{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":71,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":71,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"d5798dda5751","filters":{"venue":"The Annals of Applied Statistics"}},"results":[{"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","authors":[],"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":"W1971541813","doi":"10.1214/10-aoas442","title":"Forecasting emergency medical service call arrival rates","year":2011,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Queueing theory; Context (archaeology); Exponential smoothing; Smoothing; Covariate; Econometrics; Mathematics; Machine learning; Geography","authors":[{"name":"David S. Matteson","is_ca":false},{"name":"Mathew W. McLean","is_ca":false},{"name":"Dawn B. Woodard","is_ca":false},{"name":"Shane G. Henderson","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5015733237736453,"gpt":0.4569802608908218,"spread":0.0445930628828235,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002878391,0.000144435,0.0002572791,0.00007569126,0.0002079507,0.00002588437,0.001454028,0.00008143521,0.001713155],"category_scores_gemma":[0.001476669,0.00008965704,0.00005692841,0.0006778354,0.00018443,0.00004371162,0.0002838196,0.0001960883,0.0001379017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003451158,"about_ca_system_score_gemma":0.00007572852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001623207,"about_ca_topic_score_gemma":0.0001369384,"domain_scores_codex":[0.9973445,0.00005362572,0.0008742545,0.0002823714,0.001153118,0.000292107],"domain_scores_gemma":[0.9970898,0.000919985,0.0004699781,0.0006920068,0.0006791198,0.000149102],"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":[0.0001244534,0.0001755315,0.0004597702,0.00002893434,0.00004374458,0.000006639461,0.003784192,0.00005717115,0.0002761819,0.6745632,0.2045794,0.1159008],"study_design_scores_gemma":[0.00009838709,0.0000666132,0.001801888,0.00001528653,0.00001646958,0.00000707596,0.000423988,0.03585814,0.004224981,0.9490374,0.008280511,0.0001693013],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1511375,0.00009534632,0.670685,0.004761314,0.000361091,0.0009549002,0.0008335729,0.0002243564,0.1709469],"genre_scores_gemma":[0.9273255,0.00005901998,0.07139488,0.0007973851,0.00009388626,0.00004509458,0.00001483779,0.0000206884,0.0002487215],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.776188,"threshold_uncertainty_score":0.9991994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098683668","doi":"10.1214/08-aoas222","title":"Handbook for the GREAT08 Challenge: An image analysis competition for cosmological lensing","year":2009,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Galaxies: Formation, Evolution, Phenomena","field":"Physics and Astronomy","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 Victoria; University of British Columbia","funders":"Science and Technology Facilities Council; European Commission; National Aeronautics and Space Administration; University College London; California Institute of Technology; Jet Propulsion Laboratory","keywords":"Weak gravitational lensing; Dark energy; Dark matter; Galaxy; Inference; Strong gravitational lensing; Cosmology; Gravitational lens; Physics; Data science; Astrophysics; Computer science; Theoretical physics; Astronomy; Artificial intelligence; Redshift","authors":[{"name":"Sarah Bridle","is_ca":false},{"name":"Mandeep Gill","is_ca":false},{"name":"Alan Heavens","is_ca":false},{"name":"Catherine Heymans","is_ca":true},{"name":"F. William High","is_ca":false},{"name":"Henk Hoekstra","is_ca":true},{"name":"Mike Jarvis","is_ca":false},{"name":"Donnacha Kirk","is_ca":false},{"name":"Thomas Kitching","is_ca":false},{"name":"Jean‐Paul Kneib","is_ca":false},{"name":"Konrad Kuijken","is_ca":false},{"name":"John Shawe‐Taylor","is_ca":false},{"name":"David Lagatutta","is_ca":false},{"name":"Rachel Mandelbaum","is_ca":false},{"name":"R. Massey","is_ca":false},{"name":"Y. Mellier","is_ca":false},{"name":"Baback Moghaddam","is_ca":false},{"name":"Y. Moudden","is_ca":false},{"name":"Reiko Nakajima","is_ca":false},{"name":"Stephane Paulin-Henriksson","is_ca":false},{"name":"Sandrine Pires","is_ca":false},{"name":"A. Rassat","is_ca":false},{"name":"A. Amara","is_ca":false},{"name":"Alexandre Réfrégier","is_ca":false},{"name":"Jason Rhodes","is_ca":false},{"name":"T. Schrabback","is_ca":false},{"name":"E. Semboloni","is_ca":false},{"name":"Marina Shmakova","is_ca":false},{"name":"Ludovic Van Waerbeke","is_ca":true},{"name":"D. K. Witherick","is_ca":false},{"name":"Lisa M Voigt","is_ca":false},{"name":"David Wittman","is_ca":false},{"name":"Douglas Applegate","is_ca":false},{"name":"S. T. Balan","is_ca":false},{"name":"Joel Bergé","is_ca":false},{"name":"G. M. Bernstein","is_ca":false},{"name":"Håkon Dahle","is_ca":false},{"name":"Thomas Erben","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05355674815407757,"gpt":0.3134809803572959,"spread":0.2599242322032183,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003950059,0.0001343111,0.0002448763,0.00004793079,0.0004044752,0.00004770325,0.0002024581,0.00002648744,0.00005243401],"category_scores_gemma":[0.00001145093,0.00008716427,0.0001091813,0.0001319341,0.0001405818,0.00007335292,0.00001586678,0.00006925328,0.000003947202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009614756,"about_ca_system_score_gemma":0.0000253283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001723866,"about_ca_topic_score_gemma":0.000008681221,"domain_scores_codex":[0.9991442,0.00002654872,0.0003064582,0.0001473167,0.0001423725,0.0002330906],"domain_scores_gemma":[0.9987215,0.0003963968,0.0002450106,0.0002978796,0.0002980164,0.00004117483],"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":[0.0002012381,0.0001731222,0.001777685,0.00001736699,0.0003687229,4.036947e-9,0.00147811,0.0009068912,0.0002308518,0.9880268,0.002361712,0.004457522],"study_design_scores_gemma":[0.0005521878,0.0003138708,0.2542897,0.000006164144,0.0005051474,1.631329e-7,0.0009796417,0.03183676,0.0007917721,0.7098748,0.000674189,0.0001755773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1229471,0.0000633166,0.873706,0.0008255875,0.0000309259,0.0008149372,0.001047242,0.00002358021,0.0005412739],"genre_scores_gemma":[0.9794814,0.00001602711,0.01958898,0.0000405308,0.000160228,0.00005978037,0.0006012557,0.000009407924,0.00004236837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8565343,"threshold_uncertainty_score":0.3554456,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2088906176","doi":"10.1214/13-aoas626","title":"Travel time estimation for ambulances using Bayesian data augmentation","year":2013,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":109,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Global Positioning System; Bayesian probability; Computer science; Estimation; Path (computing); Data mining; Statistics; Mathematics; Artificial intelligence; Engineering","authors":[{"name":"Bradford S. Westgate","is_ca":false},{"name":"Dawn B. Woodard","is_ca":false},{"name":"David S. Matteson","is_ca":false},{"name":"Shane G. Henderson","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.144214332618472,"gpt":0.3997035024737231,"spread":0.2554891698552512,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004718816,0.00005922241,0.00009775727,0.00003156291,0.0002988578,0.00005464441,0.0002203806,0.00003469992,0.00009942732],"category_scores_gemma":[0.00007312853,0.00005035216,0.00001112416,0.0001111309,0.0001196552,0.0001765738,0.000006788614,0.0000305193,0.0000125485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006523734,"about_ca_system_score_gemma":0.00007136088,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005746029,"about_ca_topic_score_gemma":0.00006144228,"domain_scores_codex":[0.9992973,0.00002852143,0.0002164894,0.0001153661,0.0002076906,0.0001346444],"domain_scores_gemma":[0.9991874,0.0002686128,0.0001916399,0.0001622457,0.0001557822,0.0000343881],"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":[0.0002402723,0.0001624666,0.0002056479,0.0001892579,0.0001469437,4.230237e-7,0.04280895,0.2643917,0.003571082,0.4875481,0.06404912,0.1366861],"study_design_scores_gemma":[0.0002808029,0.00002916332,0.004817868,0.00002046753,0.00005928511,9.208622e-8,0.003049316,0.9244984,0.0006221131,0.06597679,0.0005056415,0.0001400779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00559155,0.00001369819,0.99077,0.0006115843,0.00004869436,0.0005370291,0.0006644346,0.00002406498,0.001738983],"genre_scores_gemma":[0.6595069,0.0000430414,0.3383746,0.0002184231,0.00007354158,0.00002477561,0.001576303,0.00001144703,0.0001708818],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6601067,"threshold_uncertainty_score":0.2298603,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891725784","doi":"10.1214/17-aoas1119","title":"Topological data analysis of single-trial electroencephalographic signals","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; King Abdullah University of Science and Technology; McMaster University; University of Wisconsin-Madison; Emory University; National Institutes of Health; National Science Foundation","keywords":"Electroencephalography; Pattern recognition (psychology); Computer science; Resampling; Neurophysiology; Artificial intelligence; Speech recognition; Neuroscience; Psychology","authors":[{"name":"Yuan Wang","is_ca":false},{"name":"Hernando Ombao","is_ca":false},{"name":"Moo K. Chung","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1682789064168544,"gpt":0.3625785741721692,"spread":0.1942996677553148,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001188821,0.0001455097,0.0005690024,0.0005031321,0.0001161457,0.00004964102,0.003409816,0.00006995512,0.0002072312],"category_scores_gemma":[0.0004181811,0.00008853448,0.000122251,0.005667158,0.0008464017,0.000103799,0.000882316,0.0001107235,0.00001208983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003124325,"about_ca_system_score_gemma":0.00003270379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007282849,"about_ca_topic_score_gemma":0.00004973857,"domain_scores_codex":[0.9979789,0.0001051017,0.0005887466,0.0004669671,0.0005202341,0.0003400936],"domain_scores_gemma":[0.9963341,0.0009834708,0.000442112,0.001863021,0.0002976941,0.00007963047],"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":[0.00126203,0.0005938684,0.0001103495,0.000008388785,0.002037518,0.00000436428,0.0001993023,0.0001883339,0.002419479,0.9519293,0.005679729,0.03556736],"study_design_scores_gemma":[0.004089332,0.005247654,0.01197251,0.00000958598,0.003376559,0.00000255436,0.0001976486,0.08542255,0.01559513,0.8667529,0.006571977,0.0007615638],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03463269,0.0001030142,0.9616544,0.0006322789,0.00006646491,0.0001661692,0.001004822,0.00003567576,0.001704478],"genre_scores_gemma":[0.9605241,0.0001104286,0.03863885,0.0004542279,0.00007412501,0.000004218691,0.0001714752,0.000003210135,0.0000193243],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9258915,"threshold_uncertainty_score":0.6336344,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2790880830","doi":"10.1214/17-aoas1092","title":"Automated threshold selection for extreme value analysis via ordered goodness-of-fit tests with adjustment for false discovery rate","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":82,"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":"Generalized Pareto distribution; Goodness of fit; False discovery rate; Statistics; Extreme value theory; Sample size determination; Mathematics; Selection (genetic algorithm); Multiple comparisons problem; Threshold limit value; Computer science; Model selection; Artificial intelligence","authors":[{"name":"B.E. Bader","is_ca":true},{"name":"Jun Yan","is_ca":true},{"name":"Xuebin Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05727779193429081,"gpt":0.3207032615150507,"spread":0.2634254695807599,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005647261,0.000172326,0.0003927139,0.00007709506,0.0001998677,0.00001504671,0.0002327009,0.00007125011,0.0001307671],"category_scores_gemma":[0.00003945872,0.0001157858,0.0001007169,0.000764271,0.0004447011,0.00008427571,0.00005282109,0.00005235731,0.00001174737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002089619,"about_ca_system_score_gemma":0.00002259533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001841898,"about_ca_topic_score_gemma":0.001246607,"domain_scores_codex":[0.9988033,0.00003530612,0.0003666413,0.0002925993,0.0002107558,0.0002914343],"domain_scores_gemma":[0.9988506,0.0003336884,0.0003639667,0.0003126834,0.00008908597,0.00004992399],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.009142936,0.001700258,0.02065358,0.0002668282,0.009292597,0.000002040365,0.003152935,0.758346,0.09443482,0.05970369,0.03213503,0.01116931],"study_design_scores_gemma":[0.0008586931,0.0008759644,0.02814783,0.000007963316,0.002478769,7.848966e-7,0.00009530316,0.8889143,0.03281695,0.04505958,0.0004613322,0.0002824983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2961437,0.00002092673,0.7018404,0.0001923077,0.00003128553,0.0007131261,0.0004823867,0.00004735539,0.0005285402],"genre_scores_gemma":[0.9778388,0.0000166986,0.02143837,0.000231979,0.0000377295,0.0001071296,0.000112858,0.00001706837,0.0001994042],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6816951,"threshold_uncertainty_score":0.472161,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057931901","doi":"10.1214/13-aoas684","title":"Beta regression for time series analysis of bounded data, with application to Canada Google® Flu Trends","year":2014,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Bounded function; Autoregressive model; Mathematics; Econometrics; Statistics; Autoregressive integrated moving average; Regression analysis; Time series; Computer science","authors":[{"name":"Annamaria Guolo","is_ca":false},{"name":"Cristiano Varin","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1102783874309793,"gpt":0.4260513457302483,"spread":0.315772958299269,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001452133,0.0001724518,0.000616824,0.0002206737,0.0001804656,0.00004802284,0.001273742,0.00003164459,0.00003208237],"category_scores_gemma":[0.001097169,0.000103817,0.00003160731,0.001572036,0.0001974144,0.00008947631,0.0002006757,0.00007725266,0.000004691998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001958248,"about_ca_system_score_gemma":0.0001523039,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003887814,"about_ca_topic_score_gemma":0.04053688,"domain_scores_codex":[0.9972239,0.00005312095,0.0007394939,0.0004823553,0.00123718,0.0002639812],"domain_scores_gemma":[0.993551,0.0034653,0.0006522527,0.001444438,0.0007579629,0.0001290643],"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":[0.001689504,0.00008747917,0.0002206128,0.00006814502,0.0005326014,0.000001005041,0.0006066966,0.0301188,0.001800302,0.2213292,0.03027077,0.7132748],"study_design_scores_gemma":[0.001018011,0.0008197451,0.01472136,0.00006472851,0.001655466,0.000001647598,0.001282276,0.3332158,0.0251427,0.4515965,0.1695379,0.0009437572],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003132759,0.00001683618,0.9891651,0.0007094865,0.00003364999,0.0002461215,0.005546974,0.0000119691,0.001137118],"genre_scores_gemma":[0.7515092,0.000006294769,0.2468514,0.0002161142,0.0000593539,0.00005203658,0.0005470035,0.00002348016,0.000735034],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7483765,"threshold_uncertainty_score":0.9769709,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1970646576","doi":"10.1214/14-aoas727","title":"Effect of breastfeeding on gastrointestinal infection in infants: A targeted maximum likelihood approach for clustered longitudinal data","year":2014,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Université de Montréal","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Breastfeeding; Confounding; Breastfeeding promotion; Context (archaeology); Estimation; Duration (music); Intervention (counseling); Random effects model; Breast feeding","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.1072896563077069,"gpt":0.3946682202134613,"spread":0.2873785639057544,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003484109,0.0002391223,0.0006125345,0.0001230564,0.0000668092,0.00002324948,0.0004361695,0.00006136534,0.00001730773],"category_scores_gemma":[0.005100156,0.0001688103,0.00004735924,0.0002266332,0.0001757678,0.00004546948,0.0001624754,0.0002334081,0.000001828855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001212294,"about_ca_system_score_gemma":0.0000339146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005714077,"about_ca_topic_score_gemma":0.00001463616,"domain_scores_codex":[0.9980633,0.0002422349,0.0006641105,0.0003439709,0.0003149966,0.0003714472],"domain_scores_gemma":[0.9909316,0.007686737,0.0004669139,0.0006743555,0.0001695046,0.00007091898],"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":[0.003794481,0.0005378001,0.002019026,0.002685345,0.00009460497,0.000001654567,0.0002261452,0.000104747,0.001281222,0.6939924,0.002988183,0.2922744],"study_design_scores_gemma":[0.001530841,0.00222639,0.01130631,0.000306633,0.0001299269,0.00001241163,0.00002286439,0.1042493,0.003997759,0.8759704,0.00001699102,0.0002302146],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01013447,0.000004269722,0.9865514,0.00004187233,0.00004140917,0.0007329925,0.001131985,0.00002204691,0.001339567],"genre_scores_gemma":[0.3952544,0.000004968681,0.6044948,0.00002530918,0.00005663879,0.00004296166,0.00009801546,0.00002173627,0.00000124684],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3851199,"threshold_uncertainty_score":0.6883883,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3191733181","doi":"10.1214/21-aoas1501","title":"The ASA president’s task force statement on statistical significance and replicability","year":2021,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":41,"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":"Task force; Statement (logic); Task (project management); Statistical analysis; Statistics; Computer science; Econometrics; Natural language processing; Mathematics; Political science; Law; Management; Economics","authors":[{"name":"Yoav Benjamini","is_ca":false},{"name":"Richard D. De Veaux","is_ca":false},{"name":"Bradley Efron","is_ca":false},{"name":"Scott Evans","is_ca":false},{"name":"Mark E. Glickman","is_ca":false},{"name":"Barry I. Graubard","is_ca":false},{"name":"Xuming He","is_ca":false},{"name":"Xiao‐Li Meng","is_ca":false},{"name":"Nancy Reid","is_ca":true},{"name":"Stephen M. Stigler","is_ca":false},{"name":"Stephen B. Vardeman","is_ca":false},{"name":"Christopher K. Wikle","is_ca":false},{"name":"Tommy Wright","is_ca":false},{"name":"Linda J. Young","is_ca":false},{"name":"Karen Kafadar","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5158428041741353,"gpt":0.5546070747217429,"spread":0.03876427054760756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00665404,0.0002911123,0.0007043376,0.00002070479,0.0003717293,0.000111555,0.0004664016,0.0001051578,0.0001442966],"category_scores_gemma":[0.05931144,0.0001773197,0.00007224241,0.0001888588,0.001137249,0.00002358842,0.0002846397,0.0004574249,0.00001908618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002943506,"about_ca_system_score_gemma":0.0001794265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001599774,"about_ca_topic_score_gemma":0.0000253112,"domain_scores_codex":[0.9953939,0.0009812603,0.001585526,0.000621802,0.0008864367,0.0005310831],"domain_scores_gemma":[0.8735695,0.1239185,0.0005614384,0.001356998,0.0004141421,0.000179473],"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":[0.0006102726,0.0002042394,0.00001491223,0.0001843501,0.0001376023,0.00001253005,0.0002407169,0.00001912398,0.0004680371,0.9313173,0.0388591,0.02793179],"study_design_scores_gemma":[0.0004638285,0.0002302706,0.001610665,0.00003591525,0.0001092518,0.000002043827,0.0003857612,0.0004401128,0.008744556,0.9844792,0.003301378,0.0001970452],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01135682,0.0001752924,0.9679732,0.005667308,0.0003797172,0.001943719,0.005576773,0.00008641865,0.006840729],"genre_scores_gemma":[0.1861091,0.0009365461,0.8101794,0.001490584,0.0001946559,0.0002388644,0.00002425157,0.0000757114,0.0007508836],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1747523,"threshold_uncertainty_score":0.9486124,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962800545","doi":"10.1214/16-aoas993","title":"A continuous-time stochastic block model for basketball networks","year":2017,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Acadia University; University of Waterloo; Royal Bank of Canada","funders":"","keywords":"Basketball; Analytics; Computer science; Stochastic block model; Data science; Offensive; Block (permutation group theory); Cluster analysis; Machine learning; Artificial intelligence; Operations research; Engineering; Geography; Mathematics","authors":[{"name":"Xin Lü","is_ca":true},{"name":"Mu Zhu","is_ca":true},{"name":"Hugh Chipman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.09067351114725328,"gpt":0.287761093136061,"spread":0.1970875819888077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006676154,0.00014501,0.0004328253,0.00004756976,0.0003554074,0.0001062671,0.0005381711,0.00006722803,0.00007502492],"category_scores_gemma":[0.00008166794,0.0001298117,0.00008296264,0.00002938996,0.0001665494,0.00005105825,0.0000798601,0.0001039752,0.00005596156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000701026,"about_ca_system_score_gemma":0.00002061155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004084063,"about_ca_topic_score_gemma":0.0000123428,"domain_scores_codex":[0.9989059,0.000001482682,0.0005156162,0.0002220445,0.00004508911,0.0003098773],"domain_scores_gemma":[0.9981932,0.0001121208,0.000832207,0.0007012487,0.00009871164,0.00006253421],"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":[0.0001057235,0.00004653666,0.0001122074,0.00002500745,0.00008477979,3.884325e-7,0.000211497,0.309082,0.000004698845,0.6732333,0.0158649,0.001229031],"study_design_scores_gemma":[0.0002781279,0.0000379716,0.0009420338,0.000007614571,0.00001537243,3.123354e-7,0.00000937253,0.8553733,0.000009100733,0.1406604,0.002518747,0.0001476403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01029217,0.0002228426,0.9735798,0.0005877569,0.0001457972,0.0004705341,0.002388807,0.00001572994,0.01229652],"genre_scores_gemma":[0.9932975,0.0001583035,0.003625304,0.0004195497,0.0001310719,0.00003308244,0.00003746691,0.00002890349,0.0022688],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9830053,"threshold_uncertainty_score":0.5293565,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2076514995","doi":"10.1214/12-aoas584","title":"Robust VIF regression with application to variable selection in large data sets","year":2013,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal","funders":"","keywords":"Outlier; Robustness (evolution); Feature selection; Computer science; Estimator; Regression; Robust regression; Lasso (programming language); Covariate; Regression analysis; Variance (accounting); Variance inflation factor; Econometrics; Artificial intelligence; Machine learning; Statistics; Mathematics; Multicollinearity; Economics","authors":[{"name":"Debbie J. Dupuis","is_ca":true},{"name":"Maria‐Pia Victoria‐Feser","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2047160822476765,"gpt":0.4366883251623959,"spread":0.2319722429147194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008861735,0.0001639441,0.0003022608,0.00006191762,0.00009659199,0.00002395704,0.00038463,0.00006123923,0.00006978209],"category_scores_gemma":[0.0004094584,0.0001049293,0.000008420686,0.0003496121,0.00004919334,0.00009904345,0.0001703287,0.0001850617,0.00001617988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001506242,"about_ca_system_score_gemma":0.00004179322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007270177,"about_ca_topic_score_gemma":0.00008725478,"domain_scores_codex":[0.9985922,0.00006877191,0.0003907051,0.0003339628,0.000287321,0.0003270689],"domain_scores_gemma":[0.9978463,0.001019803,0.0002142138,0.0006266607,0.0002018383,0.00009119402],"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":[0.0001728842,0.0001908478,0.00001631392,0.0001186417,0.00002214335,6.22886e-7,0.0003153549,0.004030419,0.002155073,0.9487077,0.01476891,0.02950107],"study_design_scores_gemma":[0.0002854628,0.00008084995,0.0002857696,0.00005142215,0.00002278657,0.000001319244,0.0001485184,0.1509293,0.0007904661,0.8463922,0.0008640371,0.0001479074],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001410584,0.000008739557,0.9952713,0.0002452426,0.00001352432,0.0009509813,0.0006691201,0.00003077578,0.001399682],"genre_scores_gemma":[0.08274702,0.00001456471,0.9165591,0.0002914398,0.00002581072,0.0001519161,0.00009663204,0.00003089113,0.00008262488],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1468989,"threshold_uncertainty_score":0.4278891,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2767505813","doi":"10.1214/21-aoas1471","title":"Improving exoplanet detection power: Multivariate Gaussian process models for stellar activity","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Astrophysics Division; Pennsylvania Space Grant Consortium; Natural Sciences and Engineering Research Council of Canada; European Commission; National Aeronautics and Space Administration; University of Pennsylvania; Simons Foundation Autism Research Initiative; Pennsylvania State University; Simons Foundation; Institute for Computational and Data Sciences, Pennsylvania State University; Division of Mathematical Sciences; National Science Foundation","keywords":"Exoplanet; Radial velocity; Physics; Planet; Astrophysics; Astronomy; Astron; Gaussian process; Gaussian; Stars","authors":[{"name":"David Jones","is_ca":false},{"name":"David C. Stenning","is_ca":true},{"name":"Eric B. Ford","is_ca":false},{"name":"Robert L. Wolpert","is_ca":false},{"name":"Thomas J. Loredo","is_ca":false},{"name":"Christian Gilbertson","is_ca":false},{"name":"X. Dumusque","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05106795244628423,"gpt":0.325273856738226,"spread":0.2742059042919418,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002851996,0.0001644246,0.0002667976,0.00007178292,0.0003995043,0.00002490374,0.000316632,0.0000537856,0.000303743],"category_scores_gemma":[0.00005186647,0.0001418242,0.00005569449,0.0002925523,0.00006343035,0.00004433297,0.00008906421,0.0002524073,0.000001408565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003304495,"about_ca_system_score_gemma":0.00006019031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000865109,"about_ca_topic_score_gemma":0.00000718726,"domain_scores_codex":[0.9988829,0.00001443456,0.0002454532,0.0002526723,0.0003097966,0.0002947194],"domain_scores_gemma":[0.9988648,0.0003259315,0.0003602583,0.0003101082,0.00008621602,0.00005265048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003056379,0.0006047696,0.00001469649,0.0009940441,0.0005992042,0.000004980574,0.002579284,0.04972141,0.8820353,0.01799382,0.001117272,0.04127887],"study_design_scores_gemma":[0.0005378397,0.0001251458,0.00002164116,0.000002979353,0.0001855153,0.000004430402,0.001919425,0.09982383,0.8625377,0.03419371,0.00039395,0.0002538324],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2502298,0.0001749747,0.7337,0.000108876,0.00008098932,0.0004855993,0.004407696,0.0001200388,0.010692],"genre_scores_gemma":[0.9976347,0.00001586091,0.001822623,0.00007655605,0.00004170834,0.0001221347,0.00007425691,0.00003002125,0.0001821344],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7474049,"threshold_uncertainty_score":0.5783425,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2990681736","doi":"10.1214/19-aoas1269","title":"Robust elastic net estimators for variable selection and identification of proteomic biomarkers","year":2019,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"University of British Columbia; Genome Canada","keywords":"Estimator; Outlier; Robustness (evolution); Feature selection; Computer science; Robust statistics; Robust regression; Elastic net regularization; Lasso (programming language); Mathematics; Statistics; Artificial intelligence; Biology","authors":[{"name":"Gabriela V. Cohen Freue","is_ca":true},{"name":"David Kepplinger","is_ca":true},{"name":"Matías Salibián‐Barrera","is_ca":true},{"name":"Ezequiel Smucler","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1225059196152924,"gpt":0.3935837860991451,"spread":0.2710778664838527,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008671258,0.0001222386,0.0003004057,0.00005113397,0.00006426391,0.00001333377,0.0001092446,0.00005580644,0.00001759176],"category_scores_gemma":[0.000730666,0.00009506667,0.0000233024,0.0001298923,0.000101573,0.00003910473,0.00002952376,0.0000705399,0.000001779658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000803827,"about_ca_system_score_gemma":0.00004030808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006752826,"about_ca_topic_score_gemma":0.00000129936,"domain_scores_codex":[0.9989305,0.00003842692,0.0005013347,0.0001896188,0.0001590328,0.0001811298],"domain_scores_gemma":[0.9971091,0.001969635,0.0004434448,0.0002099035,0.0002267146,0.00004117721],"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":[0.0002701027,0.00005218511,0.00001404246,0.0006856208,0.00007406486,4.371392e-8,0.0001366037,0.00431983,0.03362146,0.9560997,0.0006038911,0.004122489],"study_design_scores_gemma":[0.0002828576,0.0001142251,0.0001715417,0.00002858722,0.00007669203,8.95147e-7,0.0000599734,0.1420996,0.01659783,0.8404275,0.00004808649,0.00009219443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02427754,0.00001184162,0.9737098,0.00003479254,0.00005203757,0.001099703,0.0005727901,0.000016107,0.0002254268],"genre_scores_gemma":[0.1957454,0.00001243315,0.8040538,0.00001710391,0.00001207554,0.00005461955,0.00001725566,0.00002182918,0.00006540704],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1714679,"threshold_uncertainty_score":0.3876706,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148429219","doi":"10.1214/10-aoas378","title":"Detecting multiple authorship of United States Supreme Court legal decisions using function words","year":2011,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Supreme court; Style (visual arts); Function (biology); Legal writing; Writing style; Statistical analysis","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.2448864315332253,"gpt":0.347889792177648,"spread":0.1030033606444227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001597384,0.0001464091,0.000225333,0.0001780299,0.0002397907,0.00003781238,0.0005782854,0.00007915979,0.00002569788],"category_scores_gemma":[0.0004497444,0.0001176751,0.00004922659,0.0007180744,0.000137919,0.000123432,0.0001866112,0.0002411137,0.000007192675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001042418,"about_ca_system_score_gemma":0.00007469267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002269908,"about_ca_topic_score_gemma":0.0000271622,"domain_scores_codex":[0.9984819,0.0001352508,0.000512569,0.0002114445,0.0003552064,0.0003036731],"domain_scores_gemma":[0.9975441,0.001074565,0.0004155559,0.0004674293,0.0004032359,0.00009510239],"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":[0.0006720368,0.0001814138,0.0006507174,0.00006238949,0.0001641758,0.000005641329,0.0165386,0.009733577,0.008798529,0.9210965,0.0006005215,0.04149589],"study_design_scores_gemma":[0.0004153797,0.0002156012,0.003629248,0.00006710214,0.00007154745,0.00000518637,0.00147629,0.6351608,0.09820084,0.2595783,0.0008729588,0.0003068008],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1376094,0.00003082987,0.861544,0.00006308993,0.0001563047,0.0001529222,0.0001098097,0.00005291263,0.0002807587],"genre_scores_gemma":[0.8363841,0.00001700424,0.1633866,0.0001352786,0.00002110706,0.000003563279,0.00002683284,0.00001101431,0.00001451759],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6987748,"threshold_uncertainty_score":0.4798653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3018701121","doi":"10.1214/20-aoas1348","title":"Markov decision processes with dynamic transition probabilities: An analysis of shooting strategies in basketball","year":2020,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Basketball; Transition (genetics); Markov chain; Computer science; Machine learning; History; Chemistry","authors":[{"name":"Nathan Sandholtz","is_ca":true},{"name":"Luke Bornn","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05151780571094042,"gpt":0.2760733188156001,"spread":0.2245555131046597,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004134946,0.0001078784,0.0004409913,0.000172197,0.0000348981,0.00003304011,0.000182738,0.00003455995,0.0001135245],"category_scores_gemma":[0.00004099346,0.00008723066,0.00003649567,0.0008216609,0.00009456602,0.0001170887,0.00001343213,0.00007872879,0.000001685623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008865011,"about_ca_system_score_gemma":0.00006025638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001791674,"about_ca_topic_score_gemma":0.001048846,"domain_scores_codex":[0.9989456,0.000004960335,0.0006165774,0.0002133969,0.0000725295,0.0001469526],"domain_scores_gemma":[0.9991331,0.0001441274,0.0003870388,0.0001937819,0.000101722,0.00004027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007694686,0.0002163345,0.007874197,0.0008729061,0.0004029553,0.000002779726,0.01764596,0.6682478,0.0000318944,0.3004698,0.00005814095,0.003407813],"study_design_scores_gemma":[0.0003554625,0.0003448754,0.05997812,0.00004946327,0.0001186064,2.210317e-7,0.004876274,0.861473,0.0000952327,0.07233477,0.0001318999,0.0002420149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.813373,0.0001412915,0.1836371,0.0002608146,0.00000770827,0.0001866181,0.0009838883,0.00000808101,0.001401496],"genre_scores_gemma":[0.9937068,0.0003690247,0.00561576,0.0001859186,0.00000884256,0.000007877792,0.00009094072,0.00001109326,0.000003805524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.228135,"threshold_uncertainty_score":0.3557163,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2068388041","doi":"10.1214/09-aoas318","title":"Modeling hourly ozone concentration fields","year":2010,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"","keywords":"Bayesian probability; Kriging; Computer science; Kalman filter; Computation; Point process; Algorithm; Machine learning; Mathematics; Statistics; Artificial intelligence","authors":[{"name":"Yiping Dou","is_ca":true},{"name":"Nhu D. Le","is_ca":true},{"name":"James V. Zidek","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1730773880426103,"gpt":0.2705241227258004,"spread":0.0974467346831901,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003962786,0.00006869735,0.0001475162,0.00001982487,0.00006665874,0.00001864599,0.0001272726,0.00005664368,0.0003665881],"category_scores_gemma":[0.00002526811,0.00006715176,0.00002617223,0.0000322545,0.00006197507,0.00005131026,0.00002234835,0.0001296472,0.0002047376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005903149,"about_ca_system_score_gemma":0.000006801833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008789293,"about_ca_topic_score_gemma":0.00003178801,"domain_scores_codex":[0.9993614,0.000003133317,0.0003576181,0.0001271379,0.00002626432,0.0001244257],"domain_scores_gemma":[0.9995408,0.00004281302,0.0001701045,0.0002038089,0.0000125916,0.00002985769],"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":[0.00001510478,0.00003035249,0.001159171,0.000007843259,0.00002043341,1.097256e-7,0.000490721,0.01358661,0.000392537,0.9812187,0.001068687,0.002009752],"study_design_scores_gemma":[0.0003362049,0.00004762408,0.01161918,0.000002663571,0.000008428744,6.047677e-7,0.0001381005,0.3310808,0.001535295,0.653794,0.001248851,0.0001882266],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7748904,0.00006178187,0.2060465,0.0004505209,0.00017433,0.0001351777,0.0003207845,0.000009523138,0.01791102],"genre_scores_gemma":[0.9943441,0.0001554862,0.004864114,0.00040821,0.00006892159,0.000008932244,0.00005201127,0.000009699512,0.00008852578],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3274247,"threshold_uncertainty_score":0.4013883,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2070512361","doi":"10.1214/12-aoas566","title":"Dating medieval English charters","year":2012,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Toronto","funders":"","keywords":"Documentation; History; Politics; Genealogy; Phrase; Variation (astronomy); Classics; Law; Computer science; Political science; Natural language processing","authors":[{"name":"Gelila Tilahun","is_ca":true},{"name":"Andrey Feuerverger","is_ca":true},{"name":"Michael Gervers","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05168577421080451,"gpt":0.3030270209621101,"spread":0.2513412467513056,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056298,0.00007340916,0.0001018223,0.0000319052,0.0001213708,0.00004835803,0.0003672772,0.00002366314,0.00001089969],"category_scores_gemma":[0.00007764272,0.00005318259,0.00001623348,0.0001254102,0.0001025013,0.0001814201,0.00008199274,0.00009826367,0.00001617562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002958715,"about_ca_system_score_gemma":0.00003271911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002338465,"about_ca_topic_score_gemma":2.398647e-7,"domain_scores_codex":[0.9992765,0.00002115179,0.0001766897,0.00009580652,0.0001947873,0.0002350934],"domain_scores_gemma":[0.9992718,0.0001461356,0.000148904,0.0002451312,0.0001348521,0.00005317029],"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":[0.00001302278,0.00004271602,0.00006138364,0.00005328888,0.00002772007,3.789038e-7,0.01103449,0.00003192882,0.001168661,0.3984548,0.01049077,0.5786208],"study_design_scores_gemma":[0.002143302,0.0003506182,0.008610364,0.0002248303,0.000163403,0.00008269973,0.008542078,0.1525857,0.3567551,0.4187633,0.04972476,0.002053869],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007043059,0.0001087903,0.9756573,0.0002156698,0.0007103182,0.00007834029,0.00002352853,0.00007644908,0.01608652],"genre_scores_gemma":[0.8428497,0.00002334629,0.1564765,0.0003168006,0.0002750862,0.00000469702,0.000005458146,0.00000628173,0.00004207178],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8358067,"threshold_uncertainty_score":0.2168723,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2890389585","doi":"10.1214/17-aoas1130","title":"Estimating and comparing cancer progression risks under varying surveillance protocols","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Cancer Institute; National Institutes of Health; Prostate Cancer Canada; Genomic Health; Canary Foundation; U.S. Department of Defense","keywords":"Prostate cancer; Schema (genetic algorithms); Medicine; Cancer; Computer science; Econometrics; Machine learning; Internal medicine; Mathematics","authors":[{"name":"Jane Lange","is_ca":true},{"name":"Janet E. Cowan","is_ca":true},{"name":"Lawrence Klotz","is_ca":true},{"name":"Ruth Etzioni","is_ca":true},{"name":"Roman Gulati","is_ca":true},{"name":"Amy Leonardson","is_ca":true},{"name":"Daniel W. Lin","is_ca":true},{"name":"Lisa F. Newcomb","is_ca":true},{"name":"Bruce J. Trock","is_ca":true},{"name":"H. Ballentine Carter","is_ca":true},{"name":"Peter R. Carroll","is_ca":true},{"name":"Matthew R. Cooperberg","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4732441895858425,"gpt":0.5406745580878244,"spread":0.06743036850198192,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009856386,0.0001608231,0.0003597543,0.00002773657,0.0002314966,0.00004971454,0.0001961701,0.00004870487,0.00006274658],"category_scores_gemma":[0.0006921028,0.0001080575,0.00001647269,0.0001234492,0.0004393143,0.0000240889,0.0001350332,0.0001646592,0.000003978905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000768563,"about_ca_system_score_gemma":0.00004112901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004779692,"about_ca_topic_score_gemma":0.00001851007,"domain_scores_codex":[0.9987192,0.00009017757,0.0004230177,0.0002100436,0.0002765334,0.000281072],"domain_scores_gemma":[0.9973704,0.001658007,0.0003573379,0.0002869449,0.0002556273,0.00007174162],"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":[0.0002076227,0.0000783419,0.001351274,0.0005027173,0.00005954416,0.000001048038,0.001036308,0.0001195942,0.001123315,0.8622962,0.001779498,0.1314445],"study_design_scores_gemma":[0.0002866006,0.0001223278,0.005754693,0.000255469,0.00001967547,0.00000142827,0.000062486,0.09000044,0.003828811,0.8994012,0.00009203212,0.0001748752],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04003439,0.0000285833,0.9522151,0.0001530786,0.00006595905,0.003062055,0.0001360859,0.0000489628,0.0042558],"genre_scores_gemma":[0.4431845,0.000007948051,0.5559741,0.00009208451,0.00009981825,0.0006130416,0.000001968363,0.00001782688,0.000008747019],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4031501,"threshold_uncertainty_score":0.4406458,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2789596487","doi":"10.1214/17-aoas1108","title":"Simultaneous modelling of movement, measurement error, and observer dependence in mark-recapture distance sampling: An application to Arctic bird surveys","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Estimator; Distance sampling; Mark and recapture; Observer (physics); Statistics; Abundance estimation; Sampling (signal processing); Observational error; Computer science; Abundance (ecology); Mathematics; Econometrics; Ecology; Biology; Computer vision","authors":[{"name":"Paul B. Conn","is_ca":true},{"name":"Ray T. Alisauskas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1082806134048536,"gpt":0.3023662759143145,"spread":0.1940856625094609,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001499207,0.000107477,0.0001515584,0.0000236412,0.00007943354,0.00000813731,0.0002233627,0.00005180954,0.00003544974],"category_scores_gemma":[0.000092672,0.0000929607,0.000009977656,0.0001909919,0.0002252621,0.00005568221,0.00007673581,0.0000841878,0.0000156686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003536886,"about_ca_system_score_gemma":0.00001449101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009449553,"about_ca_topic_score_gemma":0.008534394,"domain_scores_codex":[0.9988681,0.00008589479,0.0003073154,0.0002459533,0.0003111158,0.0001816284],"domain_scores_gemma":[0.9991731,0.0002179724,0.0001781112,0.0002866283,0.00008779893,0.000056385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0007073272,0.0004270856,0.2475734,0.0001148086,0.0000450998,0.000001755851,0.003864791,0.6814324,0.013408,0.01477282,0.000250561,0.03740199],"study_design_scores_gemma":[0.0002856179,0.0002395841,0.7120999,0.00003383215,0.00002224379,4.471486e-7,0.000273621,0.211582,0.002386665,0.0726606,0.0001803963,0.0002350228],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4848453,0.00001166729,0.5145482,0.0001381398,0.00001526583,0.00029342,0.0000352347,0.00000753373,0.000105211],"genre_scores_gemma":[0.9839863,0.00002403776,0.01531709,0.0006005944,0.0000131665,0.00002807034,0.000007526809,0.00001161977,0.00001156206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4992311,"threshold_uncertainty_score":0.4762392,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2884750441","doi":"10.1214/18-aoas1160sf","title":"When should modes of inference disagree? Some simple but challenging examples","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Frequentist inference; Fiducial inference; Inference; Bayes' theorem; Computer science; Simple (philosophy); Bayesian inference; Statistical inference; Artificial intelligence; Machine learning; Predictive inference; Econometrics; Bayesian probability; Mathematics; Epistemology; Statistics; Philosophy","authors":[{"name":"D. A. S. Fraser","is_ca":true},{"name":"Nancy Reid","is_ca":true},{"name":"Wei Lin","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2025395505903315,"gpt":0.3616324196098393,"spread":0.1590928690195079,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004608606,0.0001635996,0.0002787034,0.00006142143,0.0001333627,0.00005157742,0.001140447,0.00005912687,0.00002179097],"category_scores_gemma":[0.00006886381,0.0001226219,0.00002973701,0.0001258335,0.0003683847,0.0001405558,0.0003219028,0.0001373658,0.00001798332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004843427,"about_ca_system_score_gemma":0.00007152157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001311001,"about_ca_topic_score_gemma":0.00001892667,"domain_scores_codex":[0.9986288,0.00003657332,0.0003947426,0.0002583133,0.0003644543,0.0003171225],"domain_scores_gemma":[0.99825,0.0004705744,0.0002358984,0.0007174834,0.0002508388,0.00007517046],"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":[0.00001778738,0.00004004002,0.00001276996,0.00003833204,0.00002317681,5.713977e-7,0.001839447,0.000864953,0.004208587,0.9540402,0.0009571902,0.03795691],"study_design_scores_gemma":[0.00009179841,0.0001237631,0.00023699,0.00002622551,0.000009766789,6.315678e-7,0.0001703508,0.1873469,0.0249234,0.7866876,0.0002267367,0.0001558753],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01584931,0.00009459157,0.9814124,0.000528627,0.0000438615,0.0001078904,0.0001713109,0.00005292252,0.001739088],"genre_scores_gemma":[0.9320842,0.0001430212,0.06729458,0.0003545003,0.00007450771,0.000007511873,0.000009514114,0.00001052543,0.00002163047],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9162349,"threshold_uncertainty_score":0.5000375,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042759248","doi":"10.1214/14-aoas804","title":"A two-step approach to model precipitation extremes in California based on max-stable and marginal point processes","year":2015,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":11,"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":"Maxima; Extreme value theory; Pairwise comparison; Statistics; Univariate; Mathematics; Block (permutation group theory); Maxima and minima; Generalized extreme value distribution; Confidence interval; Point estimation; Precipitation; Econometrics; Multivariate statistics; Meteorology; Geography; Combinatorics; Mathematical analysis","authors":[{"name":"Hongwei Shang","is_ca":false},{"name":"Jun Yan","is_ca":false},{"name":"Xuebin Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05744828277066105,"gpt":0.2899532334536131,"spread":0.232504950682952,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005973579,0.0001065013,0.0001637119,0.00005186569,0.00005251943,0.00001337719,0.0001400666,0.0000342756,0.00003083819],"category_scores_gemma":[0.00008973229,0.00007850732,0.00001082091,0.000263421,0.0001290221,0.00004168296,0.00005727307,0.00007974014,0.00005213612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002016639,"about_ca_system_score_gemma":0.00003300597,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000133623,"about_ca_topic_score_gemma":0.00024812,"domain_scores_codex":[0.999119,0.0000376253,0.0001904147,0.0002052682,0.0002568026,0.0001909248],"domain_scores_gemma":[0.9995214,0.0001141521,0.00007650258,0.0001732602,0.00002528955,0.00008936185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005102594,0.0001880107,0.001188636,0.00003147264,0.000009372154,0.000001052999,0.001562169,0.9849266,0.0001543477,0.004641671,0.005293019,0.001493397],"study_design_scores_gemma":[0.0003985633,0.00008581413,0.001005135,0.000006021686,0.00002316613,4.63292e-7,0.000309707,0.9595014,0.0004444846,0.03779814,0.0003087079,0.0001183674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1974913,0.00003505441,0.7352064,0.001095705,0.00001083946,0.0005665427,0.0003349759,0.00002114386,0.0652381],"genre_scores_gemma":[0.9239516,0.000007297931,0.07496198,0.0008915359,0.00000628065,0.00004291233,0.00003617234,0.000007997091,0.00009423086],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7264603,"threshold_uncertainty_score":0.3201436,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3037512058","doi":"10.1214/20-aoas1331","title":"Focused model selection for linear mixed models with an application to whale ecology","year":2020,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"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":"Norges Forskningsråd","keywords":"Whaling; Generalized linear mixed model; Model selection; Mixed model; Estimator; Linear model; Selection (genetic algorithm); Computer science; Whale; Information Criteria; Ecology; Econometrics; Mathematics; Statistics; Artificial intelligence; Machine learning; Biology","authors":[{"name":"Céline Cunen","is_ca":true},{"name":"Lars Walløe","is_ca":false},{"name":"Nils Lid Hjort","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1948717162346481,"gpt":0.4055610505485011,"spread":0.210689334313853,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000380028,0.000160603,0.0003375256,0.00003296451,0.0001098465,0.00001858277,0.0002444773,0.00007090159,0.000009309274],"category_scores_gemma":[0.0002878908,0.0001161474,0.00002520595,0.0001950555,0.00007694692,0.00004491927,0.00003462644,0.0001137631,0.000005215308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008866215,"about_ca_system_score_gemma":0.00007518889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007655241,"about_ca_topic_score_gemma":0.00004289983,"domain_scores_codex":[0.9988687,0.00004896395,0.0003534589,0.0002803299,0.0001952493,0.0002533093],"domain_scores_gemma":[0.9981661,0.0008783569,0.0001949865,0.0002485243,0.0003536749,0.0001583103],"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":[0.0007017859,0.0000889631,0.000001507794,0.0001193445,0.00003273709,1.422145e-7,0.0008430343,0.01455812,0.001435547,0.9583472,0.002712067,0.02115958],"study_design_scores_gemma":[0.0001835423,0.0004135621,0.000009065523,0.00000339372,0.0000349932,2.62871e-7,0.00005341037,0.4868664,0.003291264,0.5090256,0.0000345286,0.00008394889],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002890785,0.000001552037,0.994058,0.0009541905,0.00001048867,0.001044271,0.0006659249,0.0000534313,0.0003213593],"genre_scores_gemma":[0.2005804,0.000003682585,0.7982055,0.0008615819,0.00005561069,0.0002280926,0.00002638089,0.00003118283,0.000007543443],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4723083,"threshold_uncertainty_score":0.4736352,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2605027696","doi":"10.1214/16-aoas1002","title":"Electricity price dependence in New York State zones: A robust detrended correlation approach","year":2017,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Electric Power System Optimization","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal","funders":"","keywords":"Econometrics; Electricity; Detrended fluctuation analysis; Grid; Estimator; Electricity price; Computer science; Economics; Statistics; Mathematics","authors":[{"name":"Debbie J. Dupuis","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0574632283859776,"gpt":0.2638624869674593,"spread":0.2063992585814817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004519231,0.0001714653,0.0002546469,0.0001156884,0.0001285011,0.00007733348,0.0004799227,0.00007659463,0.000007160458],"category_scores_gemma":[0.0001306881,0.0001541425,0.000022304,0.0002930542,0.00004285192,0.0001047261,0.00003594192,0.000239111,0.00001220127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004330999,"about_ca_system_score_gemma":0.00008814939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002037572,"about_ca_topic_score_gemma":0.0001418633,"domain_scores_codex":[0.998769,0.00002935701,0.0004037983,0.0001791808,0.0002902815,0.0003283891],"domain_scores_gemma":[0.9988666,0.0001744673,0.0002825843,0.0005380798,0.00007245247,0.00006583711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007399255,0.00004171237,0.0002269253,0.0001128384,0.00004626012,0.00000154497,0.001110589,0.9619842,0.0002097574,0.01852815,0.004021719,0.01364233],"study_design_scores_gemma":[0.0004248454,0.00003712566,0.006963256,0.00002955173,0.00001988436,0.000003261767,0.00005008503,0.9818798,0.001494235,0.00871611,0.0001493371,0.0002324896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00327006,0.0002217047,0.9817686,0.00002157463,0.0001129109,0.0003937643,0.00003915745,0.00007581488,0.01409639],"genre_scores_gemma":[0.947821,0.0002049918,0.05157713,0.00001867846,0.00003991878,0.000018513,0.00003125333,0.00003560421,0.0002529208],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9445509,"threshold_uncertainty_score":0.6285747,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2012397316","doi":"10.1214/14-aoas774","title":"Evaluating epoetin dosing strategies using observational longitudinal data","year":2014,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"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":"Medicine; Observational study; Dosing; Regimen; Kidney disease; Intensive care medicine; Proportional hazards model; Dialysis; Anemia; Marginal structural model; Randomized controlled trial; Hemodialysis; Epoetin alfa; Clinical trial; Survival analysis; Internal medicine","authors":[{"name":"Cecilia A. Cotton","is_ca":true},{"name":"Patrick J. Heagerty","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.9581370777790906,"gpt":0.6916552922079258,"spread":0.2664817855711649,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01239526,0.0002409413,0.0006620561,0.00004741552,0.0002409785,0.0001094924,0.001010298,0.0001037424,0.0001798441],"category_scores_gemma":[0.05388528,0.0001808944,0.00005303343,0.0002356451,0.0004574197,0.0001046965,0.0004751866,0.0003135091,0.00001243639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001314405,"about_ca_system_score_gemma":0.0001813103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000247145,"about_ca_topic_score_gemma":0.000007014683,"domain_scores_codex":[0.996226,0.0006658548,0.001354326,0.0004534321,0.0009066242,0.0003937494],"domain_scores_gemma":[0.9303155,0.06679905,0.0009416576,0.00140497,0.0004454023,0.00009342547],"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":[0.0001663185,0.00008470025,0.00005175691,0.0001834142,0.00009474265,0.00000105162,0.0001285697,0.001063218,0.001579047,0.9683631,0.002226356,0.02605771],"study_design_scores_gemma":[0.0003421144,0.00008420849,0.001043905,0.0000704619,0.0001636625,0.00000195439,0.000153383,0.114061,0.0007326079,0.8830413,0.0001242243,0.000181212],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03000422,0.00001966179,0.965673,0.0002794347,0.0002065027,0.0003887916,0.0009834107,0.00004558978,0.002399394],"genre_scores_gemma":[0.132631,0.00001239914,0.8666702,0.0002254365,0.0003597032,0.000008474837,0.00004045658,0.00003840443,0.00001392629],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1129978,"threshold_uncertainty_score":0.9540843,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2492804687","doi":"10.1214/16-aoas909","title":"A Bayesian graphical model for genome-wide association studies (GWAS)","year":2016,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; York University; University of Toronto","funders":"National Cancer Institute","keywords":"Genome-wide association study; Computer science; Bayesian probability; Genetic association; Graphical model; Single-nucleotide polymorphism; Computational biology; Data mining; Machine learning; Artificial intelligence; Biology; Genetics","authors":[{"name":"Laurent Briollais","is_ca":true},{"name":"Adrian Dobra","is_ca":true},{"name":"Jinnan Liu","is_ca":true},{"name":"Matt Friedlander","is_ca":true},{"name":"Hilmi Özçelik","is_ca":true},{"name":"Hélène Massam","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0591072333190735,"gpt":0.3411212849881219,"spread":0.2820140516690484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008045704,0.0001100554,0.0002240155,0.00002378153,0.000101226,0.000004196525,0.0001574782,0.0001213691,0.000003444628],"category_scores_gemma":[0.001841696,0.00006762816,0.00007277091,0.00004511805,0.00009807602,0.000001125465,0.00006282305,0.00003808992,0.000003016398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001317286,"about_ca_system_score_gemma":0.00004848178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001476646,"about_ca_topic_score_gemma":0.00002269193,"domain_scores_codex":[0.9990865,0.00004432602,0.0003093939,0.0001883046,0.0001076874,0.0002637663],"domain_scores_gemma":[0.9982867,0.0008393208,0.0002836845,0.0002331412,0.0003173248,0.00003981415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001192611,0.0003531126,0.02695198,0.000185347,0.00340415,7.402058e-7,0.00155078,0.01535481,0.1462078,0.1123313,0.6693136,0.02315374],"study_design_scores_gemma":[0.002201993,0.00074798,0.04437144,0.00002435889,0.0002864987,8.964428e-7,0.0004887376,0.01553028,0.01435968,0.8880709,0.03320287,0.0007143494],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07723756,0.00027221,0.9144621,0.006464248,0.0000547447,0.0003255907,0.0008462415,0.000007761311,0.0003295313],"genre_scores_gemma":[0.9752475,0.001509487,0.02026451,0.001928931,0.0001028405,0.00008556317,0.00007590502,0.00001656085,0.0007687142],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.89801,"threshold_uncertainty_score":0.2757796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028703934","doi":"10.1214/14-aoas747","title":"Imputation of truncated p-values for meta-analysis methods and its genomic application","year":2014,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; University of Toronto","funders":"National Institute of Mental Health","keywords":"Inference; Imputation (statistics); False discovery rate; Raw data; Genomics; Statistical power; Multiple comparisons problem","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.106927202962884,"gpt":0.4195952967598843,"spread":0.3126680937970003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007267873,0.00008267395,0.0002683918,0.0000500378,0.00004436574,0.000006018849,0.000115287,0.00005301495,0.000006537093],"category_scores_gemma":[0.0000671275,0.00005945823,0.0001127729,0.0001213016,0.00005166835,0.000001288009,0.00002853042,0.00002229829,4.156483e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000001405738,"about_ca_system_score_gemma":0.00001738056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003735806,"about_ca_topic_score_gemma":0.000002425804,"domain_scores_codex":[0.9993207,0.00007577088,0.0002664218,0.0001813734,0.0000773416,0.00007834622],"domain_scores_gemma":[0.9990771,0.00009839179,0.0003235346,0.0002543311,0.0002205222,0.0000261308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001213331,0.00002091572,0.000003394722,0.00003930375,0.003921119,2.105056e-9,0.0001044034,0.001896572,0.9524307,0.02593139,0.0007090251,0.01482179],"study_design_scores_gemma":[0.0002050652,0.0001094203,0.001117995,4.491032e-7,0.009029138,1.301673e-7,0.00007434287,0.02400391,0.9349216,0.02573301,0.004706781,0.00009819301],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02814751,0.0005871945,0.9703842,0.0001649806,0.00001010857,0.0002973368,0.0002062684,0.000003486545,0.0001988546],"genre_scores_gemma":[0.9410914,0.0001625004,0.05807738,0.0001499346,0.00002346587,0.0001492869,0.0002750372,0.000009568595,0.0000614688],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9129438,"threshold_uncertainty_score":0.2424636,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2043089632","doi":"10.1214/12-aoas537","title":"A model for sequential evolution of ligands by exponential enrichment (SELEX) data","year":2012,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced biosensing and bioanalysis techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Systematic evolution of ligands by exponential enrichment; Oligonucleotide; Computational biology; Biology; DNA; Computer science; Genetics; RNA","authors":[{"name":"Juli Atherton","is_ca":true},{"name":"Nathan Boley","is_ca":true},{"name":"B. H. Brown","is_ca":true},{"name":"Nobuo Ogawa","is_ca":true},{"name":"Stuart M. Davidson","is_ca":true},{"name":"Michael B. Eisen","is_ca":true},{"name":"Mark D. Biggin","is_ca":true},{"name":"Peter J. Bickel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08406956993041677,"gpt":0.3643286796780921,"spread":0.2802591097476754,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004028318,0.0001063093,0.0001604927,0.00002220352,0.00005348207,0.000004764104,0.0002653333,0.00007516122,7.185415e-7],"category_scores_gemma":[0.00003916953,0.00008041185,0.000044715,0.00005216403,0.0001278851,0.000004011009,0.0001552533,0.00003866043,2.578713e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005034874,"about_ca_system_score_gemma":0.00003661262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007791053,"about_ca_topic_score_gemma":0.000004409168,"domain_scores_codex":[0.9992111,0.00001180088,0.0002644035,0.0001691189,0.0001430782,0.0002005197],"domain_scores_gemma":[0.9990737,0.00002210185,0.0002247334,0.0005091606,0.0001306714,0.00003960674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002744949,0.000123114,0.00001245632,0.00002714012,0.000104454,2.10378e-8,0.00004628816,0.00009397882,0.9600891,0.004603588,0.03218699,0.002438363],"study_design_scores_gemma":[0.0001915683,0.0001055419,0.00001770238,0.000004732598,0.00009853804,5.622188e-7,0.00005448904,0.01478549,0.9789835,0.003274856,0.002370646,0.0001123523],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07452681,0.0003586566,0.9212986,0.00005878968,0.00002888519,0.0002156358,0.003399525,0.000008691252,0.0001044637],"genre_scores_gemma":[0.9525377,0.0002252878,0.04548425,0.00007076227,0.0001100071,0.000009978644,0.001472513,0.00001198796,0.00007749532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8780109,"threshold_uncertainty_score":0.32791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4297333613","doi":"10.1214/22-aoas1600","title":"Bayesian hierarchical random-effects meta-analysis and design of phase I clinical trials","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute","keywords":"Meta-analysis; Random effects model; Computer science; Bayesian probability; Parametric statistics; Clinical study design; Statistics; Clinical trial; Data mining; Artificial intelligence; Mathematics; Medicine","authors":[{"name":"Ruitao Lin","is_ca":false},{"name":"Haolun Shi","is_ca":true},{"name":"Guosheng Yin","is_ca":false},{"name":"Peter F. Thall","is_ca":false},{"name":"Ying Yuan","is_ca":false},{"name":"Christopher R. Flowers","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8487982915840147,"gpt":0.6507765650971692,"spread":0.1980217264868455,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08113342,0.0003299056,0.005871309,0.0002164164,0.0002135034,0.00002564893,0.0006438179,0.0001334861,0.001197642],"category_scores_gemma":[0.1484256,0.0002113337,0.001343585,0.0007714313,0.0009207862,0.00001884968,0.0003840451,0.0007176891,0.000002004303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007691122,"about_ca_system_score_gemma":0.0001131898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008131169,"about_ca_topic_score_gemma":0.000001157983,"domain_scores_codex":[0.9738373,0.01914114,0.004863102,0.0005736763,0.001170242,0.0004146061],"domain_scores_gemma":[0.5867282,0.4100325,0.002035631,0.0008266892,0.000184106,0.0001929768],"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":[0.01126936,0.002135742,0.000006429858,0.0003322172,0.1243932,0.00002306556,0.0004913687,0.0006351654,0.0005221032,0.8004571,0.01045725,0.04927695],"study_design_scores_gemma":[0.004050089,0.000886257,0.00001885375,0.00000251247,0.1148919,0.000001305729,0.00006219816,0.007649299,0.00155808,0.8705837,0.0001107758,0.0001850486],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005404325,0.0002219951,0.9931199,0.000523346,0.0001304614,0.002052602,0.003099087,0.00002786893,0.0002843048],"genre_scores_gemma":[0.1327813,0.0001725615,0.8659258,0.0005824588,0.00009444062,0.0003348166,0.00001434695,0.00004262651,0.00005167913],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3908913,"threshold_uncertainty_score":0.9997154,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320169867","doi":"10.1214/22-aoas1639","title":"Modeling panels of extremes","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation HEC; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Pooling; Extreme value theory; Inference; Computer science; Regression; Econometrics; Statistics; Regression analysis; Data mining; Mathematics; Machine learning; Artificial intelligence","authors":[{"name":"Debbie J. Dupuis","is_ca":true},{"name":"Sebastian Engelke","is_ca":false},{"name":"Luca Trapin","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2390188881059419,"gpt":0.3158408307269341,"spread":0.07682194262099223,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007718411,0.00008872995,0.0003234109,0.0001135411,0.00006513853,0.000009215589,0.0002194264,0.00004756848,0.00003639497],"category_scores_gemma":[0.0001239652,0.00008324947,0.00005533171,0.0002732154,0.00006749413,0.0000313696,0.00006266982,0.00008525779,0.00009236911],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003974266,"about_ca_system_score_gemma":0.00001638924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001737588,"about_ca_topic_score_gemma":0.000007060684,"domain_scores_codex":[0.9989488,0.000005187586,0.0006292064,0.0001584002,0.00005474716,0.0002036444],"domain_scores_gemma":[0.9992507,0.0001285924,0.000227646,0.0002955489,0.00007041881,0.00002712148],"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":[0.0000418663,0.00002500496,0.0002190916,0.00006512694,0.00002596243,3.967867e-7,0.001462286,0.06069091,0.0001423817,0.9310403,0.0007406198,0.005546039],"study_design_scores_gemma":[0.00007754732,0.00001604815,0.0009083436,0.000007012171,0.000003099408,5.290249e-8,0.0001391057,0.4944863,0.0003787848,0.503486,0.000431079,0.00006658998],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5314291,0.0004371044,0.4577497,0.0002779812,0.0001218586,0.000200406,0.00148527,0.00004079353,0.00825783],"genre_scores_gemma":[0.995268,0.000811002,0.00367918,0.0000632428,0.00003522013,0.000007030623,0.00002477483,0.00001546866,0.0000961069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4638389,"threshold_uncertainty_score":0.3394815,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965857117","doi":"10.1214/08-aoas199","title":"$\\mathcal{G}$-SELC: Optimization by sequential elimination of level combinations using genetic algorithms and Gaussian processes","year":2009,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Georgia Research Foundation; Acadia University; University of Georgia; Pfizer; National Science Foundation","keywords":"Gaussian process; Set (abstract data type); Process (computing); Gaussian; Data set; Genetic algorithm","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.107672180175107,"gpt":0.3684116037186514,"spread":0.2607394235435444,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002811195,0.0001128737,0.0001733916,0.00007605503,0.0001046297,0.00006089291,0.0003272985,0.00003454248,0.000002409604],"category_scores_gemma":[0.0001176397,0.00009995749,0.00001673602,0.0004124226,0.0001084465,0.0001509727,0.00007366655,0.00006381168,4.643988e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009400029,"about_ca_system_score_gemma":0.0001312779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009684961,"about_ca_topic_score_gemma":6.109219e-7,"domain_scores_codex":[0.9989036,0.00006877038,0.0003518756,0.0001946252,0.0003503519,0.0001307985],"domain_scores_gemma":[0.9987714,0.0003112005,0.0003122427,0.000178021,0.0003787607,0.00004833255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002136303,0.0001659859,0.000002664016,0.00008933841,0.00002510515,8.451385e-7,0.001368742,0.571112,0.002038771,0.3641126,0.0003053923,0.06075718],"study_design_scores_gemma":[0.0002018004,0.00008707136,0.001247774,0.00001404311,0.00001779086,0.000002951851,0.00003799422,0.8584626,0.0082022,0.1316129,0.00001487492,0.00009795339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004325229,0.00009022461,0.9939224,0.001015906,0.00003080138,0.0002098851,0.0002151689,0.0000193439,0.0001710221],"genre_scores_gemma":[0.4385985,0.00005603028,0.5611499,0.0001462485,0.00001105881,0.000002468824,0.00002774312,0.000004898705,0.000003120722],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4342733,"threshold_uncertainty_score":0.4076148,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388054702","doi":"10.1214/23-aoas1776","title":"Continuous-time modelling of behavioural responses in animal movement","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Bureau of Medicine and Surgery; National Marine Fisheries Service; U.S. Department of Defense; U.S. Fleet Forces Command; Office of Naval Research; U.S. Navy","keywords":"Baseline (sea); Nonparametric statistics; Computer science; Covariate; Stochastic modelling; Sound exposure; Statistics; Machine learning; Mathematics","authors":[{"name":"Théo Michelot","is_ca":true},{"name":"Richard Glennie","is_ca":false},{"name":"Len Thomas","is_ca":false},{"name":"Nicola J. Quick","is_ca":false},{"name":"Catriona M. Harris","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1385718350172995,"gpt":0.3100216156854771,"spread":0.1714497806681776,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006372123,0.0001020861,0.0002381237,0.00003174489,0.00004634809,0.000005191847,0.0002397923,0.0000234814,0.0004213406],"category_scores_gemma":[0.00003287011,0.00008087124,0.00002961628,0.0002654108,0.000189692,0.00002320613,0.0003767204,0.00007564111,0.0001436529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001578889,"about_ca_system_score_gemma":0.000006952575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001532468,"about_ca_topic_score_gemma":0.0001964645,"domain_scores_codex":[0.998911,0.00003375987,0.0003544404,0.0001453746,0.0003178219,0.0002376422],"domain_scores_gemma":[0.9993702,0.0002399626,0.000154342,0.0001906642,0.00001630202,0.00002859201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.008666168,0.001716468,0.2307207,0.0005989735,0.0003918139,0.0001413998,0.01647634,0.2473996,0.1020599,0.1484233,0.1326666,0.1107387],"study_design_scores_gemma":[0.0007368423,0.0005905165,0.8716635,0.00005085377,0.00005410384,6.367983e-7,0.0009635003,0.06908851,0.0151727,0.03934944,0.001911586,0.0004178722],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918398,0.0000254602,0.0005632413,0.0001965134,0.000009558359,0.0002476218,0.000200645,0.00001649046,0.006900637],"genre_scores_gemma":[0.9967005,0.0002213564,0.002535217,0.0001843967,0.000005971212,0.00001621733,0.000009671573,0.00001170348,0.000315017],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6409428,"threshold_uncertainty_score":0.4613384,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220666549","doi":"10.1214/21-aoas1499","title":"Bayesian adjustment for preferential testing in estimating infection fatality rates, as motivated by the COVID-19 pandemic","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Institute of Genetics; Canadian Institutes of Health Research; European Commission","keywords":"Coronavirus disease 2019 (COVID-19); Bayesian probability; Pandemic; Statistics; Case fatality rate; Econometrics; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Identifiability; Demography; 2019-20 coronavirus outbreak; Population; Statistical hypothesis testing; Mathematics; Geography; Actuarial science; Medicine; Economics; Virology; Sociology; Outbreak","authors":[{"name":"Harlan Campbell","is_ca":true},{"name":"Perry de Valpine","is_ca":false},{"name":"Lauren Maxwell","is_ca":false},{"name":"Valentijn M. T. de Jong","is_ca":false},{"name":"Thomas P. A. Debray","is_ca":false},{"name":"Thomas Jaenisch","is_ca":false},{"name":"Paul Gustafson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5179263313108267,"gpt":0.4970631588051286,"spread":0.02086317250569808,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003620915,0.0002109357,0.0004313167,0.00004020869,0.0006807205,0.0000181132,0.0003221796,0.00005054754,0.00007235591],"category_scores_gemma":[0.01685737,0.0001349558,0.0000558829,0.0003194343,0.0001777535,0.00002208005,0.0003922134,0.0003577558,0.000001453078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001716923,"about_ca_system_score_gemma":0.0001128512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001384182,"about_ca_topic_score_gemma":0.000160525,"domain_scores_codex":[0.9978384,0.0004125808,0.0007505181,0.0003009513,0.0003262088,0.0003713405],"domain_scores_gemma":[0.9805422,0.01834862,0.0006166311,0.0003258399,0.00009901691,0.00006765116],"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":[0.002023069,0.001669369,0.02783417,0.002532478,0.0007818535,0.000005148841,0.01039737,0.2035809,0.003506772,0.4475045,0.2412989,0.0588654],"study_design_scores_gemma":[0.0007311207,0.0002618083,0.003016546,0.00001470243,0.00008235206,0.00000363656,0.0005219591,0.06160468,0.0002247085,0.9307804,0.002547492,0.0002106424],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1534746,0.0001215066,0.8395098,0.001940294,0.0001400431,0.00257493,0.001758434,0.0001518936,0.0003284721],"genre_scores_gemma":[0.9684618,0.0000293272,0.02766902,0.002719344,0.00006442027,0.0008468906,0.0001468614,0.00002708332,0.00003522371],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8149872,"threshold_uncertainty_score":0.9914241,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174385715","doi":"10.1214/21-aoas1570","title":"Estimation of the marginal effect of antidepressants on body mass index under confounding and endogenous covariate-driven monitoring times","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"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; Endogeneity; Confounding; Statistics; Body mass index; Propensity score matching; Marginal structural model; Econometrics; Selection bias; Index (typography); Medicine; Computer science; Mathematics; Internal medicine","authors":[{"name":"Janie Coulombe","is_ca":true},{"name":"Erica E. M. Moodie","is_ca":true},{"name":"Robert W. Platt","is_ca":true},{"name":"Christel Renoux","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1758420278101468,"gpt":0.4153412653801332,"spread":0.2394992375699864,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006953872,0.0001460667,0.0003517733,0.00006250304,0.0001579151,0.000009622526,0.0002847149,0.00003548892,0.00002343743],"category_scores_gemma":[0.0002151563,0.0000996579,0.00003355506,0.000132733,0.0001956001,0.00002980193,0.0001808274,0.0002163623,3.766921e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002188444,"about_ca_system_score_gemma":0.00003142979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002166432,"about_ca_topic_score_gemma":4.518756e-7,"domain_scores_codex":[0.9987543,0.0001468892,0.0003725769,0.0001293723,0.0004323504,0.0001645237],"domain_scores_gemma":[0.996807,0.002164672,0.0005786813,0.0003552394,0.00007218526,0.00002218711],"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":[0.0006867533,0.0001137692,0.001472354,0.0005449316,0.0001951804,0.00000320046,0.0007900802,0.03795011,0.0952588,0.8574548,0.0002252688,0.005304724],"study_design_scores_gemma":[0.0003685142,0.0003874432,0.002414512,0.0000937156,0.00009510558,0.000004658931,0.0002571713,0.00963583,0.4412389,0.5453765,0.000006511083,0.0001212234],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7394337,0.00004247969,0.256559,0.00004768555,0.000104073,0.001120252,0.0005312348,0.00005783783,0.00210378],"genre_scores_gemma":[0.9842955,0.00003385396,0.01556215,0.00001298346,0.00001195961,0.00004183122,0.000005949762,0.00002249025,0.00001327314],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.34598,"threshold_uncertainty_score":0.4063931,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1987751717","doi":"10.1214/10-aoas342","title":"A nonlinear mixed effects directional model for the estimation of the rotation axes of the human ankle","year":2010,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Rotation (mathematics); Orientation (vector space); Nonlinear system; Measure (data warehouse); Monte Carlo method; Linear model; Sample (material); Data set","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.07298192094243762,"gpt":0.3524230450008768,"spread":0.2794411240584392,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006979908,0.00009943788,0.0001828735,0.00002062514,0.0002771849,0.00001137691,0.0003586758,0.00006162787,0.00001368367],"category_scores_gemma":[0.0008403938,0.00004260143,0.00009410662,0.0001599198,0.0002337435,0.00001887438,0.0000753298,0.000163846,6.174221e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000367097,"about_ca_system_score_gemma":0.00003550412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001786621,"about_ca_topic_score_gemma":0.00003198137,"domain_scores_codex":[0.9990919,0.00004968934,0.0003698748,0.00009488985,0.0002843874,0.0001092953],"domain_scores_gemma":[0.9962417,0.002556582,0.0005294888,0.0004323514,0.0002253577,0.00001452459],"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":[0.00003684115,0.0002075576,0.00003110725,0.0001591849,0.00006594579,1.970743e-8,0.0004599134,0.01071978,0.02521156,0.9556474,0.004156779,0.003303914],"study_design_scores_gemma":[0.0002315034,0.0000332243,0.004652725,0.00001872888,0.0001023908,3.988175e-7,0.00005593978,0.3860056,0.05889736,0.5499045,0.00004445055,0.0000531428],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3006868,0.000009434496,0.6962429,0.0005625513,0.0001448294,0.001136802,0.0007470918,0.00001138558,0.0004581747],"genre_scores_gemma":[0.8706961,0.000003382273,0.1289973,0.00008122008,0.00003898646,0.00007046414,0.00001433495,0.00001112239,0.00008713966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5700093,"threshold_uncertainty_score":0.213191,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2569003638","doi":"10.1214/16-aoas964","title":"Inferring rooted population trees using asymmetric neighbor joining","year":2016,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"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":"Population; Artificial intelligence; Computer science; Mathematics; Geography; Demography; Sociology","authors":[{"name":"Yongliang Zhai","is_ca":true},{"name":"Alexandre Bouchard‐Côté","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06098441619541242,"gpt":0.3102171999441594,"spread":0.2492327837487469,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001381141,0.0000959712,0.0001130627,0.00005644117,0.00009648679,0.00001211939,0.0001341867,0.00007381602,0.00002387577],"category_scores_gemma":[0.00008373743,0.00006361245,0.00003285202,0.0001227146,0.00004885704,0.000002825752,0.00007736439,0.00003573926,0.000003549667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003876852,"about_ca_system_score_gemma":0.00001962945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003547004,"about_ca_topic_score_gemma":0.00001937179,"domain_scores_codex":[0.9993544,0.00002462953,0.0001908585,0.000139859,0.0001445382,0.0001457318],"domain_scores_gemma":[0.9994473,0.0000396295,0.0001660876,0.0002153707,0.00009422017,0.00003737815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0005661028,0.00006184719,0.03376963,0.00005936555,0.0002862709,0.00000208558,0.0003930432,0.01268784,0.6884413,0.05689302,0.00472395,0.2021156],"study_design_scores_gemma":[0.001500335,0.0002649368,0.698015,0.00005788536,0.0001354837,0.000007640064,0.0002386237,0.001645291,0.2576973,0.02996065,0.009864996,0.0006118285],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8947126,0.0000696819,0.1036632,0.00009932843,0.00007973333,0.0001139563,0.0002208235,0.000007981338,0.001032667],"genre_scores_gemma":[0.9920478,0.00004955248,0.007487464,0.0001696239,0.0000860347,0.00000107232,0.00007683819,0.00001032925,0.0000713282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6642454,"threshold_uncertainty_score":0.259404,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4221109862","doi":"10.1214/21-aoas1518","title":"Accounting for drop-out using inverse probability censoring weights in longitudinal clustered data with informative cluster size","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":5,"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":"Censoring (clinical trials); Statistics; Inverse probability; Inference; Generalized estimating equation; Mathematics; Random effects model; Estimating equations; Marginal structural model; Econometrics; Causal inference; Computer science; Medicine; Estimator; Artificial intelligence; Meta-analysis","authors":[{"name":"Aya Mitani","is_ca":true},{"name":"Kerrie P. Nelson","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1611153341132059,"gpt":0.3564482760153331,"spread":0.1953329419021272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002188983,0.0001707237,0.0002996118,0.00006954012,0.0003089939,0.00008107564,0.001353899,0.00003043965,0.000005280575],"category_scores_gemma":[0.0001134199,0.0001239213,0.00002566391,0.0002947747,0.0001112007,0.0003766797,0.001332475,0.0002586098,7.572377e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004006247,"about_ca_system_score_gemma":0.000153716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003195826,"about_ca_topic_score_gemma":0.00007212636,"domain_scores_codex":[0.9983383,0.0001228082,0.0004537266,0.0003634646,0.0003668781,0.0003547788],"domain_scores_gemma":[0.9975334,0.0009100044,0.0003864685,0.0009764017,0.000146895,0.0000468142],"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":[0.001762279,0.0003700943,0.0004511995,0.0007444011,0.0002184071,0.00001465345,0.04414371,0.02428716,0.0005661051,0.8649769,0.002477566,0.05998757],"study_design_scores_gemma":[0.0007216842,0.0000972458,0.0004831139,0.00002556991,0.00002265783,0.000006193919,0.0002587874,0.7755817,0.000337238,0.2216986,0.0005537302,0.0002135057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02162133,0.00001013617,0.9764931,0.0002346724,0.00008046503,0.0007946896,0.0003932223,0.00002099589,0.0003513717],"genre_scores_gemma":[0.2200986,0.000003189015,0.7793494,0.0004347116,0.00002892576,0.00004111768,0.00002191343,0.0000112596,0.00001090358],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7512945,"threshold_uncertainty_score":0.5053365,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320176121","doi":"10.1214/22-aoas1624","title":"Regularized fingerprinting in detection and attribution of climate change with weight matrix optimizing the efficiency in scaling factor estimation","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":5,"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":"National Science Foundation","keywords":"Covariance matrix; Mathematics; Statistics; Estimator; Matrix (chemical analysis); Linear regression; Covariance; Estimation of covariance matrices; Applied mathematics","authors":[{"name":"Yan Li","is_ca":false},{"name":"Kun Chen","is_ca":false},{"name":"Jun Yan","is_ca":false},{"name":"Xuebin Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08214424114205639,"gpt":0.2889005372703241,"spread":0.2067562961282677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008758586,0.00007250324,0.0002303886,0.0002107275,0.00007285165,0.00002002608,0.00009354992,0.00003503947,0.000007398913],"category_scores_gemma":[0.00005529671,0.0000532341,0.00001762203,0.0006216278,0.00006488594,0.00005691979,0.0000481489,0.00008306721,0.000005497908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009994878,"about_ca_system_score_gemma":0.000003976501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003550625,"about_ca_topic_score_gemma":0.0001090524,"domain_scores_codex":[0.9992248,0.00001588172,0.0004161697,0.0001383787,0.00004740004,0.000157384],"domain_scores_gemma":[0.9992822,0.0001749394,0.0003605622,0.0001451508,0.00002482594,0.00001229405],"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":[0.001035639,0.0002075279,0.07411245,0.0009175556,0.0001728515,0.000006916475,0.01937734,0.07830653,0.002929358,0.6205073,0.00001475885,0.2024118],"study_design_scores_gemma":[0.000397054,0.00003911264,0.2392238,0.00005916585,0.00001331495,4.474534e-7,0.0002936783,0.7373252,0.001462793,0.02105251,0.00001767071,0.0001152487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8507195,0.0001293566,0.148129,0.0002191554,0.00002401021,0.0002335734,0.000453487,0.00001026284,0.00008167923],"genre_scores_gemma":[0.9951596,0.0007242318,0.004017788,0.00001377424,0.00001255787,0.00001974693,0.00004367665,0.000007036504,0.000001544859],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6590187,"threshold_uncertainty_score":0.2170824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2602208471","doi":"10.1214/18-aoas1162","title":"Exact spike train inference via $\\ell_{0}$ optimization","year":2018,"lang":"en","type":"preprint","venue":"The Annals of Applied Statistics","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":5,"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":"Python (programming language); Computer science; TRACE (psycholinguistics); Inference; Software; Optimization problem; Spike (software development); Convex optimization; Measure (data warehouse); Algorithm; Mathematical optimization; Regular polygon; Mathematics; Artificial intelligence; Programming language","authors":[{"name":"Sean Jewell","is_ca":false},{"name":"Daniela Witten","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1049976159803365,"gpt":0.3403495868487135,"spread":0.235351970868377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004330612,0.0003054341,0.000360374,0.00009801225,0.0001712822,0.00009523723,0.000659725,0.0001795906,0.0001879115],"category_scores_gemma":[0.0004249624,0.0002346732,0.00007342583,0.0001946258,0.0004021421,0.00003990231,0.0004345694,0.0004750439,0.00004814697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000157258,"about_ca_system_score_gemma":0.0000938075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002603397,"about_ca_topic_score_gemma":0.000007048166,"domain_scores_codex":[0.9980721,0.0001017547,0.000508605,0.000531196,0.0004705434,0.0003158375],"domain_scores_gemma":[0.9977005,0.0007059727,0.0006291714,0.0006979559,0.0001895205,0.00007686457],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006820332,0.0003701025,0.000009640927,0.0006220379,0.00007149809,0.00001683102,0.001237707,0.6296076,0.08964818,0.1984293,0.01629035,0.06301475],"study_design_scores_gemma":[0.0002113985,0.0002096027,0.0002118416,0.00006565473,0.00005440368,0.000003144309,0.00002263727,0.6234893,0.05109907,0.3231981,0.000974904,0.0004599519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01688724,0.00001474291,0.9702796,0.0005657828,0.0007851507,0.0008313087,0.001581005,0.00008837552,0.008966781],"genre_scores_gemma":[0.9820464,0.0006292879,0.01463029,0.001840959,0.000257624,0.00004881907,0.0002157555,0.00005709242,0.0002737299],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9651592,"threshold_uncertainty_score":0.9569696,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2990428857","doi":"10.1214/19-aoas1274","title":"Joint model of accelerated failure time and mechanistic nonlinear model for censored covariates, with application in HIV/AIDS","year":2019,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; City University of New York; National Science Foundation","keywords":"Covariate; Proportional hazards model; Accelerated failure time model; Econometrics; Inference; Statistics; Survival analysis; Computer science; Outcome (game theory); Mathematics; Artificial intelligence","authors":[{"name":"Hongbin Zhang","is_ca":true},{"name":"Lang Wu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08529347782029319,"gpt":0.3467134122240529,"spread":0.2614199344037597,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006101011,0.0001917118,0.0005506563,0.0000709527,0.00003793245,0.00001730118,0.0001795532,0.00008924532,0.0000171047],"category_scores_gemma":[0.0002237782,0.0001346193,0.00002448823,0.0001550013,0.0001181941,0.00002904306,0.00005104639,0.00013221,0.000004316734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000937952,"about_ca_system_score_gemma":0.00008660583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009003549,"about_ca_topic_score_gemma":0.000009835358,"domain_scores_codex":[0.9987016,0.00003564607,0.0005444715,0.0002524461,0.0002280589,0.0002377478],"domain_scores_gemma":[0.9978275,0.001077537,0.0003590691,0.0003628749,0.0003176747,0.00005528749],"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":[0.0004255228,0.0001082301,0.000004018495,0.0003670369,0.00003809992,1.971138e-7,0.0004034229,0.006696357,0.02198725,0.9678791,0.0002189044,0.001871919],"study_design_scores_gemma":[0.0003829664,0.00008666236,0.000008432045,0.0000290115,0.00003536915,3.504864e-7,0.00003879576,0.5098462,0.003396999,0.4860878,0.000001866097,0.00008552257],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006837304,0.000004180013,0.9885118,0.00009178671,0.000004495738,0.001076211,0.003167198,0.00001663335,0.0002903793],"genre_scores_gemma":[0.1749898,0.000009672599,0.8247065,0.00005510731,0.000007027235,0.00005986835,0.00007489569,0.00002922726,0.00006785704],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5031499,"threshold_uncertainty_score":0.5489616,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107904222","doi":"10.1214/10-aoas398l","title":"Discussion of: A statistical analysis of multiple temperature proxies: Are reconstructions of surface temperatures over the last 1000 years reliable?","year":2011,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Tree-ring climate responses","field":"Earth and Planetary Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Proxy (statistics); Autocorrelation; Statistical analysis; Paleoclimatology; Econometrics; History; Geology; Psychology; Statistics; Mathematics; Climate change; Oceanography","authors":[{"name":"Stephen McIntyre","is_ca":true},{"name":"Ross McKitrick","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03359346518537585,"gpt":0.2685703369750909,"spread":0.2349768717897151,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004492565,0.0001419028,0.0004545357,0.0001234945,0.00009326403,0.00001328099,0.0003210776,0.00006976709,0.0006006976],"category_scores_gemma":[0.0001856256,0.00007043437,0.00008185222,0.0006698745,0.0006708392,0.00004171841,0.00002929871,0.0001764535,0.000003760423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000167258,"about_ca_system_score_gemma":0.00007408018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008625427,"about_ca_topic_score_gemma":0.002126361,"domain_scores_codex":[0.9986317,0.0001104881,0.0005168458,0.0001773302,0.000364705,0.0001989234],"domain_scores_gemma":[0.9976903,0.001163105,0.0004953952,0.0004275418,0.0001691532,0.00005448573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003108187,0.0003262568,0.9138372,0.000523927,0.002124317,0.00001059747,0.009690369,0.03154078,0.008426641,0.01812486,0.006545685,0.005741206],"study_design_scores_gemma":[0.0001530407,0.0001069894,0.9890602,0.00004962349,0.0003089039,0.000001442783,0.002055869,0.001589834,0.004860011,0.001608642,0.0001043806,0.0001011028],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9859228,0.0001148531,0.0002048291,0.00004947214,0.00005522138,0.0002283121,0.01294091,0.00001030741,0.0004733288],"genre_scores_gemma":[0.9903628,0.0001803041,0.009233731,0.00002045726,0.000009724415,0.000001360875,0.0001428861,0.000006331219,0.00004244923],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07522299,"threshold_uncertainty_score":0.6577218,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401373758","doi":"10.1214/24-aoas1877","title":"Probabilistic contrastive dimension reduction for case-control study data","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Human Genome Research Institute; National Heart, Lung, and Blood Institute; Canadian Institute for Advanced Research; National Cancer Institute; National Science Foundation; National Institutes of Health; National Institute of Environmental Health Sciences; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Dimensionality reduction; Dimension (graph theory); Reduction (mathematics); Probabilistic logic; Computer science; Statistics; Data reduction; Artificial intelligence; Natural language processing; Mathematics","authors":[{"name":"Didong Li","is_ca":false},{"name":"Andrew Jones","is_ca":false},{"name":"Barbara E. Engelhardt","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08856121255749513,"gpt":0.3719493295497239,"spread":0.2833881169922288,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004749844,0.0000977247,0.0001132686,0.00002537348,0.00008625281,0.00002635171,0.0001815156,0.00004429366,0.000007841327],"category_scores_gemma":[0.00009952002,0.00006927795,0.00002201161,0.00006896704,0.00007434025,0.000002877755,0.00006112267,0.00005496619,0.000002397803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000403731,"about_ca_system_score_gemma":0.0000720512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005658106,"about_ca_topic_score_gemma":0.00000907161,"domain_scores_codex":[0.9991999,0.00004173016,0.0002131308,0.0003188233,0.0001057359,0.0001206274],"domain_scores_gemma":[0.9991201,0.00008913199,0.00007988784,0.0005367504,0.0001421342,0.00003196763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002329604,0.0004770856,0.00001031435,0.0002623922,0.0006118977,0.00001914549,0.001206231,0.001550747,0.6604241,0.0316538,0.1607811,0.1406736],"study_design_scores_gemma":[0.01000546,0.008310993,0.004756493,0.000266823,0.002890694,0.0004947893,0.0236182,0.1609548,0.5147943,0.1051017,0.1665483,0.00225735],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.230203,0.001533162,0.7522666,0.001080269,0.0008453505,0.004724707,0.008618321,0.00005396456,0.000674581],"genre_scores_gemma":[0.9980373,0.00005252431,0.001093435,0.00007208587,0.0001819907,0.0001256611,0.0003085835,0.00001705467,0.0001113882],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7678343,"threshold_uncertainty_score":0.2825073,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3181775732","doi":"10.1214/20-aoas1423","title":"A compositional model to assess expression changes from single-cell RNA-seq data","year":2021,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Science Foundation; National Institutes of Health; National Cancer Institute; National Institute of Dental and Craniofacial Research; University of Wisconsin-Madison","keywords":"Cluster analysis; Bayesian probability; Expression (computer science); Mixture model; Computer science; Prior probability; Hierarchical clustering; Posterior probability; Probability distribution; Computational biology; Mathematics; Data mining; Artificial intelligence; Statistics; Biology","authors":[{"name":"Xiuyu Ma","is_ca":false},{"name":"Keegan Korthauer","is_ca":true},{"name":"Christina Kendziorski","is_ca":false},{"name":"Michael A. Newton","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2149168327828449,"gpt":0.3373738237349338,"spread":0.1224569909520889,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001325131,0.0001429508,0.0001773485,0.00001727629,0.00008589616,0.00003349275,0.0004729328,0.00008602849,0.00002641172],"category_scores_gemma":[0.00003151502,0.0001219683,0.00002731068,0.00006002231,0.00006642575,0.000002760474,0.0003184963,0.00008692309,0.000006065211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003512524,"about_ca_system_score_gemma":0.00008727011,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001869662,"about_ca_topic_score_gemma":0.00006684665,"domain_scores_codex":[0.9990107,0.00003555507,0.0002014394,0.000345867,0.0002169305,0.0001895435],"domain_scores_gemma":[0.9988419,0.00007122169,0.00009194018,0.0007360837,0.0001754654,0.00008339313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00022545,0.0002145434,0.000006627343,0.00002184018,0.00003376698,0.000002704526,0.0001206964,0.001921194,0.9785481,0.0006926832,0.01626116,0.001951243],"study_design_scores_gemma":[0.0002898862,0.0000815328,0.00003912231,0.00001948612,0.00002812225,8.626538e-7,0.00008186162,0.005373984,0.9867226,0.003136539,0.004066022,0.0001599999],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3341382,0.0003594639,0.6510773,0.0008173263,0.0001263328,0.0001977992,0.01030722,0.00001280983,0.002963503],"genre_scores_gemma":[0.8782606,0.0002042382,0.1130405,0.002237316,0.0002074877,0.00001118166,0.005829296,0.00003000002,0.0001793246],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5441224,"threshold_uncertainty_score":0.4973725,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4367598648","doi":"10.1214/22-aoas1675","title":"Mixed-frequency extreme value regression: Estimating the effect of mesoscale convective systems on extreme rainfall intensity","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation HEC","keywords":"Extreme value theory; Flash flood; Mesoscale meteorology; Generalized extreme value distribution; Maxima; Environmental science; Climatology; Intensity (physics); Covariate; Statistics; Mesoscale convective system; Regression analysis; Meteorology; Flood myth; Geography; Mathematics; Geology","authors":[{"name":"Debbie J. Dupuis","is_ca":true},{"name":"Luca Trapin","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06433382728355574,"gpt":0.2969347383230752,"spread":0.2326009110395194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001992907,0.0001914051,0.0004337824,0.00004348769,0.0002659193,0.00001179234,0.000444897,0.00008290796,0.0001237169],"category_scores_gemma":[0.0003531744,0.0001006128,0.00008652558,0.000452911,0.0007031616,0.0000328516,0.0001971208,0.0002274557,0.0002080715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002114621,"about_ca_system_score_gemma":0.000009709378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003138868,"about_ca_topic_score_gemma":0.00003280907,"domain_scores_codex":[0.9983112,0.0002870982,0.0003994532,0.0002600962,0.0004540998,0.0002881107],"domain_scores_gemma":[0.9972098,0.001777951,0.0003763015,0.0005458749,0.00003472629,0.00005531133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002681953,0.0002939192,0.02316033,0.0005565424,0.001350755,0.000116097,0.0139606,0.6164984,0.0409628,0.1221251,0.1488161,0.02947743],"study_design_scores_gemma":[0.001245051,0.001357854,0.04468517,0.0002476243,0.0006054122,0.00001504564,0.001310776,0.7780538,0.05074734,0.1205495,0.0005256217,0.0006567376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9570333,0.00008291645,0.02103587,0.000890197,0.0003491669,0.0008149393,0.0002007885,0.00007985089,0.01951292],"genre_scores_gemma":[0.9982814,0.00001671437,0.001236318,0.0001577351,0.00004276752,0.00003347467,0.00002300765,0.00001431543,0.0001943209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1615555,"threshold_uncertainty_score":0.410287,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2983854231","doi":"10.1214/21-aoas1565","title":"Measurement error correction in particle tracking microrheology","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Streptococcal Infections and Treatments","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; University of Waterloo","funders":"","keywords":"Microrheology; Estimator; Range (aeronautics); Computer science; Power law; Bandwidth (computing); Viscoelasticity; Algorithm; Statistical physics; Physics; Acoustics; Mathematics; Statistics; Engineering; Telecommunications; Aerospace engineering","authors":[{"name":"Yun Ling","is_ca":true},{"name":"Martin Lysy","is_ca":true},{"name":"Ian Seim","is_ca":false},{"name":"Jay Newby","is_ca":true},{"name":"David B. Hill","is_ca":false},{"name":"Jeremy Cribb","is_ca":false},{"name":"M. Gregory Forest","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.151902174140617,"gpt":0.3692182806897776,"spread":0.2173161065491606,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003361041,0.00006162694,0.0001417164,0.00004146626,0.0001080232,0.000003248027,0.00003919283,0.00001449497,0.0002155372],"category_scores_gemma":[0.00003966924,0.00004835358,0.00002523679,0.0001740694,0.00005266334,0.000008098456,0.00003188346,0.0001303931,0.000007077866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004818111,"about_ca_system_score_gemma":0.00004166301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001062382,"about_ca_topic_score_gemma":0.00005335788,"domain_scores_codex":[0.9993343,0.00003676634,0.0002000234,0.0001005079,0.0001882114,0.0001401715],"domain_scores_gemma":[0.9996148,0.00005991807,0.00007774901,0.0001433277,0.00007633308,0.00002787402],"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":[0.007428852,0.009086649,0.2028211,0.0002472455,0.001283449,0.0001804825,0.008898854,0.02194053,0.122831,0.1402996,0.04534609,0.4396362],"study_design_scores_gemma":[0.006230158,0.002637981,0.7846357,0.00006846536,0.0003702478,0.0001154174,0.004435417,0.01467616,0.1509853,0.02551973,0.009950837,0.000374545],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877898,0.000154473,0.00635075,0.0008586746,0.0003004686,0.0007542303,0.00006530346,0.00002846621,0.003697831],"genre_scores_gemma":[0.9991224,0.00001319586,0.0003224687,0.0003023871,0.00001503281,0.0001213714,0.00001165054,0.000007893532,0.00008361192],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5818146,"threshold_uncertainty_score":0.2359982,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2761069967","doi":"10.1214/17-aoas1044","title":"Latent class modeling using matrix covariates with application to identifying early placebo responders based on EEG signals","year":2017,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Mental Health Research Topics","field":"Psychology","cited_by":3,"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":"National Institute of Mental Health","keywords":"Covariate; Latent class model; Latent variable; Statistics; Placebo; Missing data; Bayesian probability; Matrix decomposition; Artificial intelligence; Computer science; Econometrics; Psychology; Mathematics; Medicine","authors":[{"name":"Bei Jiang","is_ca":true},{"name":"Eva Petkova","is_ca":false},{"name":"Thaddeus Tarpey","is_ca":false},{"name":"R. Todd Ogden","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2593056180934468,"gpt":0.4945810377768523,"spread":0.2352754196834055,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001540842,0.0001867,0.0002744097,0.0001533426,0.0005929238,0.0001282447,0.0006298753,0.00008801395,0.00008271269],"category_scores_gemma":[0.00008667043,0.0001450271,0.0000302707,0.0001218853,0.000138557,0.00004936838,0.00009929218,0.0002841346,0.0001168936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005309676,"about_ca_system_score_gemma":0.0001061209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000764442,"about_ca_topic_score_gemma":0.00004520691,"domain_scores_codex":[0.997959,0.0001367642,0.0004230661,0.0003573124,0.0006170873,0.0005068225],"domain_scores_gemma":[0.9976426,0.0004778108,0.0003881102,0.001098927,0.0002123049,0.0001802736],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.02320308,0.000434749,0.0005939588,0.0004903491,0.0002568579,0.00003615442,0.00497179,0.525338,0.01406941,0.4108565,0.002345885,0.01740325],"study_design_scores_gemma":[0.002313721,0.0008169188,0.007692899,0.0002217172,0.0000746496,0.000002465636,0.0009152523,0.9538374,0.003159608,0.03014606,0.0003689842,0.0004503194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2450099,0.0000182876,0.749113,0.001123547,0.00008360347,0.001473694,0.0002482467,0.0000289269,0.002900802],"genre_scores_gemma":[0.9697488,0.000006871117,0.02915638,0.0006591534,0.00005224995,0.0001200202,0.00002248892,0.00004344984,0.0001905995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7247389,"threshold_uncertainty_score":0.5914034,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408585636","doi":"10.1214/24-aoas1958","title":"Poisson cluster process models for detecting ultra-diffuse galaxies","year":2025,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Computer science; Cluster (spacecraft); Poisson distribution; Statistical physics; Statistics; Mathematics; Physics","authors":[{"name":"Dayi Li","is_ca":true},{"name":"Alex Stringer","is_ca":true},{"name":"Gwendolyn M. Eadie","is_ca":true},{"name":"Roberto Abraham","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05633146807322464,"gpt":0.3493496021781208,"spread":0.2930181341048962,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008319571,0.0001545328,0.0002533464,0.00007791069,0.0001839771,0.00008453341,0.0007890146,0.000063367,0.000001029084],"category_scores_gemma":[0.0001052167,0.0001123609,0.00005250779,0.0002548603,0.00007602385,0.0001080812,0.00006278367,0.0001298819,0.000001010789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006151842,"about_ca_system_score_gemma":0.00007946326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006286009,"about_ca_topic_score_gemma":0.000004903586,"domain_scores_codex":[0.9988726,0.00004374451,0.0003229713,0.0002747521,0.0001826393,0.0003032789],"domain_scores_gemma":[0.9982433,0.0007877488,0.0001709902,0.0004975264,0.0002563442,0.00004404327],"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":[0.00007106003,0.00004496643,0.000001578096,0.0001723168,0.00003579693,2.611627e-7,0.001938158,0.001097462,0.0008396943,0.908945,0.001996434,0.08485731],"study_design_scores_gemma":[0.00027587,0.00003433818,0.00003012972,0.00002538878,0.00001560688,6.335731e-7,0.00004913308,0.1853988,0.03805694,0.7758914,0.0001200495,0.0001016404],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008778773,0.00008776939,0.9929473,0.001089657,0.0001029057,0.0004724395,0.00005121927,0.00005550864,0.004315362],"genre_scores_gemma":[0.4760613,0.00002784755,0.5229937,0.0006736569,0.00002554624,0.00005864252,0.000002418552,0.000009430526,0.0001474105],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4751835,"threshold_uncertainty_score":0.4581943,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391418111","doi":"10.1214/23-aoas1795","title":"Network-level traffic flow prediction: Functional time series vs. functional neural network approach","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":2,"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":"Time series; Computer science; Series (stratigraphy); Artificial neural network; Traffic flow (computer networking); Artificial intelligence; Machine learning; Geology; Computer network","authors":[{"name":"Tao Ma","is_ca":false},{"name":"Fang Yao","is_ca":false},{"name":"Zhou Zhou","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04532785483451583,"gpt":0.2309017812429498,"spread":0.185573926408434,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003827967,0.0002358422,0.0002262756,0.00007237021,0.0001831634,0.00008390478,0.0001673891,0.00009465709,0.0001986546],"category_scores_gemma":[0.00000552647,0.0001986643,0.00007312212,0.0003632524,0.0001402504,0.0001233152,0.00005381396,0.0003079135,0.00007045375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002021393,"about_ca_system_score_gemma":0.00002788235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":6.739328e-7,"about_ca_topic_score_gemma":0.000001748332,"domain_scores_codex":[0.9986416,0.0000235351,0.0003830769,0.0002311938,0.0003650037,0.0003556685],"domain_scores_gemma":[0.9994571,0.0001233514,0.00004159048,0.0002448434,0.0000639885,0.00006917593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006552333,0.00001206561,7.130141e-7,0.00006815075,0.0001106883,0.000001197229,0.00004549897,0.4821236,0.000009775099,0.04163096,0.4623255,0.01360633],"study_design_scores_gemma":[0.0001257302,0.00006218448,0.001326567,0.00002498689,0.00007632868,0.00001224389,0.00002850665,0.9217191,0.00001957558,0.00583454,0.07059396,0.0001762317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003013065,0.0004864441,0.9760524,0.0003023672,0.001349859,0.0003913039,0.0008910208,0.00406791,0.0161574],"genre_scores_gemma":[0.9410669,0.0006364376,0.05022205,0.0007463479,0.003435302,0.0002721182,0.001743319,0.0001366386,0.001740847],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9407656,"threshold_uncertainty_score":0.8101293,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4287780226","doi":"10.1214/22-aoas1701","title":"The scalable birth–death MCMC algorithm for mixed graphical model learning with application to genomic data integration","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; York University; Lunenfeld-Tanenbaum Research Institute; University of New Brunswick","funders":"National Center for Advancing Translational Sciences; National Cancer Institute","keywords":"Subtyping; Lasso (programming language); Computer science; Inference; Scalability; Biological data; Feature selection; Computational biology; Data mining; Machine learning; Artificial intelligence; Bioinformatics; Biology","authors":[{"name":"Nanwei Wang","is_ca":true},{"name":"Hélène Massam","is_ca":true},{"name":"Xin Gao","is_ca":true},{"name":"Laurent Briollais","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.062091907064135,"gpt":0.3370713860687274,"spread":0.2749794790045924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005107475,0.0001003399,0.00009396458,0.00003528685,0.000255176,0.00003269353,0.0004323761,0.00005424046,7.777236e-7],"category_scores_gemma":[0.0000497082,0.00006142817,0.00001920399,0.0001837318,0.00006799491,0.000002808162,0.0001381882,0.00007600213,0.000006496711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004116359,"about_ca_system_score_gemma":0.00006867328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005848217,"about_ca_topic_score_gemma":0.00002344802,"domain_scores_codex":[0.9991745,0.00002560129,0.0001894131,0.0002814026,0.0001490202,0.0001800233],"domain_scores_gemma":[0.9989778,0.00006558027,0.0001272225,0.0006205107,0.000160575,0.00004824708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004914891,0.00003589521,0.00001468564,0.00002034064,0.00006428049,7.518504e-8,0.0001607853,0.02468698,0.5278847,0.03220607,0.04438555,0.3700491],"study_design_scores_gemma":[0.0003651809,0.0002196931,0.0006975697,0.000008869251,0.00002974581,5.949792e-7,0.0005387677,0.7984532,0.1042778,0.01347363,0.08175438,0.0001806546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01616811,0.0000471067,0.9818909,0.0007457046,0.00002682425,0.0005108046,0.0004318695,0.00001804407,0.0001606624],"genre_scores_gemma":[0.9283915,0.0008390281,0.06563561,0.0003568783,0.0001452217,0.000537894,0.00312945,0.0000459689,0.0009184314],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9162552,"threshold_uncertainty_score":0.2504968,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3021847850","doi":"10.1214/21-aoas1526","title":"Permutation tests under a rotating sampling plan with clustered data","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Forest ecology and management","field":"Environmental Science","cited_by":2,"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":"Permutation (music); Sampling (signal processing); Resampling; Statistics; Parametric statistics; Inference; Econometrics; Sampling distribution; Computer science; Mathematics; Artificial intelligence","authors":[{"name":"Jiahua Chen","is_ca":true},{"name":"Yukun Liu","is_ca":false},{"name":"Carilyn G. Taylor","is_ca":true},{"name":"James V. Zidek","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1241012765550882,"gpt":0.3257595050175824,"spread":0.2016582284624941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004496063,0.00006992635,0.00008639797,0.00001524535,0.000325169,0.00001086327,0.0004201974,0.0000104217,0.0006330819],"category_scores_gemma":[0.00001732998,0.00005289144,0.000005673553,0.0001124614,0.0001379342,0.00004049337,0.0007032655,0.0001058271,0.00002760155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001472786,"about_ca_system_score_gemma":0.0000106766,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006726577,"about_ca_topic_score_gemma":0.0002283424,"domain_scores_codex":[0.9992477,0.00003184881,0.0001443159,0.0001795397,0.000239184,0.0001574617],"domain_scores_gemma":[0.9992835,0.0001921803,0.0001377722,0.0003582127,0.000005316526,0.00002302634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0002069565,0.0001188532,0.001410868,0.0000231274,0.00006436541,0.000006403521,0.002051482,0.8558905,0.0002784115,0.114952,0.01523566,0.009761369],"study_design_scores_gemma":[0.00141849,0.0007591925,0.4313174,0.00001405325,0.0001735783,0.00001982036,0.009242653,0.1845738,0.0002303517,0.3602465,0.01138731,0.000616883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5487289,0.0000162247,0.4352711,0.001549715,0.00009219505,0.001003872,0.001114233,0.00005393726,0.01216986],"genre_scores_gemma":[0.9815085,0.000003651434,0.01719761,0.0009472806,0.000008239468,0.00003514707,0.0002202337,0.000009558759,0.00006979111],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6713167,"threshold_uncertainty_score":0.6931803,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4408584779","doi":"10.1214/24-aoas1964","title":"A three-state coupled Markov switching model for COVID-19 outbreaks across Quebec based on hospital admissions","year":2025,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"McGill University","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Outbreak; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Markov chain; Markov model; Statistics; State (computer science); Geography; Computer science; Econometrics; Virology; Medicine; Mathematics; Algorithm; Infectious disease (medical specialty)","authors":[{"name":"Dirk Douwes‐Schultz","is_ca":true},{"name":"Alexandra M. Schmidt","is_ca":true},{"name":"Yan Shen","is_ca":true},{"name":"David L. Buckeridge","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2507333540244364,"gpt":0.4762858184953547,"spread":0.2255524644709184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002246819,0.0003674483,0.0008022925,0.0000670226,0.0006586458,0.00004530097,0.0005795845,0.0001249151,0.00002708826],"category_scores_gemma":[0.01745434,0.000244935,0.0001866305,0.0002175467,0.000220962,0.00002399288,0.0002819496,0.000304504,0.000004490496],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000113769,"about_ca_system_score_gemma":0.0005712711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007725967,"about_ca_topic_score_gemma":0.003066955,"domain_scores_codex":[0.9976274,0.00006146231,0.0008565731,0.0004661459,0.0003558593,0.0006326074],"domain_scores_gemma":[0.9796067,0.01867719,0.0004927854,0.0007263509,0.0002481481,0.0002488151],"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":[0.00280898,0.0008542431,0.0001740617,0.00151777,0.0004297107,0.000006921042,0.005018089,0.1024792,0.0002395124,0.7004051,0.1703563,0.01570998],"study_design_scores_gemma":[0.0006141143,0.00008039689,0.0002436318,0.00004349174,0.00005396401,4.397257e-8,0.000185267,0.4867508,0.0000564796,0.5107318,0.001075567,0.0001644326],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008930438,0.00003497887,0.9701421,0.01647937,0.00007032019,0.001549945,0.002312441,0.0001282769,0.00035211],"genre_scores_gemma":[0.831948,0.00006427603,0.1432702,0.02328701,0.00005675944,0.0005911856,0.00006844397,0.00006078759,0.0006533493],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8268719,"threshold_uncertainty_score":0.998816,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}