{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":64,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":64,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"a2370beb7ca4","filters":{"venue":"Stat"}},"results":[{"id":"W2033713899","doi":"10.1002/sta4.43","title":"A mixture of common skew‐t factor analysers","year":2014,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":42,"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":"Cluster analysis; Mixture model; Expectation–maximization algorithm; Component (thermodynamics); Maximization; Factor (programming language); Correlation clustering","retraction":null,"screen_n_in":null,"score":{"opus":0.01268216102388279,"gpt":0.2760293468635502,"spread":0.2633471858396674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002151734,0.00008728879,0.0001883867,0.00006082019,0.00003317581,0.00002912045,0.0004686271,0.00004810535,0.00001614715],"category_scores_gemma":[0.00002491562,0.00006811344,0.00007319985,0.0002044834,0.00003038753,0.0001255664,0.00008846688,0.00009039418,0.0000077202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008970695,"about_ca_system_score_gemma":0.00001933492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002812206,"about_ca_topic_score_gemma":0.00001578621,"domain_scores_codex":[0.9992107,0.0001324153,0.0001454258,0.0001950222,0.0001546774,0.0001617201],"domain_scores_gemma":[0.9992386,0.000087236,0.00007435858,0.0004843026,0.00004138591,0.00007418692],"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":[0.000007799024,0.00007033981,0.001325667,0.00004601351,0.00004263963,0.000004881932,0.001997906,0.00001441635,0.007676349,0.3416377,0.003332205,0.6438441],"study_design_scores_gemma":[0.001306355,0.0005900993,0.01685415,0.00009055112,0.00005103696,0.00001721854,0.00003234614,0.16026,0.0637313,0.686875,0.0693025,0.0008894436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01173439,0.00007004057,0.9828755,0.0003749316,0.0001532413,0.00004999768,0.000005722618,0.00004206926,0.004694145],"genre_scores_gemma":[0.5618331,0.000004892668,0.4376844,0.0002573724,0.00002437776,0.00000133167,0.00000105821,0.000004265713,0.0001891513],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6429546,"threshold_uncertainty_score":0.2777585,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2950411888","doi":"10.1002/sta4.143","title":"A matrix variate skew‐<i>t</i> distribution","year":2017,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Canada Research Chairs","keywords":"Random variate; Matrix (chemical analysis); Skewness; Work (physics); Data Matrix; Multivariate normal distribution; Distribution (mathematics); Maximization","retraction":null,"screen_n_in":null,"score":{"opus":0.01635138442095585,"gpt":0.3195315884150852,"spread":0.3031802039941293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003309887,0.00007998394,0.00009797906,0.0000128567,0.0003550439,0.0003955259,0.0008219081,0.00004042558,0.000008687061],"category_scores_gemma":[0.00005288031,0.00006733335,0.00004626707,0.00003783851,0.00003446143,0.0004443943,0.0002523118,0.00008166514,0.00006245924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001973888,"about_ca_system_score_gemma":0.00003542136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004728754,"about_ca_topic_score_gemma":0.000004635554,"domain_scores_codex":[0.9992902,0.00004732056,0.00009698543,0.000233284,0.0001227955,0.0002093616],"domain_scores_gemma":[0.9988609,0.00002269528,0.0000900451,0.0009121397,0.0000381425,0.00007605252],"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":[0.000002992838,0.00001518885,0.00008460697,0.000005672347,0.000005904755,0.00001757644,0.0001247315,6.653726e-7,0.0004206697,0.8346812,0.004158299,0.1604826],"study_design_scores_gemma":[0.000518608,0.00006189862,0.007248441,0.00002161065,0.00001081784,0.00002190474,0.000001814906,0.02458742,0.002389371,0.8812623,0.08358889,0.0002869296],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006016935,0.00005835954,0.9914686,0.001635395,0.0005100982,0.00006973376,0.0000223946,0.00007664434,0.005557058],"genre_scores_gemma":[0.2872172,0.00002564818,0.7106784,0.0001676714,0.0001121876,0.000007667427,0.000007134269,0.000006323324,0.001777811],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2866155,"threshold_uncertainty_score":0.3814065,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1547093648","doi":"10.1002/sta4.42","title":"Quantile regression analysis of length‐biased survival data","year":2014,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council","keywords":"Covariate; Statistics; Censoring (clinical trials); Econometrics; Estimator; Quantile regression; Quantile; Population; Regression analysis; Asymptotic distribution; Mathematics; Computer science; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.263199802400526,"gpt":0.465014255199343,"spread":0.201814452798817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001000251,0.00008445742,0.000375977,0.00008481899,0.00003241362,0.00001185032,0.0003034894,0.00003895423,0.0005699231],"category_scores_gemma":[0.005503014,0.00006013196,0.00005101281,0.0003257972,0.00005757574,0.00004469766,0.0001350517,0.00007086911,0.000009211681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005758953,"about_ca_system_score_gemma":0.0000156382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007759093,"about_ca_topic_score_gemma":0.00005708426,"domain_scores_codex":[0.9988773,0.0002525334,0.0002789848,0.0002172318,0.0002369229,0.0001370009],"domain_scores_gemma":[0.995814,0.003012782,0.0001362988,0.0009085406,0.00007237173,0.0000560398],"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":[0.00007107212,0.0002369346,0.007982513,0.0001914694,0.000589909,0.000003335736,0.0004309827,0.000008361446,0.002465407,0.847896,0.008981727,0.1311423],"study_design_scores_gemma":[0.0008460088,0.0002610018,0.02963736,0.0001599494,0.002366745,5.659539e-7,0.0005556435,0.4530307,0.003484894,0.5009173,0.008261654,0.0004782278],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1114385,0.00001903141,0.88171,0.00006367254,0.0001576273,0.00006780274,0.0005437378,0.00003289355,0.00596676],"genre_scores_gemma":[0.6169848,0.00001189627,0.3826811,0.00002287989,0.00002910352,0.00000162131,0.00009571501,0.00001055281,0.0001622911],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5055463,"threshold_uncertainty_score":0.6588019,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2894669578","doi":"10.1002/sta4.205","title":"A doubly robust weighting estimator of the average treatment effect on the treated","year":2018,"lang":"en","type":"article","venue":"Stat","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Public Health Ontario; University of Toronto; McGill University; McGill University Health Centre","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Weighting; Mathematics; Statistics; Matching (statistics); Inverse probability weighting; Minimum-variance unbiased estimator; Estimation; Sampling (signal processing); Inverse; Computer science; Medicine; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1247763223054699,"gpt":0.3810167172586393,"spread":0.2562403949531693,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002141493,0.0001723253,0.0002065986,0.0000264292,0.000159266,0.00001598185,0.0001954193,0.00004555256,0.0001465256],"category_scores_gemma":[0.0003468468,0.00007003453,0.00008614703,0.00014166,0.0001651975,0.00004227021,0.00004981589,0.00008891736,0.00002677915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001153545,"about_ca_system_score_gemma":0.00002245133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004672037,"about_ca_topic_score_gemma":0.00004140418,"domain_scores_codex":[0.999182,0.0001292291,0.0001843047,0.0001505235,0.0001667749,0.0001871263],"domain_scores_gemma":[0.9981143,0.001099873,0.0001498215,0.0005510425,0.00005846914,0.00002652714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00114788,0.001499657,0.01087654,0.0004198199,0.000843125,0.00006082562,0.01071337,0.0002401771,0.1007215,0.7723602,0.02215567,0.07896125],"study_design_scores_gemma":[0.0005402692,0.002043269,0.0002445573,0.000240258,0.00007254972,0.000005891992,0.00004943638,0.001163903,0.9078532,0.08650281,0.001122794,0.000161017],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.977063,0.00001067865,0.008185042,0.0002815078,0.00007450223,0.0008922032,0.00002994416,0.0002178312,0.01324531],"genre_scores_gemma":[0.9916885,0.000002832741,0.007258102,0.00004731875,0.00004760914,0.00008036564,0.000001696421,0.00002585961,0.0008477222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8071318,"threshold_uncertainty_score":0.2855925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2894838513","doi":"10.1002/sta4.202","title":"A practical implementation of weighted kernel density estimation for handling shape constraints","year":2018,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Kernel density estimation; Estimator; Kernel (algebra); Simple (philosophy); Computer science; Process (computing); Density estimation; Algorithm; Variable kernel density estimation; Multivariate kernel density estimation; Mathematical optimization; Software; Kernel method; Applied mathematics; Mathematics; Artificial intelligence; Statistics; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1615686082529887,"gpt":0.4920312988856346,"spread":0.3304626906326459,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004380664,0.00006867629,0.0001513186,0.00002728095,0.00006401449,0.00001569264,0.00003517778,0.00003644302,0.0006357703],"category_scores_gemma":[0.002128377,0.00005963627,0.00002830082,0.00005617605,0.0001647155,0.00006297432,0.00001815258,0.00004285499,0.000008395124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002002845,"about_ca_system_score_gemma":0.00007335155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001630692,"about_ca_topic_score_gemma":0.00002203714,"domain_scores_codex":[0.9992811,0.00005606368,0.0002690949,0.0001263199,0.0001283568,0.000139079],"domain_scores_gemma":[0.997852,0.001574247,0.0001487856,0.00009719345,0.0002839197,0.00004384111],"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":[0.00007982248,0.00006702483,0.0006524001,0.0001491781,0.00003754401,0.000001212892,0.0007339558,6.18987e-8,0.00286205,0.765574,0.001741146,0.2281016],"study_design_scores_gemma":[0.0007770892,0.0003509689,0.002101425,0.00004550424,0.00007758262,0.000006455606,0.000575954,0.08158101,0.04133311,0.8729742,0.00006611065,0.0001105741],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1770413,0.000001004295,0.8221464,0.00011449,0.0000759281,0.0002522225,0.00007580483,0.00001806954,0.0002747535],"genre_scores_gemma":[0.4401338,5.835905e-7,0.5597891,0.00002325221,0.00002669856,0.000008929183,0.000006690075,0.000004751345,0.000006101243],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2630925,"threshold_uncertainty_score":0.6961239,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2948259043","doi":"10.1002/sta4.232","title":"Stochastic volatility generated by product autoregressive models","year":2019,"lang":"en","type":"article","venue":"Stat","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"University Grants Commission","keywords":"Autoregressive model; Stochastic volatility; STAR model; Econometrics; Volatility (finance); Markov chain; Nonlinear autoregressive exogenous model; SETAR; Mathematics; Hidden Markov model; Computer science; Applied mathematics; Autoregressive integrated moving average; Statistics; Time series; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02891016496328693,"gpt":0.2160526202988636,"spread":0.1871424553355766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003320989,0.0001703035,0.0003631688,0.0000820022,0.00008763032,0.00005029662,0.0001740126,0.00007848805,0.0003247585],"category_scores_gemma":[0.00008834365,0.0001879273,0.00007736116,0.0001453335,0.00003708846,0.0003519761,0.00005121325,0.0001802631,0.0005744314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009806159,"about_ca_system_score_gemma":0.00003878309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004593419,"about_ca_topic_score_gemma":0.00002200079,"domain_scores_codex":[0.9985439,0.00001387031,0.0004675351,0.0005842355,0.00005012988,0.000340321],"domain_scores_gemma":[0.9991859,0.00002771406,0.0001978737,0.0004469422,0.00006563216,0.00007599453],"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":[0.0005314774,0.00111055,0.193557,0.0004600075,0.0003808958,0.00001045201,0.01185795,0.3109242,0.003421566,0.4033095,0.05207713,0.02235929],"study_design_scores_gemma":[0.0003593852,0.00003814684,0.001574914,0.00001131675,0.000003087766,4.806791e-7,0.00002308831,0.9340349,0.00009618377,0.0609439,0.002664303,0.000250247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8609029,0.003275269,0.1303509,0.0001588606,0.0005837542,0.0004064971,0.0005318302,0.00007314111,0.00371679],"genre_scores_gemma":[0.9960351,0.00002562375,0.000644116,0.00007959651,0.00007058016,0.0000170207,0.00007444277,0.00002606292,0.003027435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6231108,"threshold_uncertainty_score":0.7663455,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3160667012","doi":"10.1002/sta4.390","title":"Robust penalized M‐estimation for function‐on‐function linear regression","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":12,"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 Science Foundation of Beijing Municipality; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Estimator; Robust regression; Linear regression; Function (biology); Regression; Mathematics; Computer science; Algorithm; Spline (mechanical); Applied mathematics; Mathematical optimization; Statistics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.2563523807401737,"gpt":0.4548840085520341,"spread":0.1985316278118604,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002703917,0.0001279512,0.0002032529,0.00003459165,0.0001613211,0.00002128534,0.00003798047,0.000068251,0.0002399079],"category_scores_gemma":[0.002203004,0.0001018069,0.00007613881,0.0001007729,0.00002212363,0.0001027224,0.00002092051,0.0001061822,0.00002318742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004052476,"about_ca_system_score_gemma":0.00004044235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.706927e-7,"about_ca_topic_score_gemma":0.000003453019,"domain_scores_codex":[0.9990172,0.00009422749,0.0002430089,0.0002727972,0.0001891943,0.0001835178],"domain_scores_gemma":[0.9982302,0.001137539,0.0001010304,0.0002365384,0.0002237213,0.00007101802],"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":[0.001143769,0.0002547888,0.000004246183,0.0003386687,0.00006452816,0.00001117771,0.0001503,0.006655858,0.003525928,0.8136027,0.02114055,0.1531075],"study_design_scores_gemma":[0.0009154108,0.0002344809,0.00001887833,0.00009303235,0.00008148939,0.000003102139,0.00008076386,0.1007357,0.002151828,0.8850614,0.01048992,0.0001339406],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008874133,0.0000456781,0.9965741,0.0002709212,0.0004775106,0.0002680123,0.00006569868,0.00009000544,0.001320662],"genre_scores_gemma":[0.005706945,0.00001454616,0.9887295,0.0002617709,0.0001457388,0.00007593321,0.0001059087,0.00003345016,0.004926176],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1529735,"threshold_uncertainty_score":0.4151565,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2790993801","doi":"10.1002/sta4.177","title":"Flexible clustering of high‐dimensional data via mixtures of joint generalized hyperbolic distributions","year":2018,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; McMaster University","funders":"Canada Research Chairs","keywords":"Identifiability; Cluster analysis; Bayesian information criterion; Computer science; Joint (building); Limiting; Mixture model; Determining the number of clusters in a data set; Mathematics; Selection (genetic algorithm); Subspace topology; Applied mathematics; Algorithm; Data mining; Statistics; Artificial intelligence; CURE data clustering algorithm; Correlation clustering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.05689455068376795,"gpt":0.3112572861862972,"spread":0.2543627355025292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000364858,0.0001045907,0.0002426177,0.00006382821,0.00007513689,0.00001885992,0.0007354877,0.00004668534,0.00004036517],"category_scores_gemma":[0.00003876594,0.00008606713,0.00004589537,0.0002289787,0.0001407232,0.0002169153,0.0008330572,0.00006637229,0.000005916944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001270751,"about_ca_system_score_gemma":0.00007207675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002556525,"about_ca_topic_score_gemma":0.00002373986,"domain_scores_codex":[0.9988822,0.00009656085,0.0002894345,0.0003177428,0.0002120247,0.0002020116],"domain_scores_gemma":[0.9985331,0.00004115816,0.0001261593,0.001084792,0.0001432832,0.00007151663],"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":[0.00006207282,0.0002386251,0.00005232927,0.0001066006,0.0001224695,0.000008807391,0.0006524777,0.0001456528,0.4380565,0.3324248,0.01503609,0.2130935],"study_design_scores_gemma":[0.0009879387,0.0002525194,0.001671358,0.00008772891,0.00003955173,0.0000410508,0.000003360748,0.3100134,0.497296,0.1859422,0.003328941,0.0003359522],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01360263,0.000200364,0.9848913,0.0003420415,0.0003806826,0.00008586918,0.0002001241,0.00003782201,0.0002591979],"genre_scores_gemma":[0.357144,0.000008962154,0.6425661,0.00008378312,0.00007506033,0.000001873837,0.00004288326,0.000005128463,0.00007213062],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3435414,"threshold_uncertainty_score":0.3509716,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1602858783","doi":"10.1002/sta4.40","title":"When are first‒order asymptotics adequate? A diagnostic","year":2014,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Engineering and Physical Sciences Research Council","keywords":"Collinearity; Boundary (topology); Inference; Class (philosophy); Skewness; Asymptotic analysis; Econometrics; Mathematics; Sample (material); Logistic regression; Applied mathematics; Mathematical economics; Computer science; Statistics; Mathematical analysis; Artificial intelligence; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.06422756562258991,"gpt":0.3386047526662154,"spread":0.2743771870436255,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003278671,0.0001509768,0.0002520646,0.00003308178,0.0000872184,0.00004467051,0.0001621522,0.00006849978,0.001303644],"category_scores_gemma":[0.02135346,0.0001230758,0.0000405485,0.00009263453,0.00007262798,0.00003935145,0.00006715519,0.0001441348,0.0003009659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002363009,"about_ca_system_score_gemma":0.00001818309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002417695,"about_ca_topic_score_gemma":0.00004675705,"domain_scores_codex":[0.9988773,0.000122688,0.0002506946,0.0002201488,0.000218355,0.0003107853],"domain_scores_gemma":[0.9902617,0.009034246,0.0001013977,0.0003500834,0.0001214373,0.0001311846],"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":[0.000009907741,0.0001275449,0.00486064,0.0001744741,0.00003291364,0.00001494264,0.000976205,0.000005658553,0.000006812247,0.9292826,0.0322407,0.03226759],"study_design_scores_gemma":[0.0003057474,0.000125038,0.00521689,0.0001131329,0.00004617955,0.000003224252,0.0001319211,0.003905313,0.00005089442,0.9744992,0.01538188,0.0002206352],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008674136,0.00004902254,0.9795744,0.0008692363,0.0003333174,0.0001807316,0.00004520142,0.00009875926,0.01017521],"genre_scores_gemma":[0.275805,0.00002174555,0.7218607,0.0004864634,0.0001893226,0.00004645575,0.00000479043,0.00004543849,0.001540133],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2671308,"threshold_uncertainty_score":0.9996093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3080792994","doi":"10.1002/sta4.310","title":"A family of parsimonious mixtures of multivariate Poisson‐lognormal distributions for clustering multivariate count data","year":2020,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":10,"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":"Count data; Multivariate statistics; Poisson distribution; Mathematics; Statistics; Multivariate normal distribution; Log-normal distribution; Cluster analysis; Latent variable; Multivariate t-distribution","retraction":null,"screen_n_in":null,"score":{"opus":0.08185702299938706,"gpt":0.3330524113410217,"spread":0.2511953883416346,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004590277,0.0001632772,0.0003484961,0.00003699476,0.00008304269,0.00003869433,0.001235982,0.00007292339,0.000002232362],"category_scores_gemma":[0.000260031,0.0001426841,0.00008516044,0.000230396,0.00006466196,0.0003491292,0.0007931461,0.0001162732,8.205636e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001631062,"about_ca_system_score_gemma":0.0001066313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002734685,"about_ca_topic_score_gemma":0.00001552359,"domain_scores_codex":[0.9984966,0.0001107471,0.0004180617,0.0004680857,0.0002019243,0.0003046151],"domain_scores_gemma":[0.9984627,0.0002610598,0.0002348808,0.0007553073,0.000156602,0.0001294223],"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":[0.0008141403,0.0007457993,0.0004278343,0.001320326,0.0006438546,0.00004954729,0.01351428,0.003643943,0.38678,0.3088297,0.009507087,0.2737235],"study_design_scores_gemma":[0.001355755,0.0002290768,0.001124097,0.00005607108,0.00004742402,0.000002972621,0.00003388201,0.9734407,0.0113751,0.007918878,0.004169255,0.0002467752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002256862,0.0002290838,0.9940991,0.0009031591,0.0002195781,0.0003657074,0.001773748,0.00005484986,0.00009792392],"genre_scores_gemma":[0.4237681,0.00001286944,0.5759174,0.0001569424,0.00003939924,0.000009840865,0.00007830458,0.000008570314,0.000008559547],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9697968,"threshold_uncertainty_score":0.5818488,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2890657944","doi":"10.1002/sta4.215","title":"Sharpen statistical significance: Evidence thresholds and Bayes factors sharpened into Occam's razor","year":2019,"lang":"en","type":"article","venue":"Stat","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Occam's razor; occam; Null hypothesis; Statistical hypothesis testing; Idealization; Mathematics; Statistics; Prior probability; p-value; Bayes factor; Computer science; Bayes' theorem; Bayesian probability; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.1533180712774028,"gpt":0.4287373050039204,"spread":0.2754192337265177,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001085322,0.0001664998,0.0002747066,0.0001089213,0.0001677985,0.0003529806,0.0006951271,0.00007452675,0.001425033],"category_scores_gemma":[0.001540584,0.0001163653,0.00004875915,0.0003956037,0.0001966205,0.0004269395,0.0002887495,0.0001558111,0.0004018519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000360538,"about_ca_system_score_gemma":0.00007640128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002763869,"about_ca_topic_score_gemma":0.00012345,"domain_scores_codex":[0.9977675,0.00007117048,0.0004379532,0.0006757914,0.000769623,0.000277927],"domain_scores_gemma":[0.9967709,0.0020705,0.0001480057,0.0006636247,0.0001729947,0.0001740395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001912356,0.0001424853,0.5458505,0.0000883125,0.00003500264,0.00001543567,0.003652367,0.00006337618,0.01833097,0.1375011,0.1712432,0.1228861],"study_design_scores_gemma":[0.000587887,0.00074906,0.1802426,0.0002498454,0.00003734236,0.00001425336,0.001695039,0.01325515,0.007320921,0.679345,0.1154923,0.001010564],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9499115,0.0001711608,0.04582501,0.001219534,0.0001333377,0.0006499264,0.000172871,0.0001412318,0.001775418],"genre_scores_gemma":[0.9746517,0.00003927957,0.02310992,0.000150367,0.0000291182,0.0000423345,0.00001427714,0.00001489048,0.001948135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5418439,"threshold_uncertainty_score":0.9994878,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1866446821","doi":"10.1002/sta4.95","title":"The perils of quasi‐likelihood information criteria","year":2015,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Jewish General Hospital; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Selection (genetic algorithm); Correlation; Statistics; Econometrics; Model selection; Information Criteria; Mathematics; Sample (material); Matrix (chemical analysis); Computer science; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.08157430578771294,"gpt":0.4012855105905634,"spread":0.3197112048028504,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006214388,0.00005701173,0.0001112271,0.00001850141,0.0000445204,0.00004432071,0.0001066705,0.00002591871,0.00006080456],"category_scores_gemma":[0.002719523,0.00003459454,0.00002220358,0.00007073016,0.00006692616,0.0001336577,0.00003062988,0.00005180566,0.00003214082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001520918,"about_ca_system_score_gemma":0.00005629879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000018927,"about_ca_topic_score_gemma":0.000006499106,"domain_scores_codex":[0.9993066,0.00008393487,0.0002488963,0.00004290935,0.0001848742,0.0001328239],"domain_scores_gemma":[0.9988242,0.0006616971,0.00009306123,0.0001780081,0.0001772842,0.0000657366],"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":[0.00003099925,0.00002278251,0.00008069297,0.0000500412,0.000008197816,4.741803e-7,0.001969298,2.442521e-8,0.0000582951,0.8194336,0.01237484,0.1659708],"study_design_scores_gemma":[0.0001777198,0.0001132991,0.0002655469,0.00001588669,0.00000880583,0.000001887576,0.001146627,0.000520087,0.0004771254,0.9879758,0.009243929,0.00005333855],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005503712,0.00002719385,0.9792522,0.000285907,0.0002473534,0.0001182999,0.00005185023,0.0000241725,0.01448938],"genre_scores_gemma":[0.1954196,0.0000131511,0.8043441,0.00008167166,0.00004740266,0.00001450689,0.000004478305,0.000007410746,0.00006766154],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1899159,"threshold_uncertainty_score":0.325572,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2279116951","doi":"10.1002/sta4.102","title":"A genome‐wide association study of multiple longitudinal traits with related subjects","year":2016,"lang":"en","type":"article","venue":"Stat","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"National Heart, Lung, and Blood Institute; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Framingham Heart Study; Pleiotropy; Trait; Type I and type II errors; Genetic association; Biology; Random effects model; Genome-wide association study; Quantitative trait locus; Statistical power; Single-nucleotide polymorphism; Genetics; Phenotype; Computational biology; Statistics; Gene; Computer science; Meta-analysis; Mathematics; Framingham Risk Score; Medicine; Genotype; Disease; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01127690114381227,"gpt":0.2104456684246835,"spread":0.1991687672808712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001108713,0.00007291263,0.00009996451,0.00002274782,0.00004507748,0.000006211591,0.00006916482,0.00005250083,0.00002313824],"category_scores_gemma":[0.000103272,0.00004711059,0.00002503955,0.00004341545,0.00001612094,0.000001950716,0.00003067469,0.0000233331,0.000006321186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001003534,"about_ca_system_score_gemma":0.00002374444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002788698,"about_ca_topic_score_gemma":0.0001144321,"domain_scores_codex":[0.9994241,0.00003383469,0.0001047767,0.0001765973,0.0001250172,0.0001356985],"domain_scores_gemma":[0.9996663,0.00003502141,0.00009027204,0.0000956474,0.00007550711,0.0000372554],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000168072,0.0001613848,0.7644367,0.000006455405,0.0001214616,0.000004753907,0.0002330508,0.00001724196,0.2340135,0.000002387769,0.0003953806,0.0004396162],"study_design_scores_gemma":[0.00229276,0.002076652,0.9818228,0.00001526386,0.00003495996,0.000002143895,0.0005038386,0.000001917731,0.0111982,0.0000163583,0.001913561,0.0001215179],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989895,0.00004506172,0.0001895849,0.00006796838,0.00002742242,0.000123083,0.00004476368,0.000006759471,0.0005059213],"genre_scores_gemma":[0.9975451,0.0000293807,0.0001082582,0.00001736381,0.00001821516,0.000002633403,0.0000150228,0.000005075228,0.002258926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2228153,"threshold_uncertainty_score":0.1921114,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2770285924","doi":"10.1002/sta4.167","title":"Bump hunting by topological data analysis","year":2017,"lang":"en","type":"article","venue":"Stat","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Studienstiftung des Deutschen Volkes","keywords":"Statistical inference; Persistent homology; Topological data analysis; Inference; Kernel density estimation; Computer science; Kernel (algebra); Data set; Statistical hypothesis testing; Statistical analysis; Algorithm; Mathematics; Data mining; Topology (electrical circuits); Statistics; Discrete mathematics; Artificial intelligence; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.07395390870928459,"gpt":0.3424577054442873,"spread":0.2685037967350027,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0004828981,0.000103395,0.0002593464,0.0001525423,0.0005481624,0.0007078116,0.00558001,0.00005441949,0.000320855],"category_scores_gemma":[0.0009452458,0.00007191251,0.00009977363,0.0008083986,0.0001396532,0.0008953024,0.003314095,0.0001115632,0.0001232572],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009901897,"about_ca_system_score_gemma":0.00001191305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008703967,"about_ca_topic_score_gemma":0.0001219842,"domain_scores_codex":[0.9985317,0.00004634419,0.0001856548,0.0006672135,0.0002661862,0.0003029166],"domain_scores_gemma":[0.9960227,0.0001574849,0.0001616727,0.003511539,0.00003448856,0.0001121136],"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":[0.000009763733,0.0003659007,0.3903705,0.000009248495,0.001751183,0.000171082,0.0001219309,0.00005809475,0.0002377104,0.1101126,0.06801969,0.4287724],"study_design_scores_gemma":[0.0006842316,0.0001890178,0.4107007,0.000005762033,0.001015382,0.000007978079,0.0001280655,0.189515,0.0003774202,0.03056442,0.3657519,0.00106013],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03150123,0.0003446935,0.9540554,0.006349409,0.0001834045,0.00005053561,0.00033952,0.0001401524,0.007035626],"genre_scores_gemma":[0.9760015,0.00006240905,0.02161041,0.0003477878,0.00005162359,0.000001824135,0.0001976994,0.000002134472,0.001724595],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9445003,"threshold_uncertainty_score":0.9998003,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2315177202","doi":"10.1002/sta4.101","title":"Estimation, filtering and smoothing in the stochastic conditional duration model: an estimating function approach","year":2016,"lang":"en","type":"article","venue":"Stat","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":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Science and Engineering Research Board","keywords":"Smoothing; Duration (music); Estimation; Econometrics; Computer science; Conditional expectation; Computation; Likelihood function; Function (biology); Stochastic modelling; Estimation theory; Mathematical optimization; Mathematics; Algorithm; Statistics; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.0465470941523309,"gpt":0.2428213682041852,"spread":0.1962742740518543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000622427,0.0000766153,0.000112954,0.00009089251,0.0001505312,0.0000672802,0.00006249606,0.00004086509,0.00001027043],"category_scores_gemma":[0.0001759494,0.00006041469,0.00001687862,0.00007383235,0.00003076429,0.0006473023,0.0000159006,0.00007131733,0.000008239364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004247922,"about_ca_system_score_gemma":0.00001141092,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005995925,"about_ca_topic_score_gemma":0.00001939079,"domain_scores_codex":[0.9992649,0.00001446425,0.000328207,0.0002237842,0.00003727024,0.0001313522],"domain_scores_gemma":[0.9996582,0.00006749815,0.0001171654,0.0001194011,0.00001557234,0.00002222031],"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":[0.00002982071,0.00005102492,0.003015234,0.00003223697,0.000005618217,3.707979e-7,0.003791961,0.6809257,0.0001056644,0.2914057,0.00002860418,0.02060806],"study_design_scores_gemma":[0.0001835223,0.0000203001,0.004659285,0.00001296026,0.000001585728,0.00000148798,0.00009035294,0.7704468,0.000001894841,0.2245069,0.000006939315,0.00006798503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2745875,0.00004835259,0.7247561,0.0001219661,0.00004998669,0.00009815415,0.00003686404,0.00001554479,0.0002855446],"genre_scores_gemma":[0.9625815,0.000003382418,0.03721287,0.0000608613,0.0000492678,0.00002966516,0.00003708542,0.000008571265,0.00001685322],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.687994,"threshold_uncertainty_score":0.246364,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2986321504","doi":"10.1002/sta4.270","title":"Testing prediction algorithms as null hypotheses: Application to assessing the performance of deep neural networks","year":2020,"lang":"en","type":"article","venue":"Stat","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Computer science; Algorithm; Machine learning; Bayesian probability; Artificial intelligence; Posterior predictive distribution; Predictive value; Set (abstract data type); Bayesian linear regression; Bayesian inference","retraction":null,"screen_n_in":null,"score":{"opus":0.1237782181359969,"gpt":0.3795740915048949,"spread":0.255795873368898,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007661847,0.00008516942,0.0001199752,0.00004095762,0.0002468509,0.0001479705,0.0005243209,0.00003566036,0.00001999303],"category_scores_gemma":[0.001075893,0.00005533138,0.00003741861,0.001147397,0.00006733683,0.0002013164,0.0001285014,0.0001313098,0.00003312158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001702363,"about_ca_system_score_gemma":0.00001796708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003316467,"about_ca_topic_score_gemma":0.000002448427,"domain_scores_codex":[0.9986348,0.00005052265,0.0003992547,0.0002919238,0.0004651012,0.0001583935],"domain_scores_gemma":[0.9983584,0.0007395097,0.0002233155,0.0003522432,0.0002434656,0.00008305347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008788189,0.00001731751,0.01391803,0.000005115005,0.000003187582,2.550643e-7,0.0005504778,0.07946551,0.002487134,0.0003114635,0.001041397,0.9021913],"study_design_scores_gemma":[0.00003880244,0.0001281599,0.01236298,0.000008239148,0.000005439562,0.000003986339,0.0003060199,0.9830521,0.0006772236,0.001133563,0.002227102,0.00005632885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3706658,0.0000199671,0.6259232,0.001508382,0.00004478381,0.0003565174,0.000008298922,0.0001122463,0.001360848],"genre_scores_gemma":[0.9693588,0.000001825313,0.02984415,0.0005352796,0.0001514891,0.00007520529,0.00000379663,0.00001037857,0.00001905917],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9035866,"threshold_uncertainty_score":0.2256348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3173482532","doi":"10.1002/sta4.398","title":"A (non‐central) chi‐squared mixture of non‐central chi‐squareds is (non‐central) chi‐squared and related results, corollaries and applications","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Chi-square test; Mathematics; Mean squared error; Representation (politics); Distribution (mathematics); Square (algebra); Degrees of freedom (physics and chemistry); Statistics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.006693404061062815,"gpt":0.2413898459035121,"spread":0.2346964418424493,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004767604,0.0007086528,0.001012654,0.0002217335,0.000522504,0.0004460861,0.0008742138,0.0004917458,0.00004811984],"category_scores_gemma":[0.0001173882,0.0006727147,0.000272116,0.001307725,0.0004274225,0.000665963,0.000529705,0.0007096202,0.000008644717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001195959,"about_ca_system_score_gemma":0.000676304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001610615,"about_ca_topic_score_gemma":0.00009413741,"domain_scores_codex":[0.9947386,0.0002908699,0.001191674,0.001657266,0.00065257,0.001469045],"domain_scores_gemma":[0.9965064,0.0001814506,0.000515135,0.00168401,0.0003429438,0.0007700927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001540506,0.002487067,0.008626435,0.002429168,0.002205665,0.0009224605,0.1533951,0.0003839937,0.05380498,0.1470891,0.04681002,0.5803055],"study_design_scores_gemma":[0.03895804,0.002669377,0.1637967,0.002525977,0.001798381,0.002427571,0.004160851,0.2702017,0.1395895,0.1777532,0.1870952,0.009023511],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03379746,0.004917732,0.951628,0.003320957,0.0007725137,0.001513109,0.0007225165,0.0002187688,0.003108954],"genre_scores_gemma":[0.7300434,0.002992292,0.2632913,0.0009484519,0.0003052567,0.0001301286,0.0003450152,0.0001060974,0.001838133],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6962459,"threshold_uncertainty_score":0.9995724,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1589625890","doi":"10.1002/sta4.37","title":"Space–time clustering and the permutation moments of quadratic forms","year":2013,"lang":"en","type":"article","venue":"Stat","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; National Natural Science Foundation of China; National Institute of General Medical Sciences; National Institute of Mental Health; Ontario Genomics Institute; Cystic Fibrosis Canada; National Institute of Environmental Health Sciences; Genome Canada; Ontario Genomics; Cystic Fibrosis Foundation","keywords":"Permutation (music); Cluster analysis; Mathematics; Quadratic equation; Resampling; Statistics; Applied mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.005786903623471097,"gpt":0.2361786579133461,"spread":0.230391754289875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001575559,0.00004683178,0.00008637589,0.00001018975,0.00003952063,0.000007004305,0.00004101083,0.00003993684,0.00002843884],"category_scores_gemma":[0.00008713962,0.00002961944,0.00002471431,0.00002023548,0.0000688436,0.000002089136,0.00004409595,0.00002055352,0.00001215738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000039446,"about_ca_system_score_gemma":0.000009603849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005137306,"about_ca_topic_score_gemma":0.0000169077,"domain_scores_codex":[0.9996213,0.00004737408,0.0001191527,0.00008380973,0.00003562102,0.00009268438],"domain_scores_gemma":[0.9997541,0.00002565274,0.00006804273,0.00009757193,0.000035614,0.00001896191],"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":[0.0002226936,0.0001110343,0.09691342,0.0001351109,0.0004987395,6.456456e-7,0.003274313,0.002261456,0.8440672,0.001574459,0.01692778,0.03401315],"study_design_scores_gemma":[0.01128407,0.001429787,0.7945104,0.00005877266,0.0001948953,0.00003860267,0.005572536,0.1047839,0.03282142,0.03718845,0.01120241,0.0009148693],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9945311,0.0002189308,0.0033978,0.000749647,0.00002539344,0.0001654435,0.000004014682,0.000001948726,0.0009057313],"genre_scores_gemma":[0.9977908,0.0001151837,0.0009402447,0.0001144478,0.00001916148,0.00002312755,0.00002585142,0.000004493577,0.0009667392],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8112458,"threshold_uncertainty_score":0.1207846,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2902433780","doi":"10.1002/sta4.209","title":"Semiparametric estimation for the accelerated failure time model with length‐biased sampling and covariate measurement error","year":2018,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Covariate; Estimator; Inference; Robustness (evolution); Observational error; Statistics; Truncation (statistics); Accelerated failure time model; Censoring (clinical trials); Computer science; Term (time); Statistical inference; Econometrics; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.3881950526518411,"gpt":0.4202038450159468,"spread":0.03200879236410575,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008421675,0.0001272058,0.0001741598,0.00004372208,0.0002075633,0.00008569523,0.00008948521,0.00004484564,0.00008275711],"category_scores_gemma":[0.00269797,0.00007497126,0.00001809988,0.0001898416,0.00009224658,0.00006440705,0.00002319933,0.00008275251,0.00000828375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003907229,"about_ca_system_score_gemma":0.00006676018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001461452,"about_ca_topic_score_gemma":0.00001701448,"domain_scores_codex":[0.9991098,0.00005100608,0.0001935021,0.0001936223,0.000251562,0.0002005198],"domain_scores_gemma":[0.9976834,0.001568422,0.00009756179,0.000193119,0.0004026148,0.00005490027],"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":[0.002242284,0.0006292156,0.0002727681,0.001250514,0.001086639,0.000004144335,0.008617914,0.01307976,0.02499048,0.5003832,0.01988246,0.4275606],"study_design_scores_gemma":[0.0004954938,0.0001892243,0.0001397313,0.00004814013,0.00009265304,0.000001547593,0.0000605364,0.8393717,0.0008995709,0.1584778,0.0001125714,0.000110993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01621262,0.00002190638,0.9826484,0.0002698409,0.00002937988,0.000551878,0.0000648705,0.00004647734,0.0001546059],"genre_scores_gemma":[0.2666347,0.000001870556,0.7331346,0.00007188932,0.00002485903,0.00005100766,0.000003953772,0.00001626824,0.00006080591],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.826292,"threshold_uncertainty_score":0.3229917,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2149706056","doi":"10.1002/sta4.46","title":"Propensity score estimation in the presence of length‐biased sampling: a non‐parametric adjustment approach","year":2014,"lang":"en","type":"article","venue":"Stat","topic":"Advanced Causal Inference Techniques","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":"McGill University","funders":"National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Propensity score matching; Estimator; Statistics; Econometrics; Hazard ratio; Parametric statistics; Survival analysis; Proportional hazards model; Estimation; Survival function; Sample size determination; Mathematics; Parametric model; Economics; Confidence interval","retraction":null,"screen_n_in":null,"score":{"opus":0.3111569212399656,"gpt":0.4069571527771932,"spread":0.09580023153722766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008884515,0.0001221615,0.0002336958,0.000118289,0.00003468548,0.00001601278,0.0002724284,0.00005471527,0.000008829698],"category_scores_gemma":[0.002111691,0.00008183145,0.00003381533,0.000419841,0.00008315637,0.0001391763,0.00006253801,0.0001790684,0.000003138164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005072592,"about_ca_system_score_gemma":0.00003042764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005294646,"about_ca_topic_score_gemma":0.00001383743,"domain_scores_codex":[0.9988844,0.0001369294,0.0002973466,0.0001943296,0.0003025751,0.0001843607],"domain_scores_gemma":[0.998335,0.0008886686,0.0001874692,0.0004755054,0.00008724484,0.00002612201],"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":[0.0003610673,0.004101573,0.01476411,0.003321044,0.00009627997,0.000009145262,0.02191022,0.01401141,0.009446794,0.6946422,0.004265159,0.233071],"study_design_scores_gemma":[0.000828602,0.0006016845,0.02189521,0.00032241,0.00006110014,0.00001114242,0.0008148155,0.1745643,0.01959657,0.780719,0.0001639072,0.0004212007],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3609091,0.00001610028,0.6364933,0.00002780505,0.00001852197,0.0008266799,0.000004159291,0.00005788846,0.001646406],"genre_scores_gemma":[0.7526736,0.000006808349,0.2471516,0.00003006277,0.000009332389,0.00008923553,0.000007268115,0.000009546176,0.00002247254],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3917645,"threshold_uncertainty_score":0.333699,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3008466225","doi":"10.1002/sta4.280","title":"A note on the applicability of the standard nonparametric maximum likelihood estimator for combined incident and prevalent cohort data","year":2020,"lang":"en","type":"article","venue":"Stat","topic":"Healthcare Policy and Management","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Nonparametric statistics; Statistics; Cohort; Econometrics; Kaplan–Meier estimator; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07488844920871786,"gpt":0.3024316783904521,"spread":0.2275432291817343,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001102792,0.0001055135,0.0002836271,0.00003916852,0.0001169886,0.00003353965,0.000485751,0.00003747187,0.00002959299],"category_scores_gemma":[0.000909166,0.00007384674,0.00005377796,0.0002362143,0.00007764254,0.00005410505,0.0004074548,0.0001130559,0.00001683649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006944536,"about_ca_system_score_gemma":0.00004197619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003238932,"about_ca_topic_score_gemma":0.00005629897,"domain_scores_codex":[0.9988544,0.00002994565,0.0004423998,0.0003911799,0.00007233465,0.0002097262],"domain_scores_gemma":[0.9985355,0.00029371,0.0002407026,0.0008125149,0.00002818495,0.00008943218],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009200323,0.0004165148,0.1475385,0.002255754,0.0003248058,0.000001439627,0.002265286,0.000110081,0.00001607474,0.7598454,0.03376048,0.05254564],"study_design_scores_gemma":[0.002738257,0.001417048,0.1807083,0.00006626378,0.00008618548,8.241491e-7,0.0002704247,0.04028714,0.0004199065,0.2485784,0.5249293,0.0004980363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6001856,0.001182509,0.1107448,0.2570927,0.0005969079,0.01055121,0.01515983,0.0000772867,0.004409105],"genre_scores_gemma":[0.9961157,0.0001392301,0.001086577,0.00244809,0.00003633789,0.000124245,0.00001866465,0.00001305514,0.00001812833],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5112669,"threshold_uncertainty_score":0.3011383,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4282827685","doi":"10.1002/sta4.481","title":"Collaborative biostatistics and epidemiology in academic medical centres: A survey to assess relationships with health researchers and ethical implications","year":2022,"lang":"en","type":"article","venue":"Stat","topic":"Diversity and Career in Medicine","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"National Center for Advancing Translational Sciences","keywords":"Biostatistics; Epidemiology; Medical education; Medicine; Engineering ethics; Psychology; Family medicine; Engineering; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.4603954431970242,"gpt":0.5285932392547489,"spread":0.06819779605772464,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01792342,0.00004599199,0.0001554214,0.00009525353,0.0008400456,0.00001237133,0.0001739287,0.0001100455,0.00006809535],"category_scores_gemma":[0.01690862,0.00004282924,0.00000371724,0.0007880453,0.0007253697,0.00003054967,0.0001594474,0.001297517,0.000001324098],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002004763,"about_ca_system_score_gemma":0.001292445,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.008092443,"about_ca_topic_score_gemma":0.08237393,"domain_scores_codex":[0.9928337,0.005937416,0.0001753122,0.0002104401,0.0005487023,0.0002943852],"domain_scores_gemma":[0.992536,0.006803151,0.00005150603,0.00006702504,0.0001056608,0.0004366332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006126018,0.0000108083,0.8032324,0.000006852855,0.00000593606,0.000005180525,0.03128736,0.000009116192,2.406416e-7,0.1472832,0.01651047,0.001587198],"study_design_scores_gemma":[0.0003208194,0.0001844947,0.8485194,0.00002046697,0.000003027963,0.000001822296,0.1277729,0.00003333285,5.498571e-8,0.00655962,0.01652338,0.00006076177],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.4250927,0.0007515473,0.00388478,0.5674998,0.00009475232,0.0007464653,0.000918638,0.00002788356,0.0009833559],"genre_scores_gemma":[0.9909323,0.0008782015,0.001296489,0.006672666,0.00002060573,0.00002951023,0.00007588464,0.000003882388,0.00009045441],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5658396,"threshold_uncertainty_score":0.9985127,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4378506279","doi":"10.1002/sta4.622","title":"Asymptotic tail properties of Poisson mixture distributions","year":2023,"lang":"en","type":"article","venue":"Stat","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":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Agence Nationale de la Recherche","keywords":"Poisson distribution; Overdispersion; Zero-inflated model; Mixing (physics); Mathematics; Compound Poisson distribution; Statistical physics; Maxima; Count data; Mixture model; Distribution (mathematics); Statistics; Applied mathematics; Mathematical analysis; Poisson regression; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.08475699466675096,"gpt":0.3555196375169224,"spread":0.2707626428501715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001943322,0.00007914636,0.000169908,0.00003784243,0.00005590672,0.0000141851,0.00009420041,0.00004249918,0.0001338684],"category_scores_gemma":[0.001713854,0.00005697091,0.0000412511,0.0002688454,0.00008958963,0.00003214712,0.00004284441,0.00008191575,0.00006399049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001635778,"about_ca_system_score_gemma":0.0000326347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001775574,"about_ca_topic_score_gemma":0.000007070595,"domain_scores_codex":[0.9992898,0.00006621316,0.0001914748,0.0001138425,0.0001529875,0.0001857151],"domain_scores_gemma":[0.9992871,0.0003526798,0.00005366821,0.0001779817,0.0000796478,0.00004898134],"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":[0.00001464888,0.00006344981,0.0003689989,0.0003482341,0.00002777323,0.000009027362,0.0005054463,2.994528e-7,0.00803831,0.959525,0.01158481,0.01951401],"study_design_scores_gemma":[0.0001340863,0.0000601551,0.002321549,0.0001296897,0.00003105558,0.000002288926,0.0002141237,0.0004212599,0.01425176,0.9814502,0.0008757097,0.0001081049],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1252242,0.00007768992,0.86977,0.001065869,0.0002331184,0.0002764035,0.0005718311,0.0002299083,0.002551026],"genre_scores_gemma":[0.816985,0.000017972,0.1820865,0.00001843032,0.00003840603,0.00002232535,0.00001855627,0.00001560937,0.0007971773],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6917608,"threshold_uncertainty_score":0.2323206,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3101355431","doi":"10.1002/sta4.328","title":"Forecasting subnational COVID‐19 mortality using a day‐of‐the‐week adjusted Bayesian hierarchical model","year":2020,"lang":"en","type":"article","venue":"Stat","topic":"COVID-19 epidemiological studies","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":"Ontario Power Generation; University of Toronto; Centre for Global Health Research; St. Michael's Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Coronavirus disease 2019 (COVID-19); Social distance; Death toll; Bayesian probability; Pandemic; Estimation; Econometrics; Statistics; Demography; Bayesian hierarchical modeling; Geography; Medicine; Bayes' theorem; Computer science; Environmental health; Mathematics; Economics; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.6383185632529674,"gpt":0.4568217987807719,"spread":0.1814967644721955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008208862,0.0001722475,0.0004071538,0.00002525673,0.0002383226,0.00001121687,0.0002671556,0.00008151763,0.00006602212],"category_scores_gemma":[0.02648192,0.0001218166,0.00017557,0.0002941617,0.0002329376,0.00005937624,0.0003754961,0.0002645325,0.000001427889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001549783,"about_ca_system_score_gemma":0.000236672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009406598,"about_ca_topic_score_gemma":0.0001099803,"domain_scores_codex":[0.9981002,0.000315967,0.0005515589,0.0003337652,0.0003979407,0.0003005529],"domain_scores_gemma":[0.9959947,0.003215037,0.0002524076,0.0002279252,0.00008944638,0.0002204697],"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":[0.0003717738,0.0007338964,0.2881251,0.002961752,0.0007494457,0.00008169365,0.01697582,0.178255,0.002463025,0.4895625,0.01681402,0.002905935],"study_design_scores_gemma":[0.0002335247,0.00002771109,0.001997505,0.00001913592,0.0000466332,0.000001850148,0.00009282838,0.6723622,0.00003953075,0.3249562,0.0001151189,0.0001077618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3616354,0.00004295726,0.6289467,0.008198568,0.00005427761,0.0003624135,0.0001601334,0.00009225889,0.0005073071],"genre_scores_gemma":[0.960175,0.000002464333,0.03680174,0.002879439,0.00008067786,0.00001223085,0.000006952037,0.00001749108,0.00002399152],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5985397,"threshold_uncertainty_score":0.9817184,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388442618","doi":"10.1002/sta4.630","title":"Mediation analysis with latent factors using simultaneous group‐wise and parameter‐wise penalization","year":2023,"lang":"en","type":"article","venue":"Stat","topic":"Multi-Criteria Decision Making","field":"Decision 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 Waterloo","funders":"","keywords":"Latent variable; Mediation; Latent variable model; Structural equation modeling; Set (abstract data type); Multivariate statistics; Dimension (graph theory); Outcome (game theory); Variable (mathematics); Feature selection; Latent class model; Computer science; Econometrics; Statistics; Data mining; Mathematics; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.176136432841983,"gpt":0.4149364984835175,"spread":0.2388000656415346,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001340049,0.00019848,0.0003910497,0.001200609,0.0002241008,0.0005782681,0.0002824872,0.0000750714,0.0003051693],"category_scores_gemma":[0.004024482,0.0001323155,0.0000981639,0.004028559,0.00008285339,0.0004615069,0.0001489758,0.00008626094,0.00007301581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006374776,"about_ca_system_score_gemma":0.0000291855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001034175,"about_ca_topic_score_gemma":0.0003259697,"domain_scores_codex":[0.9964525,0.0002594776,0.000622059,0.0006592989,0.001699229,0.0003074314],"domain_scores_gemma":[0.9948478,0.003818893,0.0003399799,0.0004970822,0.0003277386,0.0001684524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002158798,0.00006807412,0.6005672,0.00001455403,0.0002855079,0.0002273706,0.00643967,0.337945,0.003710691,0.0001309839,0.0003345697,0.05006053],"study_design_scores_gemma":[0.0003688448,0.00005655422,0.07454905,0.00001138113,0.0001275007,0.00000388068,0.001006526,0.9212847,0.00009510465,0.001867671,0.0004201728,0.0002086114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8775855,0.00003430945,0.1217886,0.00005939755,0.0001835943,0.0001928315,0.00004936321,0.00008729476,0.00001917899],"genre_scores_gemma":[0.9946141,0.00002239807,0.004990659,0.00004757434,0.00003155907,0.000004377123,0.00007503024,0.00002047901,0.0001937926],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5833397,"threshold_uncertainty_score":0.5576252,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2551761829","doi":"10.1002/sta4.113","title":"Visualization of robust L1PCA","year":2016,"lang":"en","type":"article","venue":"Stat","topic":"Advanced Statistical Methods and Models","field":"Mathematics","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":"Ontario Genomics Institute; Cystic Fibrosis Canada; Genome Canada; Ontario Genomics; Cystic Fibrosis Foundation","keywords":"Principal component analysis; Outlier; Visualization; Robust principal component analysis; Computer science; Representation (politics); Principal (computer security); Population; Norm (philosophy); Population stratification; Data set; Set (abstract data type); Data mining; Mathematics; Artificial intelligence; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.1772460752989591,"gpt":0.4623745827884682,"spread":0.285128507489509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001279597,0.00004598225,0.0001049184,0.00001876845,0.00001488528,0.000001836331,0.00003831449,0.00002124499,0.0001613849],"category_scores_gemma":[0.0007894125,0.00002744174,0.00001908368,0.00004159644,0.00003727185,0.00004896959,0.00001621759,0.0000130978,0.000006636201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000111755,"about_ca_system_score_gemma":0.000009131381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000128497,"about_ca_topic_score_gemma":0.000002330633,"domain_scores_codex":[0.9995512,0.00003759107,0.0001445453,0.00008311642,0.00009286299,0.00009061882],"domain_scores_gemma":[0.9991738,0.0005640383,0.00005839412,0.0001136983,0.00005926018,0.00003086562],"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":[0.00001081183,0.00002566335,0.00003825962,0.00003424485,0.000005006077,7.89032e-7,0.00007858392,0.000004786856,0.00475462,0.9442906,0.0007222597,0.05003433],"study_design_scores_gemma":[0.0002169164,0.00004510854,0.0000395357,0.0000422912,0.000008610958,5.255292e-7,0.00001951733,0.0003634418,0.007405932,0.9904889,0.001315217,0.00005398809],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002713376,0.00001226968,0.9942695,0.00005919991,0.00004874013,0.00006207838,0.00003398033,0.00002383194,0.002777006],"genre_scores_gemma":[0.1280865,0.00002508083,0.8704308,0.0000213882,0.00002303678,0.000004887196,0.000001137507,0.00001427039,0.001392885],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1253732,"threshold_uncertainty_score":0.1767052,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391244114","doi":"10.1002/sta4.641","title":"Differentially private outcome‐weighted learning for optimal dynamic treatment regime estimation","year":2024,"lang":"en","type":"article","venue":"Stat","topic":"Privacy-Preserving Technologies in Data","field":"Computer 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":"McGill University; University of New Brunswick","funders":"Canadian Statistical Sciences Institute; Fonds de Recherche du Québec - Santé; National Institutes of Health; National Institute of Mental Health; Canada Excellence Research Chairs, Government of Canada","keywords":"Differential privacy; Computer science; Support vector machine; Leverage (statistics); Machine learning; Context (archaeology); Artificial intelligence; Estimator; Data mining; Precision medicine; Outcome (game theory); Information privacy; Set (abstract data type); Mathematics; Computer security; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02996735987845892,"gpt":0.3163899338247644,"spread":0.2864225739463054,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0001666391,0.0001893845,0.0001819442,0.0001756742,0.0001405294,0.0004030283,0.005184174,0.00008384882,0.00001113247],"category_scores_gemma":[0.001502746,0.0001541035,0.00008539291,0.0002848125,0.00004673414,0.0005506175,0.008397186,0.0001582203,0.00006325329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002801739,"about_ca_system_score_gemma":0.0000511616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001044231,"about_ca_topic_score_gemma":0.000005566251,"domain_scores_codex":[0.9986175,0.00003716526,0.0002501767,0.0005568594,0.0001905534,0.0003476996],"domain_scores_gemma":[0.9971772,0.0002261552,0.00006580003,0.002457397,0.00002927033,0.00004421972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002977025,0.0001020428,0.0004501851,0.0001990086,0.000191361,0.00007639838,0.0003782525,0.00123549,0.00202724,0.02904011,0.01089679,0.9553733],"study_design_scores_gemma":[0.0002488986,0.0002188824,0.0002745798,0.0000422189,0.00001817904,0.00000699893,0.000006350065,0.9142307,0.001308798,0.07705989,0.006423715,0.0001607832],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05174463,0.0002007916,0.9365358,0.008440658,0.0005304282,0.0003558284,0.00002555543,0.002087193,0.00007907343],"genre_scores_gemma":[0.3285601,0.000046367,0.6705488,0.00001568935,0.00001631811,0.00008444646,0.0001069077,0.00002094651,0.0006004586],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9552126,"threshold_uncertainty_score":0.9996227,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220688425","doi":"10.1002/sta4.465","title":"A machine learning approach to classification for traders in financial markets","year":2022,"lang":"en","type":"article","venue":"Stat","topic":"Financial Markets and Investment Strategies","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Alfred P. Sloan Foundation","keywords":"Limit (mathematics); Order book; Cluster analysis; Stock exchange; Order (exchange); Aggregate (composite); Computer science; Financial market; Matching (statistics); Stock (firearms); Financial economics; Artificial intelligence; Economics; Finance; Engineering; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05759928840718442,"gpt":0.2285195839206742,"spread":0.1709202955134898,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006342456,0.00009707757,0.0002012156,0.0002280768,0.0002027691,0.00003486711,0.000145249,0.00003095883,0.0001334338],"category_scores_gemma":[0.0001359296,0.0001227442,0.00005941109,0.0002985827,0.00001879797,0.0001063408,0.00004275196,0.0001646904,0.00001468813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001481241,"about_ca_system_score_gemma":0.00003519096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001330138,"about_ca_topic_score_gemma":0.00002000735,"domain_scores_codex":[0.999042,0.00002649843,0.0003229888,0.0003239595,0.0000339249,0.0002505958],"domain_scores_gemma":[0.9996921,0.00003256796,0.0001152354,0.0001142973,0.000006791611,0.00003903455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002247989,0.0002066604,0.01557636,0.00004636357,0.000007261052,0.00000105906,0.001508183,0.001607019,0.00002558169,0.9706122,0.005959707,0.004224765],"study_design_scores_gemma":[0.001023187,0.0002940853,0.1803186,0.000004277626,0.000002299909,0.000001387062,0.0006423335,0.04314205,0.000005290965,0.06068727,0.7135606,0.0003186245],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5039735,0.003089678,0.03213018,0.005607988,0.001554099,0.003228749,0.00155271,0.0001541753,0.4487089],"genre_scores_gemma":[0.994974,0.00004738744,0.002084088,0.0005150627,0.00004447207,0.000579246,0.0001131496,0.00001946349,0.001623116],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.909925,"threshold_uncertainty_score":0.5005363,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392735719","doi":"10.1002/sta4.706","title":"On Wilks' joint moment formulas for embedded principal minors of Wishart random matrices","year":2024,"lang":"en","type":"preprint","venue":"Stat","topic":"Random Matrices and Applications","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Wishart distribution; Principal (computer security); Moment (physics); Joint (building); Mathematics; Statistics; Computer science; Engineering; Physics; Multivariate statistics; Structural engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.06466996678281328,"gpt":0.358930089701596,"spread":0.2942601229187827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006217998,0.0003392909,0.0007492575,0.0002076434,0.00005903455,0.00009295308,0.0002907007,0.0001781832,0.00009028008],"category_scores_gemma":[0.000137819,0.0002651,0.00051446,0.0001279278,0.0000382939,0.00003079236,0.000428312,0.0003488799,0.00004180399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000903056,"about_ca_system_score_gemma":0.0001418637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002801393,"about_ca_topic_score_gemma":0.00002177343,"domain_scores_codex":[0.9980006,0.00003945452,0.0007985549,0.0004898093,0.0003837463,0.0002878424],"domain_scores_gemma":[0.9978261,0.000787724,0.0005024138,0.0006697571,0.0001274214,0.00008655538],"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":[0.001557083,0.001016601,0.00001097053,0.02004396,0.001111079,0.000009341319,0.006409239,0.001651881,0.0005313212,0.8263623,0.136453,0.004843323],"study_design_scores_gemma":[0.00368748,0.0001452094,0.000009549603,0.0006733306,0.0004941051,0.000002382017,0.0002222986,0.00448242,0.002966227,0.9737259,0.01322763,0.0003635262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8810506,0.001747616,0.07430827,0.002529901,0.001530378,0.01251168,0.004585686,0.000406992,0.02132887],"genre_scores_gemma":[0.8801463,0.0006154181,0.09792489,0.0001978162,0.0005664892,0.005970148,0.0005511833,0.0002989731,0.01372873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1473636,"threshold_uncertainty_score":0.9999801,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4284899235","doi":"10.1002/sta4.487","title":"Bayesian group sequential designs for cluster‐randomized trials","year":2022,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Mitacs","keywords":"Randomized controlled trial; Cluster (spacecraft); Sample size determination; Interim; Cluster randomised controlled trial; Bayesian probability; Computer science; Statistics; Psychology; Medicine; Artificial intelligence; Mathematics; Surgery; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.7519692633517723,"gpt":0.6057972438282709,"spread":0.1461720195235013,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05353413,0.0002290892,0.00230122,0.000091542,0.0003230545,0.00006024443,0.0003636112,0.00009367293,0.003502973],"category_scores_gemma":[0.3462178,0.0001862787,0.0008863317,0.0001694865,0.000182011,0.00004685435,0.0002250269,0.0002968138,0.00001120167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001155791,"about_ca_system_score_gemma":0.00008535892,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001192557,"about_ca_topic_score_gemma":0.000004363086,"domain_scores_codex":[0.9809944,0.01527703,0.002205442,0.0004799016,0.0005760385,0.0004672086],"domain_scores_gemma":[0.6858251,0.3129466,0.0006301961,0.0003928237,0.00006946387,0.0001357504],"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":[0.1262303,0.0004408925,0.000003728498,0.0002529889,0.0006556351,0.00001707784,0.0004114885,0.00003790159,0.0007158461,0.7835327,0.06347994,0.02422157],"study_design_scores_gemma":[0.1057654,0.0003037399,3.520232e-7,0.00001236945,0.0005015968,0.000004238676,0.0001077154,0.002986036,0.0002729807,0.8861315,0.003707272,0.0002068715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003895056,0.00004146993,0.9898792,0.0007031245,0.002344681,0.004564044,0.0009540534,0.0001375886,0.0009863342],"genre_scores_gemma":[0.01193476,0.00001035355,0.983613,0.0005961732,0.0006229323,0.002344666,0.00002171012,0.00007241133,0.0007840443],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2976696,"threshold_uncertainty_score":0.997408,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3194214446","doi":"10.1002/sta4.412","title":"A joint model for longitudinal outcomes with potential ceiling and floor effects and survival times, with applications to analysis of quality of life data from a cancer clinical trial","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Natural Science Foundation of Anhui Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Estimator; Random effects model; Statistics; Proportional hazards model; Survival analysis; Clinical trial; Mixed model; Hazard; Econometrics; Computer science; Mathematics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.6448060757827686,"gpt":0.5370935728534298,"spread":0.1077125029293388,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006498768,0.0001345202,0.001727701,0.0001656246,0.00007472339,0.00003473539,0.0001473215,0.00007148293,0.00003598915],"category_scores_gemma":[0.00187959,0.0001310379,0.00009667537,0.0002462334,0.0000930036,0.0001579783,0.0001150379,0.00007702965,0.000002563813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004743287,"about_ca_system_score_gemma":0.0003992526,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003325961,"about_ca_topic_score_gemma":0.008094136,"domain_scores_codex":[0.9962223,0.0002268977,0.00255709,0.0007132543,0.0001027533,0.0001777693],"domain_scores_gemma":[0.9960077,0.001552455,0.00139255,0.0007108945,0.0001484924,0.0001878596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005551855,0.0005131179,0.962756,0.001246072,0.005772026,7.044525e-7,0.001093514,0.01204338,0.00001453275,0.009768735,0.0005276671,0.000712344],"study_design_scores_gemma":[0.01877964,0.0002914967,0.6441994,0.00006627669,0.0007309621,2.314666e-7,0.0005435862,0.3332431,0.000006379843,0.001662734,0.0001488575,0.0003273195],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6703237,0.0006661154,0.3195396,0.002451241,0.00006363131,0.0008103776,0.006126773,0.000006151552,0.00001241684],"genre_scores_gemma":[0.9594965,0.0001140393,0.0388589,0.0006792302,0.0001196811,0.0002296103,0.000415746,0.00001862404,0.00006768511],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3211997,"threshold_uncertainty_score":0.5343572,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3135656960","doi":"10.1002/sta4.375","title":"Composite likelihood ratio testing under nonstandard conditions using tangent cones","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Likelihood-ratio test; Monte Carlo method; Mixing (physics); Statistics; Parameter space; Statistic; Statistical hypothesis testing; Null hypothesis; Composite number; Projection (relational algebra); Null distribution; Null (SQL); Boundary (topology); Maximum likelihood; Test statistic; Applied mathematics; Mathematical analysis; Algorithm; Computer science; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.2037071763156445,"gpt":0.425003614604793,"spread":0.2212964382891486,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000174867,0.0001111674,0.0002037048,0.00002632988,0.0001957248,0.00007711888,0.00005341067,0.00003844336,0.0005620474],"category_scores_gemma":[0.001289816,0.0001038608,0.00003767,0.0001844443,0.00008102565,0.0000514684,0.00005375673,0.0001119892,0.00001798203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005825827,"about_ca_system_score_gemma":0.0001750674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001602508,"about_ca_topic_score_gemma":0.000017177,"domain_scores_codex":[0.9990259,0.000129684,0.0002522401,0.000183458,0.0001858183,0.0002228872],"domain_scores_gemma":[0.9976131,0.001722169,0.00007571433,0.0001820645,0.0003125025,0.00009449907],"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":[0.00001203863,0.0001941321,0.001783011,0.0001305939,0.0001049485,0.000129533,0.0004850768,0.00007862304,0.1417783,0.8448706,0.001989918,0.008443248],"study_design_scores_gemma":[0.0005231322,0.00006349183,0.001178188,0.0002546747,0.0001306702,0.00007692039,0.001035705,0.0125118,0.0223934,0.961237,0.0002973895,0.0002976749],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09556308,0.00009991645,0.8975168,0.0001933689,0.0002035926,0.0001154325,0.0004457654,0.00006289743,0.005799135],"genre_scores_gemma":[0.2519456,0.000004361192,0.7476386,0.0002355752,0.00005517635,0.000006418712,0.00001725058,0.00001697029,0.0000801291],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1563825,"threshold_uncertainty_score":0.6154025,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405528262","doi":"10.1002/sta4.70007","title":"A Corrected Score Function Framework for Modelling Circadian Gene Expression","year":2024,"lang":"en","type":"article","venue":"Stat","topic":"Circadian rhythm and melatonin","field":"Neuroscience","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 British Columbia","funders":"","keywords":"Offset (computer science); Circadian rhythm; Function (biology); Regression; Expression (computer science); Sample (material); Computer science; Sample size determination; Statistics; Transcriptome; Regression analysis; Computational biology; Biology; Data mining; Gene expression; Mathematics; Gene; Genetics; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.05786834505823168,"gpt":0.2837284382235453,"spread":0.2258600931653136,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007697915,0.0001154434,0.0001000703,0.0001091324,0.0001596837,0.0001144644,0.00007678061,0.0001083078,0.00009476891],"category_scores_gemma":[0.0001287597,0.0001071692,0.0000778634,0.0002736786,0.00003374005,0.0001716101,0.00001909295,0.0002073336,0.0001454695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004574968,"about_ca_system_score_gemma":0.00006789991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004423342,"about_ca_topic_score_gemma":0.000001092348,"domain_scores_codex":[0.9989656,0.0000279293,0.0001351627,0.0004318881,0.0001449371,0.0002944806],"domain_scores_gemma":[0.9993472,0.000299703,0.00002568427,0.0001880985,0.00001991752,0.0001193735],"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":[0.0002047148,0.00004815628,0.0001637307,0.0002142558,0.00001013208,0.00009397959,0.002785785,0.007507564,0.7717206,0.1796221,0.004899335,0.03272955],"study_design_scores_gemma":[0.000219723,0.00009827116,0.00006940993,0.0003629348,0.00002310332,0.00003232755,0.00007047664,0.1547813,0.769635,0.03504612,0.03941121,0.0002501319],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2457428,0.0008855462,0.7496188,0.0001217598,0.002518362,0.0003080154,0.00006343166,0.0002689875,0.0004723088],"genre_scores_gemma":[0.9917633,0.00008637043,0.006077259,0.0003555864,0.0004180338,0.00007238491,0.00001457313,0.0000425356,0.001169935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7460205,"threshold_uncertainty_score":0.4370233,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3162338773","doi":"10.1002/sta4.387","title":"A constrained minimum method for model selection","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Model selection; Consistency (knowledge bases); Selection (genetic algorithm); Bayesian information criterion; Computer science; Information Criteria; Mathematical optimization; Mathematics; Bayesian probability; Sample size determination; Algorithm; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.1484828444350864,"gpt":0.4531084936834141,"spread":0.3046256492483277,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003051422,0.0000715606,0.0001577168,0.00001673908,0.0000508286,0.00002038501,0.00003597769,0.00004329735,0.0001849343],"category_scores_gemma":[0.002869077,0.00006439709,0.00004824911,0.00008361648,0.00002153593,0.00002168104,0.00001493438,0.00005977931,0.000003530301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001770085,"about_ca_system_score_gemma":0.0001158126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002371455,"about_ca_topic_score_gemma":0.000008698247,"domain_scores_codex":[0.9993601,0.00007813478,0.0001590406,0.0001621827,0.0000814351,0.0001591325],"domain_scores_gemma":[0.9978554,0.001780505,0.00003857079,0.00009599546,0.0001786599,0.00005090218],"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":[0.00001870128,0.00004298999,0.000005275469,0.00008139291,0.0000202612,0.000001888008,0.0001765892,0.00002240054,0.01139874,0.9337646,0.004249696,0.05021743],"study_design_scores_gemma":[0.0001972418,0.00002574867,0.000002568288,0.000007928494,0.00002070896,0.000005483416,0.00006867046,0.3964771,0.006682743,0.5960116,0.0004453918,0.00005485893],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008083056,0.00001045531,0.9931031,0.0002361944,0.00007036312,0.0001328379,0.0001116282,0.00004085544,0.00548623],"genre_scores_gemma":[0.005017283,0.000002425643,0.9929144,0.0001766223,0.0000338752,0.00003782539,0.000005594028,0.00001222874,0.001799777],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3964547,"threshold_uncertainty_score":0.343476,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1650463848","doi":"10.1002/sta4.64","title":"Additive models for conditional copulas","year":2014,"lang":"en","type":"preprint","venue":"Stat","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":2,"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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Copula (linguistics); Covariate; Conditional probability distribution; Bivariate analysis; Econometrics; Inference; Joint probability distribution; Conditional dependence; Conditional expectation; Conditional probability; Conditional variance; Computer science; Marginal distribution; Bayesian inference; Mathematics; Bayesian probability; Statistics; Artificial intelligence; Random variable; Autoregressive conditional heteroskedasticity","retraction":null,"screen_n_in":null,"score":{"opus":0.07907764633782566,"gpt":0.2693837230659103,"spread":0.1903060767280846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004170588,0.0002315601,0.0005885335,0.0001484078,0.0001250054,0.00007155555,0.0002318541,0.0003014231,0.0002140365],"category_scores_gemma":[0.0001576188,0.0002990403,0.0002809672,0.00003962385,0.00005909166,0.0001151192,0.0001727028,0.0003232516,0.000190013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001336785,"about_ca_system_score_gemma":0.0000699275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002215673,"about_ca_topic_score_gemma":0.00003740445,"domain_scores_codex":[0.9983614,0.00001032807,0.0006289736,0.0006497248,0.00004137775,0.0003081728],"domain_scores_gemma":[0.9989418,0.0001145845,0.0004063262,0.0003558151,0.0001071964,0.00007421043],"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":[0.00004817227,0.00004833107,0.0003466574,0.0001543548,0.00006526268,6.617375e-7,0.000364191,0.04825819,4.129415e-7,0.9270459,0.02218117,0.001486684],"study_design_scores_gemma":[0.0002182614,0.00002392436,0.0002132799,0.00001950993,0.00000542347,1.845078e-7,0.000008799967,0.386202,0.000005433801,0.5724327,0.04067101,0.0001994757],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01646209,0.001086887,0.9452341,0.0002568059,0.00096327,0.0006262569,0.02438902,0.00005703099,0.01092455],"genre_scores_gemma":[0.9826196,0.0002236336,0.01086449,0.0002929487,0.0005402284,0.0003037124,0.004078323,0.00004900877,0.001028096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9661575,"threshold_uncertainty_score":0.9999462,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4361289113","doi":"10.1002/sta4.568","title":"Bayesian outcome selection modeling","year":2023,"lang":"en","type":"article","venue":"Stat","topic":"Fatty Acid Research and Health","field":"Nursing","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Australian Research Council Centre of Excellence for Mathematical and Statistical Frontiers; National Institute on Alcohol Abuse and Alcoholism; Australian Research Council; Canadian Institutes of Health Research; National Institutes of Health; University of Melbourne","keywords":"Outcome (game theory); Bayesian probability; Selection (genetic algorithm); Computer science; Psychology; Econometrics; Machine learning; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07869389687444273,"gpt":0.3922452916117336,"spread":0.3135513947372909,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002738991,0.00005435742,0.00007804034,0.0001362312,0.0002016276,0.00003030146,0.00005919766,0.00003679325,0.00008598088],"category_scores_gemma":[0.0000755588,0.00005046359,0.00003060799,0.0003768483,0.00001178185,0.00008472023,0.00001813034,0.0001790446,0.0006697548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008473323,"about_ca_system_score_gemma":0.00002346656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002955807,"about_ca_topic_score_gemma":0.0002746567,"domain_scores_codex":[0.9990984,0.00004343986,0.0001262509,0.0001372466,0.0001981464,0.0003965012],"domain_scores_gemma":[0.9997224,0.00003147685,0.00001330426,0.00008866095,0.00003400973,0.0001101143],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001866445,0.0002704976,0.2486864,0.001669156,0.00009412545,0.0001212141,0.00928545,0.1219717,0.08111227,0.003009633,0.2243182,0.307595],"study_design_scores_gemma":[0.000322289,0.0001329549,0.002205067,0.00001569334,0.000003185039,0.000002849348,0.0002964432,0.9887663,0.002312289,0.00335928,0.002487475,0.00009618684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8552144,0.0001040011,0.1084719,0.02538028,0.001993835,0.0005890446,0.00002805072,0.001522728,0.006695764],"genre_scores_gemma":[0.9976357,0.00001494136,0.001362897,0.0003074872,0.0001426298,0.000007684613,0.00001851227,0.00001779663,0.0004923315],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8667946,"threshold_uncertainty_score":0.8608565,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2798517237","doi":"10.1002/sta4.316","title":"Nonasymptotic support recovery for high‐dimensional sparse covariance matrices","year":2020,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods and Inference","field":"Mathematics","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 Alberta","funders":"","keywords":"Estimator; Covariance; Covariance matrix; Estimation of covariance matrices; Matrix norm; Computation; Regularization (linguistics); Thresholding","retraction":null,"screen_n_in":null,"score":{"opus":0.1169873063794826,"gpt":0.3572124556471022,"spread":0.2402251492676196,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002419608,0.0001309974,0.0002636631,0.00002083081,0.00006357505,0.00003100151,0.0001273315,0.00005264676,0.0011868],"category_scores_gemma":[0.002206032,0.0001119212,0.00005774543,0.0001113347,0.00004303869,0.00006812104,0.0000490054,0.00009124963,0.0001488943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002001366,"about_ca_system_score_gemma":0.00008338215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000784554,"about_ca_topic_score_gemma":0.000001646945,"domain_scores_codex":[0.9989557,0.00004854559,0.0002855417,0.0002640485,0.0001965908,0.000249599],"domain_scores_gemma":[0.9975268,0.001978269,0.00010261,0.000148649,0.00009873588,0.0001449672],"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":[0.0002540104,0.0000828597,0.0001004156,0.00036323,0.00005463544,0.00002688883,0.000157254,0.00002798663,0.0008048895,0.8881674,0.08353642,0.02642401],"study_design_scores_gemma":[0.000766657,0.0006715268,0.0004044496,0.00004081956,0.00007629528,0.000006088664,0.00004296598,0.005560107,0.001392694,0.9840285,0.006728443,0.0002814514],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0102671,0.00003297924,0.9847214,0.001790524,0.0003095838,0.0003733377,0.0006148365,0.00008261716,0.00180759],"genre_scores_gemma":[0.07378355,0.00001211906,0.9238725,0.001611811,0.0001846726,0.00003418831,0.00002502421,0.00002644104,0.0004496975],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0958611,"threshold_uncertainty_score":0.9997262,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3082112708","doi":"10.1002/sta4.462","title":"A hierarchical meta‐analysis for settings involving multiple outcomes across multiple cohorts","year":2022,"lang":"en","type":"preprint","venue":"Stat","topic":"Prenatal Substance Exposure Effects","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Australian Research Council Centre of Excellence for Mathematical and Statistical Frontiers; National Institute on Alcohol Abuse and Alcoholism; National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Foundation for the National Institutes of Health","keywords":"Confounding; Random effects model; Cohort; Propensity score matching; Psychology; Cognition; Cohort study; Multilevel model; Medicine; Demography; Meta-analysis; Clinical psychology; Statistics; Internal medicine; Mathematics; Psychiatry","retraction":null,"screen_n_in":null,"score":{"opus":0.05359399379942213,"gpt":0.3461517645884846,"spread":0.2925577707890624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001602839,0.0007288367,0.003254803,0.0003572285,0.0003638434,0.0001130563,0.0005176679,0.0003796705,0.0004312429],"category_scores_gemma":[0.003010241,0.0006227484,0.00344238,0.0005641015,0.0001627144,0.0001029478,0.001765735,0.001711073,0.00001109712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004081581,"about_ca_system_score_gemma":0.0002295447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004822381,"about_ca_topic_score_gemma":0.001219519,"domain_scores_codex":[0.9953516,0.0002926957,0.0008619237,0.001474219,0.001007643,0.001011882],"domain_scores_gemma":[0.9939823,0.003421949,0.0004895012,0.001497534,0.0002126161,0.0003960965],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.00105167,0.0004782341,0.7136039,0.002586102,0.2662209,0.0004020994,0.00597122,0.004940445,0.001469894,0.00004833097,0.002430799,0.0007964188],"study_design_scores_gemma":[0.01517268,0.001048954,0.3792473,0.0002942056,0.4774045,0.00004899852,0.002323829,0.07859265,0.00722295,0.00315702,0.03147954,0.004007384],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9558919,0.01027045,0.01482314,0.002642198,0.001454622,0.006870373,0.007142143,0.0007345782,0.0001706032],"genre_scores_gemma":[0.9696159,0.00006391193,0.02100545,0.001107093,0.0001756696,0.003052139,0.003608717,0.0001453965,0.001225737],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3343566,"threshold_uncertainty_score":0.9996224,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386620668","doi":"10.1002/sta4.613","title":"On pairwise interaction multivariate Pareto models","year":2023,"lang":"en","type":"article","venue":"Stat","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":1,"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":"Pareto principle; Pairwise comparison; Multivariate statistics; Class (philosophy); Mathematics; Basis (linear algebra); Parametric statistics; Parametric model; Econometrics; Mathematical economics; Statistical physics; Computer science; Statistics; Artificial intelligence; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.2719243919800507,"gpt":0.4067526109303313,"spread":0.1348282189502806,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001043097,0.00009168949,0.0001273357,0.0002028605,0.00007572754,0.00008624396,0.0002459419,0.0000412913,0.0001496015],"category_scores_gemma":[0.00174556,0.00006245748,0.00005602571,0.0005551312,0.00002324272,0.000207517,0.00005646901,0.0001053203,0.00263039],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004048525,"about_ca_system_score_gemma":0.00002401732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001661979,"about_ca_topic_score_gemma":0.000004318722,"domain_scores_codex":[0.9986413,0.00007523478,0.0002476558,0.000294431,0.0005422168,0.0001992222],"domain_scores_gemma":[0.9980532,0.00138502,0.00005216081,0.0003493565,0.00008338717,0.0000769055],"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":[0.00004937828,0.00002704148,0.00003226753,0.000003531371,0.000009149459,0.00002240721,0.0006912084,0.8731581,0.000197064,0.03854292,0.06542486,0.02184209],"study_design_scores_gemma":[0.0001403294,0.00004579781,0.0004693944,0.00001451942,0.000002390419,9.677059e-7,0.0002111686,0.6902044,0.00006168864,0.3055165,0.003249141,0.00008376445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08662432,0.00001744332,0.9009067,0.0006851209,0.001895246,0.0002193234,0.00003658372,0.0004972566,0.009117974],"genre_scores_gemma":[0.9952426,0.000005836774,0.001085168,0.00008119833,0.00004687047,0.00001507226,0.00000597811,0.00001116681,0.003506122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9086183,"threshold_uncertainty_score":0.9981462,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2567613594","doi":"10.1002/sta4.131","title":"Inferring population size: extending the multiplier method to incorporate multiple traits with a likelihood‐based approach","year":2016,"lang":"en","type":"article","venue":"Stat","topic":"Census and Population Estimation","field":"Mathematics","cited_by":1,"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 British Columbia","funders":"","keywords":"Estimator; Multiplier (economics); Bayesian probability; Statistics; Population; Population size; Trait; Binary number; Uncorrelated; Mathematics; Computer science; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.05558968949043339,"gpt":0.3369787559199183,"spread":0.2813890664294849,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006536607,0.0001728775,0.0001864196,0.00007920854,0.0001924542,0.0000437878,0.0001099618,0.00005518012,0.00003614655],"category_scores_gemma":[0.0005524193,0.00008898638,0.00004650086,0.0002558086,0.0000178147,0.0001745969,0.00003169063,0.00008042263,0.00001426269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009271794,"about_ca_system_score_gemma":0.00002772306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009081058,"about_ca_topic_score_gemma":0.0001905719,"domain_scores_codex":[0.9987503,0.0001452982,0.0003033956,0.0002609341,0.0002838455,0.0002562426],"domain_scores_gemma":[0.9982904,0.001064911,0.0001984321,0.0002540933,0.00009754156,0.00009458607],"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":[0.0008288515,0.0004626819,0.2689564,0.0003667559,0.0001379262,0.000008430276,0.005210551,0.02415992,0.02024624,0.05073278,0.001127593,0.6277618],"study_design_scores_gemma":[0.004599426,0.0002139291,0.6695538,0.0004284604,0.0001388613,0.00001973131,0.0002849047,0.252656,0.002776129,0.06608851,0.002347221,0.0008930393],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2425061,0.000004176304,0.7560365,0.0004583303,0.00003922676,0.0005622656,0.00002430697,0.0001044472,0.0002646982],"genre_scores_gemma":[0.6226403,2.727265e-7,0.3770182,0.00008391868,0.00004422976,0.00005524058,0.0000109196,0.00002585304,0.0001210808],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6268688,"threshold_uncertainty_score":0.3628759,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3130349901","doi":"10.1002/sta4.372","title":"Mode merging for the finite mixture of <i>t</i>‐distributions","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Component (thermodynamics); Expectation–maximization algorithm; Gaussian; Cluster (spacecraft); Mode (computer interface); Computer science; Population; Algorithm; Mathematics; Statistical physics; Artificial intelligence; Statistics; Maximum likelihood; Physics; Thermodynamics","retraction":null,"screen_n_in":null,"score":{"opus":0.02012592673133263,"gpt":0.3013657857676358,"spread":0.2812398590363032,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001977452,0.00006163146,0.00009784188,0.00001374836,0.0001240787,0.00003859095,0.000314213,0.00002978342,0.000007073312],"category_scores_gemma":[0.0001065845,0.00004239798,0.00008758706,0.0002179328,0.00002754397,0.00009039666,0.00009824104,0.00007162973,0.000001157516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008397519,"about_ca_system_score_gemma":0.00008842053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007170155,"about_ca_topic_score_gemma":0.00001083804,"domain_scores_codex":[0.9994171,0.00005137127,0.0001174725,0.0001652364,0.00009508568,0.0001536991],"domain_scores_gemma":[0.998935,0.0004460476,0.00004387709,0.000409582,0.0001330183,0.00003240521],"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":[0.000003484896,0.00002681286,0.00000850529,0.00002308713,0.00002903227,0.000004179497,0.0007102456,0.0003268469,0.005461265,0.8712971,0.006391434,0.115718],"study_design_scores_gemma":[0.0003995155,0.00003653857,0.00007652137,0.00003196683,0.00003763871,0.00001305274,0.00005471032,0.3271443,0.08073568,0.4768821,0.1144055,0.000182505],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000882869,0.0008922443,0.9943126,0.003554103,0.0002537545,0.00008873676,0.0001078579,0.00002269394,0.0006796495],"genre_scores_gemma":[0.08129038,0.00006912494,0.9175463,0.0004263725,0.0000533151,0.00002121744,0.00001337923,0.000005260611,0.000574593],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.394415,"threshold_uncertainty_score":0.1728939,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404187292","doi":"10.1002/sta4.70013","title":"Function‐Valued Marked Spatial Point Processes on Linear Networks: Application to Urban Cycling Profiles","year":2024,"lang":"en","type":"article","venue":"Stat","topic":"Point processes and geometric inequalities","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Cycling; Function (biology); Point (geometry); Geography; Mathematics; Geometry; Biology; Evolutionary biology; Archaeology","retraction":null,"screen_n_in":null,"score":{"opus":0.03173143556612405,"gpt":0.3155858103610735,"spread":0.2838543747949495,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004950658,0.0002006867,0.000219344,0.0002533731,0.0001230593,0.0001326897,0.0001390283,0.00007944187,0.0001262547],"category_scores_gemma":[0.0008534507,0.0001644661,0.00005980147,0.0009754382,0.00002161034,0.0001549642,0.00005555413,0.0001801233,0.0001812781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006728007,"about_ca_system_score_gemma":0.0001020657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004825126,"about_ca_topic_score_gemma":0.00003144532,"domain_scores_codex":[0.9985654,0.00003535031,0.0003749021,0.0003829075,0.0003248231,0.0003166083],"domain_scores_gemma":[0.9988479,0.0005378521,0.00007686979,0.0002585583,0.0001877751,0.00009104138],"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":[0.002117109,0.001027265,0.0005322858,0.0203626,0.0007278488,0.00005378064,0.01235808,0.007692721,0.0007669316,0.4853812,0.1974674,0.2715127],"study_design_scores_gemma":[0.001388774,0.002265402,0.0003500011,0.002762052,0.0004784023,0.00002294394,0.003748684,0.2723641,0.0112045,0.4479067,0.2553701,0.002138307],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02378823,0.0006843766,0.9694161,0.0006914971,0.0005504111,0.0007829,0.00005849192,0.0005486378,0.003479403],"genre_scores_gemma":[0.9856564,0.00005851854,0.007653472,0.0004143447,0.001498571,0.000353587,0.00008346352,0.00007465824,0.004206932],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9618682,"threshold_uncertainty_score":0.6706731,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964291876","doi":"10.1002/sta4.21","title":"Simultaneous model selection and estimation for mean and association structures with clustered binary data","year":2013,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; York University","funders":"National Science Council","keywords":"Estimator; Mathematics; Covariate; Model selection; Applied mathematics; Oracle; Mathematical optimization; Selection (genetic algorithm); Feature selection; Estimating equations; Mean squared error; Binary number; Statistics; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.08105860480608996,"gpt":0.3705794344871222,"spread":0.2895208296810323,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001657842,0.00007213518,0.0001072411,0.00002042735,0.00007781338,0.00006421307,0.00004147341,0.00004485267,0.00001235186],"category_scores_gemma":[0.001508105,0.00005356872,0.000003903118,0.0000328501,0.00001619104,0.0001505544,0.00003459156,0.00004984377,5.217086e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002669669,"about_ca_system_score_gemma":0.00001557426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003083077,"about_ca_topic_score_gemma":0.000052503,"domain_scores_codex":[0.9994876,0.00003343999,0.0001097614,0.0001653739,0.00009820212,0.0001055728],"domain_scores_gemma":[0.998314,0.001352961,0.00008293929,0.0001104289,0.0001019788,0.00003763989],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004373102,0.0001556901,0.001892104,0.001438445,0.0002684409,0.000002653659,0.004388357,0.01804296,0.004788069,0.1829511,0.01357032,0.7720646],"study_design_scores_gemma":[0.0002007898,0.00009228219,0.0002250877,0.000008777625,0.00002757335,0.000001927055,0.00004083907,0.6744658,0.00004413936,0.3248325,0.000007849108,0.00005239997],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2184177,0.000009933855,0.7809459,0.0001036754,0.0000146163,0.0003244673,0.0001153063,0.00002479609,0.00004354925],"genre_scores_gemma":[0.4221447,0.000004309873,0.5777,0.00002214657,0.000009844091,0.00001118609,0.00002500996,0.000007009794,0.00007584833],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7720122,"threshold_uncertainty_score":0.2184469,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1921128344","doi":"10.1002/sta4.74","title":"Spanifold: spanning tree flattening onto lower dimension","year":2015,"lang":"en","type":"article","venue":"Stat","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dimensionality reduction; Isomap; Intrinsic dimension; Mathematics; Data point; Nonlinear dimensionality reduction; Pairwise comparison; Minimum spanning tree; Flattening; Tree (set theory); Dimension (graph theory); Hessian matrix; Manifold (fluid mechanics); Curse of dimensionality; Energy minimization; Embedding; Algorithm; Combinatorics; Computer science; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03618122214182163,"gpt":0.2608451679219877,"spread":0.2246639457801661,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001886991,0.00009461818,0.00009726129,0.00006306917,0.00007567155,0.0001022334,0.0002359959,0.00004190384,0.00002717431],"category_scores_gemma":[0.00003378115,0.00007961581,0.00003548491,0.0001434221,0.00001257377,0.0005627139,0.0001781857,0.00008678878,0.0004508484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003287936,"about_ca_system_score_gemma":0.00003882305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004817963,"about_ca_topic_score_gemma":0.00001991823,"domain_scores_codex":[0.9990892,0.00003459879,0.0001233034,0.0002553661,0.0002682231,0.0002293221],"domain_scores_gemma":[0.9994178,0.00002974974,0.00004675822,0.0002750521,0.00008036346,0.0001503206],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001462553,0.0002682626,0.005758993,0.00003384339,0.00004995837,0.0004370394,0.01236311,0.001107653,0.08310971,0.005564684,0.4434043,0.4477561],"study_design_scores_gemma":[0.007698391,0.002041775,0.01243094,0.001181207,0.00006536326,0.0001875168,0.003549656,0.3455347,0.1295941,0.0442803,0.4505537,0.002882396],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6068421,0.000228032,0.3670577,0.001749567,0.002059903,0.0001620547,0.000002317907,0.0004217647,0.02147658],"genre_scores_gemma":[0.9520707,0.000005820404,0.04562007,0.0006239064,0.0000914362,0.000005831853,0.000006183918,0.00001014488,0.001565938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4448738,"threshold_uncertainty_score":0.5794894,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996157724","doi":"10.1002/sta4.257","title":"A note on cyclic shift permutation testing for large eigenvalues","year":2019,"lang":"en","type":"article","venue":"Stat","topic":"Random Matrices and Applications","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Canadian Foundation on Fetal Alcohol Research","keywords":"Eigenvalues and eigenvectors; Permutation (music); Dimension (graph theory); Null hypothesis; Null (SQL); Variation (astronomy); Statistical hypothesis testing; Mathematics; Matrix (chemical analysis); Variety (cybernetics); Combinatorics; Statistics; Computer science; Physics; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.05098638282593149,"gpt":0.3617718285407223,"spread":0.3107854457147908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001788408,0.00007151806,0.0001080185,0.00003233191,0.00009260323,0.00002905069,0.00006712561,0.00002947233,0.00004318207],"category_scores_gemma":[0.0002177155,0.00006005865,0.00004744186,0.00009240708,0.000004515479,0.0000479099,0.00001196859,0.00004579473,0.0001978549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001952247,"about_ca_system_score_gemma":0.00001596704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007393655,"about_ca_topic_score_gemma":0.00000963158,"domain_scores_codex":[0.9994512,0.00001211222,0.0001396625,0.0001403032,0.00009950859,0.0001572713],"domain_scores_gemma":[0.9987534,0.0009320999,0.00007977408,0.0001720281,0.00003621801,0.00002651206],"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":[0.0001366522,0.0003733434,0.0040691,0.0005843382,0.00004060061,0.000001220835,0.00464628,0.0001103989,0.005307673,0.9682952,0.004798796,0.01163645],"study_design_scores_gemma":[0.004206399,0.0003836101,0.005465452,0.0001052747,0.00009219454,0.000002373813,0.0006786994,0.02004696,0.00217935,0.943951,0.02248839,0.0004002984],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9542753,0.00002232877,0.0332646,0.0003736193,0.00008182128,0.001044305,0.00009554177,0.0001134113,0.01072912],"genre_scores_gemma":[0.9684219,0.000001783976,0.03045935,0.00009755269,0.00007823358,0.0001054104,0.00001926526,0.00002089096,0.0007955738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02434414,"threshold_uncertainty_score":0.2543091,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402315119","doi":"10.1002/sta4.70000","title":"A Joint Temporal Model for Hospitalizations and ICU Admissions Due to COVID‐19 in Quebec","year":2024,"lang":"en","type":"article","venue":"Stat","topic":"Emergency and Acute Care Studies","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec - Santé; Institut de Valorisation des Données","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Joint (building); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Medicine; Demography; Virology; Outbreak; Sociology; Internal medicine; Engineering; Disease; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.0441442977239963,"gpt":0.3535457784377864,"spread":0.3094014807137901,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006632901,0.00007632765,0.000142996,0.00009950616,0.00006999631,0.00001238365,0.0000183248,0.00002766517,0.00004781382],"category_scores_gemma":[0.0004095968,0.00005948444,0.00004008264,0.0001635222,0.00002063484,0.00004795515,0.00003372045,0.00005074374,0.000003743557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000677299,"about_ca_system_score_gemma":0.0003322477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001274657,"about_ca_topic_score_gemma":0.01016842,"domain_scores_codex":[0.9994806,0.000006210787,0.0001399988,0.0001755912,0.00006578225,0.0001318268],"domain_scores_gemma":[0.9996115,0.00003194451,0.000008156197,0.00008097758,0.00004020227,0.0002272013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009839547,0.0001264814,0.004811964,0.001120383,0.000127578,0.0002259814,0.03400267,0.0007119627,0.0008494738,0.02254233,0.9299892,0.005393643],"study_design_scores_gemma":[0.002666066,0.0009853952,0.006689413,0.001523559,0.0003632122,0.00005708731,0.01542495,0.1977003,0.000414206,0.03040023,0.7429554,0.0008202014],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4412476,0.01909134,0.3417879,0.1847634,0.001165108,0.003944072,0.001562057,0.000503423,0.005935115],"genre_scores_gemma":[0.9748909,0.0003589631,0.004280921,0.00251188,0.00008496278,0.0002008745,0.0001059843,0.00002311107,0.01754243],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5336433,"threshold_uncertainty_score":0.5674219,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3200858256","doi":"10.1002/sta4.421","title":"Parsimonious mixture‐of‐experts based on mean mixture of multivariate normal distributions","year":2021,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Multivariate statistics; Cluster analysis; Multivariate normal distribution; Expectation–maximization algorithm; Mixture model; Data set; Artificial intelligence; Mathematics; Computer science; Robust regression; Statistics; Machine learning; Regression; Maximum likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.01420866795104854,"gpt":0.2737574186497133,"spread":0.2595487506986647,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002708852,0.000170285,0.0002907837,0.00006433048,0.00008499496,0.00003346507,0.00042921,0.0001063569,0.00002910965],"category_scores_gemma":[0.0001082523,0.0001448556,0.0001588095,0.0004279936,0.0000647597,0.000130729,0.0001277453,0.0001537872,0.000002507851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002925267,"about_ca_system_score_gemma":0.00018831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003885646,"about_ca_topic_score_gemma":0.00002823774,"domain_scores_codex":[0.9984671,0.0002562368,0.0002984646,0.0003797679,0.0003063201,0.0002920969],"domain_scores_gemma":[0.9985453,0.0002186057,0.0001393702,0.0007527785,0.000224412,0.0001195065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001480642,0.001672674,0.0005778524,0.0002502638,0.0001773675,0.0003852374,0.005541627,0.001227347,0.1256722,0.6265061,0.009451065,0.2283901],"study_design_scores_gemma":[0.002347843,0.0004801124,0.002275243,0.000284377,0.00006665363,0.00003014525,0.00006876405,0.1733411,0.7591497,0.04464023,0.01654124,0.000774603],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003488704,0.0002076143,0.9929244,0.0009141907,0.0003869328,0.0001083118,0.0001392845,0.00004465181,0.001785894],"genre_scores_gemma":[0.5714962,0.000009254244,0.4280452,0.0002305252,0.00003177234,0.000006188086,0.00003237304,0.000008312149,0.0001400959],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6334774,"threshold_uncertainty_score":0.5907038,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3169822441","doi":"10.1002/sta4.410","title":"A multivariate normal approximation for the Dirichlet density and some applications","year":2021,"lang":"en","type":"preprint","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Mathematics; Estimator; Multivariate statistics; Dirichlet distribution; Applied mathematics; Gaussian; Statistics; Covariance matrix; Equivalence (formal languages); Asymptotic expansion; Mathematical analysis; Pure mathematics; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.0268865058758163,"gpt":0.2975746641302438,"spread":0.2706881582544275,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004967088,0.0001421691,0.0001761135,0.00003390425,0.0002119417,0.000329045,0.0004559803,0.0001100732,0.00000114257],"category_scores_gemma":[0.0000349292,0.0001038832,0.00007586741,0.00008066096,0.00003883839,0.0001749344,0.0009159825,0.0002356419,0.00000102745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002210402,"about_ca_system_score_gemma":0.00009543839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004254849,"about_ca_topic_score_gemma":0.00001151895,"domain_scores_codex":[0.9989921,0.0000903767,0.0001627717,0.0004634119,0.0001206201,0.0001707211],"domain_scores_gemma":[0.9987391,0.0002707955,0.0001196292,0.0006991246,0.0001187972,0.00005257802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006839818,0.00004788264,0.00001569405,0.0002271082,0.00007058695,0.000001692902,0.002353481,0.0001291495,0.0006253733,0.378838,0.0003114052,0.6173728],"study_design_scores_gemma":[0.0002586306,0.00001301449,0.0006662227,0.00002939925,0.00005088406,0.000008051057,0.00002997978,0.5720763,0.001221992,0.4222904,0.003105369,0.0002497285],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006547328,0.0007840915,0.9951651,0.001959998,0.0002642296,0.0009988907,0.0000255117,0.00005975831,0.00008771155],"genre_scores_gemma":[0.02451607,0.0001451546,0.9739907,0.0003657033,0.0001597522,0.0006746533,0.00003427731,0.000009839334,0.0001038019],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6171231,"threshold_uncertainty_score":0.4236234,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2767955851","doi":"10.1002/sta4.159","title":"A class of flexible models for analysis of complex structured correlated data with application to clustered longitudinal data","year":2017,"lang":"en","type":"article","venue":"Stat","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; Western University; University of Waterloo","funders":"","keywords":"Pairwise comparison; Computer science; Class (philosophy); Generalized linear mixed model; Longitudinal data; Data mining; Linear model; Generalized linear model; Theoretical computer science; Machine learning; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.3607933941593603,"gpt":0.4755354921140453,"spread":0.114742097954685,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003690988,0.0001127687,0.0004889704,0.00009582785,0.00009361343,0.00003662701,0.001283095,0.0000471061,0.00005023229],"category_scores_gemma":[0.0005891268,0.00008661178,0.00002872564,0.0002102554,0.0001202526,0.0001834237,0.0004969369,0.00005381964,5.640288e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000123318,"about_ca_system_score_gemma":0.00004524994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002298011,"about_ca_topic_score_gemma":0.0006918091,"domain_scores_codex":[0.9988267,0.00003653539,0.0003622478,0.0004092795,0.0002095763,0.00015567],"domain_scores_gemma":[0.9953447,0.000555346,0.0004497672,0.00335608,0.0002257013,0.00006842421],"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":[0.001719216,0.0003271713,0.00736123,0.000746296,0.003489388,0.000003019585,0.0007579566,0.001339666,0.001694011,0.8717272,0.006069625,0.1047653],"study_design_scores_gemma":[0.0004484835,0.0001062268,0.01384514,0.00003307722,0.001252103,6.729999e-7,0.0000581025,0.7840585,0.0001163304,0.1999144,0.00005824707,0.000108726],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00328824,0.000005273491,0.9841627,0.00007098622,0.00002407094,0.0005150483,0.01161358,0.00001360913,0.0003064649],"genre_scores_gemma":[0.4371295,8.769291e-7,0.562034,0.00000672162,0.000007186733,0.0000109896,0.0007805555,0.000008421503,0.00002173891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7827188,"threshold_uncertainty_score":0.3531926,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2969211293","doi":"10.1002/sta4.243","title":"A bootstrap‐augmented alternating expectation‐conditional maximization algorithm for mixtures of factor analyzers","year":2019,"lang":"en","type":"article","venue":"Stat","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":1,"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, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation","keywords":"Latent variable; Expectation–maximization algorithm; Cluster analysis; Curse of dimensionality; Benchmark (surveying); Computer science; Nonparametric statistics; Maximization; Latent variable model; Mixture model; Algorithm; Factor (programming language); Artificial intelligence; Machine learning; Mathematics; Statistics; Mathematical optimization; Maximum likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.02134522745326021,"gpt":0.300813821875367,"spread":0.2794685944221068,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001223412,0.00009714624,0.0001453153,0.0001121296,0.00004513759,0.00004318667,0.0002502644,0.00003791591,0.00006062695],"category_scores_gemma":[0.00002126671,0.00008933472,0.00008145399,0.0001546924,0.00001718054,0.0002980526,0.0000341599,0.00004751249,0.0000034739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002453792,"about_ca_system_score_gemma":0.00004564824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001025954,"about_ca_topic_score_gemma":0.000001154324,"domain_scores_codex":[0.9991144,0.00004745549,0.000215247,0.0002527399,0.0002103536,0.0001597823],"domain_scores_gemma":[0.9993453,0.000119072,0.0001575274,0.000197229,0.0001351002,0.00004576134],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002675829,0.0001421438,0.001037388,0.0001209864,0.0002081771,0.000004375228,0.003247448,0.001290016,0.03639529,0.1058113,0.001188874,0.8505272],"study_design_scores_gemma":[0.001082064,0.0001564325,0.001829857,0.0000312753,0.00001238746,0.000004633928,0.00006241338,0.8920657,0.04164328,0.06258272,0.0003078104,0.000221411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01112664,0.00005304356,0.9877648,0.0001111626,0.0002574013,0.0002812206,0.0001031995,0.00004009929,0.0002624248],"genre_scores_gemma":[0.1740846,0.000004478475,0.82547,0.00008930867,0.00004049478,0.00001881623,0.00005944096,0.000007833219,0.0002250734],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8907757,"threshold_uncertainty_score":0.3642964,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}