome (game theory); Range (aeronautics); Artificial intelligence; Predictive modelling; Data mining; Statistics; Mathematics","score_opus":0.2535139144086483,"score_gpt":0.4251422307621626,"score_spread":0.17162831635351433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318067345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.48179165,0.000120728124,0.5119709,0.0009334237,0.0002778482,0.0011769306,0.00031567662,0.0003825582,0.0030303218],"genre_scores_gemma":[0.92949396,0.00049017003,0.069059014,0.000063967214,0.00011278067,0.00015792702,0.000026308695,0.000025612186,0.00057028263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99895746,0.000042436437,0.0003269897,0.00014156871,0.00034760172,0.00018397407],"domain_scores_gemma":[0.99847007,0.001043003,0.00008557617,0.0002554962,0.00010228551,0.00004359917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005356165,0.0001138824,0.00023397147,0.00013833752,0.000046853733,0.0000026040236,0.0001325531,0.000032632983,0.00003490682],"category_scores_gemma":[0.00078461564,0.00007208513,0.000012348723,0.0003874168,0.00009801732,0.00005173915,0.000033924392,0.00010171805,0.0000058894693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021065497,0.00031192385,0.01195835,0.0011496537,0.0001745661,0.00005054548,0.05671098,0.0136581585,0.012313688,0.766417,0.043397516,0.093646936],"study_design_scores_gemma":[0.0013770588,0.0022619544,0.009245682,0.0012527964,0.00012136201,0.00000882517,0.0025477537,0.21694823,0.0064604287,0.7580605,0.0014394848,0.00027590504],"about_ca_topic_score_codex":0.00012966026,"about_ca_topic_score_gemma":0.00011366068,"teacher_disagreement_score":0.4477023,"about_ca_system_score_codex":0.00014568178,"about_ca_system_score_gemma":0.00002871421,"threshold_uncertainty_score":0.29395464},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"grok","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4318755449","doi":"10.1002/sim.9675","title":"Multistate models as a framework for estimand specification in clinical trials of complex processes","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Econometrics; Computer science; Estimator; Limiting; Statistics; Artificial intelligence; Mathematics","score_opus":0.7226251117965159,"score_gpt":0.6472965689702329,"score_spread":0.07532854282628298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318755449","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0036453726,0.000060097584,0.9938658,0.0004001733,0.00010118189,0.0011758633,0.00036037114,0.000105174106,0.00028595232],"genre_scores_gemma":[0.10934044,0.00090297824,0.88915855,0.000057155776,0.00010539659,0.00013219842,0.00018841011,0.00003132136,0.00008355544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968501,0.00025635725,0.0021155397,0.00026709915,0.00028456972,0.00022635718],"domain_scores_gemma":[0.96873844,0.029938841,0.0006828304,0.00028701845,0.00029615685,0.000056736724],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006827249,0.00014686478,0.0009826015,0.0002672882,0.00002075436,0.0000051692705,0.0001817179,0.00012616986,0.00006023993],"category_scores_gemma":[0.129482,0.00012221532,0.000028898512,0.000571002,0.00028301682,0.00006114843,0.00003412666,0.0002325101,0.0000032301812],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021096724,0.00013941778,0.00032437555,0.0009582142,0.000015496127,0.000018205224,0.0013378263,0.00030285257,0.00023162551,0.9659793,0.008895449,0.021586264],"study_design_scores_gemma":[0.0010930994,0.00030817144,0.00045743908,0.0008339437,0.00002816287,9.123155e-7,0.00039930097,0.040354576,0.00024905137,0.9559451,0.0002242577,0.00010600421],"about_ca_topic_score_codex":0.000038609684,"about_ca_topic_score_gemma":0.00011005222,"teacher_disagreement_score":0.12265475,"about_ca_system_score_codex":0.00004688031,"about_ca_system_score_gemma":0.00010305611,"threshold_uncertainty_score":0.8778507},"labels":[],"label_agreement":null},{"id":"W4319058127","doi":"10.1002/sim.9663","title":"The Personalised Randomized Controlled Trial: Evaluation of a new trial design","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Menzies Centre for Australian Studies, King's College London, University of London; Medical Research Council Canada; King's College London; Medical Research Council; National Institute for Health and Care Research","keywords":"Randomized controlled trial; Pooling; Randomization; Computer science; Clinical trial; Ranking (information retrieval); Outcome (game theory); Medicine; Intervention (counseling); Machine learning; Artificial intelligence; Mathematics; Surgery; Psychiatry","score_opus":0.32244574998036885,"score_gpt":0.5144343715594577,"score_spread":0.19198862157908886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319058127","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061436775,0.0002716038,0.9702922,0.0011354896,0.00089903903,0.019563455,0.000015926124,0.00017985338,0.0014987511],"genre_scores_gemma":[0.2978032,0.0029166231,0.67405933,0.00028796727,0.002367116,0.013951214,0.00016502908,0.00021478477,0.008234729],"study_design_codex":"randomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9947929,0.0021305745,0.0013510754,0.00017849848,0.00130981,0.00023715345],"domain_scores_gemma":[0.9621731,0.03644032,0.00060905976,0.0003017912,0.00042070355,0.000055011496],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027971735,0.00016199528,0.0014204386,0.0001820295,0.000058131485,0.000008561518,0.0001966222,0.00007405569,0.00020364128],"category_scores_gemma":[0.13939115,0.00008930849,0.00008321807,0.00039153904,0.00034618593,0.00003155602,0.000024068651,0.00018420604,0.0000044660123],"study_design_candidate":"randomized_trial","study_design_consensus":"randomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.80736595,0.000030056164,1.4070159e-7,0.000013496883,0.00006963203,0.0000027161932,0.000955619,0.00002671525,0.00007341924,0.16953619,0.018458847,0.0034672176],"study_design_scores_gemma":[0.5040283,0.00037582268,4.2514534e-7,0.00006271382,0.00024746705,2.1734476e-7,0.00022114739,0.015551906,0.000038774066,0.4794095,0.000021139722,0.000042603995],"about_ca_topic_score_codex":0.000048815156,"about_ca_topic_score_gemma":0.000033079377,"teacher_disagreement_score":0.3098733,"about_ca_system_score_codex":0.000089242785,"about_ca_system_score_gemma":0.0003731539,"threshold_uncertainty_score":0.9694501},"labels":[],"label_agreement":null},{"id":"W4319063464","doi":"10.1002/sim.9677","title":"Conditional concordance‐assisted learning under matched case‐control design for combining biomarkers for population screening","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"University of Texas Health Science Center at Houston; National Center for Advancing Translational Sciences; University of Texas at Austin; National Institute of Diabetes and Digestive and Kidney Diseases; Center for Clinical and Translational Sciences, University of Texas Health Science Center at Houston; National Cancer Institute; National Institutes of Health; Cancer Prevention and Research Institute of Texas","keywords":"Concordance; Confounding; Logistic regression; Biomarker; Population; Discriminative model; Prostate cancer; Computer science; Medicine; Case-control study; Oncology; Machine learning; Statistics; Cancer; Internal medicine; Mathematics; Environmental health; Biology","score_opus":0.530148671326099,"score_gpt":0.5642905653385226,"score_spread":0.034141894012423624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319063464","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012358204,0.00001980863,0.99373114,0.00066260336,0.0007231455,0.0020328138,0.0013608629,0.00018092165,0.000052906693],"genre_scores_gemma":[0.19742548,0.000005745872,0.801045,0.00021342708,0.00030961793,0.00044582796,0.000364388,0.00006996942,0.00012052801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961304,0.000980591,0.0014631383,0.00046512554,0.00043848858,0.00052227266],"domain_scores_gemma":[0.8091722,0.18981977,0.00045467663,0.00017715772,0.00025423235,0.000121960315],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009850793,0.00026359007,0.0010003584,0.0002798527,0.00027100526,0.0000257717,0.00014558145,0.00018613873,0.00018623326],"category_scores_gemma":[0.17255142,0.00024434144,0.000077956596,0.00046111303,0.00027812447,0.000050452545,0.00003026897,0.00031023138,0.0000046987507],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021600567,0.0001248682,0.0020609358,0.0010447705,0.0006773513,0.00046708094,0.00039887158,0.0061572436,0.0005857436,0.8945986,0.028308569,0.06341589],"study_design_scores_gemma":[0.008610307,0.0005134684,0.00443037,0.00028909682,0.0002708624,0.000039329236,0.000917208,0.21529908,0.000012640051,0.7693537,0.000048284033,0.00021569253],"about_ca_topic_score_codex":0.00006917219,"about_ca_topic_score_gemma":0.000044019453,"teacher_disagreement_score":0.20914184,"about_ca_system_score_codex":0.000102430386,"about_ca_system_score_gemma":0.00006059226,"threshold_uncertainty_score":0.9963955},"labels":[],"label_agreement":null},{"id":"W4321351204","doi":"10.1002/sim.9685","title":"Impute‐then‐exclude versus exclude‐then‐impute: Lessons when imputing a variable used both in cohort creation and as an independent variable in the analysis model","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research; Ontario Ministry of Health and Long-Term Care; Heart and Stroke Foundation of Canada","keywords":"Missing data; Imputation (statistics); Statistics; Sample size determination; Variable (mathematics); Random variable; Computer science; Mathematics; Medicine; Econometrics","score_opus":0.09486507976885547,"score_gpt":0.4341099087394667,"score_spread":0.33924482897061126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321351204","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022832552,0.000030474605,0.9735207,0.0005566003,0.00016209342,0.00058325724,0.00025968955,0.000059979586,0.00199464],"genre_scores_gemma":[0.22312301,0.00012922217,0.7760537,0.0001756594,0.00011922349,0.0001067409,0.00013836057,0.000043530657,0.00011052158],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960649,0.00075773353,0.001021531,0.000667986,0.0008254889,0.00066238065],"domain_scores_gemma":[0.98922193,0.009631381,0.00026130836,0.00061618397,0.00011283083,0.00015635842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067496966,0.0003299466,0.0008794083,0.0007744321,0.00012989358,0.00008197974,0.00043358043,0.00020193041,0.00017250654],"category_scores_gemma":[0.00731872,0.000237325,0.000029885272,0.0019775846,0.00021236078,0.00013702779,0.00015720262,0.00055238174,0.0000047330877],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012734126,0.00015227037,0.011789311,0.000117373675,0.00013260846,0.00014398526,0.008429614,0.0009851122,0.000120068195,0.9667372,0.00063944247,0.010625675],"study_design_scores_gemma":[0.0016266704,0.00014280138,0.017461395,0.00016159072,0.00026210974,0.0000046269583,0.00091655034,0.36504558,0.0000025649101,0.6141801,0.00001817137,0.00017787078],"about_ca_topic_score_codex":0.002495173,"about_ca_topic_score_gemma":0.0013632611,"teacher_disagreement_score":0.36406046,"about_ca_system_score_codex":0.00020747614,"about_ca_system_score_gemma":0.0002156583,"threshold_uncertainty_score":0.9677833},"labels":[],"label_agreement":null},{"id":"W4321605231","doi":"10.1002/sim.9691","title":"Identifying important gene signatures of BMI using network structure‐aided nonparametric quantile regression","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institute of Diabetes and Digestive and Kidney Diseases; National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Quantile regression; Computer science; Nonparametric statistics; Penalty method; Regression; Data mining; Machine learning; Mathematics; Statistics; Mathematical optimization","score_opus":0.021451876655548905,"score_gpt":0.32355374604990617,"score_spread":0.30210186939435724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321605231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85563916,0.0051076165,0.1367508,0.00005002225,0.001566724,0.0003906257,0.00030352798,0.000021424568,0.00017011103],"genre_scores_gemma":[0.9516873,0.001056815,0.045741297,0.00010856328,0.00050060917,0.000002970052,0.0008014497,0.000027411023,0.000073596435],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841416,0.000049289698,0.0006865379,0.00023741135,0.00026437745,0.00034825347],"domain_scores_gemma":[0.9990784,0.00008593657,0.00034781138,0.00032343698,0.00008984981,0.00007456766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059332646,0.0001764357,0.00033566967,0.00019243424,0.00006861217,0.0000091597985,0.00019643399,0.00018743321,0.000044227054],"category_scores_gemma":[0.0003145932,0.000141252,0.00003400365,0.0006728844,0.00014435542,0.0000033169347,0.00013222992,0.00020175679,0.0000014136543],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028813392,0.000046988524,0.017984219,0.0005047951,0.00020944967,0.00013666,0.000629527,0.046653714,0.84196657,0.005428389,0.07461008,0.011541476],"study_design_scores_gemma":[0.008729263,0.0020546834,0.06580729,0.0023795164,0.00046896678,0.00013616528,0.0020622755,0.6590128,0.09541595,0.15467408,0.007050334,0.0022086676],"about_ca_topic_score_codex":0.00006454403,"about_ca_topic_score_gemma":0.00008459709,"teacher_disagreement_score":0.7465506,"about_ca_system_score_codex":0.000018127375,"about_ca_system_score_gemma":0.00006601138,"threshold_uncertainty_score":0.576009},"labels":[],"label_agreement":null},{"id":"W4323350148","doi":"10.1002/sim.9704","title":"A two‐level copula joint model for joint analysis of longitudinal and competing risks data","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Alberta Health Services","funders":"Natural Sciences and Engineering Research Council of Canada; KU Leuven","keywords":"Copula (linguistics); Econometrics; Covariate; Quantile; Computer science; Statistics; Bayesian probability; Marginal model; Mathematics; Regression analysis","score_opus":0.6336928598209846,"score_gpt":0.5331565992678886,"score_spread":0.10053626055309595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323350148","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01046115,0.00004294755,0.9829473,0.00018484978,0.00007879201,0.00025634284,0.005809259,0.000023781535,0.00019556962],"genre_scores_gemma":[0.22961211,0.00007268407,0.7697561,0.000036398385,0.000038131053,0.000015812539,0.00040354836,0.000016178798,0.000049028073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980357,0.00010771139,0.00085694395,0.00037479462,0.0003508091,0.00027404155],"domain_scores_gemma":[0.9938594,0.0050501875,0.00026966713,0.000532158,0.00019151495,0.00009705706],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031065291,0.0001582132,0.0008957834,0.00040902113,0.000057303252,0.000009382571,0.00019786485,0.000045639466,0.000075563024],"category_scores_gemma":[0.020791441,0.0001276924,0.000026778729,0.00070665,0.00027695418,0.000026547534,0.00023139625,0.00016990409,9.981912e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004899656,0.00007747131,0.0052257166,0.0008122308,0.00043176775,0.00003002779,0.0016894155,0.001063146,0.00038157872,0.9669973,0.0043939664,0.018848382],"study_design_scores_gemma":[0.00058849266,0.00006628808,0.016290966,0.0001422681,0.000630234,9.954512e-7,0.00032976785,0.6406205,0.000008322759,0.34123492,0.0000035815026,0.00008360187],"about_ca_topic_score_codex":0.00041497583,"about_ca_topic_score_gemma":0.0004816366,"teacher_disagreement_score":0.6395574,"about_ca_system_score_codex":0.000024964733,"about_ca_system_score_gemma":0.00004509759,"threshold_uncertainty_score":0.98745686},"labels":[],"label_agreement":null},{"id":"W4360938449","doi":"10.1002/sim.9715","title":"Penalized maximum likelihood inference under the mixture cure model in sparse data","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Ontario Institute for Cancer Research","keywords":"Inference; Maximum likelihood; Expectation–maximization algorithm; Computer science; Mixture model; Statistics; Econometrics; Mathematics; Artificial intelligence","score_opus":0.22343168482760778,"score_gpt":0.4621887924704388,"score_spread":0.23875710764283103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360938449","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018894773,0.000112552785,0.99029243,0.0039015734,0.0002926412,0.0003965352,0.00095725624,0.000065806795,0.0020917333],"genre_scores_gemma":[0.13905245,0.0011010369,0.85677695,0.001547961,0.00024195573,0.0000812892,0.000526862,0.00007611,0.00059539505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99737227,0.000316431,0.00071741996,0.00046429556,0.00060606765,0.0005235021],"domain_scores_gemma":[0.9910376,0.007463889,0.00014476581,0.0011231258,0.00011357181,0.00011706658],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002637884,0.0002489031,0.00053469784,0.00018848796,0.00007068964,0.000024182737,0.0009011857,0.00012318527,0.0004550055],"category_scores_gemma":[0.01313744,0.00015695715,0.000014629572,0.0008521688,0.00034585065,0.000062433115,0.00039975368,0.0007219186,0.000049262475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037817077,0.000075570264,0.00042699365,0.00017285818,0.000017966415,0.00011795656,0.0014420483,0.00019704373,0.000082137856,0.9121595,0.071199216,0.014070921],"study_design_scores_gemma":[0.0007532161,0.00004492659,0.0019843318,0.00023439665,0.00003275737,0.0000027796852,0.0006675544,0.29283366,0.000002802923,0.7029619,0.00034818976,0.00013342583],"about_ca_topic_score_codex":0.00024655258,"about_ca_topic_score_gemma":0.001029784,"teacher_disagreement_score":0.29263663,"about_ca_system_score_codex":0.0000504317,"about_ca_system_score_gemma":0.00017017868,"threshold_uncertainty_score":0.9951753},"labels":[],"label_agreement":null},{"id":"W4362455928","doi":"10.1002/sim.9709","title":"New late‐emphasis and combination tests based on infimum and supremum logrank statistics with application in oncology trials","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ligue Contre le Cancer","keywords":"Infimum and supremum; Statistics; Log-rank test; Medicine; Clinical trial; Hazard; Survival analysis; Statistical hypothesis testing; Rank (graph theory); Computer science; Mathematics; Internal medicine","score_opus":0.36581877912489835,"score_gpt":0.575420074643495,"score_spread":0.20960129551859663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362455928","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006754394,0.000033897504,0.9877119,0.0023998276,0.00035652437,0.0015036563,0.0006026272,0.00008543146,0.0005517373],"genre_scores_gemma":[0.04873318,0.0003094432,0.9498528,0.00045193057,0.00019963001,0.00012911977,0.00013712634,0.00005660196,0.00013013008],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9952948,0.0015606455,0.001624921,0.00054804515,0.00058810634,0.00038349128],"domain_scores_gemma":[0.86313915,0.13575688,0.00045137617,0.00031648,0.0001355762,0.0002005342],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0099542,0.0002889867,0.0014276998,0.00055454765,0.000056899113,0.000022690358,0.0001438955,0.00024072245,0.0001045245],"category_scores_gemma":[0.14537239,0.00022472668,0.000015658918,0.000862808,0.0004539839,0.000037385707,0.00005394918,0.00046459903,0.000009283803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013747901,0.00040385284,0.017827386,0.0006528243,0.000060735274,0.00025157645,0.0009676529,0.000120706536,0.00021223625,0.47212937,0.024074802,0.48192406],"study_design_scores_gemma":[0.010513413,0.0020320667,0.0372665,0.00037713724,0.00015066474,0.0000039753068,0.00012742216,0.03281161,0.00002187314,0.9158426,0.0006174169,0.0002353248],"about_ca_topic_score_codex":0.00026155685,"about_ca_topic_score_gemma":0.0007797392,"teacher_disagreement_score":0.48168874,"about_ca_system_score_codex":0.0001334833,"about_ca_system_score_gemma":0.0001789963,"threshold_uncertainty_score":0.9164088},"labels":[],"label_agreement":null},{"id":"W4362458453","doi":"10.1002/sim.9721","title":"A Bayesian approach for two‐stage multivariate Mendelian randomization with mixed outcomes","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Ottawa; Princess Margaret Cancer Centre; Ottawa Hospital; Queen's University; University of Toronto; University Health Network","funders":"Princess Margaret Cancer Foundation","keywords":"Mendelian randomization; Multivariate statistics; Bayesian probability; Randomization; Multivariate analysis; Statistics; Computer science; Econometrics; Mathematics; Randomized controlled trial; Internal medicine; Medicine; Biology; Genetic variants; Genetics","score_opus":0.01779488646499171,"score_gpt":0.3049085384656339,"score_spread":0.2871136520006422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362458453","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009209533,0.00005979528,0.9885184,0.00015054812,0.00019338763,0.00069984025,0.00027805768,0.000021667867,0.0008687633],"genre_scores_gemma":[0.455119,0.000016800364,0.53995454,0.00016356303,0.00018319166,0.0001635446,0.0023331398,0.000039146933,0.002027072],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9989297,0.00006634671,0.00026714292,0.00031660753,0.00016315465,0.00025708848],"domain_scores_gemma":[0.9994121,0.00011777164,0.00008254056,0.00023890918,0.00007633079,0.000072333496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039781348,0.00016536236,0.00026557216,0.00009327176,0.000059697813,0.000006726614,0.00012934503,0.00007168818,0.000022516473],"category_scores_gemma":[0.00035118655,0.00011970949,0.000021340493,0.00017387448,0.00012627595,0.0000017311238,0.000030589224,0.000073093724,0.0000018315448],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013168923,0.0010682073,0.09666067,0.0015808196,0.0016729026,0.000033176388,0.006488766,0.31901592,0.0447878,0.37120315,0.07632295,0.06799672],"study_design_scores_gemma":[0.19863412,0.0063520395,0.5754676,0.000283593,0.0006549661,0.000017126898,0.0050953,0.12993465,0.0039594276,0.05329744,0.023729308,0.002574443],"about_ca_topic_score_codex":0.000041982785,"about_ca_topic_score_gemma":0.00007036942,"teacher_disagreement_score":0.4788069,"about_ca_system_score_codex":0.000008702417,"about_ca_system_score_gemma":0.000048403133,"threshold_uncertainty_score":0.48816115},"labels":[],"label_agreement":null},{"id":"W4362507535","doi":"10.1002/sim.9733","title":"Online error rate control for platform trials","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Innovative Medicines Initiative; Medical Research Council Canada; European Commission; Department of Health and Social Care; National Institute for Health and Care Research; Springworks Therapeutics; Medical Research Council; European Federation of Pharmaceutical Industries and Associations","keywords":"False discovery rate; Bonferroni correction; Word error rate; Computer science; Multiple comparisons problem; Type I and type II errors; Null hypothesis; Statistical hypothesis testing; Protocol (science); Control (management); Error detection and correction; Statistics; Artificial intelligence; Algorithm; Mathematics; Medicine","score_opus":0.7550225175797985,"score_gpt":0.6523072582200737,"score_spread":0.10271525935972481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362507535","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013659557,0.000037909118,0.98219603,0.003179685,0.0025336677,0.002207299,0.007804569,0.0002010067,0.00047387287],"genre_scores_gemma":[0.0075113378,0.00013394094,0.98771113,0.0010945131,0.0017302596,0.0003044123,0.00020422666,0.00008998373,0.0012202109],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941457,0.0012422103,0.0029552411,0.00048467887,0.00053597044,0.0006361849],"domain_scores_gemma":[0.70201445,0.2967349,0.0005039951,0.00037333957,0.00020924714,0.00016404485],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03278321,0.00030005156,0.0022935697,0.00030580332,0.00007933337,0.000014894248,0.00033438706,0.00021238835,0.0007267047],"category_scores_gemma":[0.7079838,0.000218111,0.000114584116,0.0005935699,0.00037069662,0.00003579993,0.000054103726,0.00040588502,0.000054789194],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00082206796,0.0002043928,0.00010096869,0.00048035503,0.00015089368,0.000096922726,0.00025210445,0.00001991175,0.00026992522,0.7780565,0.18616891,0.03337707],"study_design_scores_gemma":[0.011192204,0.0005902082,0.0010136005,0.00028045935,0.0002932817,0.0000018356685,0.00029406085,0.0139477635,0.000037715832,0.9687779,0.003347157,0.00022381007],"about_ca_topic_score_codex":0.000022106255,"about_ca_topic_score_gemma":0.00007929522,"teacher_disagreement_score":0.6752006,"about_ca_system_score_codex":0.00008824127,"about_ca_system_score_gemma":0.000098661076,"threshold_uncertainty_score":0.9959532},"labels":[],"label_agreement":null},{"id":"W4362658038","doi":"10.1002/sim.9734","title":"Point estimation for adaptive trial designs <scp>II</scp>: Practical considerations and guidance","year":2023,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Cambridge Biomedical Research Centre; Medical Research Council; National Institute for Health and Care Research; Medical Research Council Canada; Department of Health and Social Care; Cancer Research UK; Health and Care Research Wales","keywords":"Estimation; Computer science; Point estimation; Point (geometry); Econometrics; Statistics; Mathematical optimization; Mathematics; Economics","score_opus":0.8358348090652867,"score_gpt":0.6690181020821543,"score_spread":0.16681670698313245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362658038","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.9204883e-7,0.16793142,0.8216316,0.00025013014,0.0014499744,0.006058553,0.002288972,0.000099041885,0.0002901156],"genre_scores_gemma":[2.3284187e-7,0.37712643,0.6204691,0.00007244316,0.00071622734,0.001119161,0.00007811776,0.00010195403,0.0003163387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9918244,0.0022871972,0.0037140287,0.000894611,0.0007150955,0.0005647039],"domain_scores_gemma":[0.6038005,0.39418584,0.0011149897,0.00041793648,0.00028421517,0.00019654333],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.011382448,0.00063440925,0.0042334506,0.00036219548,0.00023441656,0.000049766713,0.00016156197,0.00063382846,0.000061962804],"category_scores_gemma":[0.81541,0.0004997159,0.00016139273,0.0004485203,0.00080034084,0.00007026196,0.00017669139,0.0010502394,0.000024402814],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022791242,0.00013807043,6.011793e-8,0.009090702,0.00020919488,0.00011580333,0.00019012617,0.0000011002439,9.678866e-8,0.80224645,0.09175807,0.096022405],"study_design_scores_gemma":[0.009957608,0.0020683387,5.1193825e-7,0.012217984,0.0024049713,0.000047758036,0.00011063611,0.0023281476,4.590624e-7,0.9318815,0.038782205,0.00019990024],"about_ca_topic_score_codex":0.000013121862,"about_ca_topic_score_gemma":0.000036285353,"teacher_disagreement_score":0.80402756,"about_ca_system_score_codex":0.0002124077,"about_ca_system_score_gemma":0.0007533566,"threshold_uncertainty_score":0.9997454},"labels":[],"label_agreement":null},{"id":"W4365459023","doi":"10.1002/sim.9727","title":"Causal inference with longitudinal data subject to irregular assessment times","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; Institute for Clinical Evaluative Sciences; University of Toronto; SickKids Foundation; Hospital for Sick Children; Public Health Ontario","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Causal inference; Inference; Subject (documents); Computer science; Longitudinal data; Statistics; Econometrics; Statistical inference; Artificial intelligence; Mathematics; Data mining","score_opus":0.21944373833936742,"score_gpt":0.5103172274469393,"score_spread":0.2908734891075719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365459023","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007964053,0.000017261395,0.9871262,0.0009890166,0.00013089908,0.00055342045,0.00040786868,0.00041024297,0.0024010595],"genre_scores_gemma":[0.2825489,0.00007546084,0.7156751,0.00014011524,0.0001280189,0.00008526386,0.0005586088,0.000053637537,0.00073488214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99781847,0.00008671858,0.0004598812,0.00050579297,0.00069065875,0.00043849493],"domain_scores_gemma":[0.99636483,0.0020560657,0.00012611844,0.0011377676,0.00016812197,0.00014708428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012515098,0.00024757706,0.00048181694,0.0003226321,0.00006120579,0.000019159732,0.0006077879,0.0000620002,0.00034288492],"category_scores_gemma":[0.0033921173,0.0001868515,0.00000698036,0.00088257424,0.00023447293,0.00013471159,0.00038941728,0.00034686556,0.000044221953],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065800974,0.00010630785,0.020619689,0.00027084697,0.00006483983,0.00095486594,0.00081334414,0.00009351039,0.0006855448,0.83184767,0.13524978,0.009227788],"study_design_scores_gemma":[0.00095668295,0.0013135264,0.04186775,0.0010255427,0.00010628761,0.000026769465,0.00067718996,0.007455991,0.0002921595,0.9436412,0.002102355,0.00053454726],"about_ca_topic_score_codex":0.00015129712,"about_ca_topic_score_gemma":0.0008660852,"teacher_disagreement_score":0.27458486,"about_ca_system_score_codex":0.00012680989,"about_ca_system_score_gemma":0.0001667354,"threshold_uncertainty_score":0.7619583},"labels":[],"label_agreement":null},{"id":"W4376121573","doi":"10.1002/sim.9765","title":"Incorporating biological knowledge in analyses of environmental mixtures and health","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of Environmental Health Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Prior probability; Computer science; Bayesian probability; Prior information; Nonparametric statistics; Dirichlet distribution; Set (abstract data type); Index (typography); Data mining; Statistics; Econometrics; Machine learning; Mathematics; Artificial intelligence","score_opus":0.23700524302746534,"score_gpt":0.5039231798181436,"score_spread":0.26691793679067827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376121573","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12557712,0.0011967666,0.8697774,0.0006741342,0.00019949098,0.00046035266,0.00060544355,0.00004830473,0.0014609948],"genre_scores_gemma":[0.57731956,0.00027815354,0.4222828,0.000040364575,0.000028563123,0.000006586499,0.000024977822,0.000006583301,0.000012402228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99872804,0.00022490072,0.00054900936,0.00017828324,0.00013767157,0.00018212422],"domain_scores_gemma":[0.99687046,0.0028086763,0.00014179581,0.00010357346,0.000010630972,0.00006483651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013648404,0.000103517355,0.00045202425,0.0002092983,0.000024413723,0.0000025724325,0.00007082551,0.000047733407,0.00009711721],"category_scores_gemma":[0.0021051017,0.00007407189,0.000010122679,0.0003395184,0.00034822588,0.000011888708,0.000059943577,0.00016110967,0.0000023503153],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021773234,0.00015593473,0.052497447,0.00045023704,0.00001893529,0.00008218237,0.0018448167,0.0000016609282,0.0027811786,0.82248104,0.0025338605,0.11713093],"study_design_scores_gemma":[0.00046630256,0.0002691571,0.1501757,0.00023041577,0.000007586153,0.0000025377938,0.0007220612,0.0028960695,0.00006755936,0.8450789,0.000011625771,0.00007206282],"about_ca_topic_score_codex":0.00012698922,"about_ca_topic_score_gemma":0.00015142944,"teacher_disagreement_score":0.45174247,"about_ca_system_score_codex":0.00003451582,"about_ca_system_score_gemma":0.00003258704,"threshold_uncertainty_score":0.3020564},"labels":[],"label_agreement":null},{"id":"W4376598528","doi":"10.1002/sim.9764","title":"A Bayesian joint model for compositional mediation effect selection in microbiome data","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"School of Medicine, New York University; York University; Washington University in St. Louis","keywords":"Computer science; Bayesian probability; Microbiome; Multivariate statistics; Mediation; Identification (biology); Selection (genetic algorithm); Benchmark (surveying); Model selection; Data mining; Econometrics; Machine learning; Artificial intelligence; Bioinformatics; Biology; Mathematics; Ecology","score_opus":0.028528566420889294,"score_gpt":0.33345932926112437,"score_spread":0.30493076284023507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376598528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11835171,0.00036301225,0.87759876,0.0009800921,0.00031824727,0.00063540385,0.0016029746,0.00001761209,0.0001321613],"genre_scores_gemma":[0.9544946,0.0006596167,0.03286833,0.00018002237,0.00031942115,0.00008791757,0.01114937,0.000022112072,0.00021864081],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990802,0.000044610642,0.00026008487,0.00030540215,0.00011066746,0.00019902753],"domain_scores_gemma":[0.9996169,0.00008694297,0.00006158986,0.00015567851,0.000047501577,0.000031373573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008030111,0.00010653832,0.00021529973,0.0002228676,0.000041928368,0.0000047658373,0.00011801377,0.00006366107,0.000008816891],"category_scores_gemma":[0.0005775815,0.00009576579,0.000012716959,0.0002722301,0.000058283073,0.0000029085031,0.00009220151,0.000075941076,0.0000020155633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016509285,0.000047413923,0.0029891673,0.00013467007,0.000052832147,0.0000049748387,0.0001255401,0.0017254868,0.9314118,0.0028529419,0.058822174,0.0016679256],"study_design_scores_gemma":[0.0039054141,0.00077931903,0.019565554,0.00006200107,0.000046497666,0.000007435638,0.000059135367,0.9549423,0.008725505,0.008940776,0.0027021668,0.0002639367],"about_ca_topic_score_codex":0.000028294462,"about_ca_topic_score_gemma":0.00046954615,"teacher_disagreement_score":0.9532168,"about_ca_system_score_codex":0.000029317363,"about_ca_system_score_gemma":0.000040704766,"threshold_uncertainty_score":0.39052156},"labels":[],"label_agreement":null},{"id":"W4377563942","doi":"10.1002/sim.9771","title":"Developing prediction models to estimate the risk of two survival outcomes both occurring: A comparison of techniques","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Chronic Disease Management Strategies","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; University of Manchester; Medical Research Council; National Institute for Health and Care Research","keywords":"Statistics; Computer science; Econometrics; Survival analysis; Proportional hazards model; Mathematics","score_opus":0.11919425273443744,"score_gpt":0.46984651115818477,"score_spread":0.3506522584237473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377563942","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18307254,0.00017414123,0.80496067,0.0019772982,0.000577283,0.0017233309,0.0006067712,0.00029505047,0.0066129207],"genre_scores_gemma":[0.9504056,0.0001226575,0.048989907,0.000099586156,0.00006592875,0.000053994405,0.00014217166,0.000024077308,0.000096058735],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981831,0.00007650883,0.0007059346,0.00020392945,0.00060285226,0.00022769488],"domain_scores_gemma":[0.9986778,0.00054770056,0.00023557477,0.00034422672,0.00012939014,0.0000653306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010239804,0.00015472838,0.00061288,0.00033734256,0.000043664568,0.0000047962417,0.00016100716,0.00003184044,0.000025871634],"category_scores_gemma":[0.0007839981,0.00010367785,0.000030461,0.00063959917,0.00022583484,0.000039090915,0.0001172302,0.00017871814,0.0000028372908],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019781945,0.00016159631,0.6516092,0.0014541139,0.000318519,0.000041996274,0.0046462985,0.013298693,0.00021264408,0.3005935,0.012089884,0.015375716],"study_design_scores_gemma":[0.0037214388,0.00087516493,0.66532695,0.002206994,0.0008278926,0.0000022931333,0.0069327657,0.21635376,0.0005568052,0.10212192,0.000824697,0.00024934646],"about_ca_topic_score_codex":0.00068835804,"about_ca_topic_score_gemma":0.0002668959,"teacher_disagreement_score":0.7673331,"about_ca_system_score_codex":0.000104654646,"about_ca_system_score_gemma":0.0001316797,"threshold_uncertainty_score":0.422786},"labels":[],"label_agreement":null},{"id":"W4377940739","doi":"10.1002/sim.9805","title":"The person‐time ratio distribution for the exact monitoring of adverse events: Historical vs surveillance Poisson data","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Manitoba Health","funders":"National Institute of General Medical Sciences; Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Poisson distribution; Statistics; Estimator; Relative risk; Confidence interval; Interval (graph theory); Medicine; Mathematics; Econometrics; Computer science","score_opus":0.18267581425771495,"score_gpt":0.4783700553137205,"score_spread":0.29569424105600556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377940739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32287478,0.014423172,0.33135056,0.15747832,0.084902234,0.012617645,0.0722613,0.0011137885,0.0029781647],"genre_scores_gemma":[0.9879636,0.00519113,0.000246081,0.00020843254,0.001271291,0.00012716159,0.0018642412,0.000025848496,0.003102217],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99857557,0.00023235794,0.0003733408,0.00023539507,0.0002408254,0.00034250197],"domain_scores_gemma":[0.9934096,0.005832722,0.00019390316,0.00036480202,0.00012047653,0.0000785013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022760043,0.00013980694,0.00024627068,0.00004889547,0.00043021815,0.0000021705873,0.0005044437,0.00008401682,0.00008570992],"category_scores_gemma":[0.0019668143,0.00008920972,0.00003223939,0.00038625713,0.00020835914,0.0000803523,0.00007281693,0.00047395288,0.000032624404],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019216805,0.00031137592,0.09475035,0.00025627343,0.00057907845,0.0000703908,0.0020429024,0.0048543895,0.017832631,0.0073863403,0.83977515,0.030219454],"study_design_scores_gemma":[0.003820503,0.00019543574,0.09839642,0.00008042595,0.0003055151,0.000007903538,0.0018174795,0.1710177,0.00074630015,0.0009818085,0.7223778,0.00025275224],"about_ca_topic_score_codex":0.00010265745,"about_ca_topic_score_gemma":0.00003609021,"teacher_disagreement_score":0.6650888,"about_ca_system_score_codex":0.00026276862,"about_ca_system_score_gemma":0.000084433064,"threshold_uncertainty_score":0.3637867},"labels":[],"label_agreement":null},{"id":"W4379967395","doi":"10.1002/sim.9802","title":"Causal inference for recurrent events via aggregated marginal odds ratio","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Inference; Causal inference; Odds ratio; Odds; Econometrics; Statistics; Marginal structural model; Computer science; Mathematics; Artificial intelligence; Logistic regression","score_opus":0.14131302433752374,"score_gpt":0.4749063944263714,"score_spread":0.33359337008884765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379967395","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004115914,0.00004332748,0.9931801,0.00047780498,0.0004615343,0.00080952566,0.00025347862,0.0003492686,0.00030905937],"genre_scores_gemma":[0.46855682,0.00060259807,0.5261688,0.00024930655,0.0004438182,0.0007983717,0.0011569343,0.00012454356,0.0018987806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980975,0.00008373708,0.0006372498,0.0003140651,0.00042430137,0.00044319517],"domain_scores_gemma":[0.9965462,0.0025268218,0.00022856414,0.00032951773,0.00026200715,0.00010685445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009156743,0.00023681985,0.00045047002,0.0002910976,0.000071307244,0.000007420637,0.00023453575,0.000101559286,0.00019539258],"category_scores_gemma":[0.007197313,0.00020636812,0.000022227372,0.00056884356,0.00016327987,0.000079421625,0.000074314215,0.000300922,0.000030441966],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018114898,0.000121778656,0.00088151434,0.0005441113,0.000039958195,0.00009974081,0.0011839331,0.000025403911,0.0019062308,0.8922354,0.051600832,0.05117993],"study_design_scores_gemma":[0.0010032294,0.0007580532,0.0013194139,0.0005510696,0.00003894943,0.0000051688053,0.00012627563,0.016424851,0.000633738,0.97790205,0.001000875,0.00023635002],"about_ca_topic_score_codex":0.000032178483,"about_ca_topic_score_gemma":0.00021317277,"teacher_disagreement_score":0.46701127,"about_ca_system_score_codex":0.00015073107,"about_ca_system_score_gemma":0.00008080515,"threshold_uncertainty_score":0.8616376},"labels":[],"label_agreement":null},{"id":"W4380537590","doi":"10.1002/sim.9823","title":"Statistical inference for the two‐sample problem under likelihood ratio ordering, with application to the ROC curve estimation","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Receiver operating characteristic; Estimator; Statistics; Statistical inference; Consistency (knowledge bases); Mathematics; Inference; Asymptotic distribution; Sample size determination; Maximum likelihood; Computer science; Applied mathematics; Artificial intelligence","score_opus":0.0702520978945821,"score_gpt":0.4293884576788077,"score_spread":0.3591363597842256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380537590","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017536491,0.000015657028,0.9924638,0.004326195,0.00013350684,0.0018854676,0.000752761,0.00008088154,0.00016631269],"genre_scores_gemma":[0.12558173,0.00002561633,0.8721662,0.0005015262,0.00015344516,0.0012537534,0.0002035263,0.000039067854,0.00007511894],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979695,0.0001556711,0.00057065056,0.00035528129,0.00052153785,0.00042735142],"domain_scores_gemma":[0.9753913,0.023568926,0.00016248933,0.00046103186,0.00030380476,0.000112406735],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019334429,0.00022001611,0.00033238824,0.00010068553,0.00025378985,0.00004985315,0.0003299904,0.000048850638,0.000114470604],"category_scores_gemma":[0.014755102,0.000115151866,0.000013049719,0.0007268949,0.0002523418,0.000039035727,0.00007432467,0.000271842,0.000035026187],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000516859,0.000031507156,0.00023052633,0.00012044286,0.000022100528,0.0000017950787,0.00094213855,0.003618254,0.000029582623,0.91027564,0.0076466915,0.07702964],"study_design_scores_gemma":[0.0005638674,0.00029978662,0.0032397865,0.00009077114,0.00006270297,0.0000017152418,0.0005082008,0.34953243,0.000011264843,0.64459807,0.0009695263,0.000121869096],"about_ca_topic_score_codex":0.00047065466,"about_ca_topic_score_gemma":0.0018638009,"teacher_disagreement_score":0.34591419,"about_ca_system_score_codex":0.00006275912,"about_ca_system_score_gemma":0.00012895273,"threshold_uncertainty_score":0.99354404},"labels":[],"label_agreement":null},{"id":"W4380589797","doi":"10.1002/sim.9811","title":"Sample size considerations for assessing treatment effect heterogeneity in randomized trials with heterogeneous intracluster correlations and variances","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"Patient-Centered Outcomes Research Institute","keywords":"Sample size determination; Univariate; Randomized controlled trial; Statistics; Context (archaeology); Cluster (spacecraft); Multivariate statistics; Sample (material); Outcome (game theory); Econometrics; Mathematics; Computer science; Medicine; Internal medicine","score_opus":0.48912071704197413,"score_gpt":0.5797179367516512,"score_spread":0.09059721970967705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380589797","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032732632,0.00007929681,0.9603394,0.0009900852,0.00058648386,0.004120388,0.0010016423,0.00007193446,0.000078083205],"genre_scores_gemma":[0.16136117,0.00015877165,0.83718294,0.000118184274,0.0001979451,0.0008960073,0.00002388906,0.000035325,0.000025745625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992157,0.00472121,0.00200772,0.00045454202,0.0003034814,0.00035604756],"domain_scores_gemma":[0.3944357,0.6048154,0.00036996463,0.00020418505,0.00008654202,0.000088193876],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018010145,0.00029798457,0.002973555,0.00020985708,0.00013063647,0.000056994664,0.0000662473,0.0001373914,0.0001595589],"category_scores_gemma":[0.732293,0.00018149734,0.00008602524,0.00031665046,0.00055260066,0.000050469942,0.000030428982,0.00018762004,0.0000020311895],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.07525103,0.0013254489,0.020760683,0.0027422078,0.0028445153,0.0010638288,0.0074488437,0.003714794,0.0004810227,0.765307,0.006209493,0.112851106],"study_design_scores_gemma":[0.09769481,0.00068148883,0.0008639222,0.00032546735,0.0005762226,0.000013671185,0.00007065996,0.022574648,0.00008626549,0.8769284,0.000015464506,0.00016899749],"about_ca_topic_score_codex":0.00013110008,"about_ca_topic_score_gemma":0.0006604456,"teacher_disagreement_score":0.7142829,"about_ca_system_score_codex":0.00010616913,"about_ca_system_score_gemma":0.000098790755,"threshold_uncertainty_score":0.74012464},"labels":[],"label_agreement":null},{"id":"W4381187244","doi":"10.1002/sim.9824","title":"Deep causal feature extraction and inference with neuroimaging genetic data","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; National Institute on Aging; Canadian Institutes of Health Research; Minnesota Supercomputing Institute, University of Minnesota; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Pfizer; Novartis Pharmaceuticals Corporation; Eisai; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; Servier; BioClinica; Bristol-Myers Squibb; Eli Lilly and Company; Biogen","keywords":"Neuroimaging; Computer science; Causal inference; Imaging genetics; Artificial intelligence; Covariate; Inference; Genome-wide association study; Biobank; Alzheimer's Disease Neuroimaging Initiative; Instrumental variable; Machine learning; Feature (linguistics); Regression; Psychology; Econometrics; Cognition; Bioinformatics; Statistics; Cognitive impairment; Psychiatry; Biology; Mathematics","score_opus":0.03034836853606217,"score_gpt":0.3566172819314706,"score_spread":0.3262689133954084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381187244","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4640126,0.001167139,0.5301654,0.00332229,0.0003478886,0.00025496204,0.00017077144,0.000027997015,0.0005309673],"genre_scores_gemma":[0.9368512,0.0021222692,0.05839036,0.0003909093,0.0002427105,0.0000107691,0.0015965262,0.000018730898,0.00037652347],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99917084,0.00007245311,0.00015036187,0.0003166596,0.000095947915,0.00019376012],"domain_scores_gemma":[0.99936956,0.00013805722,0.000067898814,0.0003250057,0.000047918165,0.00005158429],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031320166,0.00009572576,0.00014022128,0.00006221429,0.00004975185,0.0000061226797,0.0001249831,0.00006825256,0.000010869431],"category_scores_gemma":[0.0010297453,0.000077400844,0.000003332193,0.00014807568,0.00013192464,0.0000024984363,0.00011602788,0.00012896853,0.0000035600399],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000770471,0.000034954624,0.8370963,0.00007998002,0.000070519316,0.00017546657,0.00034232752,0.0023397678,0.02041893,0.0005659345,0.07509323,0.063705586],"study_design_scores_gemma":[0.0006113475,0.0002695619,0.94745266,0.000024314892,0.000031445663,0.000042719006,0.00024571997,0.044220578,0.000022103073,0.0011173796,0.0058336216,0.00012853698],"about_ca_topic_score_codex":0.00009329993,"about_ca_topic_score_gemma":0.0006995456,"teacher_disagreement_score":0.4728386,"about_ca_system_score_codex":0.0000068389954,"about_ca_system_score_gemma":0.000037209138,"threshold_uncertainty_score":0.31563148},"labels":[],"label_agreement":null},{"id":"W4381469694","doi":"10.1002/sim.9831","title":"Permutation‐based multiple testing corrections for P$$ P $$‐values and confidence intervals for cluster randomized trials","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council Canada; Medical Research Council; National Institute for Health and Care Research","keywords":"Confidence interval; Statistics; Permutation (music); Resampling; Bonferroni correction; Multiple comparisons problem; Mathematics; Inference; Standard error; Type I and type II errors; Confidence distribution; Statistical hypothesis testing; Computer science; Artificial intelligence","score_opus":0.7094685578629825,"score_gpt":0.6281742164474525,"score_spread":0.08129434141552994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381469694","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008237105,0.00004244618,0.98890656,0.0016038677,0.0017246035,0.005177015,0.0014596793,0.00013574316,0.00012637072],"genre_scores_gemma":[0.012789611,0.00003256614,0.98378086,0.00050660205,0.00045696888,0.0018983958,0.00007549651,0.00005463664,0.00040488216],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9937644,0.0025096014,0.0025527664,0.00045486566,0.0003467974,0.00037158583],"domain_scores_gemma":[0.43456146,0.56422627,0.0005107617,0.00017982545,0.0004317337,0.000089976806],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.042812202,0.00024339193,0.0023702106,0.00029416967,0.00015767927,0.000034016528,0.00015822751,0.00013708688,0.000090021094],"category_scores_gemma":[0.94493717,0.00018276766,0.00012856987,0.00041058895,0.0007015463,0.000037845773,0.000045349894,0.00020171357,0.0000041619437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06825701,0.00035328345,0.0014640912,0.0050335946,0.0006135629,0.000027052865,0.004239385,0.0005699809,0.0012007643,0.62494135,0.18076773,0.1125322],"study_design_scores_gemma":[0.0805058,0.00023945096,0.000091211645,0.00049808196,0.0003328769,0.0000010298849,0.0002660627,0.26453942,0.00006186183,0.65327513,0.000060489325,0.0001285688],"about_ca_topic_score_codex":0.000053983706,"about_ca_topic_score_gemma":0.000054989112,"teacher_disagreement_score":0.902125,"about_ca_system_score_codex":0.000053683205,"about_ca_system_score_gemma":0.00008906563,"threshold_uncertainty_score":0.9856263},"labels":[],"label_agreement":null},{"id":"W4381716816","doi":"10.1002/sim.9768","title":"A combined multilevel factor analysis and covariance regression model with mixed effects in the mean and variance structure","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Mental Health Research Topics","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"FP7 Health","keywords":"Covariance; Multilevel model; Factor regression model; Regression analysis; Statistics; Hierarchical database model; Regression; Factor analysis; Covariance matrix; Bayesian probability; Mathematics; Analysis of covariance; Computer science; Bayesian multivariate linear regression; Proper linear model; Data mining","score_opus":0.0573277386348996,"score_gpt":0.43326040256639037,"score_spread":0.3759326639314908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381716816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.771939,0.00031326406,0.22384976,0.0018104286,0.00023255969,0.0011543296,0.0005106604,0.00002778175,0.00016225377],"genre_scores_gemma":[0.979893,0.00011061207,0.019143354,0.00032594646,0.000029072196,0.000049397975,0.00009977229,0.000012622798,0.00033617907],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983331,0.00041420624,0.00025089184,0.00031698102,0.00037083632,0.00031401444],"domain_scores_gemma":[0.99794805,0.0015464926,0.00008047722,0.0002916106,0.0000366785,0.0000966965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006902035,0.00013781578,0.0003407094,0.00029631073,0.00007076064,0.000009733691,0.0001366919,0.00008245305,0.00005868319],"category_scores_gemma":[0.00043474225,0.00007866905,0.0000055886558,0.00086023856,0.00023679274,0.000024630948,0.00004196616,0.0004364487,0.0000017988968],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032128736,0.0003776331,0.45462885,0.003171053,0.0006573629,0.0035551607,0.13946745,0.0018343125,0.0009833699,0.21645643,0.013527943,0.16212755],"study_design_scores_gemma":[0.003344698,0.0003498151,0.791399,0.00019816967,0.000049966733,0.0000049659507,0.0008081234,0.19183588,0.0000053894096,0.011895265,0.000020991361,0.000087724155],"about_ca_topic_score_codex":0.00056504423,"about_ca_topic_score_gemma":0.001999066,"teacher_disagreement_score":0.33677015,"about_ca_system_score_codex":0.000038188682,"about_ca_system_score_gemma":0.00002691524,"threshold_uncertainty_score":0.32080308},"labels":[],"label_agreement":null},{"id":"W4382182859","doi":"10.1002/sim.9818","title":"Handling misclassified stratification variables in the analysis of randomised trials with continuous outcomes","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Health and Medical Research Council; Medical Research Council Canada; Medical Research Council; University of Adelaide","keywords":"Covariate; Stratification (seeds); Statistics; Econometrics; Medicine; Mathematics","score_opus":0.5420455474370366,"score_gpt":0.5745915147372646,"score_spread":0.03254596730022796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382182859","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030195503,0.000034748853,0.9635227,0.0015241866,0.00034996544,0.0019822791,0.0007572112,0.000052285173,0.0015811744],"genre_scores_gemma":[0.33838233,0.00010460594,0.6606981,0.00015176478,0.00010895611,0.00021635466,0.00012445905,0.0000293057,0.00018408052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99212146,0.0036353203,0.0028212944,0.0003336512,0.0008056912,0.00028256286],"domain_scores_gemma":[0.7332164,0.2653943,0.00076087855,0.00044038938,0.00014499587,0.000043063923],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036390387,0.00020039373,0.0026082206,0.00062819815,0.00004061828,0.000018364899,0.00032649343,0.00011432586,0.00025703968],"category_scores_gemma":[0.3725915,0.00010450652,0.0000969228,0.00255764,0.00037210816,0.00002211725,0.000021280393,0.00030138926,0.0000023247503],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040360726,0.00046526428,0.030581288,0.00048624555,0.0025797698,0.00015427722,0.0060227634,0.0006327259,0.0008378331,0.9355928,0.005401803,0.013209208],"study_design_scores_gemma":[0.019550549,0.00019505838,0.06655961,0.00026121654,0.003048991,6.0185124e-7,0.0026088802,0.00939053,0.000062640225,0.8981459,0.000019937064,0.00015606874],"about_ca_topic_score_codex":0.00012328856,"about_ca_topic_score_gemma":0.0003818702,"teacher_disagreement_score":0.3362011,"about_ca_system_score_codex":0.000031465086,"about_ca_system_score_gemma":0.00007256868,"threshold_uncertainty_score":0.9922389},"labels":[],"label_agreement":null},{"id":"W4384406729","doi":"10.1002/sim.9848","title":"Inference for covariate‐adjusted time‐dependent prognostic accuracy measures","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Discriminative model; Receiver operating characteristic; Estimator; Computer science; Inference; Statistics; Econometrics; Artificial intelligence; Machine learning; Mathematics","score_opus":0.2147288485494072,"score_gpt":0.45917408079072347,"score_spread":0.24444523224131628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384406729","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020158181,0.000040539515,0.9935758,0.00057365966,0.0004855459,0.0010276041,0.00069586,0.00018074778,0.0014043998],"genre_scores_gemma":[0.1716736,0.00016426345,0.8248718,0.00030439554,0.00036587415,0.0004813092,0.0002894916,0.00008722376,0.0017620518],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974409,0.00024050397,0.00078316877,0.0003940392,0.00060889067,0.0005325053],"domain_scores_gemma":[0.96720403,0.031705562,0.00020180254,0.0003538189,0.00038094132,0.00015386508],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0024160086,0.00025399134,0.00060922187,0.0002476998,0.000096262374,0.0000257314,0.00030440176,0.00011349016,0.00061599154],"category_scores_gemma":[0.14706382,0.00020121617,0.000026665517,0.0005762534,0.00021847126,0.00004279235,0.00008387587,0.00028638905,0.00013978123],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009497091,0.00010575744,0.0010520287,0.000533367,0.00005135477,0.00009044901,0.0011483234,0.000036862883,0.000795055,0.9006424,0.03434243,0.061107006],"study_design_scores_gemma":[0.0015720177,0.00043057094,0.007444033,0.0004046707,0.00011271507,0.0000045763577,0.00025424777,0.037062015,0.00008831131,0.95168006,0.00068200566,0.000264799],"about_ca_topic_score_codex":0.00009349854,"about_ca_topic_score_gemma":0.00006429262,"teacher_disagreement_score":0.16965778,"about_ca_system_score_codex":0.00006625011,"about_ca_system_score_gemma":0.00013427733,"threshold_uncertainty_score":0.86012083},"labels":[],"label_agreement":null},{"id":"W4385235004","doi":"10.1002/sim.9855","title":"A time‐dependent Poisson‐Gamma model for recruitment forecasting in multicenter studies","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University Health Centre; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Poisson distribution; Gamma process; Constant (computer programming); Gamma distribution; Generalization; Econometrics; Poisson process; Bayesian probability; Computer science; Poisson regression; Statistics; Compound Poisson process; Count data; Range (aeronautics); Stochastic modelling; Mathematics; Demography; Population; Engineering","score_opus":0.4169691259152335,"score_gpt":0.5039540648960044,"score_spread":0.08698493898077087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385235004","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020185164,0.000085582426,0.9947456,0.00086405774,0.00026879399,0.0012912119,0.00037537058,0.000057599093,0.00029328],"genre_scores_gemma":[0.012174483,0.00014292928,0.9856834,0.00025702576,0.00011131336,0.00059447065,0.000048236885,0.000042675147,0.0009454906],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978506,0.0001434951,0.000786307,0.00035788,0.00036556658,0.00049616926],"domain_scores_gemma":[0.990706,0.008667387,0.00015090562,0.00022523808,0.00016424344,0.00008617624],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0023062627,0.00021729863,0.0006313559,0.0002796136,0.00005828033,0.000009517122,0.0001596891,0.00006902316,0.00007387365],"category_scores_gemma":[0.019519424,0.00017164004,0.000024454645,0.0003250948,0.0001809825,0.000034679022,0.000092686714,0.00021319491,0.000015223028],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041524344,0.000369269,0.0011621476,0.0025295373,0.00017372095,0.00061160495,0.02510063,0.0008407607,0.00046150252,0.69854754,0.09656948,0.1732186],"study_design_scores_gemma":[0.0011979812,0.00011179293,0.000119459444,0.00045308392,0.000028906046,0.000001553048,0.00076744164,0.48230818,0.000011881366,0.5148419,0.000054036387,0.00010378159],"about_ca_topic_score_codex":0.00002763473,"about_ca_topic_score_gemma":0.00027153897,"teacher_disagreement_score":0.48146743,"about_ca_system_score_codex":0.00016565826,"about_ca_system_score_gemma":0.000039623803,"threshold_uncertainty_score":0.98873955},"labels":[],"label_agreement":null},{"id":"W4386010298","doi":"10.1002/sim.9879","title":"A threshold longitudinal Tobit quantile regression model for identification of treatment‐sensitive subgroups based on interval‐bounded longitudinal measurements and a continuous covariate","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Science Foundation of Anhui Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Covariate; Statistics; Estimator; Mathematics; Tobit model; Econometrics; Quantile; Confidence interval; Random effects model; Identification (biology); Regression analysis; Quantile regression; Computer science; Medicine","score_opus":0.27177774041003855,"score_gpt":0.443233959218317,"score_spread":0.17145621880827844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386010298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07343205,0.000015815973,0.92460275,0.00013730895,0.00019035111,0.00072597555,0.0007291106,0.000036824826,0.00012982753],"genre_scores_gemma":[0.8488518,0.000028329523,0.15066843,0.000030111572,0.000036759142,0.000094344985,0.000116029754,0.00002653867,0.00014766376],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979447,0.00013171903,0.0007975804,0.00041880002,0.00042009904,0.00028706368],"domain_scores_gemma":[0.9958749,0.003014251,0.00036834434,0.00030304145,0.00035120628,0.000088300796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016286471,0.00024174411,0.0006885698,0.00025789934,0.00008622719,0.00001972859,0.00010083329,0.000081962105,0.000020722198],"category_scores_gemma":[0.00529285,0.00017974661,0.000038106355,0.00026948153,0.00026016004,0.000035603345,0.0000303061,0.00012072011,0.0000025717375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036705455,0.001138508,0.021451866,0.0019153343,0.00033222622,0.000121273966,0.006456622,0.001520241,0.016596751,0.92190593,0.007331265,0.01755945],"study_design_scores_gemma":[0.0023717552,0.0011815288,0.009959092,0.0006688211,0.00015223128,0.0000022614424,0.00021910979,0.7060572,0.00082220073,0.27842778,0.0000026144605,0.00013544076],"about_ca_topic_score_codex":0.00010935467,"about_ca_topic_score_gemma":0.00013898706,"teacher_disagreement_score":0.7754198,"about_ca_system_score_codex":0.0001396524,"about_ca_system_score_gemma":0.0000740809,"threshold_uncertainty_score":0.73298544},"labels":[],"label_agreement":null},{"id":"W4386116424","doi":"10.1002/sim.9867","title":"A comparison of Bayesian information borrowing methods in basket trials and a novel proposal of modified exchangeability‐nonexchangeability method","year":2023,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Medical Research Council Canada; Department of Health and Social Care; Medical Research Council; National Institute for Health and Care Research","keywords":"Bayesian probability; Type I and type II errors; Sample size determination; Computer science; Econometrics; Homogeneity (statistics); Statistics; Bayesian inference; Generalization; Contrast (vision); Bayesian hierarchical modeling; Machine learning; Artificial intelligence; Mathematics","score_opus":0.7989345094425112,"score_gpt":0.7116990724016434,"score_spread":0.08723543704086778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386116424","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000014908209,0.1249162,0.86697435,0.000063263535,0.00064727373,0.0043146037,0.0028908837,0.00003873976,0.00015320975],"genre_scores_gemma":[0.00000442778,0.2461243,0.7532302,0.00001112925,0.00012791481,0.0003365137,0.00009417321,0.00006261706,0.000008744603],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95791537,0.022239182,0.01672221,0.0009820109,0.001414939,0.00072627456],"domain_scores_gemma":[0.68872756,0.30565354,0.004268568,0.0008334675,0.00034747325,0.00016941024],"candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11154485,0.00071961764,0.0148992045,0.0013529717,0.00003399218,0.00001599664,0.00054428,0.0008673798,0.00015764555],"category_scores_gemma":[0.64935654,0.0005406122,0.0003033233,0.001814123,0.0008226094,0.00011099372,0.0003624025,0.001346668,0.0000013179393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013458636,0.00030755633,0.000028685661,0.11980686,0.0001853286,0.000004363717,0.0018074049,0.0000032052315,0.000006855548,0.097429745,0.00024311947,0.7800423],"study_design_scores_gemma":[0.003107708,0.0006654857,0.00006141906,0.03466898,0.0022446353,0.0000052776663,0.00072649785,0.007466149,0.000019454204,0.9473505,0.0031717173,0.00051218295],"about_ca_topic_score_codex":0.00036068435,"about_ca_topic_score_gemma":0.00016463992,"teacher_disagreement_score":0.84992075,"about_ca_system_score_codex":0.00025939845,"about_ca_system_score_gemma":0.0005370804,"threshold_uncertainty_score":0.99972564},"labels":[],"label_agreement":null},{"id":"W4386243887","doi":"10.1002/sim.9887","title":"Analysis of secondary failure time responses in studies with response‐dependent sampling schemes","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"University of Waterloo; National Natural Science Foundation of China","keywords":"Estimator; Sample size determination; Statistics; Computer science; Gaussian; Sampling (signal processing); Econometrics; Mathematics","score_opus":0.1401599664157765,"score_gpt":0.4655415873936388,"score_spread":0.32538162097786233,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386243887","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65554214,0.00031835982,0.34125954,0.0009871204,0.000097010045,0.0003607371,0.0009897461,0.00007058855,0.0003747724],"genre_scores_gemma":[0.32025805,0.0001822104,0.67844045,0.000089079964,0.00003431688,0.000042365158,0.00005402699,0.000033199434,0.00086628116],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975651,0.0005679023,0.0007674195,0.00030262434,0.0005065029,0.00029044427],"domain_scores_gemma":[0.97314215,0.026063671,0.00019740507,0.00032223464,0.00021431227,0.00006021758],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004082633,0.00018224782,0.0009834002,0.0012092687,0.000036506917,0.0000060499733,0.00016137051,0.00006272306,0.00045307254],"category_scores_gemma":[0.0358608,0.00013113546,0.000024230982,0.002259561,0.0003930784,0.000027847798,0.00006288398,0.0002945002,0.000008195709],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012198766,0.0005736943,0.07502679,0.003087846,0.0057666968,0.0021079967,0.044552058,0.00063542876,0.026181003,0.7566125,0.013803932,0.059453327],"study_design_scores_gemma":[0.004035556,0.0017478123,0.28835812,0.0022152667,0.0017042576,0.000010542283,0.020319482,0.011782492,0.0008435489,0.66779584,0.0005101775,0.0006769347],"about_ca_topic_score_codex":0.00005145946,"about_ca_topic_score_gemma":0.0004222385,"teacher_disagreement_score":0.33718094,"about_ca_system_score_codex":0.00007441248,"about_ca_system_score_gemma":0.00011603919,"threshold_uncertainty_score":0.97226053},"labels":[],"label_agreement":null},{"id":"W4386878567","doi":"10.1002/sim.9899","title":"Addressing missing data in the estimation of time‐varying treatments in comparative effectiveness research","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada","keywords":"Missing data; Inverse probability weighting; Imputation (statistics); Weighting; Confounding; Statistics; Inverse probability; Covariate; Econometrics; Computer science; Mathematics; Medicine; Posterior probability; Propensity score matching; Bayesian probability","score_opus":0.6914773159287642,"score_gpt":0.6378653717663129,"score_spread":0.0536119441624513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386878567","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45630333,0.0002246032,0.53523004,0.00052076904,0.00010277273,0.0027128484,0.00035322004,0.00013849084,0.0044139195],"genre_scores_gemma":[0.88146126,0.00003821154,0.118032254,0.000008792105,0.000017345903,0.000061173654,0.0003497207,0.000014669997,0.000016550224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974968,0.0010057369,0.00046761104,0.00023860346,0.00053333864,0.0002579532],"domain_scores_gemma":[0.98510766,0.014187366,0.00011828911,0.000484072,0.00008180651,0.000020809906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006176893,0.00011296058,0.0004015633,0.0005147202,0.000052267882,0.000009978951,0.0003671461,0.000050048773,0.00001840856],"category_scores_gemma":[0.007224138,0.00008088804,0.0000051109273,0.0012550624,0.00029113668,0.00013182312,0.00013398782,0.00038336514,0.0000057073757],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012450087,0.0025635622,0.042805873,0.007565953,0.0002049347,0.0025544444,0.18108334,0.012623332,0.05070772,0.34557292,0.019977687,0.33309522],"study_design_scores_gemma":[0.0010148403,0.00018014542,0.018870894,0.0037105363,0.000015631256,0.0000030817034,0.0016108865,0.18000013,0.0013160366,0.79318005,0.0000049599366,0.00009283982],"about_ca_topic_score_codex":0.0003154903,"about_ca_topic_score_gemma":0.00014739487,"teacher_disagreement_score":0.44760713,"about_ca_system_score_codex":0.00016934985,"about_ca_system_score_gemma":0.00006221633,"threshold_uncertainty_score":0.864849},"labels":[],"label_agreement":null},{"id":"W4387326446","doi":"10.1002/sim.9917","title":"Joint clustering multiple longitudinal features: A comparison of methods and software packages with practical guidance","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; Queen's University","keywords":"Cluster analysis; Computer science; Data mining; Machine learning; Software; Bayesian probability; Popularity; Feature (linguistics); Frequentist inference; Artificial intelligence; Data science; Bayesian inference","score_opus":0.09040215515519481,"score_gpt":0.4441058922588974,"score_spread":0.3537037371037026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387326446","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00056247343,0.0004762067,0.9974522,0.0009943979,0.00017963025,0.00015926245,0.000014663785,0.000061926956,0.00009922717],"genre_scores_gemma":[0.05411411,0.00009092346,0.94558835,0.00007618225,0.000045251218,0.000011803601,0.0000060956663,0.000011486644,0.00005580587],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842525,0.00029291582,0.0003857945,0.0003597111,0.0002782018,0.00025816046],"domain_scores_gemma":[0.9972849,0.0019863944,0.00016534503,0.00035355406,0.000109383094,0.00010042943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016953918,0.00015059773,0.00047976038,0.00017320752,0.000055908815,0.000021391932,0.00019275951,0.00005929274,0.0000047707667],"category_scores_gemma":[0.0027221753,0.00010728144,0.000011941835,0.0005018225,0.00023494715,0.00009788334,0.00019820548,0.00029865943,8.442877e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012719151,0.00013298812,0.039048668,0.0008810379,0.000082733524,0.00045901214,0.011089373,0.00035102825,0.002774984,0.13353285,0.017237343,0.7942828],"study_design_scores_gemma":[0.0034081729,0.0016467227,0.25238103,0.001634272,0.000088696484,0.00024967152,0.00082709675,0.6341227,0.002172196,0.101897866,0.00096396136,0.0006075475],"about_ca_topic_score_codex":0.0000810979,"about_ca_topic_score_gemma":0.00017949105,"teacher_disagreement_score":0.79367524,"about_ca_system_score_codex":0.000020737492,"about_ca_system_score_gemma":0.00005255387,"threshold_uncertainty_score":0.43748102},"labels":[],"label_agreement":null},{"id":"W4387697644","doi":"10.1002/sim.9934","title":"Rank selection for non‐negative matrix factorization","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Non-negative matrix factorization; Matrix decomposition; Rank (graph theory); Computer science; Feature selection; Pattern recognition (psychology); Dimensionality reduction; Matrix (chemical analysis); Model selection; Computation; Selection (genetic algorithm); Dimension (graph theory); Algorithm; Mathematics; Artificial intelligence; Eigenvalues and eigenvectors","score_opus":0.018925110906542836,"score_gpt":0.354111484269837,"score_spread":0.33518637336329415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387697644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023432454,0.000045502256,0.97443587,0.0005344959,0.0005779615,0.0004068083,0.00009875525,0.000022067503,0.00044611082],"genre_scores_gemma":[0.98749727,0.00032262522,0.006923671,0.00011764524,0.00042734237,0.00012886981,0.0013173228,0.000019017081,0.0032462513],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99938506,0.000025811589,0.0001655092,0.00019159364,0.00010728671,0.00012471862],"domain_scores_gemma":[0.9996505,0.000044926965,0.00006341994,0.00009597263,0.00011144315,0.000033751752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019243597,0.00007283667,0.000091762086,0.00010268584,0.000046461035,0.000004415837,0.000057781086,0.000067882,0.00003208861],"category_scores_gemma":[0.0004849963,0.00006490229,0.000011630875,0.00027112433,0.000038551927,0.0000017398663,0.000012909091,0.000045307523,0.000007338328],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001404243,0.000018575907,0.003172169,0.000058509788,0.000015630058,5.697936e-7,0.00033515913,0.00029271145,0.812606,0.0024874096,0.17371629,0.007156548],"study_design_scores_gemma":[0.013280718,0.0028927582,0.13492282,0.00029140583,0.000111628564,0.0000073309834,0.0031462004,0.071395285,0.43805337,0.05008293,0.28484118,0.00097436964],"about_ca_topic_score_codex":0.00001669565,"about_ca_topic_score_gemma":0.00004723724,"teacher_disagreement_score":0.9675122,"about_ca_system_score_codex":0.000020371397,"about_ca_system_score_gemma":0.000043469536,"threshold_uncertainty_score":0.26466385},"labels":[],"label_agreement":null},{"id":"W4388398918","doi":"10.1002/sim.9940","title":"Principal stratification for quantile causal effects under partial compliance","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données; Compute Canada","keywords":"Quantile; Econometrics; Causal inference; Copula (linguistics); Covariate; Missing data; Statistics; Bivariate analysis; Identifiability; Inference; Mathematics; Computer science; Artificial intelligence","score_opus":0.2595680897329376,"score_gpt":0.5012533153693227,"score_spread":0.24168522563638511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388398918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009180914,0.00001834423,0.9884038,0.0004037848,0.00031051232,0.0008679812,0.00010928885,0.00031732125,0.0003880369],"genre_scores_gemma":[0.6266121,0.000045942925,0.37169972,0.00013059759,0.00022961022,0.0004488296,0.00028617322,0.000047783953,0.0004992254],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986592,0.000060397153,0.000432178,0.00025711875,0.00027390925,0.00031721796],"domain_scores_gemma":[0.99626917,0.00310113,0.00014576563,0.00029484805,0.00012396071,0.00006510942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006582256,0.00015335553,0.0003199563,0.00012106771,0.0000630478,0.000008988714,0.00014766211,0.00007472691,0.000044209897],"category_scores_gemma":[0.0030914245,0.00013585255,0.000014944139,0.0002958722,0.00018205699,0.00005370392,0.000030130332,0.00017128956,0.000022760756],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027168753,0.00003896149,0.00016109516,0.0004155856,0.000010063764,0.000016529097,0.00033597418,0.000044916884,0.0051723025,0.97692174,0.014000094,0.0028555933],"study_design_scores_gemma":[0.0006749341,0.00031781325,0.0027385443,0.00030084973,0.000027260288,0.00000193818,0.00019455138,0.016204257,0.0033470893,0.9755824,0.0004570502,0.00015331178],"about_ca_topic_score_codex":0.000021177104,"about_ca_topic_score_gemma":0.00012733942,"teacher_disagreement_score":0.6174312,"about_ca_system_score_codex":0.00007832233,"about_ca_system_score_gemma":0.000045303805,"threshold_uncertainty_score":0.5539906},"labels":[],"label_agreement":null},{"id":"W4388458822","doi":"10.1002/sim.9954","title":"A flexible model based on piecewise linear approximation for the analysis of left truncated right censored data with covariates, and applications to Worcester Heart Attack Study data and Channing House data","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Science and Engineering Research Board; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Piecewise; Computer science; Parametric model; Parametric statistics; Robustness (evolution); Proportional hazards model; Inference; Hazard; Applied mathematics; Statistics; Mathematics; Algorithm; Data mining; Artificial intelligence","score_opus":0.2283174352599303,"score_gpt":0.46335943499915616,"score_spread":0.23504199973922585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388458822","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00085401704,0.000011225155,0.9623764,0.0018768987,0.000010246802,0.0019632576,0.032820143,0.00007267665,0.00001509128],"genre_scores_gemma":[0.37525484,0.000027901846,0.57863975,0.0003789349,0.00005096058,0.00037948904,0.04513587,0.000050727263,0.00008150648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824,0.00006784741,0.0005309499,0.0006080907,0.00037256867,0.00018057642],"domain_scores_gemma":[0.99362075,0.003558593,0.0001749731,0.002367097,0.00018051227,0.00009805847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014778109,0.00015942068,0.0004122146,0.00029311847,0.00017904238,0.000030717725,0.00067351374,0.00003682893,0.000023935358],"category_scores_gemma":[0.0022969139,0.00010855391,0.000006020834,0.0012610883,0.00018495755,0.00009386251,0.00033743438,0.000117534764,0.0000027174935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012704829,0.0031187043,0.007386189,0.0016002655,0.0021895159,0.000010212723,0.0069854246,0.19097897,0.00018121493,0.5634398,0.20241638,0.020422833],"study_design_scores_gemma":[0.001205646,0.000105573585,0.008794175,0.000060812865,0.0011439808,5.661533e-7,0.00051114423,0.98281753,0.000003171253,0.004476362,0.00076765125,0.00011336586],"about_ca_topic_score_codex":0.000049476886,"about_ca_topic_score_gemma":0.00026477932,"teacher_disagreement_score":0.7918386,"about_ca_system_score_codex":0.000018700299,"about_ca_system_score_gemma":0.00005965152,"threshold_uncertainty_score":0.44267},"labels":[],"label_agreement":null},{"id":"W4388851130","doi":"10.1002/sim.9963","title":"Two‐stage targeted maximum likelihood estimation for mixed aggregate and individual participant data analysis with an application to multidrug resistant tuberculosis","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; Université de Montréal; McGill University; McMaster University","funders":"Canadian Institutes of Health Research","keywords":"Aggregate data; Weighting; Computer science; Missing data; Estimation; Tuberculosis; Aggregate (composite); Inverse probability weighting; Meta-analysis; Statistics; Population; Contrast (vision); Medicine; Econometrics; Machine learning; Artificial intelligence; Mathematics; Internal medicine; Estimator; Pathology","score_opus":0.1470997536980372,"score_gpt":0.4430485501490196,"score_spread":0.2959487964509824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388851130","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06072353,0.000032429387,0.93449014,0.0004479822,0.00002508559,0.0011841087,0.0028402992,0.0002443912,0.000012013902],"genre_scores_gemma":[0.28766167,0.00003345851,0.7074398,0.00006718573,0.000030238483,0.00039052792,0.0043236315,0.00003633802,0.000017180588],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782634,0.00010637808,0.0006141932,0.000600627,0.00045180524,0.00040063373],"domain_scores_gemma":[0.9971807,0.001247904,0.0002526418,0.00094680756,0.00017714576,0.00019479531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018513019,0.00023102763,0.00054517563,0.0005368121,0.000099923906,0.000029918136,0.0003294079,0.00006220178,0.000014843436],"category_scores_gemma":[0.002879417,0.00018695912,0.00001269166,0.0013556273,0.00014193432,0.00018629388,0.00015808307,0.00015104536,0.000002790417],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002922502,0.0011828198,0.009199622,0.0029819221,0.0041491375,0.00026549332,0.030728083,0.01113864,0.029559512,0.4493851,0.01709635,0.4413908],"study_design_scores_gemma":[0.0013003798,0.0007121553,0.006305296,0.0001768251,0.0018581729,0.000001266343,0.0017268525,0.57314855,0.000982188,0.41336074,0.00010311045,0.00032447703],"about_ca_topic_score_codex":0.000357855,"about_ca_topic_score_gemma":0.0053523337,"teacher_disagreement_score":0.5620099,"about_ca_system_score_codex":0.000049107326,"about_ca_system_score_gemma":0.00004310614,"threshold_uncertainty_score":0.76239717},"labels":[],"label_agreement":null},{"id":"W4389676925","doi":"10.1002/sim.9973","title":"Accommodating misclassification effects on optimizing dynamic treatment regimes with Q‐learning","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Covariate; Computer science; Econometrics; Estimation; Statistics; Machine learning; Artificial intelligence; Mathematics","score_opus":0.09089600466695962,"score_gpt":0.43294174638760535,"score_spread":0.3420457417206457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389676925","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063864864,0.000042467476,0.9270312,0.0010247581,0.00012691432,0.00092179806,0.0000183668,0.0010474293,0.0059222076],"genre_scores_gemma":[0.46504235,0.00024156128,0.5329236,0.000052880718,0.000065647946,0.00019622598,0.00016605448,0.00006613113,0.0012455542],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877924,0.000118704644,0.00029240505,0.00026374048,0.00027785503,0.00026808283],"domain_scores_gemma":[0.9957135,0.0037043171,0.00018785146,0.00028399003,0.00005752752,0.00005282081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040306506,0.00019720722,0.0003354667,0.000253593,0.00009170705,0.000010886666,0.00010510617,0.000055734534,0.000019689707],"category_scores_gemma":[0.0020972625,0.00014027354,0.0000108871955,0.0003996035,0.00009190542,0.000048580496,0.000023243845,0.00026312855,0.000016690678],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002337197,0.00023191859,0.0025926367,0.0009258032,0.00013302854,0.0006958063,0.008734629,0.0031777627,0.012942693,0.55182606,0.0046719247,0.413834],"study_design_scores_gemma":[0.004389892,0.007356266,0.0056818156,0.005782649,0.00020800435,0.000025820664,0.005298896,0.1396579,0.010012213,0.819703,0.0010032771,0.0008802519],"about_ca_topic_score_codex":0.000023913044,"about_ca_topic_score_gemma":0.00004032514,"teacher_disagreement_score":0.41295373,"about_ca_system_score_codex":0.00028029052,"about_ca_system_score_gemma":0.000028207698,"threshold_uncertainty_score":0.57201886},"labels":[],"label_agreement":null},{"id":"W4390031813","doi":"10.1002/sim.9984","title":"Modeling multiple correlated end‐organ disease trajectories: A tutorial for multistate and joint models with applications in diabetes complications","year":2023,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Diabetes Management and Research","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sinai Health System; Public Health Ontario; University of Toronto; Lunenfeld-Tanenbaum Research Institute; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Statistical Sciences Institute; Canadian Institutes of Health Research","keywords":"Biostatistics; Computer science; Discretization; Outcome (game theory); Contrast (vision); Multivariate statistics; Process (computing); Machine learning; Intensive care medicine; Data mining; Artificial intelligence; Medicine; Epidemiology; Mathematics; Internal medicine","score_opus":0.05080697279266112,"score_gpt":0.33082962055929593,"score_spread":0.2800226477666348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390031813","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30791122,0.00032851007,0.68174464,0.0032091246,0.00023415592,0.005248512,0.0008064245,0.00019892445,0.00031846194],"genre_scores_gemma":[0.98615557,0.00012993373,0.0103963455,0.00007169328,0.00014141915,0.0009773005,0.0017941019,0.000042489883,0.0002911529],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984949,0.000031599822,0.00040639748,0.00035424184,0.00032456458,0.00038826597],"domain_scores_gemma":[0.9987833,0.0005323313,0.000039541606,0.00025726095,0.00017418526,0.00021336555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004568381,0.000161919,0.00037156104,0.00046512595,0.000103116545,0.000015461495,0.00007450121,0.000044067474,0.000010515045],"category_scores_gemma":[0.00061028154,0.00012510968,0.000016305054,0.00071147375,0.00023863825,0.000059059865,0.00004539625,0.00021471563,0.0000031878424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027884496,0.002173944,0.44935676,0.00903973,0.0007109906,0.0002721687,0.01813001,0.22439948,0.006729323,0.23929757,0.010863853,0.036237705],"study_design_scores_gemma":[0.005258589,0.00021073256,0.023597065,0.00037512073,0.00009573809,1.8583974e-7,0.00080266746,0.95510787,0.000008422029,0.014070351,0.0003388389,0.00013439324],"about_ca_topic_score_codex":0.00009890915,"about_ca_topic_score_gemma":0.00022644261,"teacher_disagreement_score":0.7307084,"about_ca_system_score_codex":0.000076783326,"about_ca_system_score_gemma":0.000084010186,"threshold_uncertainty_score":0.5101825},"labels":[],"label_agreement":null},{"id":"W4390883403","doi":"10.1002/sim.10009","title":"A Bayesian framework for modeling COVID‐19 case numbers through longitudinal monitoring of SARS‐CoV‐2 RNA in wastewater","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"SARS-CoV-2 detection and testing","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Health Services; University of Alberta; University of Calgary","funders":"National Institute of General Medical Sciences; Canadian Institutes of Health Research; Illinois State University; National Institutes of Health; Alberta Health; Natural Sciences and Engineering Research Council of Canada; Alberta Health Services; University of Minnesota","keywords":"Coronavirus disease 2019 (COVID-19); Wastewater; Bayesian probability; Computer science; Missing data; Pandemic; Data mining; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Process (computing); Statistics; Environmental science; Artificial intelligence; Machine learning; Medicine; Mathematics; Environmental engineering; Internal medicine","score_opus":0.12995340238863706,"score_gpt":0.4334511856835037,"score_spread":0.30349778329486665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390883403","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35307124,0.000678185,0.6441827,0.0004023669,0.00087646226,0.00038256074,0.000044224205,0.000062917345,0.00029935304],"genre_scores_gemma":[0.8021669,0.000039331044,0.19692123,0.00030127066,0.00045603298,0.000040373925,0.000013055464,0.00004314076,0.000018687508],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980951,0.00004811806,0.0007509803,0.00040068896,0.0003352725,0.00036982298],"domain_scores_gemma":[0.99825305,0.0012299868,0.00008425353,0.00024498848,0.000102864964,0.0000848817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007102021,0.0002184199,0.0005376511,0.00035470774,0.000059436323,0.0000151658205,0.00007257565,0.00014736436,0.00003231298],"category_scores_gemma":[0.0037927728,0.00018725201,0.000047615507,0.00056802586,0.00014122252,0.000070899216,0.000031077398,0.0005893604,0.000003332588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0045805676,0.0012267445,0.14473043,0.03717428,0.0013834282,0.1604216,0.15845527,0.01205872,0.27633873,0.1302063,0.006124703,0.06729925],"study_design_scores_gemma":[0.006775328,0.0012831462,0.00014396296,0.012073845,0.0005125123,0.005128041,0.01392661,0.75081307,0.049135912,0.15861498,0.00097279076,0.0006197856],"about_ca_topic_score_codex":0.0021738417,"about_ca_topic_score_gemma":0.00031623713,"teacher_disagreement_score":0.7387544,"about_ca_system_score_codex":0.0002731409,"about_ca_system_score_gemma":0.00016793153,"threshold_uncertainty_score":0.7635915},"labels":[],"label_agreement":null},{"id":"W4391138204","doi":"10.1002/sim.10011","title":"Multiple imputation strategies for missing event times in a multi‐state model analysis","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; University of Bristol; Medical Research Council Canada; Wellcome Trust; NHS Blood and Transplant","keywords":"Imputation (statistics); Computer science; Missing data; Data mining; Statistics; Machine learning; Mathematics","score_opus":0.09443405681533493,"score_gpt":0.4594438165445142,"score_spread":0.36500975972917926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391138204","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008655985,0.00019177204,0.99745566,0.0002513771,0.0001265119,0.0003744684,0.0004948135,0.00004720502,0.00019261414],"genre_scores_gemma":[0.2515623,0.000027141272,0.7480989,0.00003548859,0.000026157843,0.00005481552,0.00006260199,0.000020290901,0.00011229702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983061,0.00011169952,0.00069961586,0.00033796436,0.0002489448,0.00029565967],"domain_scores_gemma":[0.99399143,0.0055924887,0.00008630944,0.00015855103,0.0000976499,0.000073596006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011461516,0.00018327177,0.0005023259,0.0005106758,0.000038280083,0.000057001464,0.000101799,0.000060838647,0.00007725624],"category_scores_gemma":[0.003917496,0.00014764711,0.00004582049,0.0006883057,0.00011877053,0.0000804541,0.000020771282,0.00020583501,0.0000022206946],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005837788,0.00011290012,0.0006462547,0.001033785,0.00015964532,0.000099851495,0.005936624,0.008062463,0.0002940733,0.8782704,0.0012918216,0.10403384],"study_design_scores_gemma":[0.00036786534,0.000041909072,0.00041924554,0.00019336445,0.00012623183,6.683895e-7,0.00031377288,0.5039386,0.000009675131,0.49449667,0.000009771796,0.000082210965],"about_ca_topic_score_codex":0.00019250675,"about_ca_topic_score_gemma":0.0009066577,"teacher_disagreement_score":0.49587616,"about_ca_system_score_codex":0.000102015896,"about_ca_system_score_gemma":0.00014802445,"threshold_uncertainty_score":0.60208744},"labels":[],"label_agreement":null},{"id":"W4391652457","doi":"10.1002/sim.10034","title":"Correction to “Using principal stratification in analysis of clinical trials”","year":2024,"lang":"en","type":"erratum","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bayer (Canada)","funders":"","keywords":"Statistics; Principal (computer security); Stratification (seeds); Computer science; Econometrics; Mathematics; Biology","score_opus":0.7621167309528273,"score_gpt":0.699804452428747,"score_spread":0.06231227852408028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391652457","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002214159,0.00027273872,0.8579487,0.00032411003,0.12789401,0.0017128381,0.002182731,0.000052534855,0.009390866],"genre_scores_gemma":[0.0012677747,0.0005971269,0.9739206,0.00014988001,0.005026922,0.00009438788,0.0005193707,0.00013026214,0.018293684],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9772938,0.007675082,0.011974127,0.0011706472,0.0014311885,0.00045519316],"domain_scores_gemma":[0.8048681,0.19114675,0.00240065,0.0009155444,0.00042481846,0.00024411581],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06774205,0.0004829765,0.006878934,0.0024443148,0.000025297164,0.000025714839,0.00046093934,0.00094546174,0.0008946944],"category_scores_gemma":[0.76153326,0.00039671577,0.00037958648,0.0038535262,0.00041731953,0.000026446884,0.0001392418,0.00318184,0.000014609168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037599975,0.00037922247,0.0007128298,0.0012603842,0.0014425052,0.00012073932,0.0006270888,0.00020456617,0.00002028086,0.08292353,0.8675707,0.044362184],"study_design_scores_gemma":[0.0014280367,0.0006665721,0.0061943475,0.005385965,0.010864818,0.0000018060715,0.00032369726,0.16262414,0.0000058215687,0.80593437,0.00606669,0.0005037626],"about_ca_topic_score_codex":0.0006329586,"about_ca_topic_score_gemma":0.0036612512,"teacher_disagreement_score":0.86150396,"about_ca_system_score_codex":0.00033208122,"about_ca_system_score_gemma":0.0007261274,"threshold_uncertainty_score":0.9998485},"labels":[],"label_agreement":null},{"id":"W4391841493","doi":"10.1002/sim.10012","title":"Statistical plasmode simulations–Potentials, challenges and recommendations","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Variety (cybernetics); Key (lock); Statistical model; Set (abstract data type); Parametric statistics; Data science; Data set; Data mining; Machine learning; Theoretical computer science; Artificial intelligence; Statistics; Mathematics","score_opus":0.11468469702013184,"score_gpt":0.44976894827582375,"score_spread":0.3350842512556919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391841493","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014151681,0.0019765624,0.99031895,0.0034863492,0.0004948472,0.00019234615,0.0009280417,0.00007819738,0.002383211],"genre_scores_gemma":[0.09137991,0.0022401179,0.9059001,0.00007757619,0.00015599928,0.000018829867,0.000086027845,0.000029506367,0.00011192866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99838024,0.00021456783,0.0005291087,0.00035360781,0.00026876526,0.00025370106],"domain_scores_gemma":[0.9880981,0.011478765,0.00004597849,0.00018554488,0.00006638306,0.00012526201],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00074962527,0.00017485645,0.00036213975,0.00021036327,0.00006417905,0.00003374277,0.000086631284,0.00007777377,0.0011279085],"category_scores_gemma":[0.005610524,0.00014166792,0.000010183752,0.00015661579,0.00028914303,0.000063315245,0.000044686447,0.00031354214,0.00001484975],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006607305,0.000026962918,0.00002303338,0.0002776107,0.00001730773,0.00006207442,0.0006977325,8.0121214e-7,0.000022108146,0.74734974,0.0068731867,0.24464285],"study_design_scores_gemma":[0.00030163734,0.00011928107,0.0014911874,0.0004827238,0.00007023183,0.000017968257,0.0002875269,0.03351584,0.0000049882296,0.959615,0.0039440617,0.00014954498],"about_ca_topic_score_codex":0.000035207864,"about_ca_topic_score_gemma":0.00016960147,"teacher_disagreement_score":0.24449332,"about_ca_system_score_codex":0.000043782587,"about_ca_system_score_gemma":0.0000479955,"threshold_uncertainty_score":0.9997852},"labels":[],"label_agreement":null},{"id":"W4396723746","doi":"10.1002/sim.10104","title":"Adaptive designs in public health: Vaccine and cluster randomized trials go Bayesian","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"National Institute of Environmental Health Sciences; National Institute on Aging","keywords":"Bayes' theorem; Bayesian probability; Computer science; Randomized controlled trial; Clinical trial; Flexibility (engineering); Psychological intervention; Non-communicable disease; Cluster (spacecraft); Public health; Matching (statistics); Cluster randomised controlled trial; Medicine; Econometrics; Risk analysis (engineering); Statistics; Artificial intelligence; Economics; Mathematics; Nursing","score_opus":0.6838323276886842,"score_gpt":0.60154715796384,"score_spread":0.08228516972484423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396723746","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008627733,0.0018900265,0.9774287,0.015307692,0.0013171049,0.0025163095,0.00030651063,0.00008323368,0.0010641826],"genre_scores_gemma":[0.030974206,0.0015034328,0.965063,0.0012615075,0.0006033127,0.00023651039,0.000017122706,0.000071954964,0.00026899972],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97774947,0.015117271,0.004863894,0.0007907441,0.00073019596,0.0007483983],"domain_scores_gemma":[0.6319265,0.3669459,0.00040665068,0.00031749328,0.00010158421,0.0003019084],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08639028,0.0003658873,0.004199752,0.00061957905,0.000049097995,0.000060319977,0.0002169182,0.00021109595,0.000919689],"category_scores_gemma":[0.57981646,0.00025063774,0.000096971235,0.00072067865,0.0004919573,0.00007758046,0.000102184626,0.00084067223,0.000014914224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0069303806,0.00011792023,0.00004287665,0.0007048364,0.0001640017,0.00021835153,0.0017302269,0.0000016933978,0.000007016096,0.84856313,0.035530012,0.10598953],"study_design_scores_gemma":[0.07384375,0.0003978106,0.000101362806,0.0012346867,0.000146082,0.000012062379,0.0002645967,0.017720288,0.0000031476127,0.90550274,0.0005663019,0.000207193],"about_ca_topic_score_codex":0.00014045855,"about_ca_topic_score_gemma":0.00028349293,"teacher_disagreement_score":0.49342617,"about_ca_system_score_codex":0.0002158182,"about_ca_system_score_gemma":0.00027979648,"threshold_uncertainty_score":0.9999946},"labels":[],"label_agreement":null},{"id":"W4396799016","doi":"10.1002/sim.10089","title":"Novel non‐linear models for clinical trial analysis with longitudinal data: A tutorial using <scp>SAS</scp> for both frequentist and Bayesian methods","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"College of Veterinarians of British Columbia","funders":"National Institute on Aging; National Institutes of Health","keywords":"Frequentist inference; Categorical variable; Bayesian probability; Repeated measures design; Random effects model; Computer science; Inference; Mixed model; Statistics; Bayesian inference; Linear model; Generalized linear mixed model; Mathematics; Econometrics; Artificial intelligence; Medicine","score_opus":0.7321217157620442,"score_gpt":0.6629236950961048,"score_spread":0.06919802066593939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396799016","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00051490625,0.00028047425,0.983961,0.00013621782,0.00448552,0.0027898776,0.0076711867,0.00007320737,0.00008763756],"genre_scores_gemma":[0.0011948255,0.00013840935,0.9923129,0.00008524227,0.005524468,0.00018839569,0.0002837432,0.00012421205,0.00014778328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931164,0.00088527775,0.003041702,0.0015457826,0.00072865427,0.0006822125],"domain_scores_gemma":[0.79044443,0.20742746,0.0005140492,0.0009834865,0.00030818948,0.00032238287],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.025351943,0.00049614644,0.0026796255,0.00045527113,0.00015392588,0.00012302151,0.00057892414,0.000390653,0.000031381198],"category_scores_gemma":[0.20573637,0.0003705869,0.00019428592,0.00083497376,0.0009284158,0.00018543654,0.0002225081,0.000704678,5.278357e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01567122,0.0014722509,0.00074817473,0.0046676653,0.0091243405,0.00029451295,0.0011466977,0.00057743065,0.00023244826,0.8817662,0.034544233,0.049754824],"study_design_scores_gemma":[0.021433061,0.001276211,0.00004426779,0.00029688375,0.005806467,0.000008004302,0.00008671925,0.5004306,0.000005537885,0.46962446,0.00084683805,0.00014095256],"about_ca_topic_score_codex":0.0001444941,"about_ca_topic_score_gemma":0.0002464135,"teacher_disagreement_score":0.49985316,"about_ca_system_score_codex":0.00011086399,"about_ca_system_score_gemma":0.00039897396,"threshold_uncertainty_score":0.9998746},"labels":[],"label_agreement":null},{"id":"W4399135167","doi":"10.1002/sim.10116","title":"Structured learning in time‐dependent Cox models","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Ministère de la Santé et des Services sociaux; Réseau Québécois de Recherche sur les Médicaments; Natural Sciences and Engineering Research Council of Canada; Heart and Stroke Foundation of Canada","keywords":"Computer science; Proportional hazards model; Econometrics; Statistics; Mathematics","score_opus":0.017194394397149235,"score_gpt":0.3004267088436853,"score_spread":0.283232314446536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399135167","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015349279,0.00046820482,0.99465054,0.0016067235,0.0002362585,0.000119150835,0.000008646045,0.000080637845,0.001294933],"genre_scores_gemma":[0.9535031,0.00016115577,0.04452063,0.00025788622,0.000132864,0.000019495441,0.000023683375,0.000010381051,0.0013708062],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990909,0.000041339023,0.00021260661,0.00024539727,0.00024376939,0.00016600413],"domain_scores_gemma":[0.99947655,0.0002690841,0.000022400363,0.00016849698,0.000018444804,0.00004501914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002948637,0.000078319,0.00012967808,0.00011886025,0.000028333629,0.000043873497,0.00031703248,0.000029590126,0.000054287546],"category_scores_gemma":[0.00004007136,0.00006330832,0.000006622709,0.00041889292,0.000043081793,0.000082760664,0.000080211496,0.00031951303,0.000024265017],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003306867,0.000017350725,0.00019718856,0.000039337523,0.0000060303937,0.00029423425,0.0013333879,0.06372786,0.000645333,0.80794466,0.013281363,0.11250992],"study_design_scores_gemma":[0.00014538101,0.00003180337,0.000372838,0.000087668435,0.00000209183,0.0000071609365,0.000013134087,0.7882533,0.000012846552,0.20957689,0.0014393481,0.000057507645],"about_ca_topic_score_codex":0.00006357319,"about_ca_topic_score_gemma":0.00006425323,"teacher_disagreement_score":0.9519682,"about_ca_system_score_codex":0.000039414554,"about_ca_system_score_gemma":0.00003145374,"threshold_uncertainty_score":0.25816384},"labels":[],"label_agreement":null},{"id":"W4399262027","doi":"10.1002/sim.10126","title":"The effect of number of clusters and magnitude of within‐cluster homogeneity in outcomes on the performance of four variance estimators for a marginal multivariable Cox regression model fit to clustered data in the context of observational research","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"Ministry of Long-Term Care; Canadian Institutes of Health Research; Ministry of Health, Ontario","keywords":"Estimator; Statistics; Homogeneity (statistics); Mathematics; Covariate; Confidence interval; Cluster (spacecraft); Econometrics; Proportional hazards model; Regression; Standard error; Regression analysis; Hazard ratio; Computer science","score_opus":0.25730499408334184,"score_gpt":0.5027874771247031,"score_spread":0.24548248304136122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399262027","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54853016,0.00006189969,0.44774324,0.0009523585,0.000092952505,0.0013164032,0.0012261673,0.0000019367183,0.00007488396],"genre_scores_gemma":[0.6868886,0.000021738608,0.3129677,0.000032785018,0.0000073034007,0.000048193484,0.000008280598,0.000008823547,0.00001660986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973516,0.00069783715,0.00089659414,0.00021232263,0.00066050247,0.00018115401],"domain_scores_gemma":[0.95356935,0.045439504,0.00023699833,0.00050499366,0.00022399283,0.00002518965],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0100396145,0.00013192152,0.00054726185,0.00011252798,0.00004003613,0.0000065775557,0.0004947365,0.000060208396,0.000009989083],"category_scores_gemma":[0.020471614,0.00005989481,0.000016934038,0.0003794149,0.000571128,0.000042815085,0.00017606796,0.0003072703,1.2487766e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003601667,0.00023455339,0.16045691,0.009673601,0.000105473075,0.000009329535,0.009912802,0.0011500379,0.0006023102,0.80026364,0.004055468,0.009934219],"study_design_scores_gemma":[0.0014886068,0.000652921,0.037521806,0.0030971407,0.00004923614,0.0000026102148,0.0006355194,0.8364463,0.00042162326,0.11961323,0.0000049426835,0.00006610408],"about_ca_topic_score_codex":0.0002253378,"about_ca_topic_score_gemma":0.00020236442,"teacher_disagreement_score":0.8352962,"about_ca_system_score_codex":0.000028533235,"about_ca_system_score_gemma":0.00010783906,"threshold_uncertainty_score":0.9877794},"labels":[],"label_agreement":null},{"id":"W4399593952","doi":"10.1002/sim.10138","title":"Non‐parametric inference on calibration of predicted risks","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Inference; Calibration; Parametric statistics; Computer science; Statistics; Econometrics; Parametric model; Mathematics; Artificial intelligence","score_opus":0.1888057989843291,"score_gpt":0.5166805173376785,"score_spread":0.3278747183533494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399593952","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007526961,0.00021117282,0.9878922,0.00021100634,0.0011395805,0.0001711611,0.00033433433,0.000037294674,0.0024763022],"genre_scores_gemma":[0.9702957,0.0000654536,0.029089788,0.000045578672,0.00016599183,0.000012420647,0.000027215858,0.000013689716,0.00028415417],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966141,0.00009068097,0.0009719815,0.00043679564,0.0016711322,0.00021528754],"domain_scores_gemma":[0.98643917,0.012679224,0.00015637555,0.0003341988,0.00028406846,0.00010695886],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0014688695,0.00014274764,0.00038413692,0.00087837345,0.000037273232,0.000042120053,0.00035661177,0.00006966386,0.00034977787],"category_scores_gemma":[0.04342823,0.00009920493,0.000015775651,0.0025807405,0.00032188458,0.0001563867,0.000055585355,0.00038037467,0.000032716227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017902441,0.00015034077,0.030029608,0.00036109172,0.00003419637,0.00036654764,0.0024022793,0.018303191,0.0006614484,0.41336536,0.022488711,0.5116582],"study_design_scores_gemma":[0.000363294,0.00048566927,0.030295756,0.00044721493,0.000017004444,0.0000015777748,0.0002667463,0.43650547,0.00031632514,0.5305965,0.0005879807,0.0001165006],"about_ca_topic_score_codex":0.0000981573,"about_ca_topic_score_gemma":0.0000247313,"teacher_disagreement_score":0.96276873,"about_ca_system_score_codex":0.00006961619,"about_ca_system_score_gemma":0.00010750701,"threshold_uncertainty_score":0.96462935},"labels":[],"label_agreement":null},{"id":"W4399721808","doi":"10.1002/sim.10151","title":"A sparse factor model for clustering high‐dimensional longitudinal data","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Computer science; Categorical variable; Dirichlet process; Curse of dimensionality; Gibbs sampling; Clustering high-dimensional data; Data mining; Bayesian probability; Artificial intelligence; Machine learning","score_opus":0.12987540817975268,"score_gpt":0.39157382235535,"score_spread":0.2616984141755973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399721808","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000074184085,0.00055165536,0.9956971,0.0014993256,0.0011783929,0.00020064945,0.00063657935,0.00006695118,0.00009516774],"genre_scores_gemma":[0.054815207,0.000036013287,0.9440892,0.00029729857,0.00023996641,0.000014098235,0.00011675004,0.000015716907,0.0003757666],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985048,0.00003693063,0.00030817097,0.0005796279,0.00029599495,0.00027443492],"domain_scores_gemma":[0.9986306,0.00049441075,0.000035995796,0.0006839758,0.000057458972,0.00009755045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007534227,0.00014901943,0.0002525354,0.00014778893,0.000048353366,0.00005212087,0.00072742894,0.000052105148,0.000027418033],"category_scores_gemma":[0.00026661652,0.00011550758,0.000014191595,0.00019771869,0.000071227354,0.00021438651,0.00039109343,0.00019751607,0.000005310759],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015661615,0.00002361768,0.00001456944,0.00020097921,0.000024901186,0.0001600151,0.0007683227,0.0011005976,0.00019045938,0.6845121,0.02963815,0.28335068],"study_design_scores_gemma":[0.00028514976,0.00005596165,0.00009157783,0.00015834052,0.000012983018,0.0000148303725,0.0000018786749,0.77468055,0.000007175301,0.22390547,0.00068587,0.00010017769],"about_ca_topic_score_codex":0.000047371974,"about_ca_topic_score_gemma":0.00010475173,"teacher_disagreement_score":0.77357996,"about_ca_system_score_codex":0.0000425242,"about_ca_system_score_gemma":0.00013007414,"threshold_uncertainty_score":0.47102624},"labels":[],"label_agreement":null},{"id":"W4399817401","doi":"10.1002/sim.10152","title":"deepAFT: A nonlinear accelerated failure time model with artificial neural network","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingston General Hospital; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Censoring (clinical trials); Covariate; Proportional hazards model; Accelerated failure time model; Computer science; Artificial neural network; Inverse probability weighting; Imputation (statistics); Weighting; Artificial intelligence; Regression; Nonparametric statistics; Survival analysis; Statistics; Machine learning; Econometrics; Mathematics; Missing data; Estimator","score_opus":0.09290964956243886,"score_gpt":0.3986075386957393,"score_spread":0.3056978891333004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399817401","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004649521,0.00011959751,0.9915687,0.0010322016,0.00023785693,0.00029097486,0.00028736278,0.00013980565,0.0016739924],"genre_scores_gemma":[0.03741907,0.00001556833,0.96091515,0.00026239842,0.0006171924,0.000028437127,0.000081414815,0.00006002995,0.00060075533],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808156,0.0001231793,0.0005571732,0.00037024284,0.00042500262,0.00044281807],"domain_scores_gemma":[0.9969192,0.0024796634,0.00006736921,0.00025496067,0.0001384988,0.00014027295],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00070847495,0.0002525572,0.0004919485,0.00011092183,0.00006594222,0.0000528897,0.00016778635,0.000097896846,0.0009408649],"category_scores_gemma":[0.001762782,0.0001715064,0.000018572739,0.0005710266,0.00026725442,0.00004991217,0.0000430653,0.0005309201,0.00005060892],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012272439,0.000070118214,0.000057684992,0.00029596998,0.000055825116,0.00056782376,0.00083337177,0.0029718739,0.00028489574,0.9148797,0.051861178,0.027998842],"study_design_scores_gemma":[0.00018730266,0.00018846734,0.000030045525,0.0002829424,0.000057166464,0.00001285511,0.00004560448,0.574055,0.00000984814,0.42476514,0.00023645158,0.00012915194],"about_ca_topic_score_codex":0.000029128789,"about_ca_topic_score_gemma":0.0001255984,"teacher_disagreement_score":0.5710831,"about_ca_system_score_codex":0.000050958526,"about_ca_system_score_gemma":0.0001229795,"threshold_uncertainty_score":0.9999724},"labels":[],"label_agreement":null},{"id":"W4399827830","doi":"10.1002/sim.10144","title":"Bayesian mixture modelling with ranked set samples","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gibbs sampling; Bayesian probability; Ranking (information retrieval); Bayesian average; Computer science; Statistics; Sampling (signal processing); RSS; Simple random sample; Bayesian inference; Data mining; Variable-order Bayesian network; Mathematics; Artificial intelligence","score_opus":0.03274320391658409,"score_gpt":0.3164800722356023,"score_spread":0.28373686831901823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399827830","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039529044,0.001631927,0.993467,0.0020828168,0.00049741805,0.00016210288,0.00004682761,0.00012934243,0.0019430728],"genre_scores_gemma":[0.056114737,0.00016986456,0.94270676,0.00046499757,0.00020513764,0.000012497375,0.000027075586,0.00002160637,0.0002773352],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984085,0.00011800688,0.0002989683,0.00047756007,0.0003787057,0.00031823915],"domain_scores_gemma":[0.9988124,0.0005451204,0.00003846761,0.00041996196,0.000062729974,0.00012133898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079132966,0.00019745991,0.0003105909,0.00022038545,0.00005559964,0.00007741178,0.00041808473,0.00007335548,0.00004959834],"category_scores_gemma":[0.000047595935,0.00013187334,0.000017555616,0.00058541994,0.00012670405,0.00014310812,0.00005471412,0.00038182567,0.000006559386],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011342304,0.000010319796,0.000035257744,0.00013619446,0.000029042867,0.0004777289,0.003288145,0.0009595926,0.000050428764,0.91692686,0.00733848,0.07073662],"study_design_scores_gemma":[0.00031221347,0.00011324004,0.000024075225,0.000374145,0.000018940042,0.000042914373,0.00003466525,0.60896695,0.000023199302,0.3825817,0.007359631,0.0001482854],"about_ca_topic_score_codex":0.00011219353,"about_ca_topic_score_gemma":0.000058773025,"teacher_disagreement_score":0.6080074,"about_ca_system_score_codex":0.000040827446,"about_ca_system_score_gemma":0.00010592051,"threshold_uncertainty_score":0.5377639},"labels":[],"label_agreement":null},{"id":"W4400098172","doi":"10.1002/sim.10149","title":"Addressing dispersion in mis‐measured multivariate binomial outcomes: A novel statistical approach for detecting differentially methylated regions in bisulfite sequencing data","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre; McGill University; Université Laval; Université du Québec à Montréal; HEC Montréal; Jewish General Hospital; York University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Genome Canada","keywords":"Multivariate statistics; Covariate; Expectation–maximization algorithm; Univariate; DNA methylation; Negative binomial distribution; Bioconductor; Computer science; Statistics; Multiplicative function; Mathematics; Biology; Poisson distribution; Genetics; Gene; Maximum likelihood","score_opus":0.42460416474090396,"score_gpt":0.4816868083342835,"score_spread":0.057082643593379556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400098172","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00721693,0.00015173909,0.9884196,0.00018342731,0.00053146714,0.0009548067,0.0022944745,0.000074809606,0.00017275914],"genre_scores_gemma":[0.31955224,0.000015773881,0.6797382,0.000039515024,0.000093634946,0.000064562686,0.00041242316,0.0000572696,0.00002637669],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958696,0.00045040916,0.0014612735,0.0009606215,0.0005670036,0.00069111097],"domain_scores_gemma":[0.98326814,0.01562512,0.00018408477,0.0006381859,0.00011666967,0.00016780559],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0038049496,0.00040529895,0.001051383,0.0006673811,0.000093703595,0.00008318597,0.00048712702,0.00021301214,0.00006713923],"category_scores_gemma":[0.04515176,0.00031854684,0.000035327554,0.00077921763,0.00026037154,0.00012938655,0.00018317824,0.0009231504,0.0000015315724],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00079372484,0.0009675367,0.0041477038,0.006238722,0.00028621103,0.00075409916,0.014771643,0.00037130818,0.041462652,0.8118675,0.0013936803,0.11694525],"study_design_scores_gemma":[0.0033362536,0.00015295515,0.0066055087,0.0021796385,0.00014781884,0.000011877056,0.0012703476,0.81890976,0.000051856805,0.1669244,0.000024130886,0.00038546463],"about_ca_topic_score_codex":0.0017770091,"about_ca_topic_score_gemma":0.0013973826,"teacher_disagreement_score":0.8185384,"about_ca_system_score_codex":0.0004718403,"about_ca_system_score_gemma":0.0002554369,"threshold_uncertainty_score":0.9999267},"labels":[],"label_agreement":null},{"id":"W4400302774","doi":"10.1002/sim.10154","title":"A Bayesian non‐stationary heteroskedastic time series model for multivariate critical care data","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Heteroscedasticity; Computer science; Markov chain Monte Carlo; Multivariate statistics; Bayesian probability; Bayesian inference; State-space representation; State space; Gibbs sampling; Series (stratigraphy); Data mining; Missing data; Statistics; Artificial intelligence; Machine learning; Algorithm; Mathematics","score_opus":0.07632011854582142,"score_gpt":0.35087499666637695,"score_spread":0.2745548781205555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400302774","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003868563,0.002803391,0.9768671,0.0008368795,0.00054310635,0.00026662814,0.017807685,0.00003642729,0.00045196325],"genre_scores_gemma":[0.73407006,0.00014816724,0.26266965,0.00012619216,0.00026793432,0.000046181533,0.0022026016,0.0000425884,0.00042660133],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984602,0.000010476994,0.0006510044,0.0005399011,0.00006005535,0.0002784125],"domain_scores_gemma":[0.9988768,0.0005514288,0.000051638042,0.00038084592,0.00006951095,0.00006974107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005580268,0.00015253088,0.0003811329,0.00020512987,0.00008693308,0.00004102117,0.00023923784,0.000081679245,0.000121252684],"category_scores_gemma":[0.0021002514,0.00016218827,0.000023254544,0.00015546924,0.00014461919,0.00024645863,0.0000873809,0.00018812515,0.000073955416],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014428889,0.00007377602,0.0012485014,0.0021237,0.000040276125,0.00006294903,0.010023675,0.009459975,0.000037672464,0.9508938,0.014148399,0.011742986],"study_design_scores_gemma":[0.00028209464,0.00008230521,0.00028282552,0.00013194254,0.000013016827,0.0000013302124,0.00010573498,0.7272974,5.9797657e-7,0.26990592,0.0017741513,0.00012265868],"about_ca_topic_score_codex":0.00016666227,"about_ca_topic_score_gemma":0.00010058469,"teacher_disagreement_score":0.7336832,"about_ca_system_score_codex":0.00008428999,"about_ca_system_score_gemma":0.00007910035,"threshold_uncertainty_score":0.6613846},"labels":[],"label_agreement":null},{"id":"W4400672891","doi":"10.1002/sim.10172","title":"Extending the DeLong algorithm for comparing areas under correlated receiver operating characteristic curves with missing data","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Nonparametric statistics; Computer science; Receiver operating characteristic; Software; Multivariate statistics; Algorithm; Statistics; Data mining; Mathematics; Machine learning","score_opus":0.15550918662417176,"score_gpt":0.44116230951500207,"score_spread":0.28565312289083034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400672891","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000094296316,0.0014384021,0.99528223,0.001087616,0.0005242292,0.0005159678,0.0005976396,0.00007243744,0.00038718345],"genre_scores_gemma":[0.014678952,0.00027119758,0.9838868,0.00027031865,0.00026103717,0.00003961214,0.0004351856,0.00005474762,0.00010217313],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998084,0.00018793982,0.0005957855,0.00046278338,0.0003139977,0.00035547608],"domain_scores_gemma":[0.98924583,0.009918201,0.00012258007,0.00049186544,0.00013177305,0.000089726665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018847084,0.0002346873,0.0004943327,0.0000954259,0.00021120024,0.00011029171,0.00038982183,0.000054405977,0.00016698317],"category_scores_gemma":[0.005025669,0.00013898483,0.000013382472,0.0003286733,0.00030015715,0.000115691866,0.000107363005,0.00046481876,0.0000031299103],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016076963,0.000034406443,0.00036220334,0.0011590568,0.000099837045,0.00011722423,0.0006350206,0.0000037556174,0.000065785935,0.47472197,0.0071413764,0.5156433],"study_design_scores_gemma":[0.00042632915,0.00009930776,0.0014073092,0.0069756,0.00023055745,0.00004698199,0.00029616393,0.62934583,0.0000059837644,0.3606143,0.0003626797,0.00018894229],"about_ca_topic_score_codex":0.000092234994,"about_ca_topic_score_gemma":0.000050040697,"teacher_disagreement_score":0.6293421,"about_ca_system_score_codex":0.00007472557,"about_ca_system_score_gemma":0.00010545215,"threshold_uncertainty_score":0.6016558},"labels":[],"label_agreement":null},{"id":"W4401037694","doi":"10.1002/sim.10167","title":"Modern approaches for evaluating treatment effect heterogeneity from clinical trials and observational data","year":2024,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bayer (Canada)","funders":"","keywords":"Observational study; Computer science; Identification (biology); Rule of thumb; Clinical trial; Medical physics; Machine learning; Artificial intelligence; Medicine; Statistics; Mathematics; Algorithm","score_opus":0.9530672804330427,"score_gpt":0.7219823764569416,"score_spread":0.23108490397610104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401037694","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008143533,0.6042439,0.3843291,0.000024875431,0.00023124451,0.0025732594,0.008512603,0.000062056075,0.000014803703],"genre_scores_gemma":[0.0000024559743,0.60254395,0.3892054,0.00001128513,0.00048107762,0.0006537865,0.0070103,0.000060795875,0.000030971572],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934943,0.0020441473,0.0028026218,0.0009983415,0.0004102376,0.00025039172],"domain_scores_gemma":[0.93012404,0.067819685,0.00090336276,0.0009915729,0.0000636356,0.00009768207],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.016098939,0.00057782716,0.004963802,0.00013543015,0.000044534998,0.00003006069,0.00040696873,0.0003587962,0.000020555934],"category_scores_gemma":[0.059856884,0.00033496064,0.00015185765,0.00012071101,0.00022331018,0.00005787926,0.00026943244,0.0004755424,0.0000026370928],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024496912,0.000052736727,0.000013261723,0.01041631,0.00046211088,0.000011039758,0.00006042682,3.315997e-7,2.5722986e-7,0.015395315,0.0024162703,0.9711474],"study_design_scores_gemma":[0.0011970942,0.0013836294,0.000004125835,0.018884683,0.010457662,0.00000657527,0.000013139609,0.031988952,8.738142e-7,0.88360935,0.052074082,0.00037984992],"about_ca_topic_score_codex":0.000031048756,"about_ca_topic_score_gemma":0.00009487042,"teacher_disagreement_score":0.9707676,"about_ca_system_score_codex":0.00021829363,"about_ca_system_score_gemma":0.00028074282,"threshold_uncertainty_score":0.99991024},"labels":[],"label_agreement":null},{"id":"W4401195388","doi":"10.1002/sim.10188","title":"Evaluation and comparison of covariate balance metrics in studies with time‐dependent confounding","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre hospitalier de l'Université Laval","funders":"Canadian Institutes of Health Research","keywords":"Covariate; Confounding; Statistics; Inverse probability weighting; Censoring (clinical trials); Marginal structural model; Weighting; Inverse probability; Mahalanobis distance; Econometrics; Causal inference; Proportional hazards model; Residual; Propensity score matching; Computer science; Mathematics; Medicine; Bayesian probability; Posterior probability","score_opus":0.26558728525217706,"score_gpt":0.5410066149450267,"score_spread":0.2754193296928496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401195388","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047685508,0.007321811,0.94199646,0.00021351341,0.00021319329,0.0008590785,0.000057609774,0.000094934316,0.0015578724],"genre_scores_gemma":[0.82056904,0.00046968274,0.17880449,0.000012556301,0.000021891594,0.000033310112,0.000011575355,0.0000148008385,0.00006268614],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99846584,0.00012623782,0.0004898176,0.00018420898,0.0006015773,0.00013232845],"domain_scores_gemma":[0.9963036,0.0031413,0.00013132536,0.00012884493,0.00027092893,0.000023963596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029832784,0.00011829697,0.000476226,0.00034518496,0.0000148035815,0.000007449915,0.00006182045,0.000039155973,0.00004070479],"category_scores_gemma":[0.0060332324,0.00008720042,0.0000041300177,0.0004659748,0.0002063339,0.00006099018,0.00003353257,0.00021049548,0.0000012234035],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008628958,0.00013935425,0.012930131,0.0021975883,0.00020785822,0.00012411732,0.015470206,0.00031111314,0.0030674436,0.91623694,0.0027248147,0.046504173],"study_design_scores_gemma":[0.0008484476,0.0004929464,0.0008729477,0.0023467985,0.00018612637,0.0000066277335,0.002100605,0.12594736,0.0007143642,0.8663069,0.00003951932,0.00013732677],"about_ca_topic_score_codex":0.0000371916,"about_ca_topic_score_gemma":0.00017308803,"teacher_disagreement_score":0.77288353,"about_ca_system_score_codex":0.00020869443,"about_ca_system_score_gemma":0.0000614177,"threshold_uncertainty_score":0.7222778},"labels":[],"label_agreement":null},{"id":"W4402555558","doi":"10.1002/sim.10210","title":"Trivariate Joint Modeling for Family Data with Longitudinal Counts, Recurrent Events and a Terminal Event with Application to Lynch Syndrome","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Genetic factors in colorectal cancer","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Public Health Ontario; Mount Sinai Hospital; Lunenfeld-Tanenbaum Research Institute; University of Toronto; Memorial University of Newfoundland; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Overdispersion; Statistics; Event (particle physics); Mixture model; Bivariate analysis; Random effects model; Colonoscopy; Bayesian probability; Count data; Computer science; Medicine; Econometrics; Mathematics; Poisson distribution; Colorectal cancer; Internal medicine; Cancer","score_opus":0.06002248682518295,"score_gpt":0.36620758516023605,"score_spread":0.3061850983350531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402555558","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.079750024,0.0010771386,0.9165373,0.0006437562,0.00028256522,0.0011367925,0.00040030564,0.000024884168,0.00014723833],"genre_scores_gemma":[0.93672544,0.00013620892,0.062247854,0.000115594376,0.00012093904,0.0001554422,0.0003448975,0.000029815168,0.00012379237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875975,0.000013001569,0.0002586826,0.00041972808,0.00036854573,0.0001802843],"domain_scores_gemma":[0.99935454,0.00009070167,0.000035556233,0.00031435076,0.00009333899,0.000111494184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037836767,0.00014110783,0.00028567555,0.00013478327,0.00002586604,0.0000087388535,0.00009000053,0.000035702662,0.000028541213],"category_scores_gemma":[0.00011826583,0.00009478155,0.000006224297,0.00019162412,0.000054677756,0.00002418513,0.00005042025,0.00015887854,0.0000061358737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013065223,0.0012866557,0.021555278,0.01651193,0.0015799247,0.0032427646,0.006154065,0.00603086,0.0032378216,0.017865514,0.0964462,0.81302375],"study_design_scores_gemma":[0.0043584546,0.009640276,0.03416949,0.0062153954,0.00084100757,0.0010812492,0.0002910153,0.9279087,0.000016836977,0.0045252503,0.010506819,0.00044550063],"about_ca_topic_score_codex":0.000077258235,"about_ca_topic_score_gemma":0.00007103115,"teacher_disagreement_score":0.92187786,"about_ca_system_score_codex":0.00013772826,"about_ca_system_score_gemma":0.00017553847,"threshold_uncertainty_score":0.38650796},"labels":[],"label_agreement":null},{"id":"W4403497067","doi":"10.1002/sim.10247","title":"A Nonparametric Global Win Probability Approach to the Analysis and Sizing of Randomized Controlled Trials With Multiple Endpoints of Different Scales and Missing Data: Beyond O'Brien–Wei–Lachin","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Missing data; Statistics; Confidence interval; Nonparametric statistics; Coverage probability; Point estimation; Mathematics; Type I and type II errors; Clinical endpoint; Sample size determination; Computer science; Randomized controlled trial; Medicine","score_opus":0.303822623694461,"score_gpt":0.5183622358018237,"score_spread":0.21453961210736272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403497067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037317257,0.0015326585,0.95459104,0.0004917549,0.00016738,0.0036947303,0.0019440632,0.00001921424,0.00024192875],"genre_scores_gemma":[0.4194494,0.00010718393,0.5802401,0.000024058127,0.00006543046,0.00007330105,0.000022290555,0.000012142809,0.000006108593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9877424,0.00656714,0.0038027926,0.0007101142,0.0009042283,0.00027331902],"domain_scores_gemma":[0.66195875,0.3361341,0.0008644245,0.0007075893,0.00017671134,0.00015842567],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.050077047,0.00032534482,0.007588797,0.00037255994,0.00005278495,0.000050938794,0.00032891458,0.00010774006,0.000024095627],"category_scores_gemma":[0.61940104,0.0001483875,0.00016629839,0.0014510498,0.0014038187,0.00004212881,0.00023457546,0.0003104824,1.40053e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.16475679,0.0016010951,0.0155304065,0.00784021,0.01577051,0.00004647645,0.0046838745,0.00015670074,0.0002982253,0.6199685,0.0006532375,0.16869402],"study_design_scores_gemma":[0.08216166,0.0002287428,0.0035642532,0.0006422456,0.009089221,0.0000045223187,0.00028717323,0.11311322,0.000035268662,0.790709,0.0000025694287,0.00016208291],"about_ca_topic_score_codex":0.00016441147,"about_ca_topic_score_gemma":0.00022734606,"teacher_disagreement_score":0.56932396,"about_ca_system_score_codex":0.000052599775,"about_ca_system_score_gemma":0.00007018615,"threshold_uncertainty_score":0.9781456},"labels":[],"label_agreement":null},{"id":"W4403879491","doi":"10.1002/sim.10236","title":"Estimands and Cumulative Incidence Function Regression in Clinical Trials: Some New Results on Interpretability and Robustness","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Econometrics; Estimator; Statistics; Multiplicative function; Regression; Robustness (evolution); Regression analysis; Censoring (clinical trials); Binomial regression; Computer science; Mathematics; Artificial intelligence","score_opus":0.31647089437465475,"score_gpt":0.5636028541672076,"score_spread":0.2471319597925528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403879491","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055447508,0.0008529956,0.939575,0.0017352719,0.0010923534,0.00047256303,0.00015582806,0.00003990729,0.0006285764],"genre_scores_gemma":[0.67063755,0.00060321734,0.3280675,0.00016000576,0.0003340911,0.000015084224,0.000021850627,0.000021276272,0.00013945023],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962614,0.0012471804,0.0014813278,0.00051690865,0.00028753292,0.00020565251],"domain_scores_gemma":[0.9562776,0.04299986,0.00016208622,0.00029128877,0.000062719504,0.00020644236],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013315821,0.00019058051,0.0007726493,0.0002359678,0.000034898545,0.00003164722,0.00009608538,0.00015280866,0.000077091616],"category_scores_gemma":[0.19734444,0.00012412752,0.000018752975,0.0002303438,0.0003712236,0.00008551835,0.000083973246,0.00067012664,0.000002266132],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012577493,0.000061209255,0.0020023393,0.0003513117,0.00001903878,0.000114896764,0.0014133155,0.000017679598,0.000011081829,0.54303503,0.005964363,0.44575197],"study_design_scores_gemma":[0.0013204017,0.0008497191,0.02764638,0.0027920664,0.000054668744,0.00000427283,0.00015357972,0.1824526,0.0000033490192,0.7845225,0.00008716415,0.00011334963],"about_ca_topic_score_codex":0.0009017977,"about_ca_topic_score_gemma":0.00088384934,"teacher_disagreement_score":0.61519,"about_ca_system_score_codex":0.000077481855,"about_ca_system_score_gemma":0.00012971312,"threshold_uncertainty_score":0.80941665},"labels":[],"label_agreement":null},{"id":"W4403955442","doi":"10.1002/sim.10260","title":"A Comparison of Variance Estimators for Logistic Regression Models Estimated Using Generalized Estimating Equations (<scp>GEE</scp>) in the Context of Observational Health Services Research","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Ministry of Long-Term Care; Canadian Institutes of Health Research; Ministry of Health, Ontario","keywords":"Estimator; Covariate; Statistics; Generalized estimating equation; Mathematics; Context (archaeology); Standard error; Estimating equations; Logistic regression; Econometrics; Variance (accounting); Generalized linear model; Cluster (spacecraft); Linear regression; Computer science","score_opus":0.5887665530378992,"score_gpt":0.6053092357592396,"score_spread":0.016542682721340407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403955442","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004584298,0.0008490984,0.9924037,0.00029420765,0.00025179624,0.00088530197,0.00064060977,0.000021316364,0.00006965818],"genre_scores_gemma":[0.30945522,0.00001703856,0.69023883,0.000051000072,0.000049261318,0.00006232913,0.0000994008,0.000019564923,0.0000073522538],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996131,0.00078045455,0.0015257988,0.00032634742,0.00084327365,0.00039312447],"domain_scores_gemma":[0.95534396,0.04335251,0.00043205253,0.00029758233,0.0005054677,0.000068443835],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005926632,0.00019482739,0.00083267427,0.00035805168,0.00014058565,0.000030737476,0.00033283973,0.00010021751,0.000014281538],"category_scores_gemma":[0.015606855,0.00013322929,0.000029335615,0.0010032805,0.00045519514,0.00008923013,0.000055697645,0.00044534967,4.7582165e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022462775,0.00014565194,0.00088163686,0.0038864622,0.000020776204,0.000009054329,0.012865212,0.0038577393,0.00023175524,0.9666906,0.0010328396,0.010355816],"study_design_scores_gemma":[0.0003404383,0.00013569863,0.00027785834,0.003627735,0.000024753443,0.0000017590966,0.0019314649,0.5166599,0.000027685157,0.4769365,0.0000052641053,0.000030947835],"about_ca_topic_score_codex":0.0012273103,"about_ca_topic_score_gemma":0.00025036145,"teacher_disagreement_score":0.5128022,"about_ca_system_score_codex":0.0001318061,"about_ca_system_score_gemma":0.00040544747,"threshold_uncertainty_score":0.9926851},"labels":[],"label_agreement":null},{"id":"W4404129156","doi":"10.1002/sim.10253","title":"Generalized Fused Lasso for Treatment Pooling in Network Meta‐Analysis","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pooling; Lasso (programming language); Meta-analysis; Computer science; Statistics; Mathematics; Econometrics; Medicine; Artificial intelligence; Internal medicine","score_opus":0.6714134504704429,"score_gpt":0.6145489179625329,"score_spread":0.056864532507910015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404129156","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003833306,0.002845303,0.9920829,0.0012622972,0.0010161307,0.0010210043,0.00082373753,0.00008636537,0.00047893715],"genre_scores_gemma":[0.007919317,0.00053133356,0.9892571,0.0002569475,0.0008036568,0.00042292388,0.00006219357,0.000058236594,0.0006882759],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959935,0.00085242867,0.0016405231,0.0005796551,0.0004044512,0.00052945124],"domain_scores_gemma":[0.8960379,0.10320985,0.00015386597,0.0003918819,0.00008081599,0.00012567811],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0061355755,0.00031583128,0.0025887473,0.0004176548,0.000042657128,0.000031236003,0.00018594995,0.00015760589,0.001059857],"category_scores_gemma":[0.037998125,0.00021738224,0.0003360144,0.0013493893,0.00016731578,0.000025549005,0.00003577503,0.00020974969,0.000008328338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001746748,0.00015661799,0.00019152155,0.00037176922,0.02757287,0.00024068916,0.0005141171,0.0011687581,0.000018894718,0.9537044,0.008980288,0.006905355],"study_design_scores_gemma":[0.001971633,0.00030704992,0.000097348806,0.00008544513,0.05983062,0.0000011207287,0.000041573254,0.05131338,0.000014840576,0.8844751,0.0016739183,0.00018797905],"about_ca_topic_score_codex":0.00021441946,"about_ca_topic_score_gemma":0.0010716832,"teacher_disagreement_score":0.102357425,"about_ca_system_score_codex":0.00021308048,"about_ca_system_score_gemma":0.000083844694,"threshold_uncertainty_score":0.9998533},"labels":[],"label_agreement":null},{"id":"W4404345839","doi":"10.1002/sim.10263","title":"ℓ1$$ {\\ell}_1 $$‐Penalized Multinomial Regression: Estimation, Inference, and Prediction, With an Application to Risk Factor Identification for Different Dementia Subtypes","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Science Foundation of Sri Lanka; York University; National Institute on Aging; National Institutes of Health; National Science Foundation","keywords":"Multinomial logistic regression; Debiasing; Inference; Robustness (evolution); Logistic regression; Econometrics; Computer science; Statistics; Multinomial distribution; Regression; Confidence interval; Contrast (vision); Mathematics; Artificial intelligence; Psychology","score_opus":0.04742279060518179,"score_gpt":0.41376036239485287,"score_spread":0.3663375717896711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404345839","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041451044,0.00010808471,0.95539206,0.00021183093,0.0002707649,0.0010790523,0.0013627487,0.000085333035,0.000039084494],"genre_scores_gemma":[0.5420267,0.00006743599,0.45718557,0.000027256161,0.0001300796,0.0002829852,0.00019291294,0.000024864816,0.00006219403],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99815494,0.00014743827,0.0006637109,0.00048195568,0.00033830732,0.00021365055],"domain_scores_gemma":[0.9961653,0.0029317108,0.00017919712,0.00029896284,0.0002556618,0.00016920871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069808454,0.0002224484,0.00035842584,0.00020093647,0.00013120296,0.00008093806,0.0001249218,0.00008005007,0.00014151046],"category_scores_gemma":[0.0044887476,0.00014784951,0.000012603703,0.00024089283,0.00014984756,0.000102167854,0.000029399835,0.00018643907,0.00000477632],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004626229,0.00018930004,0.01149503,0.0011063549,0.00012875737,0.000006382485,0.0040119896,0.000078977224,0.001736805,0.5841787,0.0037529843,0.3928521],"study_design_scores_gemma":[0.0012617848,0.0008230121,0.080011696,0.0006100332,0.0003112973,0.0000040184013,0.00023491029,0.35907173,0.00039523057,0.556539,0.00049284595,0.00024445425],"about_ca_topic_score_codex":0.000088416346,"about_ca_topic_score_gemma":0.00020357707,"teacher_disagreement_score":0.50057566,"about_ca_system_score_codex":0.000059565114,"about_ca_system_score_gemma":0.000050548195,"threshold_uncertainty_score":0.6029128},"labels":[],"label_agreement":null},{"id":"W4404567028","doi":"10.1002/sim.10223","title":"Q‐Learning in Dynamic Treatment Regimes With Misclassified Binary Outcome","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Outcome (game theory); Artificial intelligence; Machine learning; Population; Binary classification; Statistics; Data mining; Medicine; Mathematics; Support vector machine","score_opus":0.10451381065403711,"score_gpt":0.4508819754438676,"score_spread":0.34636816478983046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404567028","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11825331,0.0014246675,0.8587128,0.0028713902,0.00044118412,0.0014050502,0.00012771608,0.0013574554,0.015406415],"genre_scores_gemma":[0.6555179,0.00041914047,0.3365663,0.00005416134,0.000046715453,0.000118594784,0.00007732459,0.000069613714,0.0071302718],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99868125,0.00007958304,0.00044843473,0.00028759762,0.00023879902,0.00026432425],"domain_scores_gemma":[0.99832994,0.001287333,0.00007161556,0.00022522912,0.000032790555,0.000053101146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036730047,0.00021390333,0.00042519285,0.00033795286,0.000024847659,0.000012142552,0.00009676059,0.00006867601,0.0001240324],"category_scores_gemma":[0.0007293827,0.0001420209,0.000013301396,0.0003597539,0.00017962998,0.000057675723,0.000024225248,0.00039618174,0.00000971309],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016605582,0.0002747477,0.017039536,0.0011116602,0.00009213573,0.005905994,0.007789266,0.00022428333,0.0015299309,0.90280765,0.0032782506,0.059780482],"study_design_scores_gemma":[0.0019892964,0.004057587,0.0057800747,0.0034452642,0.00012770353,0.000068142384,0.0030902636,0.046401065,0.00020262582,0.9309851,0.0033121957,0.00054067734],"about_ca_topic_score_codex":0.000082803876,"about_ca_topic_score_gemma":0.0004603318,"teacher_disagreement_score":0.5372646,"about_ca_system_score_codex":0.0004537818,"about_ca_system_score_gemma":0.00007116841,"threshold_uncertainty_score":0.5791444},"labels":[],"label_agreement":null},{"id":"W4404837160","doi":"10.1002/sim.10278","title":"Dynamic Treatment Regimes on Dyadic Networks","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Dyad; Computer science; Context (archaeology); Outcome (game theory); Population; Path (computing); Mathematical optimization; Econometrics; Machine learning; Mathematics; Medicine; Psychology","score_opus":0.07713181625879532,"score_gpt":0.45058179005342597,"score_spread":0.37344997379463063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404837160","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012373207,0.001198644,0.9860435,0.00079553045,0.0004970385,0.00037596718,0.00005812386,0.00045613266,0.009337742],"genre_scores_gemma":[0.5945712,0.0033460527,0.39290053,0.0003584393,0.00030729867,0.00018167312,0.00015023729,0.00011905526,0.00806555],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988629,0.000052051564,0.00034139096,0.00026944166,0.00021908488,0.00025509336],"domain_scores_gemma":[0.997594,0.0019422699,0.00005054583,0.00031736062,0.00003103291,0.00006480814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028707916,0.00020205531,0.00032753826,0.00019752639,0.000028699618,0.000012493921,0.00010678699,0.00007798416,0.00024772336],"category_scores_gemma":[0.00061285705,0.00014247009,0.00001939527,0.00023823121,0.00016552559,0.00003502419,0.00001843615,0.00026417707,0.00002505573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016999327,0.00005419229,0.000025506799,0.000088695044,0.000027895943,0.00043240312,0.00047854724,0.00007670243,0.000034555105,0.91909045,0.021040235,0.058633838],"study_design_scores_gemma":[0.00029501578,0.00095637684,0.00008102798,0.00095949986,0.000050937273,0.000014219496,0.000117345146,0.05002395,0.00005700452,0.94336635,0.003927683,0.00015059108],"about_ca_topic_score_codex":0.000033553533,"about_ca_topic_score_gemma":0.000072897834,"teacher_disagreement_score":0.59333384,"about_ca_system_score_codex":0.00039846404,"about_ca_system_score_gemma":0.000038745464,"threshold_uncertainty_score":0.5809762},"labels":[],"label_agreement":null},{"id":"W4404898302","doi":"10.1002/sim.10277","title":"Bayesian Decision Curve Analysis With Bayesdca","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Children's Hospital; University of British Columbia","funders":"Provincial Health Services Authority; BC Children's Hospital; Children's Hospital Foundation","keywords":"Frequentist inference; Computer science; Bayesian probability; Workflow; Machine learning; Decision analysis; False positives and false negatives; False positive paradox; Probabilistic logic; Bayes' theorem; Artificial intelligence; Data mining; Bayesian inference; Statistics; Mathematics","score_opus":0.17346630158868082,"score_gpt":0.4589526291861392,"score_spread":0.2854863275974584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404898302","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038416092,0.0044308654,0.9705925,0.01286457,0.0007226255,0.0003309714,0.0007376445,0.00005832763,0.006420874],"genre_scores_gemma":[0.8661509,0.0005952517,0.12551789,0.0051019154,0.00065108703,0.00008042403,0.0003550816,0.00006595291,0.0014815064],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99581647,0.00016125654,0.0028817896,0.0006158678,0.00018020038,0.00034441604],"domain_scores_gemma":[0.99544877,0.0033645595,0.0004918065,0.000462384,0.00005745364,0.00017501708],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0118945,0.00019003086,0.0011001825,0.0013517101,0.000074402495,0.000058466518,0.00020329506,0.00009383033,0.0027058506],"category_scores_gemma":[0.0039585666,0.00018161102,0.00005058617,0.0013415763,0.00014789763,0.00017766573,0.000026656182,0.00026689682,0.00069103984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037588085,0.00005796064,0.11624894,0.00053865125,0.0005605739,0.00009581945,0.003907466,0.0015353804,5.727834e-7,0.75446606,0.118436955,0.004114062],"study_design_scores_gemma":[0.0015988982,0.00044563808,0.09471374,0.00094114966,0.00023406676,0.000015314885,0.00160185,0.41879058,8.083547e-7,0.3786723,0.102341294,0.0006443682],"about_ca_topic_score_codex":0.0014907682,"about_ca_topic_score_gemma":0.002769291,"teacher_disagreement_score":0.8623093,"about_ca_system_score_codex":0.0004244133,"about_ca_system_score_gemma":0.00011888342,"threshold_uncertainty_score":0.99820584},"labels":[],"label_agreement":null},{"id":"W4406146487","doi":"10.1002/sim.10273","title":"Editorial","year":2025,"lang":"en","type":"editorial","venue":"Statistics in Medicine","topic":"Health and Medical Research Impacts","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Gratitude; Editor in chief; Editorial board; Library science; Sadness; History; Management; Psychology; Computer science; Economics","score_opus":0.04959678286750923,"score_gpt":0.4880930862123854,"score_spread":0.43849630334487616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406146487","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.94275e-7,0.0008494398,0.002028908,0.0062612994,0.9703082,0.00079404557,0.0009823658,0.000051218307,0.018723857],"genre_scores_gemma":[0.0000027742483,0.005504806,0.002140872,0.0019083446,0.9710848,0.000063579486,0.0034928282,0.000046814122,0.015755227],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923438,0.00017762827,0.0010096963,0.0005779558,0.0044691013,0.0014218647],"domain_scores_gemma":[0.9820584,0.010223718,0.00022018277,0.00083517627,0.0014680009,0.005194538],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0039475583,0.000397815,0.0014798102,0.00077366165,0.00006072326,0.000012444815,0.00028355085,0.0015667587,0.0008478152],"category_scores_gemma":[0.54917556,0.00030308086,0.000050787145,0.00061833847,0.00049896503,0.000026727874,0.000102664504,0.004856235,0.000085048436],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005865539,0.000105308136,0.000025970823,0.0028669646,0.000044515244,0.00047529335,0.00008382445,9.543289e-8,0.0000055013024,0.00032073722,0.98134065,0.014144581],"study_design_scores_gemma":[0.0058317794,0.0013464686,0.000025678823,0.0047708275,0.00014767813,0.000002139938,0.000052100844,0.000031319956,0.000001514317,0.0018252357,0.9857851,0.00018010722],"about_ca_topic_score_codex":0.0014008322,"about_ca_topic_score_gemma":0.00020351092,"teacher_disagreement_score":0.545228,"about_ca_system_score_codex":0.0009655119,"about_ca_system_score_gemma":0.029583719,"threshold_uncertainty_score":0.9999421},"labels":[],"label_agreement":null},{"id":"W4406801646","doi":"10.1002/sim.10324","title":"Supervised Functional Principal Component Analysis Under the Mixture Cure Rate Model: An Application to Alzheimer'S Disease","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institute on Aging; Natural Sciences and Engineering Research Council of Canada","keywords":"Principal component analysis; Computer science; Censoring (clinical trials); Bivariate analysis; Artificial intelligence; Disease; Functional principal component analysis; Proportional hazards model; Neuroimaging; Event (particle physics); Pattern recognition (psychology); Machine learning; Econometrics; Statistics; Mathematics; Medicine; Psychiatry; Internal medicine","score_opus":0.08268806086690261,"score_gpt":0.40944814030246357,"score_spread":0.32676007943556096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406801646","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038731552,0.0001001442,0.9901606,0.0044576577,0.00013634578,0.00049113104,0.000369528,0.000033232413,0.00037822424],"genre_scores_gemma":[0.62041116,0.00002816704,0.37571543,0.0029844653,0.00011845076,0.00019306042,0.0003474902,0.000019716925,0.00018208164],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982367,0.00029696865,0.00048446056,0.0003672268,0.0003828144,0.00023181863],"domain_scores_gemma":[0.99690187,0.0020307226,0.00008238127,0.00055768015,0.00022086425,0.00020645976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010287988,0.00018807739,0.00038162112,0.00021193763,0.00012747654,0.000020365458,0.00024986043,0.000056450568,0.00023053677],"category_scores_gemma":[0.001097303,0.00012309817,0.000035668672,0.0008541336,0.00017375985,0.00002631905,0.00006917513,0.000261872,0.0000057698617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011481,0.00012647604,0.0008120329,0.00004154797,0.00020208309,0.0000043341697,0.00029620697,0.013607452,0.0000992376,0.97636575,0.004249657,0.004080444],"study_design_scores_gemma":[0.00027673223,0.000029759927,0.037482265,0.000027741395,0.00080420444,1.3412574e-7,0.00015216136,0.47563952,0.0000054598586,0.4853447,0.00015268502,0.000084639934],"about_ca_topic_score_codex":0.00009143748,"about_ca_topic_score_gemma":0.0002484668,"teacher_disagreement_score":0.616538,"about_ca_system_score_codex":0.000060439066,"about_ca_system_score_gemma":0.00010737905,"threshold_uncertainty_score":0.50197977},"labels":[],"label_agreement":null},{"id":"W4406808516","doi":"10.1002/sim.10321","title":"Bioequivalence Design With Sampling Distribution Segments","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bioequivalence; Sampling (signal processing); Sample size determination; Computer science; Statistics; Sampling distribution; Sampling design; Mathematics; Econometrics; Medicine","score_opus":0.22427735462934364,"score_gpt":0.5229092611377446,"score_spread":0.298631906508401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406808516","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012490004,0.00026406004,0.99502414,0.00041249712,0.00041354267,0.0002969844,0.000088956636,0.00002160862,0.0022291758],"genre_scores_gemma":[0.16397,0.00004317413,0.83448094,0.00031915682,0.000035909987,0.00002486655,0.000036842357,0.000008215878,0.0010809038],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971043,0.0004538249,0.000630746,0.00045074848,0.0010869551,0.00027345773],"domain_scores_gemma":[0.99481195,0.004322701,0.00014758996,0.0004073792,0.00023020925,0.000080187885],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047796383,0.0001524652,0.00034270016,0.00025197066,0.00009712664,0.000049858307,0.00046528774,0.000050652678,0.0003052957],"category_scores_gemma":[0.00797304,0.00009981777,0.000012136413,0.0013893443,0.00041861064,0.00010292058,0.000085632586,0.00017801517,0.00003352675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015634916,0.000414239,0.046213977,0.00009815891,0.00009595497,0.00029670636,0.002294649,0.006791167,0.041465644,0.35414192,0.10388607,0.44273803],"study_design_scores_gemma":[0.0064323805,0.0024677585,0.08995401,0.001480535,0.0001258791,0.000027372713,0.0059090364,0.06972103,0.016922373,0.79519147,0.010945429,0.0008227165],"about_ca_topic_score_codex":0.00006122252,"about_ca_topic_score_gemma":0.000009031988,"teacher_disagreement_score":0.4419153,"about_ca_system_score_codex":0.00016099418,"about_ca_system_score_gemma":0.00010856549,"threshold_uncertainty_score":0.95450497},"labels":[],"label_agreement":null},{"id":"W4407173849","doi":"10.1002/sim.70000","title":"Regression—A Means, Not an End","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Statistics; Regression; Regression analysis; Mathematics","score_opus":0.1246073718061269,"score_gpt":0.4895811887662412,"score_spread":0.3649738169601143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407173849","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020770915,0.000099793455,0.9754211,0.00097283523,0.00028391555,0.00027524173,0.00007027439,0.00021686869,0.02058289],"genre_scores_gemma":[0.13311806,0.00019967247,0.8626459,0.0010093462,0.000107768086,0.000047203856,0.00005776503,0.00002738357,0.002786858],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987096,0.00009410232,0.00044155697,0.00023828304,0.00029125166,0.00022519933],"domain_scores_gemma":[0.9979784,0.0012781593,0.000103392165,0.00045701268,0.00011621099,0.00006683153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064504263,0.00016036225,0.00035657946,0.00021758185,0.00004756601,0.0000064954293,0.0002307947,0.00008494752,0.00042246154],"category_scores_gemma":[0.00421939,0.00012067408,0.000010063089,0.0002661295,0.0002444689,0.00006796983,0.000057226105,0.00031028752,0.0000048806455],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022643726,0.0000518944,0.00027576598,0.00010151345,0.000007100013,0.000049213602,0.000419056,0.0000011459398,0.0014232474,0.93932855,0.03123243,0.027087443],"study_design_scores_gemma":[0.00044080988,0.00014388032,0.0005855665,0.0006008532,0.000025239768,0.0000024217807,0.0003378608,0.00065115554,0.002592831,0.9903932,0.004109778,0.00011640514],"about_ca_topic_score_codex":0.000058689853,"about_ca_topic_score_gemma":0.00023340572,"teacher_disagreement_score":0.13104098,"about_ca_system_score_codex":0.00009257036,"about_ca_system_score_gemma":0.000061324274,"threshold_uncertainty_score":0.5051309},"labels":[],"label_agreement":null},{"id":"W4407262364","doi":"10.1002/sim.70009","title":"Inverse Probability of Treatment Weighting Using the Propensity Score With Competing Risks in Survival Analysis","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research","keywords":"Propensity score matching; Inverse probability weighting; Inverse probability; Statistics; Weighting; Survival analysis; Econometrics; Inverse; Average treatment effect; Computer science; Posterior probability; Mathematics; Medicine; Bayesian probability","score_opus":0.3133595065600282,"score_gpt":0.4585707417670098,"score_spread":0.1452112352069816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407262364","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6643048,0.000013931926,0.3344631,0.00006554718,0.000021703174,0.00049493875,0.000018677727,0.00002181144,0.0005954722],"genre_scores_gemma":[0.7294624,0.00001476682,0.27045226,0.000014881113,0.000009460397,0.00001677241,0.0000090107405,0.0000066870775,0.00001376728],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99852633,0.00027108582,0.00057097455,0.00022587275,0.00021715554,0.00018858185],"domain_scores_gemma":[0.9973945,0.0017453108,0.00027221153,0.00038373529,0.00018037923,0.000023869421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014179181,0.0001559918,0.0006450625,0.00024936796,0.00005409339,0.000004829229,0.00013478998,0.00004274516,0.000021446978],"category_scores_gemma":[0.001999321,0.00008804639,0.0000213916,0.0011748369,0.00042137832,0.000033858156,0.000061595434,0.00021566948,8.202676e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008348625,0.00014886481,0.873932,0.000266947,0.00017167766,0.000027166861,0.0022396527,0.001678843,0.00047804535,0.119276084,0.000010390197,0.001686824],"study_design_scores_gemma":[0.0019836833,0.0006257776,0.12150501,0.0019132113,0.0013413832,0.0000026687683,0.003819599,0.072122715,0.00234997,0.79403275,0.000011707816,0.0002915006],"about_ca_topic_score_codex":0.003825331,"about_ca_topic_score_gemma":0.018533858,"teacher_disagreement_score":0.75242704,"about_ca_system_score_codex":0.0004096045,"about_ca_system_score_gemma":0.00013787254,"threshold_uncertainty_score":0.99937534},"labels":[],"label_agreement":null},{"id":"W4407295943","doi":"10.1002/sim.70013","title":"Challenges for Predictive Modeling With Neural Network Techniques Using Error‐Prone Dietary Intake Data","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Overfitting; Computer science; Machine learning; Artificial neural network; Artificial intelligence; Replicate; Predictive modelling; Data mining; Statistics; Mathematics","score_opus":0.16158573192486647,"score_gpt":0.40385528688710676,"score_spread":0.24226955496224029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407295943","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032972945,0.018321514,0.9613976,0.009603362,0.00041752792,0.0017921289,0.0007127602,0.00010687514,0.0043509556],"genre_scores_gemma":[0.48714775,0.0056808335,0.50210404,0.0016262113,0.0015333786,0.00016070361,0.0016117657,0.000047142676,0.000088161796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986567,0.000026838921,0.00036174693,0.00039968747,0.00025648135,0.00029852914],"domain_scores_gemma":[0.99895185,0.00032496086,0.00006685314,0.000372078,0.00022018049,0.000064066975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045147433,0.00017887834,0.00049739506,0.00010786554,0.00011895002,0.0000041071153,0.00014204542,0.000064263426,0.000009043707],"category_scores_gemma":[0.00035608164,0.00013149016,0.000014363305,0.00021717988,0.00020129805,0.00005225371,0.00014010453,0.00024147765,1.6835868e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.030958537,0.0026374534,0.031664047,0.014529513,0.0037169699,0.0012965125,0.0033268882,0.049878333,0.00075419224,0.14916429,0.28280327,0.42927],"study_design_scores_gemma":[0.0036126052,0.0019626596,0.006023464,0.0038491844,0.00057928805,0.00002829968,0.0021092342,0.94412744,0.000007712233,0.034521274,0.0029750955,0.00020375762],"about_ca_topic_score_codex":0.00015446957,"about_ca_topic_score_gemma":0.00041777053,"teacher_disagreement_score":0.8942491,"about_ca_system_score_codex":0.00008737802,"about_ca_system_score_gemma":0.00007827263,"threshold_uncertainty_score":0.5362013},"labels":[],"label_agreement":null},{"id":"W4407777323","doi":"10.1002/sim.70007","title":"Identification and Estimation of the Average Causal Effects Under Dietary Substitution Strategies","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Nutritional Studies and Diet","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Cancer Institute; Natural Sciences and Engineering Research Council of Canada; Harvard T.H. Chan School of Public Health; Brigham and Women's Hospital","keywords":"Counterfactual thinking; Substitution (logic); Estimator; Estimation; Red meat; Econometrics; Intervention (counseling); Identification (biology); Food science; Statistics; Computer science; Medicine; Environmental health; Mathematics; Economics; Psychology; Biology; Social psychology","score_opus":0.01628704538152652,"score_gpt":0.3313234211693104,"score_spread":0.3150363757877839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407777323","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5770461,0.003645013,0.40619788,0.007860191,0.0010593671,0.0010124897,0.000078339304,0.000025119929,0.0030755019],"genre_scores_gemma":[0.99794436,0.00037275348,0.0012213661,0.00021374617,0.000033453507,0.000012097687,0.00005564581,0.0000027213246,0.00014384797],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9994035,0.000030262698,0.00022449398,0.0001013026,0.00017134039,0.00006912122],"domain_scores_gemma":[0.99948156,0.00026672854,0.000057702666,0.00010237686,0.00007421267,0.00001740516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017138619,0.00006296284,0.00016635786,0.000065624685,0.00006133239,0.000004127123,0.000027728049,0.000030861444,0.000008927897],"category_scores_gemma":[0.00038474606,0.00004164451,0.000009697425,0.00017946766,0.0002792721,0.000029750661,0.000020652677,0.00009063257,5.862396e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020357495,0.00018028513,0.016341675,0.0024390044,0.00009898914,0.000019722913,0.00038584258,0.0011189362,0.00930321,0.9540688,0.008204562,0.007635433],"study_design_scores_gemma":[0.0013748251,0.000111360976,0.8548687,0.00074556575,0.00011575315,0.0000039735532,0.000343163,0.0043106875,0.00046616586,0.13753709,0.0000853371,0.000037359903],"about_ca_topic_score_codex":0.00012715401,"about_ca_topic_score_gemma":0.00008381328,"teacher_disagreement_score":0.838527,"about_ca_system_score_codex":0.00004259232,"about_ca_system_score_gemma":0.000048643647,"threshold_uncertainty_score":0.1698214},"labels":[],"label_agreement":null},{"id":"W4407860565","doi":"10.1002/sim.70025","title":"A Double Machine Learning Approach for the Evaluation of COVID‐19 Vaccine Effectiveness Under the Test‐Negative Design: Analysis of Québec Administrative Data","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Influenza Virus Research Studies","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de Santé Publique du Québec; Université Laval; Université de Montréal","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Fonds de Recherche du Québec - Santé; Centre de Recherches Mathématiques","keywords":"Estimator; Econometrics; Identifiability; Consistency (knowledge bases); Causal inference; Computer science; Nonparametric statistics; Robustness (evolution); Confounding; Asymptotic distribution; Mathematics; Coronavirus disease 2019 (COVID-19); Statistics; Artificial intelligence; Medicine; Biology","score_opus":0.36590857376146146,"score_gpt":0.5361572645866105,"score_spread":0.17024869082514904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407860565","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025871706,0.0042790715,0.984316,0.0027771445,0.000049716982,0.004376024,0.0007958583,0.00001313649,0.00080590625],"genre_scores_gemma":[0.98076636,0.00034511834,0.017479155,0.00027536764,0.000040126997,0.00050817063,0.00035439068,0.00001575781,0.00021555916],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99687123,0.0009265095,0.000636172,0.00037166977,0.00096491544,0.00022948592],"domain_scores_gemma":[0.952848,0.04476114,0.00032171851,0.00073933555,0.0012694048,0.0000604045],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011652206,0.0001905272,0.0008394556,0.00045323148,0.00022260008,0.000006422053,0.0004143151,0.000055764827,0.00010151343],"category_scores_gemma":[0.06319519,0.00009816489,0.000051444105,0.0019191814,0.0006943434,0.000037049645,0.00018758676,0.00039572624,2.555408e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03774651,0.0025621913,0.21091402,0.0077598174,0.04640762,0.000027244843,0.033564214,0.56443584,0.004508578,0.039218478,0.013877773,0.03897774],"study_design_scores_gemma":[0.012420902,0.0011980647,0.099298224,0.00023030727,0.011345078,0.0000018453352,0.0076582087,0.8621985,0.00059128116,0.0047289524,0.00022375023,0.00010493694],"about_ca_topic_score_codex":0.011381119,"about_ca_topic_score_gemma":0.008149244,"teacher_disagreement_score":0.97817916,"about_ca_system_score_codex":0.00035830415,"about_ca_system_score_gemma":0.0018561995,"threshold_uncertainty_score":0.9952022},"labels":[],"label_agreement":null},{"id":"W4408408683","doi":"10.1002/sim.70034","title":"Guidelines and Best Practices for the Use of Targeted Maximum Likelihood and Machine Learning When Estimating Causal Effects of Exposures on Time‐To‐Event Outcomes","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Institut National de Santé Publique du Québec; Université Laval","funders":"Canadian Institutes of Health Research; Canada Research Chairs; Fonds de Recherche du Québec - Santé; International Society for Pharmacoepidemiology","keywords":"Computer science; Outcome (game theory); Machine learning; Counterfactual thinking; Event (particle physics); Causal inference; Covariate; A priori and a posteriori; Artificial intelligence; Data mining; Statistics","score_opus":0.16736663226226037,"score_gpt":0.4647206712009353,"score_spread":0.29735403893867496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408408683","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010962751,0.00053936534,0.9856863,0.0015773686,0.00009589971,0.0009849517,0.00007941516,0.000035617624,0.000038338458],"genre_scores_gemma":[0.017925797,0.00011878603,0.98119193,0.00021728492,0.00002757661,0.00007369191,0.000015515592,0.000021326987,0.00040809324],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99868476,0.000103594655,0.00064663164,0.0001849064,0.00022149234,0.00015860765],"domain_scores_gemma":[0.980132,0.018807372,0.0005572874,0.00019702617,0.0002679997,0.00003834638],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.000845587,0.00017023161,0.0005000303,0.00016198715,0.000060344133,0.000010348825,0.00010016709,0.00005238818,0.000013439996],"category_scores_gemma":[0.07612917,0.000108848704,0.000013753748,0.000108488304,0.00015845383,0.000059063586,0.000091949514,0.00019156132,2.5820535e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008847423,0.0008352403,0.03733682,0.012267311,0.0008366526,0.000055966048,0.009006996,0.0020059694,0.029642314,0.19952033,0.04297217,0.6646355],"study_design_scores_gemma":[0.0024714908,0.003902004,0.0025415588,0.005305071,0.00063582946,0.0000051428206,0.0005269161,0.11835946,0.008145823,0.8555183,0.0022700094,0.00031839762],"about_ca_topic_score_codex":0.00037707374,"about_ca_topic_score_gemma":0.00014214596,"teacher_disagreement_score":0.6643171,"about_ca_system_score_codex":0.000020688243,"about_ca_system_score_gemma":0.000029860608,"threshold_uncertainty_score":0.93165296},"labels":[],"label_agreement":null},{"id":"W4408651332","doi":"10.1002/sim.70023","title":"Variable Selection for Progressive Multistate Processes Under Intermittent Observation","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Computer science; Maximization; Variable (mathematics); Selection (genetic algorithm); Feature selection; Expectation–maximization algorithm; Regression; Exploit; Poisson regression; Machine learning; Artificial intelligence; Statistics; Mathematical optimization; Maximum likelihood; Mathematics; Medicine","score_opus":0.10407953292784239,"score_gpt":0.4503327739983338,"score_spread":0.34625324107049144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408651332","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006742021,0.000089555404,0.9962367,0.00052093825,0.00047609198,0.0007121806,0.00012684894,0.000043295895,0.0011201918],"genre_scores_gemma":[0.011205832,0.000019140914,0.98612916,0.00041988265,0.00008633533,0.00029597597,0.000059251444,0.000016328742,0.0017680902],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99873793,0.00008098815,0.0005065513,0.00025684288,0.0001789876,0.00023869095],"domain_scores_gemma":[0.99455523,0.0045202114,0.00015713047,0.00012590487,0.00059877423,0.000042743835],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006190648,0.00014662185,0.00032359085,0.00013161256,0.0000770016,0.000018370552,0.00011080914,0.00006651506,0.00012347392],"category_scores_gemma":[0.019422578,0.00011750024,0.0000099846575,0.00049781543,0.00012947313,0.000041808962,0.000025808009,0.00015816069,0.0000012179211],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067565416,0.000088040615,0.0007338029,0.001236501,0.000026646461,0.0000021122453,0.00024542486,0.000015959824,0.00016079849,0.959688,0.0105014555,0.027233666],"study_design_scores_gemma":[0.0010529162,0.0002262799,0.0023850237,0.0008477488,0.00007143962,0.0000017261998,0.00026835577,0.025183592,0.00017867652,0.9686722,0.0010011928,0.000110807276],"about_ca_topic_score_codex":0.00008144375,"about_ca_topic_score_gemma":0.000108825305,"teacher_disagreement_score":0.027122857,"about_ca_system_score_codex":0.00010892125,"about_ca_system_score_gemma":0.00017488518,"threshold_uncertainty_score":0.98883724},"labels":[],"label_agreement":null},{"id":"W4409368810","doi":"10.1002/sim.70049","title":"A Generalized Phase I/II Dose Optimization Trial Design With Multi‐Categorical and Multi‐Graded Outcomes","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Simon Fraser University","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Categorical variable; Monotonic function; Benchmarking; Robustness (evolution); Computer science; Maximum tolerated dose; Optimal design; Clinical trial; Continuous variable; Reliability (semiconductor); Reliability engineering; Mathematical optimization; Medicine; Mathematics; Machine learning","score_opus":0.5347114705751628,"score_gpt":0.5995985752183284,"score_spread":0.0648871046431656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409368810","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020561283,0.000077128825,0.99397,0.00086601276,0.00074917806,0.0020389785,0.00009249491,0.00008173856,0.00006835194],"genre_scores_gemma":[0.006637603,0.00013358534,0.9917489,0.0004489562,0.00013247826,0.0001929787,0.000021625861,0.00004184213,0.00064198166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957371,0.0013295988,0.0014973476,0.0005644524,0.00048230842,0.0003892395],"domain_scores_gemma":[0.9596681,0.03919164,0.00033103337,0.00042377991,0.00019804151,0.0001873837],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0035831097,0.00035913833,0.0014037881,0.0002817375,0.00014286836,0.000026163076,0.00022304992,0.00021264334,0.00021387401],"category_scores_gemma":[0.12525445,0.00024275041,0.0000369579,0.0005311327,0.0005995711,0.00004435603,0.00010510023,0.00044920712,0.0000015389205],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05786354,0.0056586936,0.0005736415,0.0005605763,0.00055923004,0.0004277707,0.0013430227,0.001324779,0.00018163635,0.8788407,0.010068171,0.04259825],"study_design_scores_gemma":[0.2666955,0.0031214773,0.00017558105,0.00020817848,0.0004924464,0.000004538228,0.0001217161,0.19418855,0.000047494363,0.5345702,0.000058322308,0.00031599408],"about_ca_topic_score_codex":0.000055825363,"about_ca_topic_score_gemma":0.000027867996,"teacher_disagreement_score":0.34427047,"about_ca_system_score_codex":0.00009320905,"about_ca_system_score_gemma":0.00013888645,"threshold_uncertainty_score":0.98990744},"labels":[],"label_agreement":null},{"id":"W4409800482","doi":"10.1002/sim.70074","title":"A Variance Estimator for Marginal Cox Regression Models Fit to Non‐Nested Multilevel Data","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Marginal model; Statistics; Estimator; Generalized linear model; Multilevel model; Generalized estimating equation; Mathematics; Regression analysis; Proportional hazards model; Covariate; Censored regression model; Variance (accounting); Econometrics","score_opus":0.18844865111631784,"score_gpt":0.4953526763331343,"score_spread":0.3069040252168165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409800482","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005937481,0.000047594105,0.9933163,0.0014119798,0.0004946809,0.0009116841,0.0025255524,0.00003705906,0.0011957808],"genre_scores_gemma":[0.006882007,0.000019142126,0.99136025,0.0005394438,0.00009604542,0.00013337262,0.00012509311,0.000026816866,0.00081783236],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99794126,0.00010591246,0.0006826409,0.0005569217,0.00032967792,0.00038361357],"domain_scores_gemma":[0.9912341,0.007323912,0.00013893392,0.0008991089,0.00024868987,0.00015520294],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0012748123,0.00024471493,0.0006383122,0.0001968423,0.00010470424,0.000022323187,0.0006115115,0.00010424786,0.00011907849],"category_scores_gemma":[0.019824892,0.00018849067,0.000014468313,0.00034411918,0.00015447843,0.00007426053,0.00022603999,0.00023916658,0.0000059303707],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018405092,0.00009629732,0.00007274948,0.0005488464,0.000020702337,0.00004108684,0.00025333898,0.000026286678,0.00010071351,0.81002283,0.12197366,0.066659436],"study_design_scores_gemma":[0.0010417936,0.00010193506,0.0006832722,0.0013381703,0.0000589889,0.0000025525414,0.000059116453,0.41614634,0.000014774297,0.5793953,0.0010331006,0.00012466266],"about_ca_topic_score_codex":0.00009653295,"about_ca_topic_score_gemma":0.00006427289,"teacher_disagreement_score":0.41612005,"about_ca_system_score_codex":0.000053997315,"about_ca_system_score_gemma":0.00017327278,"threshold_uncertainty_score":0.9884315},"labels":[],"label_agreement":null},{"id":"W4410429608","doi":"10.1002/sim.70077","title":"A Personalized Predictive Model That Jointly Optimizes Discrimination and Calibration","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Weighting; Calibration; Computer science; Flexibility (engineering); Function (biology); Measure (data warehouse); Population; Field (mathematics); A-weighting; Machine learning; Artificial intelligence; Similarity (geometry); Statistics; Econometrics; Data mining; Mathematics; Medicine","score_opus":0.028596481618226307,"score_gpt":0.34266400478740733,"score_spread":0.314067523169181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410429608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00096856506,0.0003270897,0.98738194,0.009127222,0.00021419491,0.00022255037,0.000022092108,0.000056654604,0.0016797218],"genre_scores_gemma":[0.57604694,0.00017392432,0.42178297,0.0010456695,0.000035275618,0.00003748928,0.000050071547,0.000007134295,0.00082053035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989207,0.00014091696,0.00022572663,0.00028943547,0.00027273662,0.00015051778],"domain_scores_gemma":[0.9991805,0.00040956555,0.00007727003,0.00019734337,0.00008217733,0.00005317315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044683513,0.000104680206,0.00019314114,0.00021466242,0.00008368544,0.00003102345,0.00018885832,0.000048809416,0.000011050357],"category_scores_gemma":[0.00078120816,0.00008839751,0.000007355807,0.00022982752,0.00014781975,0.00016423792,0.00009949382,0.00022463706,3.7631298e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035731176,0.000021704882,0.0065810243,0.00023462146,0.000010721728,0.000013795244,0.0094341785,0.00921044,0.000037735474,0.9517881,0.0040141447,0.018617755],"study_design_scores_gemma":[0.00065244373,0.000083451894,0.008266279,0.0001898559,0.000009862539,0.000002183743,0.0002740762,0.89156646,0.000009386067,0.09884671,0.00003880968,0.00006051116],"about_ca_topic_score_codex":0.00025872636,"about_ca_topic_score_gemma":0.00010233266,"teacher_disagreement_score":0.882356,"about_ca_system_score_codex":0.000074326264,"about_ca_system_score_gemma":0.00010383589,"threshold_uncertainty_score":0.3604746},"labels":[],"label_agreement":null},{"id":"W4410480739","doi":"10.1002/sim.70102","title":"Continuous‐Time Causal Inference With Marked Point Process Weights: An Example on Sodium‐Glucose Co‐Transporters 2 Inhibitor Medications and Urinary Tract Infection","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Marginal structural model; Covariate; Confounding; Medicine; Causal inference; Time point; Clinical endpoint; Internal medicine; Statistics; Clinical trial; Mathematics","score_opus":0.043079783093944224,"score_gpt":0.39116520241493435,"score_spread":0.34808541932099013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410480739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46371552,0.000050957922,0.53077507,0.0005281613,0.00010857253,0.0010932895,0.00013379597,0.00034759264,0.003247074],"genre_scores_gemma":[0.9472442,0.00022711791,0.05145119,0.00028080275,0.0000776067,0.00020135046,0.0002716443,0.00003911747,0.00020696943],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998094,0.00013109866,0.00061487063,0.0004522763,0.00040568426,0.00030204296],"domain_scores_gemma":[0.9973951,0.0015868297,0.00023886582,0.00040554357,0.00022628164,0.00014736297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070480956,0.00030230475,0.0005305656,0.0003923493,0.00011653245,0.000018939527,0.00014638028,0.00013385374,0.00015510869],"category_scores_gemma":[0.00078338804,0.00023505538,0.000012146415,0.0003506653,0.0005757267,0.00022923794,0.000017957429,0.0004943787,0.0000028713905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018261168,0.005672331,0.1033865,0.0030494719,0.0003202387,0.00089394615,0.017528718,0.000025933017,0.005347625,0.82173955,0.007953575,0.032255974],"study_design_scores_gemma":[0.003978851,0.006124005,0.06637472,0.0036657068,0.00034408964,0.00008257687,0.0013806657,0.0019881038,0.004238292,0.9103819,0.0007033087,0.0007377752],"about_ca_topic_score_codex":0.0003345123,"about_ca_topic_score_gemma":0.0002680777,"teacher_disagreement_score":0.48352867,"about_ca_system_score_codex":0.00012766082,"about_ca_system_score_gemma":0.00017316705,"threshold_uncertainty_score":0.95852804},"labels":[],"label_agreement":null},{"id":"W4410503910","doi":"10.1002/sim.70094","title":"Why Recommended Visit Intervals Should Be Extracted When Conducting Longitudinal Analyses Using Electronic Health Record Data: Examining Visit Mechanism and Sensitivity to Assessment Not at Random","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; Public Health Ontario; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medicine; Cohort; Health records; Sensitivity (control systems); Population; Longitudinal data; Statistics; Computer science; Data mining; Health care; Mathematics; Environmental health; Internal medicine","score_opus":0.5415146117263445,"score_gpt":0.5572399168944151,"score_spread":0.01572530516807058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410503910","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04173347,0.00008915214,0.9516879,0.0049153757,0.00038564915,0.0005841513,0.00042818324,0.00004466652,0.00013148834],"genre_scores_gemma":[0.2220102,0.00012082977,0.7735488,0.0039872215,0.00009813945,0.000014465795,0.0001250479,0.000031012412,0.000064275664],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99552274,0.0013454738,0.0011848719,0.0008086801,0.00048086268,0.0006573876],"domain_scores_gemma":[0.9860095,0.012500136,0.0004213552,0.00064663915,0.00020948917,0.00021289532],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0070939506,0.0003525088,0.0012942692,0.0003565878,0.00025098448,0.000060186067,0.00020386706,0.0001042266,0.00029708067],"category_scores_gemma":[0.013982882,0.00030873396,0.000021474296,0.00040086242,0.0001141307,0.000120039345,0.00053863693,0.0006894673,6.153514e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013818434,0.0005164196,0.004244696,0.0025049562,0.0011073218,0.00054146413,0.005058137,0.00003335433,0.06469318,0.6813105,0.03829762,0.20031054],"study_design_scores_gemma":[0.0074401028,0.0018382979,0.0053912103,0.0043309587,0.0009695742,0.00012009615,0.0034142586,0.24357803,0.0015111835,0.7293038,0.0011096384,0.000992877],"about_ca_topic_score_codex":0.0021367786,"about_ca_topic_score_gemma":0.00315627,"teacher_disagreement_score":0.24354468,"about_ca_system_score_codex":0.00060772087,"about_ca_system_score_gemma":0.00023432144,"threshold_uncertainty_score":0.99993646},"labels":[],"label_agreement":null},{"id":"W4410608924","doi":"10.1002/sim.70064","title":"Dynamic Single‐Index Scalar‐On‐Function Model","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Air Quality and Health Impacts","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Environmental Health Sciences; National Institutes of Health; York University","keywords":"Estimator; Bivariate analysis; Univariate; Spline (mechanical); Parametric statistics; Applied mathematics; Scalar (mathematics); Nonparametric statistics; Computer science; Model selection; Generalized additive model; Parametric model; Tensor product; Econometrics; Mathematics; Statistics; Mathematical optimization; Multivariate statistics","score_opus":0.03100083973489925,"score_gpt":0.3523898610175001,"score_spread":0.32138902128260083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410608924","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064928434,0.000031725893,0.93553823,0.0076436857,0.00035328075,0.00018384072,0.000028813522,0.000028102659,0.049699496],"genre_scores_gemma":[0.9625184,0.00010104716,0.017207723,0.0161476,0.000026237009,0.000011000951,0.000036417645,0.000010685892,0.0039408808],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989376,0.000049609323,0.00027121083,0.00020164004,0.0002967761,0.0002431487],"domain_scores_gemma":[0.99947035,0.00019758337,0.000050236722,0.00018324821,0.0000072306775,0.00009132151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004829193,0.00009563032,0.00015841117,0.00012522403,0.00008129468,0.0000045482084,0.00009810082,0.00006282477,0.0006960397],"category_scores_gemma":[0.00045969954,0.00008081333,0.000007482241,0.00038585655,0.00024554666,0.00004122157,0.00004121419,0.00021517341,0.000105112355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004315013,0.00047009555,0.019416144,0.00024339734,0.00001764824,0.0000348566,0.0014287411,0.13373321,0.00076580583,0.08285419,0.5952418,0.1653626],"study_design_scores_gemma":[0.0007662798,0.00029247682,0.09425748,0.00013550067,0.000013139076,6.1717327e-7,0.00012374051,0.7442168,0.0000065167437,0.15516196,0.004933535,0.00009192157],"about_ca_topic_score_codex":0.00029808187,"about_ca_topic_score_gemma":0.0008542114,"teacher_disagreement_score":0.95602554,"about_ca_system_score_codex":0.0002824432,"about_ca_system_score_gemma":0.000022188375,"threshold_uncertainty_score":0.7621147},"labels":[],"label_agreement":null},{"id":"W4410783369","doi":"10.1002/sim.70121","title":"Integrating Complex Selection Rules Into the Latent Overlapping Group Lasso for the Construction of Coherent Prediction Models","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Réseau Québécois de Recherche sur les Médicaments; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Heart and Stroke Foundation of Canada","keywords":"Interpretability; Feature selection; Lasso (programming language); Latent variable; Computer science; Variable (mathematics); Machine learning; Predictive modelling; Selection (genetic algorithm); Elastic net regularization; Proxy (statistics); Artificial intelligence; Data mining; Mathematics","score_opus":0.3549779274483894,"score_gpt":0.5195250836602353,"score_spread":0.1645471562118459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410783369","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017327669,0.000090592715,0.9936487,0.0012442628,0.0012285558,0.0012066262,0.00022489423,0.000035650508,0.0005879289],"genre_scores_gemma":[0.063801266,0.00016751864,0.9353432,0.00015692723,0.00024855082,0.00018471769,0.000024926516,0.000016833961,0.000056031487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997416,0.0005339423,0.0012760274,0.00024752604,0.00032825457,0.00019822855],"domain_scores_gemma":[0.9372635,0.06172373,0.00042314586,0.00024909413,0.00031096296,0.000029589093],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0044293213,0.00016460838,0.00053541316,0.000105580155,0.00020598757,0.000016445169,0.00021695225,0.00010396756,0.00006250115],"category_scores_gemma":[0.049777884,0.00009121151,0.000051338193,0.00033478587,0.0006386097,0.000035509933,0.00006017791,0.00037989952,4.106452e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012524184,0.000050961567,0.00049719785,0.00029274906,0.000105953695,2.9544108e-7,0.00070895575,0.00019084815,0.000541309,0.9333298,0.0041648727,0.05999177],"study_design_scores_gemma":[0.00093925395,0.00017503547,0.0014478012,0.00044692814,0.00019336097,0.000001236671,0.0009281923,0.2572146,0.000047387526,0.73833895,0.00021546187,0.000051777395],"about_ca_topic_score_codex":0.00026563683,"about_ca_topic_score_gemma":0.00033430892,"teacher_disagreement_score":0.25702375,"about_ca_system_score_codex":0.00015049102,"about_ca_system_score_gemma":0.00005535225,"threshold_uncertainty_score":0.95822626},"labels":[],"label_agreement":null},{"id":"W4411070250","doi":"10.1002/sim.70140","title":"High‐Dimensional Multiresponse Partially Functional Linear Regression","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Sensory Analysis and Statistical Methods","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Functional principal component analysis; Estimator; Curse of dimensionality; Scalar (mathematics); Covariate; Mathematics; Principal component analysis; Applied mathematics; Linear regression; Regression analysis; Regression; Partial least squares regression; Consistency (knowledge bases); Computer science; Statistics; Artificial intelligence","score_opus":0.04955572462124787,"score_gpt":0.3533515474465572,"score_spread":0.30379582282530937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411070250","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8089934,0.0006176246,0.16517562,0.018211905,0.0027042406,0.00049468904,0.00077667355,0.00012339815,0.0029024235],"genre_scores_gemma":[0.9003351,0.000059237365,0.091778986,0.0023029214,0.0005247419,0.000018265013,0.0005335358,0.0000014873079,0.0044457414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99845856,0.00034734618,0.00039454593,0.00028422562,0.000311603,0.00020369513],"domain_scores_gemma":[0.9964175,0.0032449109,0.00006710524,0.00006257523,0.00012443664,0.00008343659],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008062908,0.00013042075,0.00029939608,0.000042764463,0.00013145438,0.0000078153,0.00010133072,0.000077472105,0.0026342205],"category_scores_gemma":[0.0028486347,0.000045437962,0.000028150072,0.00046379297,0.00018175619,0.000021858466,0.000039926257,0.0001950197,0.000021179998],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014619182,0.00034053807,0.01268484,0.000033143402,0.00006778308,0.0002301809,0.00006529154,0.00082318025,0.15105213,0.3762405,0.09255254,0.36444795],"study_design_scores_gemma":[0.0015470675,0.0005842858,0.79084504,0.00038144336,0.00011703055,0.0000062769577,0.00022596524,0.04027201,0.0014632099,0.13669686,0.02750364,0.0003571717],"about_ca_topic_score_codex":0.0002833176,"about_ca_topic_score_gemma":0.00055985776,"teacher_disagreement_score":0.7781602,"about_ca_system_score_codex":0.00002811582,"about_ca_system_score_gemma":0.000017458127,"threshold_uncertainty_score":0.9982775},"labels":[],"label_agreement":null},{"id":"W4411101265","doi":"10.1002/sim.70135","title":"A Comparison Between Markov Switching Zero‐Inflated and Hurdle Models for Spatio‐Temporal Infectious Disease Counts","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Negative binomial distribution; Markov chain; Markov model; Econometrics; Zero (linguistics); Statistics; Binomial distribution; Covariate; Count data; Mathematics; Overdispersion; Computer science; Poisson distribution","score_opus":0.1652249539145567,"score_gpt":0.46877656738093065,"score_spread":0.30355161346637394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411101265","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020972682,0.00036448834,0.97514373,0.0010805796,0.00015341271,0.00050601544,0.0001571155,0.000057085188,0.0015648644],"genre_scores_gemma":[0.97275,0.00007381958,0.026334457,0.00039729202,0.000070817616,0.000045948145,0.00007680481,0.000011397143,0.00023947838],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99892867,0.00007217006,0.00047250983,0.00020773473,0.00013622505,0.00018271728],"domain_scores_gemma":[0.9944387,0.0051555373,0.00012287749,0.00013795015,0.0000745882,0.00007032202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007397422,0.00013349605,0.0005082369,0.0000906742,0.00008907176,0.0000072096573,0.00007075235,0.000056683828,0.000028669416],"category_scores_gemma":[0.008019093,0.00010452574,0.000016523247,0.00013365288,0.000101127625,0.000023257548,0.000068115514,0.00016567222,0.0000016355783],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117447176,0.00008197156,0.6442844,0.0011232987,0.000109736895,0.000012245168,0.0007296541,0.00020597498,0.0000034650034,0.20951472,0.12067919,0.023137888],"study_design_scores_gemma":[0.00086457055,0.000073495044,0.033756606,0.00022622042,0.00011851348,1.0837249e-7,0.000040499555,0.07466653,5.602687e-7,0.88767165,0.0024827064,0.000098530145],"about_ca_topic_score_codex":0.00019198246,"about_ca_topic_score_gemma":0.00015937335,"teacher_disagreement_score":0.9517773,"about_ca_system_score_codex":0.000086762666,"about_ca_system_score_gemma":0.00003860033,"threshold_uncertainty_score":0.96001834},"labels":[],"label_agreement":null},{"id":"W4411180042","doi":"10.1002/sim.70161","title":"The Impact of Violation of the Proportional Hazards Assumption on the Calibration of the Cox Proportional Hazards Model","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Proportional hazards model; Calibration; Statistics; Econometrics; Mathematics","score_opus":0.022430769567123875,"score_gpt":0.290078751311249,"score_spread":0.26764798174412513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411180042","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6673345,0.00054362684,0.30647224,0.0085050445,0.0012111824,0.0019594973,0.0015845363,0.000008695589,0.012380646],"genre_scores_gemma":[0.99896353,0.00019364322,0.00020358039,0.000098369084,0.00004307955,0.000030559557,0.000026865333,0.0000058297223,0.00043452712],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.998676,0.00004606572,0.00084088667,0.00013347092,0.00019001594,0.000113569484],"domain_scores_gemma":[0.99854606,0.00017002606,0.0008033649,0.00032770974,0.0001435725,0.000009237044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013824555,0.000092503564,0.00022821283,0.0000879208,0.0001486632,0.000007000533,0.00025262052,0.00005016298,0.00004194741],"category_scores_gemma":[0.00088631484,0.000043402444,0.00007560501,0.00036492693,0.00035921452,0.00004511531,0.000039564387,0.00016906552,9.295733e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063907515,0.00006542315,0.069117114,0.000039811453,0.00003523486,1.00754036e-7,0.0002574403,0.019568142,0.000060497907,0.9042469,0.004579587,0.0019658369],"study_design_scores_gemma":[0.0002749623,0.000070309055,0.51627505,0.00009672807,0.0000108415925,1.18372796e-7,0.00004903181,0.20576258,0.0001168623,0.2771561,0.00015168547,0.00003572174],"about_ca_topic_score_codex":0.00042963208,"about_ca_topic_score_gemma":0.00015436666,"teacher_disagreement_score":0.6270908,"about_ca_system_score_codex":0.00011992111,"about_ca_system_score_gemma":0.0001901581,"threshold_uncertainty_score":0.17699003},"labels":[],"label_agreement":null},{"id":"W4411515984","doi":"10.1002/sim.70176","title":"Precision of Treatment Hierarchy: A Metric for Quantifying Certainty in Treatment Hierarchies From Network Meta‐Analysis","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft; Hellenic Foundation for Research and Innovation; European Commission","keywords":"Metric (unit); Ranking (information retrieval); Hierarchy; Pairwise comparison; Statistics; Mathematics; Frequentist inference; Rank (graph theory); Certainty; Variance (accounting); Similarity (geometry); Computer science; Bayesian probability; Econometrics; Artificial intelligence; Bayesian inference","score_opus":0.7096301178491243,"score_gpt":0.5685468593222872,"score_spread":0.14108325852683712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411515984","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01849564,0.026303327,0.94921273,0.000972563,0.00037864695,0.0024155225,0.000746447,0.0000051246466,0.0014700115],"genre_scores_gemma":[0.80702573,0.0015179918,0.1862488,0.00012657062,0.00008564591,0.00047059671,0.00025180174,0.0000140209795,0.0042588785],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9816496,0.0057885223,0.008967068,0.0010848067,0.0021418214,0.00036818234],"domain_scores_gemma":[0.9440317,0.050866537,0.0023323453,0.002140083,0.00052945403,0.00009988371],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037213217,0.00041028732,0.009117238,0.0033666447,0.00012294261,0.000078471545,0.0008225415,0.000086530126,0.0023646904],"category_scores_gemma":[0.028400041,0.00018127152,0.0016926479,0.008698816,0.00014387697,0.000055395012,0.00012520092,0.000100246674,0.000013381178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004828739,0.00089663465,0.2921605,0.00025843165,0.18797776,0.000054093056,0.0095287105,0.0714571,0.000039134033,0.09625768,0.018396188,0.32249087],"study_design_scores_gemma":[0.0036577887,0.0013122938,0.061836205,0.00016803922,0.18135564,5.714864e-7,0.0019010021,0.25414342,0.00003253012,0.4768298,0.018401848,0.00036086986],"about_ca_topic_score_codex":0.0038619868,"about_ca_topic_score_gemma":0.012612509,"teacher_disagreement_score":0.78853005,"about_ca_system_score_codex":0.0003007835,"about_ca_system_score_gemma":0.00013887527,"threshold_uncertainty_score":0.99854726},"labels":[],"label_agreement":null},{"id":"W4412424131","doi":"10.1002/sim.70038","title":"Natural Effects in the Presence of an Intermediate Confounder: Evaluation of Pragmatic Estimation Strategies With an Emphasis on the Relationship Between Natural and Interventional Effects","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Estimator; Confounding; Outcome (game theory); Natural (archaeology); Econometrics; Statistics; Mediation; Computer science; Mathematics; Biology","score_opus":0.09314129423726326,"score_gpt":0.47612402867371983,"score_spread":0.3829827344364566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412424131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8344435,0.00010003324,0.16390696,0.00017100146,0.00006652447,0.0011485132,0.000013240179,0.000016068301,0.00013414313],"genre_scores_gemma":[0.96660066,0.000002849853,0.03315113,0.000029199551,0.000013275293,0.00011329869,0.00007780324,0.000006958016,0.0000048177117],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976603,0.0010496343,0.00046031305,0.00015141406,0.0005713951,0.00010696311],"domain_scores_gemma":[0.9793888,0.019834824,0.00028987686,0.00026268704,0.00020827004,0.00001555528],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0029233678,0.0001320999,0.00027899144,0.00020708088,0.000042067004,0.000016440112,0.00019742157,0.000047487592,0.0000040875916],"category_scores_gemma":[0.014405873,0.000072399875,0.000010428044,0.00029830594,0.00045120798,0.00022060992,0.000023820234,0.00034984486,9.399036e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008609254,0.00010663759,0.01086097,0.0012113071,0.0000270536,0.0000033322847,0.0035702486,0.00011214907,0.00011243291,0.97214234,0.00004024093,0.011727196],"study_design_scores_gemma":[0.00068583037,0.00070414745,0.31246504,0.0021482217,0.00009136491,0.000001313285,0.001154188,0.02917117,0.00019778479,0.6533351,8.880677e-8,0.000045766486],"about_ca_topic_score_codex":0.000042190713,"about_ca_topic_score_gemma":0.00036278894,"teacher_disagreement_score":0.31880724,"about_ca_system_score_codex":0.00006873897,"about_ca_system_score_gemma":0.00008622258,"threshold_uncertainty_score":0.9938962},"labels":[],"label_agreement":null},{"id":"W4412453904","doi":"10.1002/sim.70181","title":"The Design of Large‐Scale Plasma Donation Trials","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Blood donation and transfusion practices","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University Medical Centre; Actua; McMaster University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; McMaster University","keywords":"Outcome (game theory); Variance (accounting); Donation; Poisson distribution; Adverse effect; Statistics; Medicine; Audit; Scale (ratio); Accrual; Econometrics; Computer science; Mathematics; Internal medicine; Economics","score_opus":0.04330349544810271,"score_gpt":0.342392463399069,"score_spread":0.2990889679509663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412453904","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025221743,0.0004608738,0.9182379,0.021648828,0.0019771825,0.00074783876,0.000025853682,0.00004356004,0.054335766],"genre_scores_gemma":[0.9785311,0.00086786883,0.013579919,0.003970072,0.00055231975,0.000056186287,0.00008890935,0.000017010769,0.0023366169],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99891984,0.00008380481,0.000524551,0.00010613759,0.00025702844,0.000108614644],"domain_scores_gemma":[0.9964586,0.0029521193,0.00027005665,0.00011372517,0.00020133167,0.0000041868725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044792895,0.000071235045,0.00022733868,0.00022265346,0.00012054142,0.000033612796,0.00013645351,0.000034632892,0.0003022511],"category_scores_gemma":[0.005334855,0.000044542772,0.000014667386,0.00047097588,0.000084911466,0.00015926234,0.000025574698,0.00010890646,0.000013294985],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018957956,0.000087878856,0.0015329634,0.0001171766,0.0000370056,0.00000335497,0.00016479768,0.00011628733,0.00023687875,0.9063148,0.04858622,0.04261304],"study_design_scores_gemma":[0.00839683,0.00004653637,0.020015312,0.00034949655,0.0003976997,6.6962656e-7,0.0036784564,0.082743436,0.00022555438,0.32523224,0.5587217,0.00019207683],"about_ca_topic_score_codex":0.0001186578,"about_ca_topic_score_gemma":0.00042765072,"teacher_disagreement_score":0.97600895,"about_ca_system_score_codex":0.000008839647,"about_ca_system_score_gemma":0.000028425098,"threshold_uncertainty_score":0.6386705},"labels":[],"label_agreement":null},{"id":"W4412453910","doi":"10.1002/sim.70186","title":"A Latent‐Class Model for Time‐To‐Event Outcomes and High‐Dimensional Imaging Data","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bivariate analysis; Covariate; Computer science; Logistic regression; Neuroimaging; Expectation–maximization algorithm; Class (philosophy); Latent class model; Artificial intelligence; Machine learning; Proportional hazards model; Identification (biology); Disease; Data mining; Econometrics; Statistics; Medicine; Mathematics; Maximum likelihood; Internal medicine","score_opus":0.1053803383116654,"score_gpt":0.4526441691017764,"score_spread":0.347263830790111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412453910","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005369787,0.000057960333,0.99239033,0.004542733,0.00017123875,0.00039758137,0.0014824237,0.000021190703,0.0003995467],"genre_scores_gemma":[0.020090597,0.000008864651,0.97558546,0.0016464008,0.00003263175,0.000034162153,0.00013275293,0.000017170287,0.002451938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986454,0.000055394336,0.0004707272,0.00035349818,0.00023129224,0.000243688],"domain_scores_gemma":[0.9946972,0.0045931204,0.00006803507,0.00042564605,0.000120100245,0.00009589205],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009966645,0.0001560884,0.00044805024,0.0001361964,0.0000576964,0.000012788684,0.00023029905,0.000035239664,0.00015994113],"category_scores_gemma":[0.011313987,0.000118443364,0.0000095661835,0.00012418107,0.00013265756,0.000029846788,0.0002577111,0.00013318834,0.000007037653],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044173572,0.00005929751,0.0006990734,0.00019585498,0.00003233926,0.0000109706,0.00015986612,0.000069096175,0.000107705855,0.8527651,0.10216105,0.043695495],"study_design_scores_gemma":[0.000622457,0.000026558204,0.001395843,0.00015245278,0.000050641753,7.210598e-7,0.0000128218635,0.5088625,0.0000032824298,0.48862237,0.00018228179,0.00006811193],"about_ca_topic_score_codex":0.000048077673,"about_ca_topic_score_gemma":0.000025133138,"teacher_disagreement_score":0.50879335,"about_ca_system_score_codex":0.000038428927,"about_ca_system_score_gemma":0.000070200455,"threshold_uncertainty_score":0.9970141},"labels":[],"label_agreement":null},{"id":"W4412527389","doi":"10.1002/sim.70194","title":"A Simple Diagnostic for the Positivity Assumption for Continuous Exposures","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; McGill University","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Simple (philosophy); Statistics; Computer science; Econometrics; Mathematics","score_opus":0.0848985461080552,"score_gpt":0.46413627148375325,"score_spread":0.37923772537569805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412527389","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015947967,0.00023346311,0.99454427,0.00097453455,0.00020670003,0.0017498469,0.00033852493,0.000083581144,0.00027431094],"genre_scores_gemma":[0.58294725,0.00017541408,0.41353422,0.00062837714,0.00019266742,0.0018044023,0.0001267089,0.000031690543,0.0005592707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990491,0.00005098333,0.0003661781,0.00017520139,0.0001345917,0.0002239363],"domain_scores_gemma":[0.9635839,0.03583392,0.00011576529,0.00024693515,0.00019571585,0.000023792209],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009440454,0.00012992369,0.0003162543,0.00008418414,0.00010092508,0.000010803787,0.00015407884,0.00006222076,0.000020808904],"category_scores_gemma":[0.031756174,0.00008882949,0.000024833716,0.00011824378,0.00017095104,0.000033364966,0.000031066586,0.00013001873,5.103427e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005875695,0.00005214388,0.001265501,0.00025435627,0.000027608965,0.0000033583115,0.00020586571,0.0000070509122,0.00053438253,0.9027185,0.07061793,0.024254547],"study_design_scores_gemma":[0.0008782601,0.00031682666,0.0032160762,0.000230802,0.00011463896,9.4324554e-7,0.00024389933,0.0020697417,0.0009659994,0.987769,0.004104732,0.0000890877],"about_ca_topic_score_codex":0.00005346413,"about_ca_topic_score_gemma":0.00039772002,"teacher_disagreement_score":0.5813525,"about_ca_system_score_codex":0.0000761106,"about_ca_system_score_gemma":0.000037751102,"threshold_uncertainty_score":0.9763998},"labels":[],"label_agreement":null},{"id":"W4412582858","doi":"10.1002/sim.70188","title":"The Mathematics of Serocatalytic Models With Applications to Public Health Data","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute for Health Research Health Protection Research Unit; National Institute for Health and Care Research; Natural Environment Research Council; International Development Research Centre; University of Oxford; Merton College, University of Oxford","keywords":"Intuition; Computer science; Data science; Epidemiology; Infectious disease (medical specialty); Context (archaeology); Public health; Disease; Management science; Medicine; Biology; Epistemology; Pathology","score_opus":0.4394107515544346,"score_gpt":0.5164224802020916,"score_spread":0.07701172864765699,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412582858","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000099581426,0.00045861996,0.961221,0.035422407,0.000034863846,0.0009135224,0.00022595236,0.000030806474,0.0015932833],"genre_scores_gemma":[0.12766173,0.0009972616,0.8658689,0.00404644,0.00006886299,0.00038762187,0.0001425648,0.000030092768,0.00079646154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981212,0.000101923375,0.0008357415,0.00029968825,0.0003228191,0.00031861436],"domain_scores_gemma":[0.9874341,0.010777902,0.0002579551,0.0012605556,0.00017617548,0.000093337076],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0032091732,0.00014441047,0.0005773122,0.00010708637,0.00016301253,0.0000085725615,0.0008104781,0.000027998873,0.000008786277],"category_scores_gemma":[0.01163988,0.000077656725,0.000009543584,0.0007239491,0.00037612897,0.000034495082,0.0004315047,0.00018240348,0.000003073479],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007726475,0.000095093776,0.0002496951,0.0005387169,0.000051347895,0.000001081998,0.00084980053,0.00006400894,0.0000016534311,0.9456636,0.044549443,0.007927864],"study_design_scores_gemma":[0.00037155498,0.00013215821,0.00050629396,0.00031670276,0.00004016264,0.0000011604014,0.0016221825,0.016736608,0.000001173748,0.966723,0.013465559,0.00008340888],"about_ca_topic_score_codex":0.0001988068,"about_ca_topic_score_gemma":0.0017795644,"teacher_disagreement_score":0.12756217,"about_ca_system_score_codex":0.00012915266,"about_ca_system_score_gemma":0.00022778826,"threshold_uncertainty_score":0.9966855},"labels":[],"label_agreement":null},{"id":"W4412654453","doi":"10.1002/sim.70198","title":"Fast Variational Bayesian Inference for Correlated Survival Data: An Application to Invasive Mechanical Ventilation Duration Analysis","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Hemodynamic Monitoring and Therapy","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The King's University; Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mechanical ventilation; Duration (music); Bayesian probability; Bayesian inference; Inference; Survival analysis; Statistics; Computer science; Econometrics; Mathematics; Artificial intelligence; Medicine; Internal medicine","score_opus":0.027712925675312767,"score_gpt":0.3847432451131363,"score_spread":0.35703031943782354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412654453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009093712,0.000011538411,0.98826325,0.0010547633,0.00041713522,0.0006922226,0.00029947105,0.000032292304,0.00013563519],"genre_scores_gemma":[0.9213437,0.000024765988,0.067448474,0.00021313434,0.00022578209,0.00008498996,0.010485949,0.000010549573,0.00016268837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855936,0.00007151835,0.00050804816,0.00040436324,0.00030379137,0.00015292365],"domain_scores_gemma":[0.99830836,0.00066170905,0.00011472754,0.0005018868,0.00030875407,0.000104584746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008833696,0.00011825578,0.00035175032,0.00043107642,0.000070573195,0.000012276203,0.00014883226,0.00009810111,0.000041786],"category_scores_gemma":[0.0018287672,0.000110699075,0.000017665387,0.0009826317,0.000034143894,0.00007337024,0.000030428158,0.0001495363,0.0000030173924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028018707,0.0011087405,0.14853218,0.00049258163,0.0017905532,0.000026750116,0.0023277565,0.013782762,0.022195721,0.6099054,0.0020644753,0.19497119],"study_design_scores_gemma":[0.001831602,0.00032123792,0.19113883,0.00013291583,0.0006629624,8.421713e-7,0.00016964127,0.79184973,0.00012443657,0.013237189,0.00042216407,0.00010846587],"about_ca_topic_score_codex":0.0002826505,"about_ca_topic_score_gemma":0.0010532008,"teacher_disagreement_score":0.92081475,"about_ca_system_score_codex":0.00014589028,"about_ca_system_score_gemma":0.00020672717,"threshold_uncertainty_score":0.4514177},"labels":[],"label_agreement":null},{"id":"W4413048133","doi":"10.1002/sim.70215","title":"Health Utility Survival for Randomized Clinical Trials: Extensions and Statistical Properties","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; Public Health Ontario; University of Toronto; University Health Network","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China; Princess Margaret Cancer Foundation","keywords":"Clinical endpoint; Sample size determination; Statistics; Survival analysis; Randomized controlled trial; Medicine; Clinical trial; Statistical hypothesis testing; Statistical power; Econometrics; Computer science; Mathematics; Surgery; Internal medicine","score_opus":0.6863747557470252,"score_gpt":0.6045958885801116,"score_spread":0.08177886716691363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413048133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00095635856,0.007665496,0.8892968,0.09370159,0.0021864949,0.003151994,0.001982239,0.000029018342,0.0010299966],"genre_scores_gemma":[0.58291364,0.011207209,0.32836628,0.06874978,0.0020495874,0.00194003,0.0009920152,0.00011575672,0.0036656957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97978127,0.006680868,0.012194197,0.00074391835,0.00012636752,0.00047339825],"domain_scores_gemma":[0.930938,0.06615059,0.00209734,0.00041126486,0.00015084955,0.00025196813],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2454639,0.00020176444,0.0046871332,0.00033138765,0.00018539146,0.000029348883,0.00014870428,0.00013900334,0.00019983815],"category_scores_gemma":[0.3509636,0.00018246128,0.00008759346,0.00015505627,0.00083262403,0.000073452844,0.00005161175,0.00030466547,0.000027151409],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024559416,0.000117809584,0.006295566,0.0008878348,0.00010324041,9.325754e-7,0.00065974746,0.000004396819,1.2862944e-7,0.86819565,0.11492513,0.006353629],"study_design_scores_gemma":[0.10391499,0.00028009477,0.027979612,0.00067993795,0.000064837484,0.0000016589594,0.0018214799,0.10423748,1.8946785e-7,0.7240397,0.03667705,0.0003029904],"about_ca_topic_score_codex":0.001804046,"about_ca_topic_score_gemma":0.00078581047,"teacher_disagreement_score":0.5819573,"about_ca_system_score_codex":0.00018633944,"about_ca_system_score_gemma":0.00046240265,"threshold_uncertainty_score":0.7769537},"labels":[],"label_agreement":null},{"id":"W4413111174","doi":"10.1002/sim.70227","title":"A Framework for Generating Realistic Synthetic Tabular Data in a Randomized Controlled Trial Setting","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Randomized controlled trial; Synthetic data; Copula (linguistics); Artificial intelligence; Machine learning; Data mining; Econometrics; Medicine; Mathematics","score_opus":0.03481874690734359,"score_gpt":0.3819513484906666,"score_spread":0.347132601583323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413111174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005461434,0.00030268123,0.99125093,0.0030634906,0.00064124836,0.0041508414,0.00016356142,0.00009466779,0.000277956],"genre_scores_gemma":[0.026929254,0.00010327529,0.9702732,0.00074566493,0.00014939894,0.0013801223,0.00033141693,0.000011014639,0.00007663276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99686974,0.0006077505,0.0013253465,0.0005877721,0.0003119198,0.0002974451],"domain_scores_gemma":[0.9827983,0.015193054,0.00038861248,0.0014521301,0.00012750147,0.00004041482],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008428017,0.00017516117,0.0013378435,0.00040744446,0.00007466012,0.00006272776,0.0013280041,0.00010048161,0.000009525116],"category_scores_gemma":[0.080666825,0.00013846085,0.000032754,0.00054110767,0.00018465825,0.00012047697,0.00027458408,0.00029975266,8.853417e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05648784,0.000051720734,0.000009756437,0.00007892392,0.00002852018,0.000014140232,0.00024711242,0.0000349771,0.000078678975,0.928783,0.0038471932,0.010338138],"study_design_scores_gemma":[0.34623167,0.00003691098,0.0000042573297,0.000412759,0.000030972427,4.6535402e-7,0.000027841375,0.43612418,0.000014211543,0.21688378,0.00016305062,0.00006991584],"about_ca_topic_score_codex":0.0000976849,"about_ca_topic_score_gemma":0.000067209854,"teacher_disagreement_score":0.7118992,"about_ca_system_score_codex":0.00009263944,"about_ca_system_score_gemma":0.00022178331,"threshold_uncertainty_score":0.9270771},"labels":[],"label_agreement":null},{"id":"W4413140657","doi":"10.1002/sim.70222","title":"An Efficient Two‐Dimensional Functional Mixed‐Effect Model Framework for Repeatedly Measured Functional Data","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"City University of Hong Kong","keywords":"Computer science; Mixed model; Functional data analysis; Econometrics; Mathematics; Machine learning","score_opus":0.054495888216838366,"score_gpt":0.35451119008282744,"score_spread":0.30001530186598907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413140657","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001241729,0.00014381573,0.994258,0.0022134862,0.0012585327,0.0004210295,0.0002497558,0.00007525116,0.00013841424],"genre_scores_gemma":[0.39260855,0.0000064907695,0.6038587,0.001530696,0.00040813204,0.00015023911,0.0012005701,0.000013913403,0.0002227005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998068,0.0000855315,0.00038326185,0.00069739216,0.0004939004,0.00027192573],"domain_scores_gemma":[0.99705833,0.0014428118,0.00008633698,0.0010917109,0.00021609226,0.000104740226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010764275,0.00017068307,0.0002474054,0.00014478466,0.00022392662,0.000036582747,0.00070547144,0.00006969963,0.00002481816],"category_scores_gemma":[0.00054389774,0.00013852325,0.000021063976,0.00052572484,0.00012615212,0.000095745796,0.00020385828,0.00028504527,0.0000052799164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004835093,0.000098785036,0.000092030845,0.000015656122,0.000015122272,0.0000029229382,0.000016846809,0.37697986,0.0001874279,0.55971617,0.05486976,0.007957081],"study_design_scores_gemma":[0.0008122717,0.00012565969,0.0014922321,0.000086095875,0.000025458658,0.0000035797768,0.000003790871,0.82559216,0.000029442896,0.1712061,0.000520727,0.00010247524],"about_ca_topic_score_codex":0.000019831266,"about_ca_topic_score_gemma":0.000029833554,"teacher_disagreement_score":0.4486123,"about_ca_system_score_codex":0.000062504136,"about_ca_system_score_gemma":0.00017043228,"threshold_uncertainty_score":0.56488144},"labels":[],"label_agreement":null},{"id":"W4414168825","doi":"10.1002/sim.70201","title":"Weighted Trigonometric Regression for Suboptimal Designs in Circadian Transcriptome Studies","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Circadian rhythm and melatonin","field":"Neuroscience","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Estimator; Sample size determination; Statistical hypothesis testing; Regression; Regression analysis; Kernel (algebra); Trigonometry; Statistical power; Kernel regression","score_opus":0.08897076563611843,"score_gpt":0.381796386422942,"score_spread":0.29282562078682356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414168825","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6666182,0.030043948,0.26633173,0.0092309965,0.007452511,0.005007565,0.00083611807,0.00021021922,0.014268675],"genre_scores_gemma":[0.9878051,0.0016573329,0.0070803734,0.00082321896,0.00009742095,0.00013572135,0.000018723513,0.000019640178,0.0023624361],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99829364,0.00012215483,0.00052859087,0.0004352295,0.00020604722,0.00041432455],"domain_scores_gemma":[0.9973562,0.0022187904,0.00007921292,0.00020053284,0.000055348937,0.00008994773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006101255,0.00018125838,0.00048273598,0.0015210451,0.00008757013,0.000009402195,0.000178781,0.00008668512,0.00005165823],"category_scores_gemma":[0.0035832594,0.00014745186,0.000027706375,0.0020463592,0.00030563335,0.00006330176,0.000017983471,0.00026150123,0.00000595619],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076918467,0.00037611893,0.01577014,0.0011166455,0.000040839754,0.0007139952,0.011324249,0.00006143851,0.06315372,0.805241,0.027302226,0.07413045],"study_design_scores_gemma":[0.06771264,0.0038373966,0.28437233,0.009347163,0.0005013619,0.00009741113,0.009400184,0.038309637,0.1673594,0.28954697,0.12674636,0.0027691505],"about_ca_topic_score_codex":0.000027033246,"about_ca_topic_score_gemma":0.00007420695,"teacher_disagreement_score":0.515694,"about_ca_system_score_codex":0.0001987013,"about_ca_system_score_gemma":0.00011607464,"threshold_uncertainty_score":0.60129124},"labels":[],"label_agreement":null},{"id":"W4414196550","doi":"10.1002/sim.70258","title":"Collapsible Kernel Machine Regression for Exposomic Analyses","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Institute of Environmental Health Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Additive model; Kernel (algebra); Causal inference; Bayesian probability; Flexibility (engineering); Covariate; Kernel method; Inference; Bayesian inference; Regression","score_opus":0.04023429796767516,"score_gpt":0.4032869001057561,"score_spread":0.36305260213808094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414196550","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11165969,0.00095516635,0.8133016,0.003901153,0.00087044714,0.0020210084,0.00040992742,0.00006760582,0.066813394],"genre_scores_gemma":[0.93387616,0.00061589206,0.05575338,0.0026372904,0.000072735835,0.00012784619,0.00016825569,0.000026922833,0.0067215282],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9985008,0.00009643772,0.0003876731,0.00042464203,0.00027431938,0.00031610767],"domain_scores_gemma":[0.99886805,0.00067372835,0.00010184518,0.00025695632,0.000009193217,0.00009024554],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007521492,0.00015277475,0.00027951153,0.00012463513,0.00012459318,0.0000061732053,0.00017228503,0.000057035068,0.0011594979],"category_scores_gemma":[0.00091782515,0.00012208745,0.000017360338,0.0003545458,0.0003013288,0.00005045337,0.00010841658,0.00016880246,0.00005546323],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046031075,0.00052157434,0.28825572,0.00057775184,0.00009927987,0.00012240029,0.003114469,0.0025789565,0.11322415,0.009389741,0.30337507,0.27828056],"study_design_scores_gemma":[0.014078957,0.0011583482,0.5443798,0.0020830077,0.00037568924,0.000009458018,0.002321105,0.12916489,0.015434122,0.1291283,0.16074604,0.0011203107],"about_ca_topic_score_codex":0.00077878736,"about_ca_topic_score_gemma":0.0006419653,"teacher_disagreement_score":0.82221645,"about_ca_system_score_codex":0.00033642317,"about_ca_system_score_gemma":0.000027348493,"threshold_uncertainty_score":0.9997536},"labels":[],"label_agreement":null},{"id":"W4414264132","doi":"10.1002/sim.70234","title":"What Is Fair? Defining Fairness in Machine Learning for Health","year":2025,"lang":"en","type":"review","venue":"Statistics in Medicine","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's and Gender Studies et Recherches Féministes; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Operationalization; Fairness measure; Capability approach; MEDLINE; Health care","score_opus":0.2301952076018682,"score_gpt":0.5545321101943922,"score_spread":0.324336902592524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414264132","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001149185,0.9684212,0.022648111,0.0043548644,0.0022144788,0.0020088928,0.00012154365,0.000029994277,0.00019975929],"genre_scores_gemma":[0.000036955116,0.9882664,0.004908393,0.0018709947,0.00037668142,0.00037597114,0.0025850951,0.000054736982,0.0015247863],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962965,0.00026555668,0.0019424832,0.00058203196,0.00034125688,0.0005721323],"domain_scores_gemma":[0.9954285,0.0033459533,0.00050465344,0.0003376634,0.00019642124,0.00018680727],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019515746,0.00038958094,0.0025652854,0.0009766874,0.000111525005,0.000023539247,0.00016279721,0.00031164088,0.00018451542],"category_scores_gemma":[0.003607586,0.00032443274,0.000098277844,0.0009164236,0.00012312057,0.00007060622,0.000041357398,0.0012526945,0.000022864078],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028656683,0.00005379926,0.00027830648,0.067873314,0.000023378423,0.000021224889,0.0026381025,0.000003865792,1.1090364e-8,0.00251278,0.005461816,0.9211047],"study_design_scores_gemma":[0.00021936507,0.00063590857,0.000020642477,0.17209387,0.0002449768,0.00002090537,0.0028436114,0.0009105647,3.291081e-7,0.005244465,0.8175284,0.00023691039],"about_ca_topic_score_codex":0.002205463,"about_ca_topic_score_gemma":0.0016168786,"teacher_disagreement_score":0.92086786,"about_ca_system_score_codex":0.0007675787,"about_ca_system_score_gemma":0.002239659,"threshold_uncertainty_score":0.9999208},"labels":[],"label_agreement":null},{"id":"W4414283105","doi":"10.1002/sim.70248","title":"The Estimand Framework in Diagnostic Accuracy Studies","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Deutsche Forschungsgemeinschaft","keywords":"Diagnostic accuracy; Test (biology); Diagnostic test; Bridge (graph theory); Interpretation (philosophy)","score_opus":0.6242570362789946,"score_gpt":0.6233312332906149,"score_spread":0.0009258029883797425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414283105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011890265,0.06555032,0.8736281,0.030590001,0.003432621,0.0017226456,0.000042855816,0.0000072168978,0.013135996],"genre_scores_gemma":[0.8833136,0.0104029495,0.08597067,0.0032429355,0.00027286448,0.00026494073,0.000011806362,0.00001681916,0.016503409],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98451436,0.004246011,0.00773904,0.00057178154,0.0026583693,0.00027045124],"domain_scores_gemma":[0.49691927,0.4968899,0.0021831628,0.0029654116,0.00096324563,0.0000790049],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08892754,0.00019282222,0.0022368461,0.00038933803,0.00014594702,0.0001638772,0.0012132841,0.000052050786,0.00089379254],"category_scores_gemma":[0.87642574,0.00007195052,0.00011009863,0.0021723125,0.0003706189,0.00004706585,0.00014829545,0.0003379475,0.0002582053],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007035151,0.000026412084,0.09844354,0.000078314406,0.00011497024,0.00006217878,0.0018952669,0.00017699451,9.3411126e-7,0.30376232,0.46973708,0.12569496],"study_design_scores_gemma":[0.00026019488,0.000029972882,0.072125204,0.0006560547,0.0000997486,0.000001129607,0.0038816198,0.004658193,6.2893e-7,0.8335492,0.08466433,0.000073718744],"about_ca_topic_score_codex":0.000036846486,"about_ca_topic_score_gemma":0.00079947204,"teacher_disagreement_score":0.87142336,"about_ca_system_score_codex":0.000057491907,"about_ca_system_score_gemma":0.00006884248,"threshold_uncertainty_score":0.97864014},"labels":[],"label_agreement":null},{"id":"W4414484180","doi":"10.1002/sim.70273","title":"Designing Stepped Wedge Cluster Randomized Trials With a Baseline Measurement of the Outcome","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"National Center for Advancing Translational Sciences; National Institute on Aging; Patient-Centered Outcomes Research Institute","keywords":"Baseline (sea); Sample size determination; Outcome (game theory); Estimator; Randomized controlled trial; Context (archaeology); Cluster randomised controlled trial; Cluster (spacecraft)","score_opus":0.2478030119876625,"score_gpt":0.4705801716423711,"score_spread":0.2227771596547086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414484180","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040924802,0.0001429188,0.9943993,0.0010288812,0.00017701808,0.0022967265,0.000027810705,0.000047623747,0.0014704821],"genre_scores_gemma":[0.23756245,0.0000450738,0.7610509,0.0005020732,0.00004733951,0.00024472605,0.00000551759,0.000024274595,0.00051764474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99553645,0.0017488946,0.001655259,0.00018963868,0.0006698234,0.0001999434],"domain_scores_gemma":[0.9827043,0.015743086,0.00063437055,0.00043641505,0.00044874154,0.000033123346],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01994594,0.00019663354,0.0016601417,0.00017752827,0.0000403523,0.0000051503475,0.00023865025,0.000062597566,0.000085007036],"category_scores_gemma":[0.09347335,0.00009699322,0.000058388287,0.00035131545,0.0004240273,0.000027955442,0.000065060376,0.00027417482,5.86241e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03885047,0.00031501072,0.002746641,0.0017807636,0.00055640674,0.000027772028,0.0018621372,0.000105412386,0.008747317,0.904017,0.03315932,0.00783176],"study_design_scores_gemma":[0.119813174,0.00015313494,0.00013580237,0.003015135,0.00075768214,0.0000021452192,0.00043569726,0.0015923745,0.009087265,0.8646889,0.00013708758,0.00018165051],"about_ca_topic_score_codex":0.000050850238,"about_ca_topic_score_gemma":0.00018325339,"teacher_disagreement_score":0.2371532,"about_ca_system_score_codex":0.00013421984,"about_ca_system_score_gemma":0.00013230121,"threshold_uncertainty_score":0.9141627},"labels":[],"label_agreement":null},{"id":"W4415153955","doi":"10.1002/sim.70269","title":"Specification of Estimands for Complex Disease Processes Using Multistate Models and Utility Functions","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Jackknife resampling; Ranking (information retrieval); Disease; Simplicity; Variance (accounting); Resampling; Clinical trial","score_opus":0.7557390693740194,"score_gpt":0.6269280900231367,"score_spread":0.1288109793508827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415153955","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019012344,0.00013399674,0.9947554,0.00020530337,0.00024688715,0.00076512236,0.0015535849,0.000021031368,0.00041745984],"genre_scores_gemma":[0.1396071,0.000058272017,0.8600328,0.0000533095,0.000059816826,0.000032627126,0.00003669214,0.000012786855,0.00010659417],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981097,0.00014914456,0.0010366866,0.00029879133,0.00022486533,0.0001807943],"domain_scores_gemma":[0.95796114,0.040952936,0.00024976442,0.00026940796,0.00046644034,0.000100290956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002272465,0.00013737107,0.00055664044,0.00016057977,0.00006859362,0.0000069984585,0.00010186203,0.00005729771,0.00005030606],"category_scores_gemma":[0.1169391,0.000117859265,0.000018743647,0.00034558895,0.0006086303,0.0000358319,0.000041707393,0.00012466358,1.5717978e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012840286,0.00037408364,0.0028416293,0.0063262545,0.00006920749,0.000006858551,0.0003210811,0.00014652836,0.0002068826,0.943565,0.0074299197,0.037428528],"study_design_scores_gemma":[0.0012690759,0.00006966034,0.004506612,0.00034379325,0.00018096846,2.7818007e-7,0.00011552271,0.2264406,0.000022391072,0.7668666,0.00011479493,0.00006966437],"about_ca_topic_score_codex":0.0000398098,"about_ca_topic_score_gemma":0.00004582336,"teacher_disagreement_score":0.22629407,"about_ca_system_score_codex":0.00003984972,"about_ca_system_score_gemma":0.00012757911,"threshold_uncertainty_score":0.8904993},"labels":[],"label_agreement":null},{"id":"W4415996186","doi":"10.1002/sim.70309","title":"Identification of Regions of Interest in Neuroimaging Data With Irregular Boundary Based on Semiparametric Transformation Models and Interval‐Censored Outcomes","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bivariate analysis; Covariate; Identification (biology); Neuroimaging; Nonparametric statistics; Boundary (topology); Domain (mathematical analysis); Transformation (genetics); Pattern recognition (psychology)","score_opus":0.18901742399715157,"score_gpt":0.4306194415401282,"score_spread":0.24160201754297664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415996186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032309514,0.000045083198,0.9660096,0.0006582997,0.00006520848,0.00027504988,0.00031002474,0.0000075214452,0.00031967182],"genre_scores_gemma":[0.8223719,0.000036328893,0.17743474,0.00007225751,0.0000027358026,0.000007282108,0.000054286036,0.0000076126066,0.000012885763],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985216,0.00016929675,0.0008063234,0.00021288756,0.00017893867,0.00011092226],"domain_scores_gemma":[0.99576557,0.0034039211,0.0002188202,0.00046954758,0.000114462026,0.000027671647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001055335,0.00011446953,0.0004329204,0.0005787297,0.000018058117,0.000008535273,0.00020478723,0.000035690282,0.000008310152],"category_scores_gemma":[0.005517847,0.00008704776,0.000008192689,0.00055689056,0.0003264013,0.00008233374,0.0000350969,0.00018483395,9.286429e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013419783,0.00017448336,0.0033945278,0.0011385889,0.000018770841,0.0000073389615,0.0009848299,0.00021167628,0.0002551767,0.9714514,0.0002876779,0.021941347],"study_design_scores_gemma":[0.0009649184,0.00013121346,0.01750367,0.0010537128,0.000052948493,7.422872e-7,0.00038206566,0.48831668,0.00013479251,0.49139675,0.0000050157623,0.000057478155],"about_ca_topic_score_codex":0.000107492495,"about_ca_topic_score_gemma":0.00015383236,"teacher_disagreement_score":0.79006237,"about_ca_system_score_codex":0.000030162922,"about_ca_system_score_gemma":0.000053754782,"threshold_uncertainty_score":0.66057765},"labels":[],"label_agreement":null},{"id":"W4416943753","doi":"10.1002/sim.70336","title":"System of Linear Equations to Derive Unreported Test Accuracy Counts for Meta‐Analysis","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Public Health Ontario; University of Toronto; Cancer Care Ontario","funders":"","keywords":"Rounding; Sensitivity (control systems); Test (biology); Linear system; Linear model; Accuracy and precision; Linear equation; Limit (mathematics)","score_opus":0.544600576239449,"score_gpt":0.5683193730780832,"score_spread":0.023718796838634204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416943753","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015413338,0.00035658205,0.9911566,0.00051169505,0.00036269307,0.00023498423,0.0003247438,0.000012966878,0.006885652],"genre_scores_gemma":[0.4647554,0.000016696782,0.5331714,0.00024850597,0.00004979215,0.00006696085,0.00003020908,0.0000051772445,0.0016558527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980963,0.00012628899,0.0008882932,0.00024097746,0.0005239896,0.00012413807],"domain_scores_gemma":[0.8593911,0.13914452,0.00033648548,0.00037204014,0.0007111113,0.000044747245],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0053319405,0.00007500551,0.0006769074,0.0011486056,0.000051263494,0.000010785675,0.0002905742,0.00003384147,0.00030391358],"category_scores_gemma":[0.47459623,0.000048860027,0.000074190066,0.005093323,0.00006363098,0.000018949224,0.00004274897,0.00006110648,0.000008619114],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011151661,0.00027481062,0.052029833,0.00052774773,0.026323138,0.00006702914,0.0019732865,0.010086912,0.0004907526,0.53373224,0.21935435,0.15502839],"study_design_scores_gemma":[0.0027058464,0.0008850005,0.06191216,0.0003170478,0.07538796,0.000005924166,0.011869711,0.5136558,0.00031533558,0.2770364,0.05527601,0.0006328308],"about_ca_topic_score_codex":0.00012568859,"about_ca_topic_score_gemma":0.000049478396,"teacher_disagreement_score":0.5035689,"about_ca_system_score_codex":0.000028109589,"about_ca_system_score_gemma":0.000068701374,"threshold_uncertainty_score":0.52982944},"labels":[],"label_agreement":null},{"id":"W4417070771","doi":"10.1002/sim.70327","title":"Likelihood‐Based Non‐Parametric Receiver Operating Characteristic Curve Analysis in the Presence of Imperfect Reference Standard","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Clinical Laboratory Practices and Quality Control","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Receiver operating characteristic; Imperfect; Gold standard (test); Index (typography); Standard error; Mean squared error","score_opus":0.042036275745086636,"score_gpt":0.41713028637182276,"score_spread":0.37509401062673614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417070771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8794856,0.0009858091,0.10304485,0.009271734,0.00041265207,0.0017374136,0.0008517142,0.00002492216,0.0041853194],"genre_scores_gemma":[0.9928173,0.00027091344,0.004591649,0.0020098733,0.0000564213,0.00003326682,0.00013955626,0.000007731382,0.000073280346],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969497,0.0006806646,0.0011439434,0.00035635752,0.00059322146,0.00027611305],"domain_scores_gemma":[0.9885052,0.0100711435,0.00033384087,0.00056867866,0.0004437073,0.00007747163],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004767082,0.00017519222,0.0009915204,0.0006782923,0.000049495015,0.000018667568,0.00024280432,0.00010554522,0.00028849323],"category_scores_gemma":[0.027026115,0.00011275517,0.000052402193,0.0038413475,0.00024292611,0.000056682147,0.000035015466,0.00073944713,0.0000031674974],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002524563,0.0008591564,0.94694215,0.0012761138,0.000692957,0.00039579964,0.0021419316,0.00041025135,0.0022546933,0.009754292,0.0035109257,0.02923715],"study_design_scores_gemma":[0.0060707666,0.0015120244,0.9236277,0.001144741,0.0018442689,0.0000015418691,0.0013281001,0.061292425,0.000088822926,0.00094967865,0.0019517316,0.00018820123],"about_ca_topic_score_codex":0.0010495953,"about_ca_topic_score_gemma":0.0009743704,"teacher_disagreement_score":0.11333172,"about_ca_system_score_codex":0.000093338815,"about_ca_system_score_gemma":0.00039999478,"threshold_uncertainty_score":0.98116964},"labels":[],"label_agreement":null}]}