{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1935,"total_is_capped":false,"direct_labels_cover":22,"predictions_cover":1935,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"94bfa5b664a1","filters":{"topic":"Statistical Methods and Inference"}},"results":[{"id":"W2140514146","doi":"10.1111/j.1467-9868.2005.00490.x","title":"Sparsity and Smoothness Via the Fused Lasso","year":2004,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2805,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Office of Naval Research; National Institutes of Health; National Science Foundation","keywords":"Lasso (programming language); Elastic net regularization; Mathematics; Smoothness; Norm (philosophy); Applied mathematics; Least-squares function approximation; Regression; Classifier (UML); Linear regression; Algorithm; Mathematical optimization; Computer science; Pattern recognition (psychology); Artificial intelligence; Statistics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.1165199762151029,"gpt":0.3663164615483013,"spread":0.2497964853331984,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005051973,0.0004071267,0.001048335,0.00002661771,0.0006727968,0.0001247915,0.0007616249,0.00029253,0.0004132078],"category_scores_gemma":[0.0331999,0.0002152457,0.0003040714,0.0002767109,0.002650922,0.0001009049,0.0004135717,0.001439258,0.000008742124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001696579,"about_ca_system_score_gemma":0.000208282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001048371,"about_ca_topic_score_gemma":0.00002835479,"domain_scores_codex":[0.9945616,0.002358873,0.001207139,0.000380839,0.0008079623,0.0006835748],"domain_scores_gemma":[0.9715581,0.02653098,0.0006622372,0.0004591042,0.0003911066,0.000398488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00031354,0.0001813013,0.0004490682,0.0001471686,0.0002642209,0.00005261119,0.0007053399,0.00005771877,0.0001942537,0.9756575,0.00583464,0.01614259],"study_design_scores_gemma":[0.001031598,0.0005396893,0.027024,0.00006916526,0.0004843962,0.0002576345,0.000414664,0.000824201,0.0003187363,0.966882,0.001868893,0.0002850209],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01028386,0.0001305053,0.9823545,0.005422603,0.0008900246,0.0003003172,0.0002877063,0.0000304161,0.0003001023],"genre_scores_gemma":[0.0589158,0.0000467874,0.9395385,0.001008787,0.0002918425,0.000009401091,0.000001942863,0.00004005957,0.0001469069],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04863194,"threshold_uncertainty_score":0.9767434,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112231177","doi":"10.3982/ecta6822","title":"Unconditional Quantile Regressions","year":2009,"lang":"en","type":"article","venue":"Econometrica","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":2210,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; Canadian Institute for Advanced Research","funders":"","keywords":"Quantile; Quantile regression; Econometrics; Mathematics; Statistics; Quantile function; Marginal distribution; Variable (mathematics); Distribution (mathematics); Random variable; Cumulative distribution function; Probability density function","retraction":null,"screen_n_in":null,"score":{"opus":0.1428703376059224,"gpt":0.4080761164386754,"spread":0.265205778832753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001804678,0.00007176313,0.0001540421,0.0002001702,0.00007001129,0.00002402758,0.0001102988,0.00003884712,0.004183981],"category_scores_gemma":[0.002969464,0.00005956179,0.00004689702,0.0004213153,0.00002542067,0.00004920065,0.00001472217,0.00008657511,0.0002354751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002494991,"about_ca_system_score_gemma":0.00002295456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001451111,"about_ca_topic_score_gemma":2.440883e-7,"domain_scores_codex":[0.9993902,0.00002821204,0.0002002705,0.0001477283,0.00008215683,0.000151446],"domain_scores_gemma":[0.9984295,0.001197838,0.00007053703,0.0001749276,0.00003286162,0.00009438729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002461005,0.00008013327,0.0002808186,0.00000297632,0.000005012905,0.000002638398,0.00001349776,3.879737e-7,0.00001446711,0.9249405,0.04209378,0.03256331],"study_design_scores_gemma":[0.0001307085,0.00009658892,0.02753612,0.00001076368,0.000006587791,0.000003759181,0.00001255158,0.0002579195,0.0001169537,0.9593335,0.01239603,0.00009855185],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.07273204,0.0002254123,0.3175828,0.00485998,0.0005974214,0.0003189245,0.0003574454,0.0002921982,0.6030338],"genre_scores_gemma":[0.6230438,0.000008466427,0.3753825,0.0003366809,0.00009195863,0.000006126276,0.000009908124,0.000005866329,0.001114645],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6019192,"threshold_uncertainty_score":0.9967263,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126292488","doi":"10.1214/09-aoas285","title":"BART: Bayesian additive regression trees","year":2010,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1515,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Division of Mathematical Sciences; Natural Sciences and Engineering Research Council of Canada; Isaac Newton Institute for Mathematical Sciences; National Science Foundation","keywords":"Frequentist inference; Bayesian probability; Nonparametric regression; Bayesian inference; Bayesian linear regression; Markov chain Monte Carlo; Boosting (machine learning); Feature selection; Inference; Bayesian average","retraction":null,"screen_n_in":null,"score":{"opus":0.130137471622647,"gpt":0.4114514803502196,"spread":0.2813140087275725,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007018677,0.0001798198,0.0003304221,0.00004200933,0.0001338134,0.00002477123,0.000327197,0.00009040145,0.0009160514],"category_scores_gemma":[0.002067459,0.0001094268,0.00004479791,0.0001286112,0.0003683027,0.00002160186,0.00008145787,0.0003687378,0.0000329773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002732005,"about_ca_system_score_gemma":0.00004554183,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001000463,"about_ca_topic_score_gemma":0.00003545016,"domain_scores_codex":[0.9987293,0.00006922084,0.0004029951,0.0001918327,0.0003307464,0.0002759064],"domain_scores_gemma":[0.9946668,0.004238597,0.0002659683,0.0005020593,0.0002181907,0.0001084017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006777944,0.00006376779,0.000005429509,0.00002764073,0.00002295044,0.000002485893,0.0004282692,6.137694e-7,0.003474567,0.8728347,0.03185389,0.09121789],"study_design_scores_gemma":[0.0001523832,0.00007675122,0.00113298,0.00002719418,0.00003329685,0.000001827509,0.0001798109,0.001046202,0.0165588,0.9773682,0.003278482,0.0001440468],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009303468,0.00001286777,0.9365047,0.0005446177,0.0002367581,0.0003832842,0.002000304,0.00006195454,0.050952],"genre_scores_gemma":[0.4372896,0.00003561506,0.5620549,0.0002661909,0.0001187624,0.00002496722,0.00001886281,0.00002609915,0.0001649899],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4279861,"threshold_uncertainty_score":0.9999973,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105171386","doi":"10.1257/jep.28.2.29","title":"High-Dimensional Methods and Inference on Structural and Treatment Effects","year":2014,"lang":"en","type":"article","venue":"The Journal of Economic Perspectives","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":716,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Booth University College","funders":"Economic and Social Research Council","keywords":"Overfitting; Computer science; Inference; Sample (material); Data mining; Sample size determination; Range (aeronautics); Predictive power; Contrast (vision); Set (abstract data type); Data set; Econometrics; Transaction data; Data science; Machine learning; Artificial intelligence; Database transaction; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04926294270180489,"gpt":0.4084235830715081,"spread":0.3591606403697032,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007607687,0.0001077092,0.000290714,0.0000546267,0.00009081925,0.0000339238,0.00006839405,0.00002635685,0.00004644266],"category_scores_gemma":[0.0009729623,0.00005907557,0.00003099394,0.00001339,0.0001782022,0.00005025274,0.0000276517,0.0001104314,0.000001595701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009707446,"about_ca_system_score_gemma":0.00002769729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005888523,"about_ca_topic_score_gemma":0.00001404388,"domain_scores_codex":[0.9991202,0.0004522649,0.0001972199,0.00009242258,0.00004449592,0.00009341706],"domain_scores_gemma":[0.9920322,0.007573562,0.0001899825,0.000103835,0.00003291617,0.00006744985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001587773,0.00002666773,0.0001414185,0.00001098833,0.0001185228,0.000001230839,0.002419378,0.00003425726,0.001243005,0.8566476,0.00003788591,0.1391603],"study_design_scores_gemma":[0.0008295101,0.001576338,0.0247282,0.00004492196,0.0001011821,0.00008337092,0.00046239,0.004728116,0.001586098,0.9657218,0.00003241294,0.0001056399],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9784668,0.0002426057,0.02044773,0.0003178816,0.0001274713,0.00006780705,0.000003268233,0.000004201548,0.0003222396],"genre_scores_gemma":[0.8006178,0.00009415005,0.1991226,0.00002777098,0.0001063698,8.317068e-7,3.751881e-8,0.000005535621,0.00002484045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1786749,"threshold_uncertainty_score":0.2409032,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2172185584","doi":"10.1214/13-aos1175","title":"A significance test for the lasso","year":2014,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":561,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Institute of Biomedical Imaging and Bioengineering","keywords":"Mathematics; Test statistic; Lasso (programming language); Null distribution; Statistical hypothesis testing; Null hypothesis; Null (SQL); Linear model; Statistics; Design matrix; Applied mathematics; Algorithm; Computer science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.3167578092553975,"gpt":0.446753198473048,"spread":0.1299953892176505,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00145938,0.0001025161,0.0002090677,0.00001265928,0.0001415783,0.00002515338,0.0003502132,0.00003008945,0.00006605431],"category_scores_gemma":[0.02970335,0.00005196155,0.00004464627,0.00008305212,0.0002589828,0.00001440727,0.00003968667,0.00009836766,0.000009914924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000317018,"about_ca_system_score_gemma":0.00002943104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002020522,"about_ca_topic_score_gemma":0.00001048892,"domain_scores_codex":[0.9990714,0.0001070778,0.000301519,0.0001105861,0.000195556,0.0002138975],"domain_scores_gemma":[0.9457298,0.05332883,0.0001942974,0.0003891024,0.0003188286,0.00003916381],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001678384,0.0000437246,0.00003651967,0.00007557325,0.00002036536,1.454846e-7,0.0001545536,0.000004706648,0.0001485593,0.8931127,0.05966416,0.04672223],"study_design_scores_gemma":[0.0001230929,0.0002219115,0.001259843,0.0000247218,0.00004945063,7.497378e-7,0.00007290943,0.01625655,0.001510914,0.9668395,0.01355941,0.0000809627],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003751875,0.00004226916,0.9940295,0.002400681,0.0000904374,0.0003120747,0.0009772722,0.00001642752,0.001756165],"genre_scores_gemma":[0.2568543,0.00009774851,0.7409644,0.00105272,0.0001846031,0.00008081365,0.000004171864,0.00002768782,0.0007334892],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2564791,"threshold_uncertainty_score":0.9784698,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109415218","doi":"10.1016/j.jeconom.2008.08.003","title":"The wild bootstrap, tamed at last","year":2008,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":502,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Economic and Social Research Council; Social Sciences and Humanities Research Council of Canada","keywords":"Heteroscedasticity; Skewness; Inference; Context (archaeology); Econometrics; Mathematics; Statistics; Regression; Bootstrap aggregating; Computer science; Artificial intelligence; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.4334227440918269,"gpt":0.3669537611539678,"spread":0.06646898293785908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001055261,0.00008513676,0.0002563293,0.0002077718,0.0002025469,0.00003163212,0.0002541787,0.00004806956,0.0002129228],"category_scores_gemma":[0.009213319,0.00005197335,0.0001198826,0.0004345689,0.000115078,0.00007606629,0.00004648759,0.0002230948,0.00002749683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000104532,"about_ca_system_score_gemma":0.00006687297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.881222e-7,"about_ca_topic_score_gemma":0.000003043426,"domain_scores_codex":[0.9988783,0.00006195054,0.0005945063,0.0000699856,0.0001899168,0.0002053113],"domain_scores_gemma":[0.9938283,0.005169829,0.0005241378,0.0001639572,0.0001672077,0.0001465568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002170473,0.0005805923,0.1025029,0.00010161,0.0004367027,0.000329971,0.0008293825,0.0000321747,0.0001338686,0.52301,0.2074201,0.1644056],"study_design_scores_gemma":[0.001743928,0.001189166,0.1188904,0.00006787704,0.0001185905,0.001837387,0.0002944618,0.0007763196,0.000835018,0.6396258,0.2341515,0.0004695987],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8734056,0.001270376,0.09902543,0.0009032967,0.001241517,0.000127057,0.00001957377,0.00001509654,0.02399201],"genre_scores_gemma":[0.8329319,0.001866697,0.1626764,0.0002034782,0.0004223404,0.000002094737,2.61897e-7,0.00002374612,0.001873044],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.163936,"threshold_uncertainty_score":0.9991325,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2598303606","doi":"10.1111/insr.12214","title":"A Tutorial on Multilevel Survival Analysis: Methods, Models and Applications","year":2017,"lang":"en","type":"article","venue":"International Statistical Review","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":495,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research","keywords":"Multilevel model; Random effects model; Proportional hazards model; Statistics; Poisson distribution; Poisson regression; Log-linear model; Hazard; Mathematics; Exponential random graph models; Hierarchical database model; Hazard ratio; Generalized linear mixed model; Survival analysis; Statistical model; Econometrics; Confidence interval; Linear model; Overdispersion; Generalized linear model; Computer science; Count data; Data mining; Medicine; Random graph","retraction":null,"screen_n_in":null,"score":{"opus":0.3174354727116557,"gpt":0.5677285560890346,"spread":0.2502930833773789,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001231564,0.0001721662,0.0005393511,0.00005816786,0.0002056917,0.0001534759,0.000464272,0.00005427519,0.0007237121],"category_scores_gemma":[0.01358582,0.0001359831,0.0001002143,0.00006078719,0.0001731612,0.00008817964,0.0001482636,0.000186415,0.00003596661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000393614,"about_ca_system_score_gemma":0.00003023011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000057433,"about_ca_topic_score_gemma":0.000009247065,"domain_scores_codex":[0.9982623,0.0002512086,0.000496821,0.0003871496,0.0004270523,0.0001754357],"domain_scores_gemma":[0.9937894,0.005031693,0.0002615226,0.000519135,0.0002320647,0.0001661819],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000009483501,0.00005372173,0.00003049859,0.0001379026,0.0001787515,0.000002773958,0.000004639699,0.000001079564,0.000002752978,0.727614,0.0005327927,0.2714315],"study_design_scores_gemma":[0.0002196251,0.00003113283,0.002500803,0.000337784,0.0005735903,0.000002213527,0.000002276706,0.01974353,0.000005408024,0.9493626,0.0270464,0.0001746894],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000008923028,0.0006935023,0.9783938,0.000638639,0.0003121689,0.0003676163,0.0005810909,0.00002725257,0.01897701],"genre_scores_gemma":[0.008097674,0.004072434,0.9865094,0.0003977054,0.0003214415,0.000261636,0.00003726292,0.00001759313,0.0002847877],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2712568,"threshold_uncertainty_score":0.9947231,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974194630","doi":"10.1175/jam2504.1","title":"Penalized Maximal t Test for Detecting Undocumented Mean Change in Climate Data Series","year":2007,"lang":"en","type":"article","venue":"Journal of Applied Meteorology and Climatology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":377,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"York University; Environment and Climate Change Canada","funders":"","keywords":"Series (stratigraphy); Statistics; Statistical power; Standard deviation; Homogeneity (statistics); Mathematics; Monte Carlo method; Sample size determination; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.1175569994762927,"gpt":0.4046140185326715,"spread":0.2870570190563788,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004449423,0.0001727953,0.0007703219,0.0002052871,0.0001006209,0.00001482513,0.0002952213,0.0002170011,0.00006008607],"category_scores_gemma":[0.002353233,0.0001400993,0.00004517845,0.0001278849,0.000210033,0.0001319192,0.0001897404,0.0003634874,0.000001460423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001962737,"about_ca_system_score_gemma":0.00002777823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004962873,"about_ca_topic_score_gemma":0.0002065612,"domain_scores_codex":[0.9980649,0.00009944649,0.0009517261,0.0002547009,0.0001049925,0.0005241885],"domain_scores_gemma":[0.9925322,0.006413683,0.0006056083,0.0002459379,0.00009828711,0.0001043113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.007682945,0.0003690652,0.01940341,0.0005115388,0.0001717304,0.0002378968,0.001248301,3.104266e-7,0.007996409,0.8940066,0.0001118038,0.06825998],"study_design_scores_gemma":[0.006733883,0.001827578,0.008622055,0.00008563605,0.0003930739,0.002438459,0.001709584,0.0008348834,0.003828944,0.9708703,0.002263402,0.0003921953],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8624161,0.0005237656,0.1327369,0.001037998,0.0004898694,0.0007535655,0.00009553299,0.00003402091,0.001912248],"genre_scores_gemma":[0.6525813,0.0002063599,0.3467462,0.0003224198,0.0001009834,0.00001668748,0.000005347857,0.00001838228,0.000002383496],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2140093,"threshold_uncertainty_score":0.5713085,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2084007633","doi":"10.1111/j.1467-9868.2007.00593.x","title":"Bootstrapping Clustered Data","year":2007,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":369,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Australian Research Council; Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Bootstrapping (finance); Consistency (knowledge bases); Variance (accounting); Computer science; Parametric statistics; Transformation (genetics); Statistics; Residual; Random effects model; Econometrics; Cluster sampling; Parametric model; Data mining; Mathematics; Algorithm; Artificial intelligence; Meta-analysis; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.3132799447114114,"gpt":0.4465436380687782,"spread":0.1332636933573668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01348197,0.000450058,0.001247933,0.00005182231,0.0004319419,0.0001118923,0.001860022,0.0003761007,0.001042265],"category_scores_gemma":[0.07498137,0.0002892512,0.0003189732,0.000370488,0.001614321,0.0001819159,0.0009344848,0.001619742,0.00001325973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001677074,"about_ca_system_score_gemma":0.0002533682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004418126,"about_ca_topic_score_gemma":0.00002687316,"domain_scores_codex":[0.9931002,0.002076778,0.002170354,0.0005530012,0.001092861,0.001006822],"domain_scores_gemma":[0.9507956,0.04607518,0.001003926,0.001047338,0.0004963626,0.0005816066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006865883,0.0002544222,0.0005175215,0.0002655608,0.0004511333,0.0001552706,0.0003936257,0.00002324223,0.0003204889,0.8788263,0.0608437,0.0572621],"study_design_scores_gemma":[0.001007108,0.0006141022,0.02102395,0.0001347034,0.000640878,0.0003344471,0.0008592377,0.00573608,0.0003274439,0.9581529,0.01068705,0.0004820773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001805506,0.0001180629,0.9927523,0.001269069,0.001614208,0.0002790161,0.0008503664,0.00004348601,0.00126803],"genre_scores_gemma":[0.02693306,0.00002436806,0.9712355,0.0007906195,0.0006436585,0.000002781158,0.00001139088,0.00005595602,0.0003027232],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.07932657,"threshold_uncertainty_score":0.999956,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2204774351","doi":"10.1080/01621459.2015.1108848","title":"Exact Post-Selection Inference for Sequential Regression Procedures","year":2016,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":352,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Inference; Lasso (programming language); Mathematics; Regression; Model selection; Algorithm; Regularization (linguistics); Computer science; Regression analysis; Statistics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.04245338162808755,"gpt":0.4014923890323961,"spread":0.3590390074043086,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001053104,0.0001227362,0.0003611492,0.00005508399,0.0001227757,0.00004013132,0.0001939782,0.00004966846,0.00008081631],"category_scores_gemma":[0.06485523,0.00005739568,0.000124682,0.0001735071,0.000103503,0.0001096233,0.00003465774,0.0001640909,0.000003943218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004068829,"about_ca_system_score_gemma":0.0002311955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001692925,"about_ca_topic_score_gemma":0.00001489513,"domain_scores_codex":[0.998162,0.0003895267,0.0005562366,0.000125189,0.0005264232,0.000240576],"domain_scores_gemma":[0.9874521,0.009615554,0.001840702,0.0001002168,0.0009008011,0.00009059634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001390373,0.0004434844,0.04400467,0.0001685872,0.0003560597,0.000004569664,0.0002951822,0.000004028444,0.09993327,0.4278401,0.05205883,0.3735008],"study_design_scores_gemma":[0.0009398409,0.001309715,0.1276315,0.0003380783,0.0002451776,0.00002326099,0.00007477774,0.0003955003,0.005019916,0.8628704,0.0009336533,0.0002182112],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1104689,0.000005273164,0.8855568,0.003237461,0.0003042068,0.0001760207,0.0001569068,0.00001447147,0.00007990083],"genre_scores_gemma":[0.7468515,0.0000213918,0.2523272,0.0001988057,0.0002734414,0.000009415042,7.453452e-7,0.00001547464,0.0003020498],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6363826,"threshold_uncertainty_score":0.9430219,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2024256095","doi":"10.1016/j.jclinepi.2008.05.015","title":"Quantile regression and restricted cubic splines are useful for exploring relationships between continuous variables","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":326,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Quantile regression; Ordinary least squares; Quantile; Regression; Linear regression; Statistics; Mathematics; Regression analysis; Continuous variable; Econometrics; Variables; Variable (mathematics); Multivariate adaptive regression splines; Polynomial regression","retraction":null,"screen_n_in":null,"score":{"opus":0.7754066535483083,"gpt":0.576074492354978,"spread":0.1993321611933303,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01853063,0.0001578689,0.002223081,0.00009935015,0.0001169278,0.00001135949,0.000179057,0.0003605254,0.00001424182],"category_scores_gemma":[0.5217999,0.0001028983,0.0002576358,0.0001126436,0.0001330799,0.0001174302,0.0000326815,0.000911054,0.00000142357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001204694,"about_ca_system_score_gemma":0.00005667739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000224775,"about_ca_topic_score_gemma":0.000001006266,"domain_scores_codex":[0.9919781,0.003523524,0.003852329,0.0002363663,0.0001227365,0.000286955],"domain_scores_gemma":[0.7859841,0.2101057,0.003077695,0.0001990962,0.0003689448,0.0002644614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003485047,0.0001364887,0.6630611,0.00006759726,0.00007332896,0.00001374679,0.00004241666,0.000005901728,0.00002260556,0.2869366,0.004899594,0.04439213],"study_design_scores_gemma":[0.00052722,0.0005924153,0.4634402,0.0002549223,0.00008762491,0.00001578631,0.00004287241,0.0004551442,0.000007135055,0.5335464,0.0009628416,0.0000673832],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5865539,0.0002329067,0.4089711,0.003574844,0.0004209858,0.0001374653,0.00001468604,0.00001698081,0.00007710477],"genre_scores_gemma":[0.3926066,0.0004667707,0.6058664,0.0002113703,0.0008000873,0.000003936096,0.000001599029,0.00001030778,0.00003299821],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5032693,"threshold_uncertainty_score":0.6422384,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2038005309243087,"gpt":0.4336053912476601,"spread":0.2298048603233514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00213575,0.0001456502,0.0003520928,0.0001079696,0.0001219727,0.00002416828,0.0001629847,0.0001050627,0.00004109528],"category_scores_gemma":[0.01684236,0.00006934835,0.00001701868,0.0004390411,0.0003415779,0.0000630884,0.00004171377,0.0002769512,3.157174e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003445659,"about_ca_system_score_gemma":0.00006078697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001449155,"about_ca_topic_score_gemma":0.00007036505,"domain_scores_codex":[0.9982336,0.0003063456,0.0007370912,0.0002000932,0.0003344023,0.0001884883],"domain_scores_gemma":[0.9826381,0.01647005,0.0003487299,0.0002789285,0.0002217455,0.00004242313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008500093,0.00002075999,0.0006365391,0.000182959,0.00001760534,0.000001397548,0.0007378232,0.0001689314,0.0003265337,0.9858239,0.001107258,0.01089129],"study_design_scores_gemma":[0.0004012694,0.0001349277,0.0003656265,0.0001770129,0.00002923034,0.000001511892,0.0005956407,0.5078098,0.00005090443,0.4903607,0.00002540589,0.00004802622],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005599792,0.0002957331,0.9920734,0.0005499726,0.0003581065,0.0007081809,0.0001120803,0.00001599633,0.0002867017],"genre_scores_gemma":[0.8627844,0.0002434043,0.1365797,0.00005798993,0.00002926998,0.00002981876,0.00004731016,0.00002093622,0.0002071809],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8571846,"threshold_uncertainty_score":0.9914392,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2007186404","doi":"10.1207/s15328007sem0702_1","title":"Point Estimation, Hypothesis Testing, and Interval Estimation Using the RMSEA: Some Comments and a Reply to Hayduk and Glaser","year":2000,"lang":"en","type":"article","venue":"Structural Equation Modeling A Multidisciplinary Journal","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":304,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Estimator; Interval estimation; Point estimation; Statistics; Statistic; Mathematics; Premise; Structural equation modeling; Econometrics; Statistical hypothesis testing; Test statistic; Sample size determination; Estimation; Sampling distribution; Point (geometry); Confidence interval; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.179461950396243,"gpt":0.3933198102466394,"spread":0.2138578598503964,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009169371,0.0002133061,0.0002522306,0.00009689795,0.0009137124,0.0003018405,0.000100614,0.0000541039,0.00004355369],"category_scores_gemma":[0.003353242,0.0001451447,0.00003066766,0.0001210146,0.0001022943,0.0004393533,0.00009427946,0.0002753219,0.000001378402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006574049,"about_ca_system_score_gemma":0.00003723574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008890935,"about_ca_topic_score_gemma":0.000003002099,"domain_scores_codex":[0.9983844,0.000220447,0.0005979825,0.0002769724,0.0002842264,0.0002359998],"domain_scores_gemma":[0.9977811,0.001487244,0.0002016141,0.0001659013,0.000172533,0.0001915928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00036959,0.0000530923,0.00340937,0.0002005064,0.0001093585,0.00001370611,0.01475969,0.3112626,0.001584973,0.005440397,0.00006588416,0.6627308],"study_design_scores_gemma":[0.0002993837,0.00008762606,0.002692404,0.0001668245,0.00004590897,0.0002117805,0.0003026084,0.6176278,0.00002326823,0.3784254,2.480413e-7,0.0001167788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6205264,0.00003894716,0.3781138,0.001049738,0.00004355784,0.0001912318,0.000007958909,0.00001890462,0.000009402516],"genre_scores_gemma":[0.501293,0.000008469468,0.4985193,0.0001027986,0.00004879952,0.000004558399,8.392647e-7,0.00001235506,0.000009824254],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.662614,"threshold_uncertainty_score":0.702763,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409376239","doi":"10.18637/jss.v112.i01","title":"Parsimoniously Fitting Large Multivariate Random Effects in <b>glmmTMB</b>","year":2025,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":302,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"University of New South Wales; Analytical Center for the Government of the Russian Federation; McMaster University","keywords":"Multivariate statistics; Computer science; Statistics; Mathematics; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.02737557881685304,"gpt":0.3755612070587689,"spread":0.3481856282419159,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001738516,0.0002002207,0.0007735188,0.0001867859,0.00008683516,0.00005539524,0.0002381103,0.0001272847,0.0001712382],"category_scores_gemma":[0.0612594,0.0001531236,0.0001083182,0.0003061218,0.0000763287,0.00008421579,0.00008731305,0.0006255203,0.000008492806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001038585,"about_ca_system_score_gemma":0.0001399806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002251596,"about_ca_topic_score_gemma":0.00001140366,"domain_scores_codex":[0.9974759,0.0004879228,0.00104946,0.0001925654,0.0003628789,0.0004312515],"domain_scores_gemma":[0.9744352,0.02466837,0.0003296543,0.0001621125,0.0002444233,0.0001602556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007305862,0.0007532274,0.02733538,0.001060168,0.0001507328,0.0008926799,0.0005387215,0.00001905841,0.0001370441,0.8253703,0.005221122,0.1377911],"study_design_scores_gemma":[0.005385196,0.0002159426,0.04905867,0.001038364,0.0001195971,0.00001812178,0.00006648909,0.0022398,0.0001314175,0.9409046,0.0006354915,0.0001863273],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01758028,0.0001553516,0.9811034,0.0001534175,0.0004249097,0.0002136476,0.00007066131,0.00002783273,0.0002705351],"genre_scores_gemma":[0.2489046,0.00001251054,0.7506986,0.00021903,0.00006414004,0.000007336678,0.000001517417,0.00001630536,0.00007598016],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2313244,"threshold_uncertainty_score":0.946648,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2021091247","doi":"10.1198/073500107000000250","title":"Nonparametric Estimation of Conditional CDF and Quantile Functions With Mixed Categorical and Continuous Data","year":2008,"lang":"en","type":"article","venue":"Journal of Business and Economic Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":254,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Estimator; Nonparametric statistics; Conditional probability distribution; Kernel regression; Quantile; Categorical variable; Kernel density estimation; Quantile function; Cumulative distribution function; Mathematics; Econometrics; Quantile regression; Statistics; Kernel (algebra); Conditional expectation; Regular conditional probability; Probability density function; Probability mass function","retraction":null,"screen_n_in":null,"score":{"opus":0.1067694690153859,"gpt":0.3248579928145062,"spread":0.2180885237991204,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002721739,0.00009632648,0.0003868731,0.0001116796,0.00008123978,0.00002936259,0.00006361857,0.00003970157,0.00005047485],"category_scores_gemma":[0.00110674,0.00007421487,0.00000800518,0.00007755326,0.0002569104,0.0001602309,0.00004519131,0.00009290197,8.254639e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001528074,"about_ca_system_score_gemma":0.0001076485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005650355,"about_ca_topic_score_gemma":0.0000112517,"domain_scores_codex":[0.9991952,0.00003232526,0.0004678119,0.000123448,0.00009084634,0.00009038495],"domain_scores_gemma":[0.997431,0.001732145,0.0004413418,0.0001145644,0.0001982745,0.0000827046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0007235888,0.0005526273,0.06955954,0.001000559,0.000512552,0.0002047209,0.0004758999,0.00115571,0.00008183238,0.7888867,0.02754964,0.1092967],"study_design_scores_gemma":[0.002302582,0.0005997412,0.6006346,0.00009189729,0.0003803477,0.003030771,0.0002423215,0.1615078,0.00002222163,0.2305824,0.0003179297,0.0002873589],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3300787,0.0001071631,0.6690909,0.00004367694,0.0000802867,0.0000435483,0.0005152543,0.000002033731,0.00003844796],"genre_scores_gemma":[0.6344638,0.0002680009,0.3651792,0.000007902583,0.0000351415,7.487987e-7,0.00002260088,0.000006679682,0.00001583161],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5583043,"threshold_uncertainty_score":0.3026395,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3014535943","doi":"10.1186/s41512-020-00074-3","title":"State of the art in selection of variables and functional forms in multivariable analysis—outstanding issues","year":2020,"lang":"en","type":"editorial","venue":"Diagnostic and Prognostic Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":249,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University Health Centre","funders":"Erasmus+; Medical Research Council; Deutsche Forschungsgemeinschaft; European Commission","keywords":"Multivariable calculus; Selection (genetic algorithm); Computer science; Variable (mathematics); Variables; Feature selection; Management science; Artificial intelligence; Machine learning; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.110322771388086,"gpt":0.4295645871614275,"spread":0.3192418157733415,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00360062,0.0001945824,0.000761674,0.0004623726,0.00007490599,0.00005373682,0.0001628722,0.0002564426,0.00008413351],"category_scores_gemma":[0.1589703,0.0001339233,0.00005667039,0.001678902,0.0003242443,0.00006100571,0.0002359416,0.001035627,9.801048e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006101056,"about_ca_system_score_gemma":0.0003221072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007002624,"about_ca_topic_score_gemma":0.0003370565,"domain_scores_codex":[0.9967397,0.0007471804,0.0007226653,0.0004172269,0.001012161,0.0003610394],"domain_scores_gemma":[0.9160858,0.08302428,0.0002026906,0.000169605,0.000437967,0.00007960681],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006667163,0.0007893679,0.6503866,0.006473866,0.0009082356,0.00004170429,0.002792825,0.0001981486,0.000232579,0.1036119,0.2256531,0.008244959],"study_design_scores_gemma":[0.001744735,0.0007758579,0.215375,0.003458828,0.0006210881,0.00000213155,0.0004023926,0.01527536,0.0004458637,0.751992,0.00942686,0.0004798931],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3835036,0.01239589,0.312332,0.003593179,0.2438512,0.02372312,0.00792477,0.0002143262,0.01246187],"genre_scores_gemma":[0.8930114,0.00510204,0.06511939,0.00001736018,0.03450119,0.0007328698,0.0002660931,0.0001349631,0.001114724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6483801,"threshold_uncertainty_score":0.8481141,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2056592727","doi":"10.1198/016214508000000751","title":"Functional Additive Models","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":245,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Functional principal component analysis; Functional data analysis; Additive model; Mathematics; Linear form; Linear model; Principal component regression; Regression analysis; Principal component analysis; Regression; Proper linear model; Generalized additive model; Linear regression; Covariance; Computer science; Bayesian multivariate linear regression; Econometrics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.08664755365517686,"gpt":0.3459915902536139,"spread":0.2593440365984371,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006552323,0.00009571287,0.0003479905,0.00004024492,0.0001462016,0.00001465009,0.0001510995,0.0000308298,0.000181303],"category_scores_gemma":[0.01165916,0.00006026649,0.0001180374,0.0002222046,0.000176841,0.00009031836,0.00003622568,0.0003249109,0.0000126496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003135162,"about_ca_system_score_gemma":0.000136157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001712231,"about_ca_topic_score_gemma":0.000001770065,"domain_scores_codex":[0.9980832,0.0004031917,0.0004830705,0.00008775392,0.0007586941,0.0001841304],"domain_scores_gemma":[0.9920375,0.005951316,0.001302812,0.0001038158,0.0005126277,0.00009193591],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002130266,0.000309104,0.007537719,0.00001027902,0.0002762958,0.00003258171,0.0003710169,0.0000985596,0.0002367935,0.6958038,0.2683633,0.02674757],"study_design_scores_gemma":[0.0002997206,0.0002080468,0.1683401,0.00001889935,0.00009065469,0.00007585658,0.0000862137,0.00221056,0.0001072121,0.827949,0.0005130687,0.0001005848],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07092641,0.000007985524,0.9255672,0.001004627,0.0003384103,0.00006662629,0.0001736085,0.00001089655,0.001904214],"genre_scores_gemma":[0.6849099,0.00003211922,0.3136577,0.0004727307,0.0002974232,0.000002968244,0.000001532112,0.00001350699,0.0006121045],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6139835,"threshold_uncertainty_score":0.9966661,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W641186146","doi":"10.1007/978-0-387-71393-9","title":"Correlated Data Analysis: Modeling, Analytics, and Applications","year":2007,"lang":"en","type":"book","venue":"Springer series in statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":228,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Data analysis; Analytics; Data science; Computer science; Longitudinal data; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.1555129092817466,"gpt":0.3959536404387591,"spread":0.2404407311570125,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009870015,0.0004304994,0.0009997074,0.0005121813,0.00009405228,0.00009601914,0.0006652317,0.0004178075,0.0002350381],"category_scores_gemma":[0.00164211,0.0004449335,0.0000504433,0.000464788,0.0003581388,0.00008932052,0.0006463277,0.0007938692,0.00001870123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001371765,"about_ca_system_score_gemma":0.0002461198,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000599638,"about_ca_topic_score_gemma":0.0007810583,"domain_scores_codex":[0.9971781,0.00007195277,0.001074961,0.0008394314,0.0004242565,0.0004112435],"domain_scores_gemma":[0.9958045,0.001672963,0.0003651864,0.001728439,0.0002584488,0.0001703932],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002143887,0.00004753899,0.0002024066,0.0003507352,0.0005504194,0.0000431327,0.00009510799,0.00015413,2.948112e-7,0.9811725,0.005260746,0.01210157],"study_design_scores_gemma":[0.0001487715,0.00003419621,0.00008844257,0.0001070007,0.001897014,0.000005829762,0.00004535364,0.1768537,3.809482e-7,0.7991813,0.021168,0.0004699713],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000003701677,0.0004845223,0.9375818,0.00001080374,0.0001286975,0.0003953514,0.005171002,0.000068108,0.05615597],"genre_scores_gemma":[0.0001003131,0.0008710113,0.914921,0.00004311023,0.000157916,0.00002722454,0.001399324,0.00008260718,0.08239743],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1819912,"threshold_uncertainty_score":0.9998003,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109413631","doi":"10.1111/1467-9868.00337","title":"Powerful Goodness-of-fit Tests Based on the Likelihood Ratio","year":2002,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":225,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada; York University","keywords":"Goodness of fit; Anderson–Darling test; Omnibus test; Mathematics; Statistics; Construct (python library); Kolmogorov–Smirnov test; Statistical hypothesis testing; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1977756507372565,"gpt":0.3830860974785688,"spread":0.1853104467413123,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005400619,0.0004949347,0.001288083,0.0000492088,0.0003929343,0.00009377087,0.001081184,0.0003313436,0.005392392],"category_scores_gemma":[0.08894967,0.0002625496,0.0005440306,0.0004520147,0.001937447,0.00007934374,0.0002135275,0.001568732,0.00003619683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001385222,"about_ca_system_score_gemma":0.0001687387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002344439,"about_ca_topic_score_gemma":0.000005249359,"domain_scores_codex":[0.9917564,0.004001546,0.001811518,0.0004057192,0.001255143,0.0007696711],"domain_scores_gemma":[0.9220825,0.07520393,0.001049581,0.0006856075,0.000607112,0.0003712178],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003374758,0.0006241174,0.0003817177,0.0002034385,0.0002430657,0.00004004272,0.0004162362,0.0001491562,0.0002496752,0.9126838,0.07249606,0.01217518],"study_design_scores_gemma":[0.001053916,0.002042766,0.008771094,0.0002250995,0.000581542,0.00006615353,0.0005115986,0.05519581,0.0008677757,0.9280703,0.002162747,0.0004511789],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002038857,0.0000876566,0.9872038,0.006327608,0.0009858119,0.0003981774,0.0007239434,0.00002926887,0.002204894],"genre_scores_gemma":[0.1007008,0.00001933556,0.897025,0.001584987,0.0002627899,0.00001365408,0.000002159185,0.00005564993,0.0003356563],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09866191,"threshold_uncertainty_score":0.9999827,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142561902","doi":"10.1145/1273496.1273629","title":"Modeling changing dependency structure in multivariate time series","year":2007,"lang":"en","type":"article","venue":"","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":221,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Multivariate statistics; Covariance; Graphical model; Dependency (UML); Computer science; Multivariate normal distribution; Series (stratigraphy); Algorithm; Bayesian probability; Artificial intelligence; Data structure; Segmentation; Time series; Pattern recognition (psychology); Mathematics; Machine learning; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.06189849823550941,"gpt":0.3702354864073767,"spread":0.3083369881718673,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000558233,0.00009537902,0.0001574087,0.0001038503,0.00003947511,0.00001692935,0.00007961629,0.00006940858,0.0008229989],"category_scores_gemma":[0.0008675142,0.00007461951,0.00001878625,0.0001603669,0.00001206775,0.00007795162,0.00004757517,0.0001295472,0.00001585839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002224,"about_ca_system_score_gemma":0.00001138085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005843672,"about_ca_topic_score_gemma":0.0001001836,"domain_scores_codex":[0.9991784,0.00003236107,0.0002376401,0.000143018,0.0001189917,0.000289601],"domain_scores_gemma":[0.9993968,0.0003686959,0.00002446592,0.0001241776,0.00003812284,0.00004776314],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002923624,0.00002917012,0.0002368509,0.0000484644,0.00001179877,0.00002597597,0.001251355,0.0001988286,0.006311205,0.971846,0.000009839378,0.02000131],"study_design_scores_gemma":[0.0001483099,0.0000159817,0.0001901481,0.00003268576,0.000005031369,0.000005837702,0.0002433534,0.2308439,0.002478555,0.7659124,0.000005052088,0.0001187372],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1560875,0.00000880048,0.8368921,0.00002822721,0.00005335729,0.00008409181,0.000005496468,0.00005052409,0.006789924],"genre_scores_gemma":[0.4561493,7.29326e-7,0.5434669,0.00002734448,0.00002722571,8.757723e-7,6.705718e-7,0.000007945977,0.000319024],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3000619,"threshold_uncertainty_score":0.9011261,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161630302","doi":"10.1198/016214502753479347","title":"Length-Biased Sampling With Right Censoring","year":2002,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":217,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Censoring (clinical trials); Estimator; Mathematics; Truncation (statistics); Survival function; Statistics; Econometrics; Nonparametric statistics; Conditional probability distribution; Asymptotic distribution; Applied mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07582687449166572,"gpt":0.351289446542451,"spread":0.2754625720507853,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0007677748,0.0001222513,0.000415229,0.0000458683,0.0001291625,0.00005380591,0.0002014295,0.00003028734,0.0004345649],"category_scores_gemma":[0.01104729,0.00006960505,0.00008017856,0.0002757588,0.0001087573,0.00006874488,0.000027269,0.0003872164,0.00001142531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003044911,"about_ca_system_score_gemma":0.00002557107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001513505,"about_ca_topic_score_gemma":0.000003342915,"domain_scores_codex":[0.9980766,0.0003595197,0.0005126322,0.000107697,0.0006861605,0.0002574054],"domain_scores_gemma":[0.9914002,0.006581375,0.001447077,0.0001489983,0.0003150268,0.0001073432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003979756,0.001099291,0.06155996,0.0001226032,0.0008517717,0.0001344717,0.001555622,0.0001456427,0.002212174,0.6017892,0.04158413,0.2885472],"study_design_scores_gemma":[0.00262864,0.002136026,0.2293276,0.0005038832,0.001127243,0.0002443485,0.0007285275,0.01460485,0.001383291,0.7384549,0.00797899,0.0008816821],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.16381,0.00001724818,0.8324912,0.001354315,0.0002305915,0.0001029024,0.00006256396,0.00001938562,0.00191188],"genre_scores_gemma":[0.4932491,0.00001446854,0.5061297,0.0002027255,0.0001661391,0.000001559669,2.605726e-7,0.00001545768,0.0002205473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3294392,"threshold_uncertainty_score":0.9972831,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2072240935","doi":"10.1198/106186008x321068","title":"Adjusted Empirical Likelihood and its Properties","year":2008,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":207,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"ASL Environmental Sciences (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Empirical likelihood; Likelihood function; Restricted maximum likelihood; Mathematics; Maximization; Expectation–maximization algorithm; Likelihood principle; Statistics; Mathematical optimization; Econometrics; Maximum likelihood; Computer science; Quasi-maximum likelihood; Confidence interval","retraction":null,"screen_n_in":null,"score":{"opus":0.1560701957070837,"gpt":0.353252275367028,"spread":0.1971820796599443,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002870651,0.0001217793,0.0003186315,0.0000928977,0.0001431908,0.00002537334,0.0000658033,0.00006322092,0.0000301178],"category_scores_gemma":[0.001740959,0.00008362722,0.000036974,0.0001287168,0.0002164377,0.0000645746,0.00003588423,0.0002608035,0.000001249819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008237195,"about_ca_system_score_gemma":0.00008228958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001517929,"about_ca_topic_score_gemma":9.076595e-7,"domain_scores_codex":[0.998683,0.0001242187,0.0005310097,0.0001103375,0.0004017413,0.000149677],"domain_scores_gemma":[0.997012,0.001982647,0.000210445,0.00003571213,0.0005342379,0.0002249663],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002526931,0.0004053893,0.009742261,0.0002672649,0.000161111,0.0002714604,0.0008564467,0.00005926362,0.00008694334,0.9518283,0.005875467,0.03019341],"study_design_scores_gemma":[0.0005886345,0.0004237986,0.07890843,0.00005685447,0.00005116689,0.0008371325,0.0000298005,0.01574652,0.00001802974,0.9029619,0.0002543553,0.0001234136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4956645,0.0005471708,0.5028055,0.0006796296,0.00007915303,0.00006960484,0.00006733573,0.000009477792,0.0000776383],"genre_scores_gemma":[0.6463267,0.0001707286,0.3532394,0.0001738507,0.00006529036,9.370223e-7,0.000001336651,0.000007038806,0.00001478338],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1506621,"threshold_uncertainty_score":0.3410219,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2092392156","doi":"10.1214/009053604000000201","title":"Mean squared error of empirical predictor","year":2004,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":206,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"National Science Foundation","keywords":"Mean squared error; Estimator; Mixed model; Linear model; Generalized linear mixed model; Best linear unbiased prediction; Term (time); Restricted maximum likelihood; Random effects model","retraction":null,"screen_n_in":null,"score":{"opus":0.3889641003180567,"gpt":0.4860981274318291,"spread":0.09713402711377245,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006306945,0.0001269183,0.0003606073,0.00003881405,0.00004557825,0.000007945286,0.0002848824,0.00005638854,0.0001793376],"category_scores_gemma":[0.005056721,0.00008292411,0.00005973781,0.0001497404,0.0003542757,0.00002452662,0.0000641888,0.0001312531,0.000009159289],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008558716,"about_ca_system_score_gemma":0.00009648158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004378191,"about_ca_topic_score_gemma":0.00001228058,"domain_scores_codex":[0.9985846,0.0001276961,0.0005580924,0.0001288497,0.0003843168,0.0002164887],"domain_scores_gemma":[0.9961218,0.002738691,0.0002838834,0.0003900712,0.0003829647,0.000082623],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000611973,0.0002010133,0.000160421,0.0001834945,0.00005290505,0.00000409613,0.001795963,0.0000211456,0.0002400607,0.9850392,0.008127712,0.004112828],"study_design_scores_gemma":[0.0003031158,0.0003576624,0.004035351,0.00008390325,0.00005272225,0.000002626378,0.0002363594,0.0004264091,0.005037254,0.9891338,0.0002356179,0.00009522727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09053833,0.00006605551,0.9045957,0.0009984706,0.0001032044,0.000216423,0.001725041,0.00002712339,0.001729648],"genre_scores_gemma":[0.4973734,0.00003174054,0.5022937,0.000175231,0.00003910809,0.00000522861,0.000005739316,0.00001616514,0.00005971853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.406835,"threshold_uncertainty_score":0.6053733,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2045551166","doi":"10.1016/s0047-259x(02)00025-8","title":"Nonparametric estimation of distributions with categorical and continuous data","year":2003,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":200,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of South Florida; Texas A and M University","keywords":"Mathematics; Estimator; Nonparametric statistics; Kernel density estimation; Kernel smoother; Kernel (algebra); Smoothing; Mean squared error; Rate of convergence; Statistics; Applied mathematics; Categorical variable; Kernel method; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.07962877485561147,"gpt":0.3902913782961905,"spread":0.3106626034405791,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001149645,0.00008720132,0.0005235,0.0002860412,0.00004095331,0.00002611582,0.000150142,0.00004398991,0.0000570575],"category_scores_gemma":[0.009307332,0.00005594198,0.0000678623,0.001227273,0.00006328138,0.0001146127,0.00002972409,0.0001393596,4.309367e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002053833,"about_ca_system_score_gemma":0.00005334967,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006536878,"about_ca_topic_score_gemma":0.000005995107,"domain_scores_codex":[0.9987427,0.0002184426,0.0005539925,0.000119429,0.0002617079,0.0001037218],"domain_scores_gemma":[0.9967508,0.001902918,0.0006285646,0.0002822849,0.000344957,0.00009043307],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002589741,0.00168292,0.03560166,0.0001738932,0.008214328,0.0001338042,0.0006122832,0.002445392,0.0009041835,0.897182,0.0004531971,0.05233734],"study_design_scores_gemma":[0.003251215,0.001006866,0.0980507,0.0001085254,0.0220341,0.0003010967,0.000506468,0.4899624,0.001768769,0.3821967,0.0002976363,0.0005155358],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1003037,0.00005897073,0.899348,0.0000414441,0.00001745286,0.00003964786,0.00004655019,0.000002731158,0.0001416058],"genre_scores_gemma":[0.5708525,0.00001227833,0.42911,0.000002394277,0.000005768126,3.252119e-7,0.000004680927,0.000002795835,0.000009221862],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5149853,"threshold_uncertainty_score":0.9990377,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3121962378","doi":"10.1016/j.jeconom.2006.07.015","title":"A consistent model specification test with mixed discrete and continuous data","year":2006,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":198,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; National Science Foundation","keywords":"Test statistic; Mathematics; Null distribution; Nonparametric statistics; Goldfeld–Quandt test; Estimator; Null (SQL); Kernel (algebra); Statistics; Kernel density estimation; Applied mathematics; Asymptotic distribution; Null hypothesis; Nonparametric regression; Kernel regression; Statistic; Specification; Statistical hypothesis testing; Z-test; Computer science; Data mining; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3725804557823318,"gpt":0.3412145933090986,"spread":0.0313658624732332,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007458819,0.0000883043,0.0003018987,0.000228253,0.00003513773,0.0000790262,0.0001944807,0.00003492543,0.00001872486],"category_scores_gemma":[0.003184592,0.00006208855,0.000023708,0.000252087,0.00007098152,0.0001632164,0.00005388779,0.0001263241,8.596281e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003411023,"about_ca_system_score_gemma":0.00004593981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000538533,"about_ca_topic_score_gemma":0.000006682908,"domain_scores_codex":[0.9990705,0.00002700207,0.0005245982,0.0001316754,0.0001324002,0.0001137859],"domain_scores_gemma":[0.9967947,0.002108344,0.0005576814,0.0002754015,0.0001841531,0.00007970772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001876454,0.001054493,0.07313979,0.0002671725,0.0002026709,0.00008596347,0.0001507309,0.0003246753,0.0004112705,0.8279517,0.02553137,0.07069246],"study_design_scores_gemma":[0.002798306,0.00124471,0.06300472,0.0001773296,0.0004476473,0.0005184861,0.0003847965,0.1764202,0.0003103672,0.75027,0.003855726,0.0005677031],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1229137,0.0003266326,0.8713081,0.0003389933,0.00007227041,0.0001036647,0.0001763691,0.000007079287,0.00475317],"genre_scores_gemma":[0.5067763,0.00006119224,0.4929476,0.00001740218,0.0000661575,5.939166e-7,0.000003540252,0.000008442047,0.0001187667],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3838626,"threshold_uncertainty_score":0.3812484,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2114563530","doi":"10.1023/a:1013916107446","title":"Bayesian Treed Models","year":2002,"lang":"en","type":"article","venue":"Machine Learning","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":184,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; University of Texas at Austin; University of Chicago; National Science Foundation","keywords":"Partition (number theory); Simple (philosophy); Computer science; Bayesian probability; Parametric statistics; Artificial neural network; Parametric model; Mathematics; Tree (set theory); Set (abstract data type); Algorithm; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1184072395273905,"gpt":0.3423309401831147,"spread":0.2239237006557242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000248045,0.0001060489,0.0001745489,0.00004088904,0.0001097405,0.00003061681,0.0001007145,0.0000440734,0.003052751],"category_scores_gemma":[0.001313519,0.00008810879,0.00004353854,0.0001021274,0.00002516547,0.00004818414,0.00003820131,0.0002633283,0.00006754662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000127976,"about_ca_system_score_gemma":0.00000230166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003408837,"about_ca_topic_score_gemma":0.000006663031,"domain_scores_codex":[0.999162,0.0001563325,0.0001769251,0.0001583534,0.0001438696,0.0002025131],"domain_scores_gemma":[0.9990478,0.0006519508,0.00005637268,0.0001467667,0.00002278004,0.00007433942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007556207,0.0000944123,0.001983815,0.00005375585,0.00002292194,0.00002115015,0.001077591,0.0007153359,0.0001924108,0.7499011,0.001531503,0.2443985],"study_design_scores_gemma":[0.0001384856,0.00004263429,0.00006342103,0.00001262474,0.000009234104,0.000004278733,0.0000159365,0.648652,0.00002167386,0.3494644,0.001487349,0.0000878927],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003192803,0.00009624543,0.8868608,0.000267501,0.00004458423,0.0000588677,0.000002962528,0.0001499663,0.1093263],"genre_scores_gemma":[0.6226776,0.00001073324,0.372422,0.00008846606,0.00005054062,0.000005444999,0.000001258863,0.00002127133,0.004722672],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6479367,"threshold_uncertainty_score":0.9978586,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080749331","doi":"10.1214/09-aos712","title":"Estimation for a partial-linear single-index model","year":2009,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":183,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China; Hong Kong Baptist University; Ministry of Education of the People's Republic of China; National Science Foundation","keywords":"Mathematics; Estimator; Asymptotic distribution; Single-index model; Applied mathematics; Nonparametric statistics; Linear model; Statistics; Delta method; Parametric statistics; Rate of convergence; Mathematical optimization; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.4180211576168986,"gpt":0.4749653535220209,"spread":0.05694419590512229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000596419,0.0001169508,0.0002461698,0.00002904493,0.00007992171,0.00001780305,0.0001686926,0.00004729475,0.00002251651],"category_scores_gemma":[0.005555209,0.00008224221,0.00004796331,0.00007938,0.0000885557,0.0000378014,0.0000166394,0.00007625295,0.000003795567],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006437449,"about_ca_system_score_gemma":0.00004017486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003790508,"about_ca_topic_score_gemma":0.000001268667,"domain_scores_codex":[0.9989835,0.00005595765,0.0004026396,0.0001239312,0.0002126272,0.0002213442],"domain_scores_gemma":[0.9966663,0.002487432,0.0002115028,0.0002740528,0.0003033835,0.00005728891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000702311,0.0001258267,0.00000213137,0.00005761257,0.00001346504,5.03851e-7,0.0002309406,0.002270371,0.0002736133,0.8751246,0.007676661,0.114154],"study_design_scores_gemma":[0.00009504268,0.0001741418,0.00003784412,0.00001916661,0.0000213093,5.376261e-7,0.00001231223,0.4819622,0.002152173,0.5154183,0.00005296653,0.00005394872],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002646697,0.0000176394,0.994711,0.001039802,0.00003725274,0.0002736683,0.0006054834,0.00002769825,0.0006407411],"genre_scores_gemma":[0.3087672,0.000010148,0.6907021,0.0003613984,0.00003494566,0.000009180199,0.000008803471,0.000009834731,0.00009645251],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4796919,"threshold_uncertainty_score":0.6650506,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147388240","doi":"10.1002/cjs.10046","title":"Estimation methods for time‐dependent AUC models with survival data","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":175,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Estimator; Covariate; Nonparametric statistics; Statistics; Receiver operating characteristic; Statistical inference; Asymptotic distribution; Mathematics; Inference; Econometrics; Gaussian; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.2761347095098711,"gpt":0.427944776573096,"spread":0.1518100670632249,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001854059,0.0001514183,0.0003899822,0.0001336401,0.000118233,0.00009789424,0.0004527578,0.00006354537,0.000127784],"category_scores_gemma":[0.005077964,0.0001210713,0.00002588133,0.0001039259,0.00007430401,0.0001934408,0.00001155145,0.0001957474,0.000003003164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001016387,"about_ca_system_score_gemma":0.001097742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001965869,"about_ca_topic_score_gemma":0.0007835352,"domain_scores_codex":[0.9985956,0.0001828446,0.000531415,0.0001640498,0.0002153652,0.0003107192],"domain_scores_gemma":[0.9957065,0.002527466,0.0003538707,0.0003730218,0.0005034615,0.0005356899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004568805,0.0000240729,0.000007863659,0.0000397654,0.00005125763,0.00005119715,0.0001594196,0.0005774086,0.00003010316,0.6231424,0.0112455,0.3646254],"study_design_scores_gemma":[0.0003591033,0.0003924749,0.00007785619,0.00005894222,0.0001335295,0.00005951074,0.00003368967,0.2927234,0.00004174727,0.7054003,0.0005899399,0.0001295629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009924803,0.00006230497,0.9964279,0.0002919216,0.0001884937,0.0001804983,0.001880423,0.000006462355,0.0008627378],"genre_scores_gemma":[0.007737006,0.000006425689,0.9918359,0.000110055,0.00009040558,0.000001444173,0.00004539084,0.00002072386,0.0001526303],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3644958,"threshold_uncertainty_score":0.6079164,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962877661","doi":"10.1002/cjs.11313","title":"Post‐selection inference for ‐penalized likelihood models","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":168,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Heart, Lung, and Blood Institute","keywords":"Lasso (programming language); Inference; Model selection; Selection (genetic algorithm); Logistic regression; Statistical inference; Statistics; Econometrics; Computer science; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1315714462399989,"gpt":0.3746781688314629,"spread":0.243106722591464,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009015446,0.0001439021,0.0003888989,0.0001353586,0.0004943318,0.000300702,0.000452807,0.00008539417,0.0002932293],"category_scores_gemma":[0.02190477,0.0001248875,0.00007794405,0.00003596,0.0001461921,0.0002012021,0.00001334095,0.0002277327,0.000004974544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001091838,"about_ca_system_score_gemma":0.0016163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001935448,"about_ca_topic_score_gemma":0.01431614,"domain_scores_codex":[0.9986036,0.00007449983,0.0006275169,0.0001240232,0.0002047315,0.0003655751],"domain_scores_gemma":[0.9950643,0.001595379,0.0008106253,0.0002724286,0.001627226,0.0006300925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000380899,0.0000165826,0.0005945899,0.00006786185,0.00004942161,0.00003640196,0.000236766,0.0000128676,0.0001116049,0.9467509,0.0103431,0.04174175],"study_design_scores_gemma":[0.0005910301,0.0003502273,0.001983525,0.00008772289,0.00008934175,0.00004265476,0.00005073125,0.009507819,0.0001404279,0.9853919,0.001607239,0.000157375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004382433,0.00003000285,0.9920011,0.000318081,0.0004868865,0.0001609222,0.001258684,0.000004045845,0.001357859],"genre_scores_gemma":[0.3175633,0.00001009382,0.6819974,0.0001007397,0.0001411137,0.000004067389,0.00000364233,0.00001899202,0.000160717],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3131808,"threshold_uncertainty_score":0.9863341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140303035","doi":"10.1016/s0022-1694(00)00270-5","title":"Bayesian change-point analysis in hydrometeorological time series. Part 1. The normal model revisited","year":2000,"lang":"en","type":"article","venue":"Journal of Hydrology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":166,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council; Hydro-Québec; Institut National de la Recherche Scientifique","funders":"","keywords":"Hydrometeorology; Bayesian probability; Bayesian inference; Inference; Gibbs sampling; Series (stratigraphy); Point estimation; Bayesian average; Bayesian statistics; Computer science; Applied mathematics; Mathematics; Statistics; Meteorology; Geology; Artificial intelligence; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.0562831747816166,"gpt":0.327230422625258,"spread":0.2709472478436414,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001977135,0.0001525592,0.0007337344,0.0002299349,0.00005698141,0.00001889147,0.0003216396,0.0001519698,0.006058379],"category_scores_gemma":[0.0007889858,0.0000893792,0.0002253557,0.0005737338,0.0001486635,0.0001287924,0.00004034185,0.0004960069,0.00003233777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003085198,"about_ca_system_score_gemma":0.00002682896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006040864,"about_ca_topic_score_gemma":0.00000935662,"domain_scores_codex":[0.9978435,0.0006125084,0.0008281856,0.0001578758,0.000227688,0.00033024],"domain_scores_gemma":[0.9983529,0.0008800609,0.0003161391,0.0002657422,0.00007479425,0.0001104043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.01333571,0.006661776,0.05316595,0.0004330081,0.01110739,0.007060147,0.01530418,0.1017726,0.004765599,0.3897687,0.03752872,0.3590962],"study_design_scores_gemma":[0.0006263096,0.000968128,0.003450104,0.00002542131,0.0006872359,0.0004374043,0.00001548784,0.4893925,0.00005223992,0.5029419,0.00120474,0.0001985752],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8802323,0.0003269227,0.0988482,0.008590224,0.00008837417,0.0003122502,0.00003311891,0.00003079106,0.01153786],"genre_scores_gemma":[0.9167801,0.0002069584,0.08083092,0.001522612,0.0002191412,0.00001118157,0.000002217512,0.00001502449,0.0004119136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3876199,"threshold_uncertainty_score":0.9948502,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2046113245","doi":"10.1002/cjs.5550350205","title":"Nonparametric estimation of copula functions for dependence modelling","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Iowa State University","keywords":"Copula (linguistics); Estimator; Kernel smoother; Mathematics; Nonparametric statistics; Smoothing; Econometrics; Joint probability distribution; Statistics; Parametric statistics; Kernel method; Computer science; Artificial intelligence; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.1481917443454699,"gpt":0.3613164904895311,"spread":0.2131247461440612,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001143958,0.00008847268,0.0002550539,0.000350522,0.00009229029,0.00002316976,0.0001306145,0.00006316817,0.00008054524],"category_scores_gemma":[0.007203643,0.00008378903,0.00004893887,0.0002623895,0.00008536138,0.0000586881,0.000003660892,0.000154219,0.000001907649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001034056,"about_ca_system_score_gemma":0.0005918656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006162726,"about_ca_topic_score_gemma":0.001843569,"domain_scores_codex":[0.9987764,0.00002871192,0.0006846649,0.00007537246,0.0001927915,0.0002420986],"domain_scores_gemma":[0.9947494,0.003567956,0.0004369942,0.000107424,0.0007660704,0.0003721995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004436573,0.00003665382,0.0005646533,0.0002184222,0.00005330117,0.00004769777,0.0003090166,0.01416755,0.00004124368,0.8838083,0.004853813,0.09585496],"study_design_scores_gemma":[0.0003526967,0.000321902,0.0006773074,0.0001175079,0.0001442081,0.00006127384,0.0001927501,0.2101814,0.0002904242,0.787096,0.0004302752,0.0001342286],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007611195,0.00007113052,0.9909383,0.00002058772,0.000347928,0.0001178231,0.0005735465,0.000002612631,0.0003168759],"genre_scores_gemma":[0.3667031,0.000003639181,0.6331857,0.00001357136,0.00003707637,7.52236e-7,0.000003321306,0.000009123955,0.0000437526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3590919,"threshold_uncertainty_score":0.8623953,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2066764941","doi":"10.1111/j.1467-9892.2004.01885.x","title":"Analysis of low count time series data by poisson autoregression","year":2004,"lang":"en","type":"article","venue":"Journal of Time Series Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":164,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Autoregressive model; Count data; Poisson distribution; Statistics; Series (stratigraphy); Econometrics; Data set; Overdispersion; Poisson regression; Information Criteria; Goodness of fit; Fisher information; Time series; Applied mathematics; Model selection","retraction":null,"screen_n_in":null,"score":{"opus":0.03424564850259719,"gpt":0.3489611884951787,"spread":0.3147155399925815,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001472546,0.0002413407,0.001602273,0.0007297965,0.0001013153,0.00008454311,0.0007433531,0.0001228297,0.003436997],"category_scores_gemma":[0.001942559,0.0001735386,0.0005860126,0.002697981,0.0001768752,0.0005909534,0.0001884944,0.0002221783,0.00001858335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009833775,"about_ca_system_score_gemma":0.0001201264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008964608,"about_ca_topic_score_gemma":0.00003246258,"domain_scores_codex":[0.9971617,0.0002030832,0.001277245,0.0002732091,0.0008312695,0.0002535138],"domain_scores_gemma":[0.996267,0.0005348734,0.001519428,0.0008894334,0.0006086289,0.0001806545],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.006259523,0.008123367,0.05111809,0.001958262,0.3979,0.0008943638,0.00749934,0.04096275,0.1700571,0.05719225,0.2204222,0.03761273],"study_design_scores_gemma":[0.005713026,0.00574298,0.04625364,0.002111373,0.4062322,0.0002600025,0.002885919,0.2007306,0.0614205,0.247406,0.01710204,0.004141756],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3862855,0.001502049,0.6022328,0.003918394,0.0002399342,0.0002808599,0.003925682,0.00008694745,0.001527838],"genre_scores_gemma":[0.1694435,0.0008211934,0.8227556,0.0001383088,0.0002448247,0.000003195101,0.0004852185,0.0000785309,0.006029598],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2205229,"threshold_uncertainty_score":0.997474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2903456956","doi":"10.1016/j.jmva.2018.11.007","title":"Recent advances in functional data analysis and high-dimensional statistics","year":2018,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":159,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"European Regional Development Fund; Natural Sciences and Engineering Research Council of Canada; European Commission; Xunta de Galicia; Ministerio de Economía y Competitividad; Canada Research Chairs; Centro Singular de Investigación de Galicia; Western Canada Research Grid","keywords":"Mathematics; Functional data analysis; Multivariate statistics; Statistics; Field (mathematics); Multivariate analysis; Econometrics; Pure mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1045196629940823,"gpt":0.4110483683305718,"spread":0.3065287053364896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002009559,0.0001538673,0.0007753481,0.0009684743,0.00007949778,0.00004531691,0.0002510908,0.00006641772,0.001306648],"category_scores_gemma":[0.004460324,0.0001139228,0.0001066659,0.002233955,0.0001341239,0.0002676848,0.0001475658,0.0002267361,0.00000371144],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000488508,"about_ca_system_score_gemma":0.00007591324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009315574,"about_ca_topic_score_gemma":0.000717894,"domain_scores_codex":[0.9976943,0.0003322041,0.0009289287,0.0002955233,0.0005524067,0.000196693],"domain_scores_gemma":[0.9958153,0.002225987,0.000678273,0.0004011961,0.0007360201,0.000143188],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001226039,0.001428789,0.1298133,0.00008456684,0.02716429,0.00019571,0.0006047663,0.003303556,0.000862626,0.1429429,0.00270306,0.6896704],"study_design_scores_gemma":[0.001309373,0.0002609392,0.4321789,0.00003971676,0.01605394,0.00001366067,0.00008821771,0.3339559,0.0000976757,0.2133638,0.002327375,0.0003104379],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03206994,0.0005414193,0.9666618,0.0001859192,0.0001476593,0.00004083199,0.000271374,0.000005027889,0.00007606616],"genre_scores_gemma":[0.2189127,0.000946914,0.7797949,0.00007008325,0.0001738885,8.4873e-7,0.00004818435,0.000008736329,0.00004369023],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.68936,"threshold_uncertainty_score":0.9996063,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1977586926","doi":"10.1191/0962280202sm289ra","title":"Analysis of data with excess zeros","year":2002,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":156,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Biometrics; Wilcoxon signed-rank test; Econometrics; Statistics; Statistical hypothesis testing; Statistical power; Test (biology); Statistical model; Computer science; Data set; Statistical analysis; Mathematics; Artificial intelligence; Mann–Whitney U test","retraction":null,"screen_n_in":null,"score":{"opus":0.640358640075248,"gpt":0.6721812143614034,"spread":0.03182257428615543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02570654,0.0001921175,0.001058953,0.000747501,0.00008296291,0.00003922754,0.001620972,0.0002278896,0.02637614],"category_scores_gemma":[0.1994536,0.0001327116,0.0000472076,0.004037904,0.001818763,0.00009033894,0.0007456067,0.001442422,0.00001929496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000569963,"about_ca_system_score_gemma":0.0001498989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000207007,"about_ca_topic_score_gemma":0.0001047144,"domain_scores_codex":[0.9872776,0.006687917,0.001020382,0.0008192266,0.00334133,0.0008535431],"domain_scores_gemma":[0.8879992,0.109448,0.0001019424,0.001440203,0.0003971854,0.0006135082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005446528,0.0003735489,0.001261994,0.000147192,0.0002099452,0.0001454651,0.0001405579,6.857373e-7,0.00003823641,0.3914808,0.001270425,0.6048767],"study_design_scores_gemma":[0.0007166402,0.0004279678,0.008828228,0.0002150507,0.0003467064,0.000007050845,0.0002282455,0.4091017,0.0001284525,0.5784771,0.001263225,0.0002596429],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00122308,0.0001158153,0.9867842,0.000521398,0.00004171276,0.0002556934,0.0003775363,0.00002234611,0.01065824],"genre_scores_gemma":[0.02918995,0.0001207674,0.9703289,0.00006022192,0.00004273868,0.00004150592,0.00002356674,0.00002539905,0.0001669883],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6046171,"threshold_uncertainty_score":0.9745139,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"Canadian Institutes of Health Research; 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","retraction":null,"screen_n_in":null,"score":{"opus":0.2756750443033474,"gpt":0.4708426292700219,"spread":0.1951675849666745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005033984,0.0003621984,0.002621033,0.0001206777,0.00004920385,0.000008172225,0.0005708532,0.0001738443,0.0001088691],"category_scores_gemma":[0.06329907,0.0001648509,0.0001374415,0.0006725626,0.0003171012,0.00002620911,0.0001516632,0.0009437075,0.000003697644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009066478,"about_ca_system_score_gemma":0.0002494781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000157985,"about_ca_topic_score_gemma":0.00003279379,"domain_scores_codex":[0.9943098,0.002422311,0.002085901,0.000301069,0.0006214374,0.0002594253],"domain_scores_gemma":[0.9728578,0.02399315,0.002049703,0.0008162266,0.0002486029,0.00003445812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00001705498,0.0001364625,0.00006668438,0.3164381,0.00006626635,0.000008777268,0.000507909,0.00003818265,0.000002339761,0.2077515,0.01346192,0.4615048],"study_design_scores_gemma":[0.0004974267,0.0001307349,0.00003361755,0.7757645,0.001927356,0.00001310717,0.00002796713,0.03811998,0.000001052028,0.15772,0.02546721,0.000297046],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000001976419,0.6782525,0.3179381,0.00005339064,0.0001196164,0.001173251,0.002311844,0.000005204232,0.0001441491],"genre_scores_gemma":[0.000008119365,0.7926552,0.2069769,0.00006743996,0.00003109814,0.00003392589,0.0001809307,0.00002380623,0.00002253241],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4612077,"threshold_uncertainty_score":0.9445912,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115877181","doi":"10.1111/jtsa.12035","title":"Inference for single and multiple change‐points in time series","year":2013,"lang":"en","type":"article","venue":"Journal of Time Series Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":149,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Inference; Series (stratigraphy); Bayes' theorem; Time series; Multivariate statistics; Econometrics; Mathematics; Change detection; Time point; Statistics; Parametric statistics; Point estimation; Computer science; Point (geometry); Statistical inference; Data mining; Algorithm; Bayesian probability; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.06858558306853108,"gpt":0.3380387638894896,"spread":0.2694531808209585,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006015304,0.000141861,0.0006524223,0.0002962493,0.00005478912,0.0001208091,0.0001621874,0.00007024443,0.001196223],"category_scores_gemma":[0.003831333,0.0001081373,0.0001615206,0.0004403822,0.00008872843,0.0005396567,0.000062554,0.0001165144,0.00002138087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003167521,"about_ca_system_score_gemma":0.0000181872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005720595,"about_ca_topic_score_gemma":0.00003752714,"domain_scores_codex":[0.9987517,0.0001036756,0.0005909323,0.0001306972,0.0002161787,0.0002068311],"domain_scores_gemma":[0.9976041,0.001378079,0.0003969124,0.0001512635,0.0003564878,0.0001131849],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00349839,0.004392083,0.4698478,0.002467215,0.0147104,0.0002376608,0.02143574,0.0003426025,0.1489909,0.04812721,0.01943579,0.2665142],"study_design_scores_gemma":[0.002752444,0.003510331,0.0883958,0.0005552814,0.003744091,0.0001363263,0.001408532,0.04944556,0.01041918,0.8358464,0.002559847,0.001226247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.900429,0.0003057648,0.09453022,0.003116647,0.0001034917,0.0006342847,0.0001012105,0.00003208486,0.0007473255],"genre_scores_gemma":[0.2497055,0.0001100781,0.7481581,0.0001216168,0.0001465501,0.00002268532,0.000004808951,0.00002479501,0.001705893],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7877191,"threshold_uncertainty_score":0.9997168,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2092322472","doi":"10.1016/j.jclinepi.2009.03.012","title":"Absolute risk reductions and numbers needed to treat can be obtained from adjusted survival models for time-to-event outcomes","year":2009,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":146,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Clinical Evaluative Sciences","funders":"Canadian Institutes of Health Research; Institute for Clinical Evaluative Sciences","keywords":"Proportional hazards model; Covariate; Statistics; Hazard ratio; Population; Regression analysis; Absolute risk reduction; Medicine; Observational study; Event (particle physics); Regression; Survival analysis; Relative risk; Confidence interval; Cohort study; Cohort; Econometrics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.4477967427714711,"gpt":0.5484543726722505,"spread":0.1006576299007794,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01097168,0.0002189288,0.002614249,0.00009939868,0.00008843865,0.00001127209,0.0002343972,0.0002817944,0.0001271964],"category_scores_gemma":[0.2057178,0.0001533966,0.0004871985,0.000113053,0.0001063847,0.00005235786,0.00004582131,0.0005304485,0.000008312189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004517362,"about_ca_system_score_gemma":0.0001076282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003338582,"about_ca_topic_score_gemma":0.00004903688,"domain_scores_codex":[0.9930695,0.002668147,0.003382677,0.0003267386,0.0001567296,0.0003962148],"domain_scores_gemma":[0.9107417,0.08663867,0.001331735,0.0002738414,0.0003012063,0.0007127696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.005556339,0.001777341,0.01866135,0.00007581028,0.001445536,0.00004052261,0.001359198,0.006118659,0.0002689699,0.2580819,0.2546085,0.452006],"study_design_scores_gemma":[0.001540952,0.001777991,0.05469811,0.00005616601,0.0003617655,0.00001212368,0.0001447835,0.0126061,0.000007167613,0.9273843,0.001221031,0.0001895081],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3301158,0.00002886178,0.6099085,0.05836913,0.0005847344,0.0003878789,0.0002334073,0.0000199847,0.0003517173],"genre_scores_gemma":[0.07328715,0.0001113952,0.9171406,0.008126712,0.0006617226,0.00001176704,0.000005041295,0.00002264838,0.0006329648],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6693024,"threshold_uncertainty_score":0.8009728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1607848239","doi":"10.1214/ss/1009212815","title":"Bayesian backfitting (with comments and a rejoinder by the authors","year":2000,"lang":"en","type":"article","venue":"Statistical Science","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Additive model; Generalization; Generalized additive model; Mathematics; Nonparametric statistics; Bayesian probability; Computer science; Mathematical optimization; Modular design; Econometrics; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04640613272490587,"gpt":0.375692202853479,"spread":0.3292860701285731,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001238056,0.0001193811,0.000149182,0.00001817339,0.0004848282,0.0001612095,0.0002652302,0.0000283463,0.001383819],"category_scores_gemma":[0.001986077,0.00006389188,0.000008494185,0.0003174967,0.001589904,0.00008412459,0.00005652029,0.0001885256,0.00001955595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002565765,"about_ca_system_score_gemma":0.00005358681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006339871,"about_ca_topic_score_gemma":0.000007423481,"domain_scores_codex":[0.998423,0.0001247283,0.0002055673,0.0003432557,0.0004913377,0.0004121467],"domain_scores_gemma":[0.9969312,0.002509903,0.0000408604,0.0002253037,0.00005089162,0.0002418226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001945173,0.00004853464,0.000609613,0.00001706486,0.000005203963,0.000007440834,0.0003192836,4.678447e-7,0.0001326398,0.7113792,0.005982784,0.2814783],"study_design_scores_gemma":[0.0003963351,0.0002828231,0.01094293,0.00006651118,0.00003515307,0.00004507287,0.0002406451,0.02256358,0.0002324726,0.9608507,0.004045622,0.0002981878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02739989,0.00001568109,0.9440871,0.001811043,0.00004510521,0.0002434458,0.0001106614,0.00004330129,0.02624372],"genre_scores_gemma":[0.5027722,0.000004911684,0.4960437,0.0005607571,0.00001642628,0.00001262153,0.000001163846,0.00000955732,0.0005787312],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4753723,"threshold_uncertainty_score":0.9995291,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136261709","doi":"10.1111/j.1467-9868.2008.00656.x","title":"Modelling Sparse Generalized Longitudinal Observations with Latent Gaussian Processes","year":2008,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Science Foundation","keywords":"Functional principal component analysis; Principal component analysis; Generalized estimating equation; Mathematics; Inference; Functional data analysis; Parametric statistics; Gaussian process; Cluster analysis; Statistical inference; Computer science; Random effects model; Missing data; Generalized linear model; Statistics; Gaussian; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.3504371586506088,"gpt":0.3761591923422724,"spread":0.02572203369166359,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002086161,0.0004847981,0.001256524,0.00004372772,0.0007441121,0.00007812424,0.0006429437,0.000256339,0.0005918913],"category_scores_gemma":[0.01600233,0.0002809677,0.0002522151,0.0004936614,0.001840667,0.0001710068,0.0001835609,0.001135403,0.000006872661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001496339,"about_ca_system_score_gemma":0.0005789357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001048483,"about_ca_topic_score_gemma":0.00001927583,"domain_scores_codex":[0.9947243,0.001542676,0.00147734,0.000459071,0.00103337,0.0007632324],"domain_scores_gemma":[0.98201,0.01527562,0.0008406905,0.0004255025,0.0009657422,0.000482438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001163175,0.0005061105,0.004657548,0.0005334608,0.0006461854,0.0003325986,0.001029831,0.00945036,0.00007243033,0.9590984,0.02131586,0.001194028],"study_design_scores_gemma":[0.001694777,0.001399707,0.01865025,0.0002318021,0.0009454069,0.001102655,0.0002755957,0.0465169,0.0002723293,0.9262636,0.001945611,0.0007013816],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01819977,0.000117094,0.9787786,0.001444453,0.0004142925,0.0003103183,0.0005215189,0.00004072086,0.0001732448],"genre_scores_gemma":[0.03248054,0.0001072585,0.9662349,0.0003866631,0.000292831,0.00002303514,0.00001196138,0.00006186745,0.0004009571],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03706654,"threshold_uncertainty_score":0.9999642,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050509804","doi":"10.1006/jmva.2000.1959","title":"A Martingale Approach to the Copula-Graphic Estimator for the Survival Function under Dependent Censoring","year":2001,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":138,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Mathematics; Copula (linguistics); Estimator; Censoring (clinical trials); Kaplan–Meier estimator; Statistics; Econometrics; Applied mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1362396011753799,"gpt":0.3889001929710463,"spread":0.2526605917956664,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003277796,0.0001444786,0.0004315434,0.0002047421,0.0003136658,0.0001040994,0.000312663,0.00005454348,0.0000480785],"category_scores_gemma":[0.003126141,0.0000710016,0.0004179042,0.0008958767,0.00003019211,0.00006575923,0.00004638926,0.0002459996,0.000002914991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004615621,"about_ca_system_score_gemma":0.00003011704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008499463,"about_ca_topic_score_gemma":0.00003966517,"domain_scores_codex":[0.9981836,0.0002973641,0.0006478661,0.0001620357,0.0004656646,0.000243459],"domain_scores_gemma":[0.9951442,0.003541605,0.0004999129,0.0003035139,0.0004014322,0.0001093453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002561797,0.002010338,0.03008267,0.0001968347,0.02435322,0.00002661294,0.003117609,0.1994705,0.004486838,0.6485316,0.002501239,0.08266079],"study_design_scores_gemma":[0.002049485,0.0005078748,0.1196866,0.0000657812,0.01633329,0.00006051472,0.004477348,0.7250479,0.0002086568,0.1282307,0.002840663,0.0004911632],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02115905,0.00005963724,0.9770545,0.000901532,0.0002454497,0.0002142263,0.000009213465,0.000009808981,0.000346547],"genre_scores_gemma":[0.7422439,0.00001702992,0.2571418,0.0001468834,0.000249212,0.00001935945,0.000001035619,0.00001544872,0.0001653008],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7210849,"threshold_uncertainty_score":0.3742509,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115621436","doi":"10.1198/jasa.2010.tm09414","title":"Composite Likelihood Bayesian Information Criteria for Model Selection in High-Dimensional Data","year":2010,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":137,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Bayesian information criterion; Information Criteria; Model selection; Marginal likelihood; Sample size determination; Bayes' theorem; Bayes factor; Consistency (knowledge bases); Selection (genetic algorithm); Computer science; Mathematics; Statistics; Quasi-maximum likelihood; Likelihood principle; Bayesian probability; Maximum likelihood; Likelihood function; Machine learning; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03807718683195343,"gpt":0.3773151863653015,"spread":0.3392379995333481,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001977683,0.0001092363,0.0003564075,0.0000892302,0.00009390223,0.00007260472,0.0003249449,0.00005947766,0.00003130627],"category_scores_gemma":[0.01303105,0.00007804945,0.00005002781,0.0002275746,0.00006015179,0.0003544019,0.00008052748,0.0004567175,0.000002269089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001864755,"about_ca_system_score_gemma":0.0001590445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006958789,"about_ca_topic_score_gemma":0.00007614283,"domain_scores_codex":[0.9982237,0.0002264404,0.0007384816,0.0001065784,0.0004793558,0.0002254069],"domain_scores_gemma":[0.9948969,0.003056481,0.001335872,0.0001654841,0.0004612141,0.00008401897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001496676,0.001130322,0.0378847,0.0002091191,0.0003610988,0.000003978518,0.0007414419,0.0009410636,0.03791437,0.5962843,0.1014819,0.221551],"study_design_scores_gemma":[0.0005476099,0.0001452205,0.06298761,0.00002501645,0.00008506494,0.000008955782,0.00001879553,0.4502508,0.000146898,0.485564,0.0001182945,0.0001018032],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1540923,8.335415e-7,0.8435527,0.001269223,0.0003014844,0.0001578377,0.0005717843,0.000008121272,0.00004565733],"genre_scores_gemma":[0.4341778,0.000001071688,0.5654404,0.0002462434,0.00009845074,0.000003514584,0.00001598723,0.000006997755,0.00000959109],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4493097,"threshold_uncertainty_score":0.9952826,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1998634868","doi":"10.1175/jcli4291.1","title":"Changepoint Detection in Periodic and Autocorrelated Time Series","year":2007,"lang":"en","type":"article","venue":"Journal of Climate","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":135,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Autocorrelation; Series (stratigraphy); Time series; Independent and identically distributed random variables; Inference; Autoregressive model; Statistics; Econometrics; Mathematics; Computer science; Geology; Random variable; Artificial intelligence; Paleontology","retraction":null,"screen_n_in":null,"score":{"opus":0.03788044043801637,"gpt":0.3508679666126991,"spread":0.3129875261746827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001457254,0.00006237184,0.0001942117,0.0001093623,0.00003287321,0.00002205681,0.00003540503,0.00005181422,0.00009211332],"category_scores_gemma":[0.0009065606,0.00004712036,0.00002708423,0.00008885967,0.00003565181,0.00009409062,0.00001875207,0.0001800344,0.000008199977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002834931,"about_ca_system_score_gemma":0.00001054224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002037247,"about_ca_topic_score_gemma":0.00001208619,"domain_scores_codex":[0.9992266,0.00005066402,0.0004116809,0.00005000329,0.0001126796,0.0001483557],"domain_scores_gemma":[0.9992195,0.0003756166,0.0002300366,0.00004692998,0.00006807526,0.00005980229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00189781,0.0004067267,0.01316208,0.0006483607,0.00009824258,0.0009297479,0.006336196,0.000005926044,0.07149538,0.05106596,0.0001817283,0.8537719],"study_design_scores_gemma":[0.002969165,0.002659356,0.3341947,0.001077869,0.0001526923,0.002817259,0.001199212,0.005639469,0.02471475,0.6221321,0.001907606,0.0005359165],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9491033,0.00008065401,0.04818005,0.0001438319,0.0001797371,0.00009125908,0.000002634563,0.00001292608,0.002205627],"genre_scores_gemma":[0.8251888,0.0002793376,0.1742644,0.00005525571,0.000113875,0.000001581375,1.754132e-7,0.0000162503,0.00008040634],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.853236,"threshold_uncertainty_score":0.1921512,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100497684","doi":"10.1111/1468-2354.00096","title":"Efficient Estimation of Additive Partially Linear Models","year":2000,"lang":"en","type":"article","venue":"International Economic Review","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":133,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Heteroscedasticity; Estimator; Mathematics; Applied mathematics; Semiparametric model; Linear model; Additive model; Polynomial; Mathematical optimization; Econometrics; Statistics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.09756214790217706,"gpt":0.4020181656963173,"spread":0.3044560177941402,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000368184,0.00007441394,0.000244938,0.00002143537,0.00001215341,0.000006531969,0.0001502522,0.00002162481,0.009660563],"category_scores_gemma":[0.0004211124,0.00006467698,0.00009683107,0.00002021599,0.00003416857,0.00003646021,0.00001640599,0.00004655503,0.0002968844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005155048,"about_ca_system_score_gemma":0.00003816563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001008056,"about_ca_topic_score_gemma":0.00000121538,"domain_scores_codex":[0.9991311,0.00004985991,0.0005270186,0.0001310956,0.00009026173,0.00007070319],"domain_scores_gemma":[0.9991555,0.0004607454,0.000165455,0.0001302912,0.00005496663,0.00003303581],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000946365,0.00005373812,0.000001729058,0.0003777001,0.00003904384,7.359296e-7,0.00003194644,0.02845869,0.000001678776,0.5131782,0.001552489,0.4562945],"study_design_scores_gemma":[0.0001167244,0.00002210764,0.00003465725,0.001754592,0.00003462215,0.000004291821,0.000001496893,0.7965172,0.00006500186,0.1971949,0.004173473,0.00008092268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03586182,0.005772534,0.7262141,0.001997752,0.0007125869,0.001179698,0.0008567371,0.00008063242,0.2273241],"genre_scores_gemma":[0.2381919,0.02343779,0.7356789,0.0009486964,0.0002373962,0.0001379607,0.00006595922,0.00003403588,0.001267374],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7680585,"threshold_uncertainty_score":0.9912447,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2025670680","doi":"10.1080/03610910701569531","title":"Selection of Models of Lagged Identification Rates and Lagged Association Rates Using AIC and QAIC","year":2007,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"Akaike information criterion; Jackknife resampling; Statistics; Identification (biology); Econometrics; Association (psychology); Mathematics; Model selection; Selection (genetic algorithm); Lag; Computer science; Biology; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2966418884028973,"gpt":0.5151367272392993,"spread":0.218494838836402,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001599412,0.0001148087,0.000263703,0.0002447455,0.0001426016,0.00004086494,0.00007966041,0.0001014985,0.000004305337],"category_scores_gemma":[0.001886879,0.000127807,0.00001337252,0.0003574607,0.0001428016,0.0001781944,0.00007020467,0.0001359984,1.871359e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007566311,"about_ca_system_score_gemma":0.00003161969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009040287,"about_ca_topic_score_gemma":0.00009180438,"domain_scores_codex":[0.9983576,0.000333524,0.000827826,0.0001713235,0.000190367,0.0001193419],"domain_scores_gemma":[0.9922704,0.006276675,0.0006645174,0.0001907298,0.0005563124,0.00004141857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001338403,0.0004220936,0.06542693,0.000627919,0.00008957676,3.884952e-7,0.005293215,0.06918839,0.00960585,0.7416565,0.00002339177,0.1075319],"study_design_scores_gemma":[0.0003436251,0.00003129079,0.04870408,0.00005381585,0.00004074994,8.203506e-7,0.0002308175,0.6557173,0.0003513919,0.2944491,0.000002066812,0.00007493282],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3632999,0.0001130686,0.6362441,0.00002150689,0.00002089898,0.0001982367,0.00003857052,0.00001202797,0.00005169423],"genre_scores_gemma":[0.6687661,0.0001104622,0.3310552,0.000006854277,0.000004903238,0.000003661394,0.00003718654,0.000008537069,0.00000714311],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5865289,"threshold_uncertainty_score":0.5211816,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1988889362","doi":"10.2307/3315976","title":"Penalized regression with model‐based penalties","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"McGill University; University of British Columbia","funders":"","keywords":"Smoothing spline; Smoothing; Spline (mechanical); Nonparametric regression; Mathematics; Computation; Applied mathematics; Nonparametric statistics; Parametric statistics; Regression; Function (biology); Parametric equation; Algorithm; Mathematical optimization; Statistics; Spline interpolation; Geometry; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.09599628667049624,"gpt":0.3328125964276031,"spread":0.2368163097571068,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003621975,0.0001539441,0.0003377528,0.0001359648,0.0001374726,0.00006730245,0.0001997506,0.00005591555,0.003899996],"category_scores_gemma":[0.0009503131,0.0001044412,0.00003953788,0.0001173019,0.0001820744,0.00006381983,0.000002673508,0.0002600971,0.0000079288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000863313,"about_ca_system_score_gemma":0.001636227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004613093,"about_ca_topic_score_gemma":0.002648887,"domain_scores_codex":[0.9987589,0.0001020074,0.0004431728,0.0001025459,0.0002940481,0.0002993331],"domain_scores_gemma":[0.9978358,0.0007421075,0.000226591,0.0001701028,0.000374555,0.0006508123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005839247,0.0001049607,0.001375855,0.0003193766,0.0001377903,0.002087944,0.00146891,0.003845873,0.00006751133,0.709951,0.1124181,0.1676387],"study_design_scores_gemma":[0.001714882,0.0007052677,0.0005765474,0.000707093,0.0002019755,0.0002431249,0.0001442248,0.1358424,0.0001990619,0.8540906,0.005157119,0.0004176733],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01412361,0.00008012622,0.9810002,0.0002310256,0.00007253403,0.00008467437,0.0004173871,0.000006865736,0.003983562],"genre_scores_gemma":[0.1713806,0.0000143123,0.8274297,0.0002153914,0.00004826234,0.000001516411,0.00000361507,0.0000237721,0.0008828486],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.167221,"threshold_uncertainty_score":0.9970106,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2164380650","doi":"10.1016/j.jeconom.2005.06.002","title":"The power of bootstrap and asymptotic tests","year":2005,"lang":"en","type":"article","venue":"Journal of Econometrics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":123,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; McGill University","funders":"","keywords":"Mathematics; Null (SQL); Null distribution; Null hypothesis; Test statistic; Independence (probability theory); Statistical hypothesis testing; Statistics; Applied mathematics; Statistic; Asymptotic analysis; Asymptotic distribution; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2579446947124292,"gpt":0.373917331147668,"spread":0.1159726364352388,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001086984,0.00005767687,0.0002106272,0.0001862499,0.00003646244,0.00003161317,0.0001313306,0.00003305772,0.0000996974],"category_scores_gemma":[0.007536049,0.00003512515,0.00005352579,0.0002458275,0.00007107388,0.00007463794,0.00002333095,0.0001320746,0.00000246446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002298784,"about_ca_system_score_gemma":0.00003351112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.212955e-7,"about_ca_topic_score_gemma":8.44e-7,"domain_scores_codex":[0.9991797,0.00003578438,0.0005223454,0.00004662814,0.0001114044,0.0001042002],"domain_scores_gemma":[0.9944473,0.004764962,0.0004558252,0.0001044853,0.0001506697,0.00007677405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004259598,0.0002707512,0.02114292,0.00007551935,0.0001555439,0.000007538618,0.0003895706,0.00001403737,0.0001381358,0.6703725,0.003977139,0.3034138],"study_design_scores_gemma":[0.0009459977,0.001104314,0.1833028,0.0000850897,0.0001080149,0.0001866726,0.0003597434,0.0008032559,0.0007431817,0.7943953,0.01775554,0.0002100126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9451477,0.002257158,0.04026211,0.0009646182,0.0003072126,0.00008329556,0.00001073304,0.000004315258,0.01096287],"genre_scores_gemma":[0.8658096,0.0002796419,0.1337155,0.00003982052,0.00006480773,2.538485e-7,1.993637e-8,0.000005624579,0.00008472933],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3032038,"threshold_uncertainty_score":0.9021899,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155042384","doi":"","title":"Optimization with EM and expectation-conjugate-gradient","year":2003,"lang":"en","type":"article","venue":"","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Expectation–maximization algorithm; Convergence (economics); Conjugate gradient method; Latent variable; Mathematical optimization; Computer science; Maximization; Maximum likelihood; Nonlinear conjugate gradient method; Estimation theory; Conjugate residual method; Variable (mathematics); Applied mathematics; Latent variable model; Gradient method; Gradient descent; Mathematics; Algorithm; Artificial intelligence; Statistics; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.04663036366903674,"gpt":0.3180362623723024,"spread":0.2714058987032657,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000983612,0.0000567145,0.00008035407,0.00001844884,0.00003848047,0.00002511992,0.00001767125,0.00001816134,0.0006550984],"category_scores_gemma":[0.0005804524,0.00003767437,0.000005936943,0.00005963762,0.00002445097,0.00003346082,0.000003938773,0.00002781827,0.000003102779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006254555,"about_ca_system_score_gemma":0.000009934388,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000274078,"about_ca_topic_score_gemma":0.000004489341,"domain_scores_codex":[0.9996095,0.00004442014,0.00009464913,0.000101326,0.00007052531,0.00007960477],"domain_scores_gemma":[0.9994765,0.0003250093,0.00002885756,0.00007695488,0.00004690573,0.00004575993],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000004625819,0.00002323588,0.0004635252,0.00001236047,0.000006206133,0.000001227232,0.0003274177,0.00006402559,0.00001257636,0.9968924,0.000196047,0.001996389],"study_design_scores_gemma":[0.001539046,0.0006040046,0.00391419,0.00006980356,0.00008012903,0.00005309612,0.004281644,0.05504908,0.00533748,0.9280051,0.0004961542,0.0005702982],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03987622,0.000008786068,0.9232475,0.00002128471,0.0000169883,0.00008525489,0.000001011388,0.00002879633,0.03671411],"genre_scores_gemma":[0.1785492,0.000004257953,0.8209926,0.00004422933,0.000004143503,0.000009435896,5.557328e-7,0.000005937241,0.0003896779],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1386729,"threshold_uncertainty_score":0.7172867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2889434192","doi":"10.21037/atm.2018.07.38","title":"Overview of model validation for survival regression model with competing risks using melanoma study data","year":2018,"lang":"en","type":"editorial","venue":"Annals of Translational Medicine","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":121,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Calibration; Computer science; Regression; Regression analysis; Data mining; Nomogram; Receiver operating characteristic; Statistics; R package; Cross-validation; Event (particle physics); Machine learning; Mathematics; Medicine; Oncology","retraction":null,"screen_n_in":null,"score":{"opus":0.7880153235232045,"gpt":0.593017412929631,"spread":0.1949979105935735,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003724342,0.0003200314,0.001184856,0.0001455118,0.00008581558,0.00000761869,0.0005184798,0.0002662289,0.00004066409],"category_scores_gemma":[0.005514376,0.000218748,0.00006937921,0.0001570737,0.000223055,0.000128987,0.00006449847,0.0002660264,1.635495e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008812524,"about_ca_system_score_gemma":0.0004009581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001202829,"about_ca_topic_score_gemma":0.00002582165,"domain_scores_codex":[0.9962686,0.0002573007,0.001172384,0.0004953519,0.001595993,0.0002103622],"domain_scores_gemma":[0.9885522,0.007736504,0.001070336,0.0007053446,0.001856662,0.0000789783],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.009584595,0.004505464,0.0008052641,0.02605792,0.003638814,0.000009633668,0.00992352,0.02830118,0.001469179,0.1209475,0.7665987,0.02815828],"study_design_scores_gemma":[0.002058839,0.001110715,0.00003494097,0.004685031,0.0008791606,4.690366e-7,0.0001381864,0.8192873,0.0001643123,0.170813,0.0005505173,0.0002775587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002425039,0.0003460814,0.9670866,0.0002507657,0.02479876,0.0009225887,0.003962455,0.00001616646,0.000191623],"genre_scores_gemma":[0.02516945,0.0002186503,0.8709403,0.00001815845,0.1009954,0.0000287536,0.00248462,0.0001009579,0.00004370417],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7909861,"threshold_uncertainty_score":0.8920286,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02742268541216722,"gpt":0.353435936698333,"spread":0.3260132512861658,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008861207,0.0001271667,0.0005913113,0.0001040089,0.00001612346,0.000002594743,0.00005877559,0.00005569097,0.00008397221],"category_scores_gemma":[0.008720471,0.00009783931,0.00001152387,0.00009986409,0.0002297662,0.0000121323,0.00002498713,0.0001232209,0.000002835591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001852665,"about_ca_system_score_gemma":0.00002126596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004493865,"about_ca_topic_score_gemma":0.00001790194,"domain_scores_codex":[0.9986182,0.0001444203,0.000609855,0.0001527122,0.0003385367,0.0001362201],"domain_scores_gemma":[0.9930196,0.006402758,0.0002540029,0.0001610327,0.0001236622,0.00003897815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000885125,0.000290406,0.0007734295,0.001581208,0.00002849739,0.0000429096,0.0004401627,0.0001676482,0.009559726,0.9711611,0.001163371,0.01470309],"study_design_scores_gemma":[0.002063227,0.001234255,0.0235394,0.0009283473,0.00009947733,0.000002711936,0.00005838501,0.0674347,0.00944903,0.8950532,0.000003561841,0.0001336803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06432628,0.00003750505,0.9334464,0.00004496178,0.0001594762,0.0002757655,0.0001228565,0.000009127328,0.001577592],"genre_scores_gemma":[0.5221412,0.00001700869,0.4776697,0.0000133722,0.00003940848,0.000005633406,0.00001742279,0.00001109921,0.00008520627],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4578149,"threshold_uncertainty_score":0.9996295,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1967858306","doi":"10.1191/0962280203sm335ra","title":"Fitting competing risks with an assumed copula","year":2003,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":119,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Consejo Nacional de Ciencia y Tecnología","keywords":"Copula (linguistics); Identifiability; Econometrics; Marginal distribution; Parametric statistics; Bivariate analysis; Multivariate statistics; Computer science; Parametric model; Mathematics; Statistics; Random variable","retraction":null,"screen_n_in":null,"score":{"opus":0.5286679617407478,"gpt":0.6699203937793321,"spread":0.1412524320385843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05656061,0.0002915993,0.0007996347,0.0002955517,0.0003023609,0.0001127024,0.0006255316,0.0003378196,0.007873846],"category_scores_gemma":[0.4458943,0.0002142551,0.00003968214,0.001136582,0.001386048,0.00008110744,0.0001774503,0.003018359,0.00003683284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001525153,"about_ca_system_score_gemma":0.0006038545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002626796,"about_ca_topic_score_gemma":0.00009744769,"domain_scores_codex":[0.9697017,0.02361649,0.001053344,0.0008835181,0.003196865,0.001548048],"domain_scores_gemma":[0.8611915,0.1361037,0.0001141861,0.0006981274,0.000515983,0.001376526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007908092,0.0002474303,0.001698433,0.0001267277,0.00001319625,0.0003021293,0.0001633256,5.838345e-7,0.00006477842,0.6697829,0.0001455538,0.3273758],"study_design_scores_gemma":[0.001056184,0.0007802604,0.004097033,0.0004014154,0.00001762162,0.00005149884,0.001085058,0.01868558,0.0004502991,0.9713578,0.001680021,0.0003371878],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008326338,0.00005652017,0.9584727,0.0002708751,0.0001285632,0.0004455917,0.00002742499,0.00006844218,0.0322035],"genre_scores_gemma":[0.05020194,0.00002158274,0.9492766,0.0001352052,0.00008974833,0.0001194445,0.00000594543,0.00005964736,0.00008989547],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3893337,"threshold_uncertainty_score":0.9992817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}