{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":24,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":24,"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":"5f78ad9233b1","filters":{"venue":"Journal of Statistical Software"}},"results":[{"id":"W1951724000","doi":"10.18637/jss.v067.i01","title":"Fitting Linear Mixed-Effects Models Using <b>lme4</b>","year":2015,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":85618,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Banff International Research Station for Mathematical Innovation and Discovery","keywords":"Restricted maximum likelihood; Deviance (statistics); Mixed model; Smoothing; Applied mathematics; Likelihood function; Mathematics; Generalized linear model; Linear model; Maximum likelihood; Generalized linear mixed model; Covariate; Algorithm; Statistics; Mathematical optimization; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05709843782498766,"gpt":0.3091346325908944,"spread":0.2520361947659067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009528171,0.0001574766,0.0004106679,0.000163185,0.00008203353,0.0001787019,0.0008681733,0.00006818924,0.000008848665],"category_scores_gemma":[0.002802184,0.0001253954,0.00009875629,0.000386668,0.00005849559,0.001176472,0.00028602,0.0003395146,0.00002376487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001370502,"about_ca_system_score_gemma":0.0002597245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002446738,"about_ca_topic_score_gemma":0.000001687414,"domain_scores_codex":[0.9977947,0.0001709911,0.0006136706,0.0002227692,0.0008701847,0.0003276457],"domain_scores_gemma":[0.997327,0.0008255639,0.0004153922,0.0003406523,0.0005814554,0.0005098938],"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":[0.0001876507,0.0009706601,0.01076648,0.0004139777,0.0007772641,0.006939227,0.002703609,0.2079741,0.0004120017,0.1951889,0.06049496,0.5131711],"study_design_scores_gemma":[0.0006922987,0.000262031,0.0004306987,0.0001278861,0.0000992819,0.0003246166,0.00004015134,0.9297093,0.0001729496,0.06743106,0.0004911469,0.000218558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005111812,0.0002128192,0.9939271,0.0001172292,0.0004791062,0.00005101738,0.00002071698,0.00004463909,0.00003560621],"genre_scores_gemma":[0.1532665,0.00000444571,0.8462998,0.0001934798,0.0002033804,5.357288e-7,0.000003158393,0.00001263424,0.00001607407],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7217352,"threshold_uncertainty_score":0.5113477,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2577537660","doi":"10.18637/jss.v076.i01","title":"<i>Stan</i> : A Probabilistic Programming Language","year":2017,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":7378,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"National Center for Research Resources; Institute of Education Sciences; U.S. Department of Energy; National Science Foundation; National Institutes of Health; Harvard University","keywords":"Python (programming language); Computer science; Markov chain Monte Carlo; Algorithm; Hybrid Monte Carlo; Monte Carlo method; Probabilistic logic; Bayesian inference; Importance sampling; Statistical inference; Inference; Monte Carlo integration; Applied mathematics; Bayesian probability; Mathematical optimization; Mathematics; Programming language; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05011962462799613,"gpt":0.3917699605443133,"spread":0.3416503359163172,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009102275,0.0001796903,0.0005167201,0.00005041066,0.0003021774,0.0002846674,0.0005245472,0.00008582782,0.0003789667],"category_scores_gemma":[0.04616964,0.0001300549,0.0001060301,0.00004811689,0.0003206751,0.0001867744,0.0001020683,0.0004133105,0.00001356263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000619938,"about_ca_system_score_gemma":0.0001206942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001502556,"about_ca_topic_score_gemma":0.00000945792,"domain_scores_codex":[0.9981489,0.0001209969,0.0006905821,0.0001780416,0.0005147245,0.0003467572],"domain_scores_gemma":[0.9949358,0.00324235,0.0007584486,0.0004370284,0.0003340052,0.0002923604],"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":[0.00008834963,0.0002058261,0.001925253,0.0003019515,0.0000539069,0.0007744918,0.0002793355,1.809188e-7,0.00005466072,0.4832549,0.00231745,0.5107437],"study_design_scores_gemma":[0.0006205324,0.0003817022,0.008532214,0.0002878917,0.000143816,0.0002051896,0.0001206169,0.00006645682,0.00007319434,0.9879004,0.001456292,0.0002116362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004052805,0.00005663355,0.9945754,0.0002112842,0.000263792,0.000163598,0.0001181129,0.00003427111,0.0005241047],"genre_scores_gemma":[0.09834418,0.000005574368,0.9012851,0.00004603297,0.0002159208,0.000005895943,0.000001359335,0.00002455867,0.00007138465],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5105321,"threshold_uncertainty_score":0.9618649,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1630835083","doi":"10.18637/jss.v050.i12","title":"<b>nparLD</b>: An<i>R</i>Software Package for the Nonparametric Analysis of Longitudinal Data in Factorial Experiments","year":2012,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":1065,"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; Deutsche Forschungsgemeinschaft; Deutscher Akademischer Austauschdienst","keywords":"Nonparametric statistics; Factorial; Outlier; Parametric statistics; Computer science; R package; Longitudinal data; Software; Econometrics; Rank (graph theory); Data science; Statistics; Data mining; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.243031611199427,"gpt":0.484862265102054,"spread":0.241830653902627,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002200078,0.0002391514,0.001022207,0.0003410255,0.00009585828,0.0000376576,0.000743563,0.0001181444,0.000166033],"category_scores_gemma":[0.02974162,0.0001547562,0.0001824326,0.0008146411,0.0001625489,0.0005601262,0.0001739099,0.0003658644,0.000001058573],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00010007,"about_ca_system_score_gemma":0.00008318007,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003088221,"about_ca_topic_score_gemma":0.00002128468,"domain_scores_codex":[0.996954,0.00025632,0.001268203,0.0002692238,0.0007434188,0.0005088022],"domain_scores_gemma":[0.9770337,0.02083327,0.0007301969,0.0007188598,0.0003625488,0.0003213816],"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":[0.005254267,0.009776946,0.3275534,0.001260687,0.008677704,0.0001773098,0.005066594,0.001507217,0.0007429969,0.3384257,0.009774415,0.2917828],"study_design_scores_gemma":[0.006181879,0.002176841,0.2457388,0.0002602568,0.01215641,0.00005817561,0.001070771,0.01490626,0.0008309653,0.71321,0.0021506,0.001259062],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01029888,0.000563761,0.9852569,0.0000191128,0.0005878925,0.0002921252,0.002964118,0.00001319941,0.000004088828],"genre_scores_gemma":[0.2894292,0.00003378169,0.7100883,0.00002217876,0.0003228139,0.00001013809,0.0000588375,0.00002595265,0.000008871629],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3747843,"threshold_uncertainty_score":0.9784313,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4404880964","doi":"10.18637/jss.v111.i09","title":"How to Interpret Statistical Models Using <b>marginaleffects</b> for <i>R</i> and <i>Python</i>","year":2024,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":371,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Python (programming language); Computer science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02178882680213142,"gpt":0.2979243716317229,"spread":0.2761355448295915,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002960102,0.0001390289,0.0002486614,0.0001162164,0.00009476318,0.0006930052,0.0002878252,0.0000365872,0.000003704401],"category_scores_gemma":[0.0003310068,0.0001174293,0.0000652143,0.0002443991,0.00005162094,0.0004839847,0.000127719,0.0001809617,0.000002660588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005480586,"about_ca_system_score_gemma":0.0001642087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003598029,"about_ca_topic_score_gemma":7.805003e-7,"domain_scores_codex":[0.9988523,0.00004254929,0.0003033386,0.0002674213,0.0003205293,0.0002138567],"domain_scores_gemma":[0.9962825,0.002963617,0.00005704466,0.0001394553,0.0002598036,0.000297645],"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":[0.00002362488,0.00003718389,0.000009450384,0.0001238789,0.0000376016,0.00004604756,0.000244035,0.001436366,0.0002956498,0.8544874,0.009046085,0.1342126],"study_design_scores_gemma":[0.0001515098,0.0002354602,0.00007613385,0.0001065701,0.00003406248,0.0001434506,0.00000779444,0.4217518,0.00004460909,0.5705971,0.006720425,0.0001310368],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005427496,0.0003670434,0.9960543,0.002109569,0.0002897317,0.0002162392,0.0003542562,0.0000485905,0.00001753451],"genre_scores_gemma":[0.2352777,0.000009224239,0.764141,0.0003603907,0.0001598862,0.00001064019,0.000006386686,0.0000159086,0.00001893111],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4203155,"threshold_uncertainty_score":0.6682665,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409376239","doi":"10.18637/jss.v112.i01","title":"Parsimoniously Fitting Large Multivariate Random Effects in <b>glmmTMB</b>","year":2025,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":302,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"University of New South Wales; Analytical Center for the Government of the Russian Federation; McMaster University","keywords":"Multivariate statistics; Computer science; Statistics; Mathematics; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.02737557881685304,"gpt":0.3755612070587689,"spread":0.3481856282419159,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001738516,0.0002002207,0.0007735188,0.0001867859,0.00008683516,0.00005539524,0.0002381103,0.0001272847,0.0001712382],"category_scores_gemma":[0.0612594,0.0001531236,0.0001083182,0.0003061218,0.0000763287,0.00008421579,0.00008731305,0.0006255203,0.000008492806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001038585,"about_ca_system_score_gemma":0.0001399806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002251596,"about_ca_topic_score_gemma":0.00001140366,"domain_scores_codex":[0.9974759,0.0004879228,0.00104946,0.0001925654,0.0003628789,0.0004312515],"domain_scores_gemma":[0.9744352,0.02466837,0.0003296543,0.0001621125,0.0002444233,0.0001602556],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007305862,0.0007532274,0.02733538,0.001060168,0.0001507328,0.0008926799,0.0005387215,0.00001905841,0.0001370441,0.8253703,0.005221122,0.1377911],"study_design_scores_gemma":[0.005385196,0.0002159426,0.04905867,0.001038364,0.0001195971,0.00001812178,0.00006648909,0.0022398,0.0001314175,0.9409046,0.0006354915,0.0001863273],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01758028,0.0001553516,0.9811034,0.0001534175,0.0004249097,0.0002136476,0.00007066131,0.00002783273,0.0002705351],"genre_scores_gemma":[0.2489046,0.00001251054,0.7506986,0.00021903,0.00006414004,0.000007336678,0.000001517417,0.00001630536,0.00007598016],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2313244,"threshold_uncertainty_score":0.946648,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1914588449","doi":"10.18637/jss.v019.i09","title":"<b>tgp</b>: An<i>R</i>Package for Bayesian Nonstationary, Semiparametric Nonlinear Regression and Design by Treed Gaussian Process Models","year":2007,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":206,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Booth University College","funders":"","keywords":"Bayesian probability; Gaussian process; Semiparametric regression; Gaussian; Computer science; Nonlinear system; Bayesian inference; Inference; Dimension (graph theory); Mathematics; Applied mathematics; Algorithm; Regression; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.0226674164356033,"gpt":0.3016473060079822,"spread":0.2789798895723788,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001047339,0.0002715984,0.0004373622,0.0002970283,0.0002441567,0.000286977,0.0006973373,0.0001526909,0.00001582363],"category_scores_gemma":[0.0007985763,0.0002032241,0.00006540014,0.0006208778,0.0001303203,0.001468787,0.00006198671,0.0003245507,0.000001717587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006146475,"about_ca_system_score_gemma":0.0003016686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004553065,"about_ca_topic_score_gemma":0.000002186955,"domain_scores_codex":[0.9975504,0.00007727622,0.0008097963,0.0004137419,0.0006443329,0.0005044754],"domain_scores_gemma":[0.9966035,0.001415218,0.0005443805,0.0002501719,0.0005775079,0.0006091731],"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":[0.001362407,0.001598005,0.002492618,0.0009351452,0.0001420148,0.0006979075,0.002804138,0.001128236,0.001000825,0.06165798,0.01425653,0.9119242],"study_design_scores_gemma":[0.003926696,0.004583565,0.003842032,0.000610692,0.0001424792,0.001028007,0.0004338151,0.4505574,0.004622402,0.5284392,0.0006572892,0.001156502],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001083757,0.0003785292,0.9975265,0.000382064,0.0001267093,0.0002815928,0.0001234117,0.00005504869,0.0000423652],"genre_scores_gemma":[0.2779157,0.00004419649,0.7216993,0.0001933672,0.00008128466,0.000005720613,0.00001571421,0.00002046276,0.0000242504],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9107677,"threshold_uncertainty_score":0.8287239,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135892144","doi":"10.18637/jss.v033.i06","title":"Categorical Inputs, Sensitivity Analysis, Optimization and Importance Tempering with<b>tgp</b>Version 2, an<i>R</i>Package for Treed Gaussian Process Models","year":2010,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","cited_by":127,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Booth University College","funders":"Engineering and Physical Sciences Research Council","keywords":"Categorical variable; Computer science; Gaussian process; Covariate; Markov chain Monte Carlo; Sensitivity (control systems); Bayesian probability; Algorithm; Gaussian; Artificial intelligence; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.00885045248584295,"gpt":0.251482053128426,"spread":0.242631600642583,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004294189,0.0001948471,0.000418677,0.0001784014,0.0001978423,0.0002948277,0.0003073695,0.0001091443,0.0000143776],"category_scores_gemma":[0.0002455896,0.0001419481,0.00006179349,0.0005640762,0.0001110492,0.001472471,0.00005523206,0.0003551253,4.126398e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003114942,"about_ca_system_score_gemma":0.0002005246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001022565,"about_ca_topic_score_gemma":0.00006095151,"domain_scores_codex":[0.9984395,0.00004504651,0.0004409241,0.0003615305,0.0004214653,0.000291563],"domain_scores_gemma":[0.9981918,0.0002699805,0.0003898047,0.0002480393,0.0005373741,0.0003629555],"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":[0.002171859,0.002901386,0.2250522,0.002404335,0.001870961,0.003260718,0.007021142,0.3614329,0.00638457,0.276996,0.001098059,0.1094059],"study_design_scores_gemma":[0.001055809,0.0007429998,0.01727372,0.00004577588,0.000309659,0.0004700559,0.00007340455,0.9522681,0.0005898789,0.02672263,0.00002830802,0.0004196658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0291948,0.00002275843,0.9701558,0.0003313259,0.00007329058,0.0001219926,0.00004452387,0.00004196188,0.00001357123],"genre_scores_gemma":[0.5772945,0.000008567083,0.4225658,0.00006126772,0.00004465449,0.000002699632,0.00001071471,0.000008285996,0.000003563798],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5908352,"threshold_uncertainty_score":0.5788474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3123059542","doi":"10.18637/jss.v091.i04","title":"Markov-Switching GARCH Models in <i>R</i>: The <b>MSGARCH</b> Package","year":2019,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institut de Valorisation des Données; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Autoregressive conditional heteroskedasticity; Heteroscedasticity; Econometrics; Markov chain; Markov chain Monte Carlo; Conditional variance; Computer science; Autoregressive model; Volatility (finance); Bayesian probability; Mathematics; Machine learning; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03152622886809661,"gpt":0.2488539276623972,"spread":0.2173276987943006,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001906551,0.0001275355,0.0004525925,0.0001659659,0.00006465697,0.00008123033,0.0003865582,0.00008376558,0.0002237892],"category_scores_gemma":[0.0007089787,0.0001012696,0.0001168946,0.0001941908,0.00003229371,0.0003248675,0.00004916598,0.0006432895,0.0001146286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007820853,"about_ca_system_score_gemma":0.0000480118,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001508284,"about_ca_topic_score_gemma":0.00002197322,"domain_scores_codex":[0.9983038,0.00005283193,0.0009888345,0.0001977073,0.0001402983,0.0003164723],"domain_scores_gemma":[0.9985716,0.0007089794,0.0003497631,0.0002275019,0.00006447197,0.00007764843],"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":[0.00029313,0.0003544482,0.3300195,0.0001888947,0.0000448353,0.0001552266,0.004357736,0.003451394,0.00002410714,0.6185455,0.001904747,0.04066047],"study_design_scores_gemma":[0.001042887,0.0002682068,0.111917,0.0001049998,0.000009415534,0.00004202159,0.0002825916,0.05106796,0.000003602917,0.8309583,0.004043642,0.0002594014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3042232,0.0008535141,0.6926445,0.0003524289,0.0002452935,0.0001326038,0.0001069767,0.000006580698,0.001434922],"genre_scores_gemma":[0.9718545,0.0001350163,0.02748656,0.0003413704,0.000103,0.000002324603,0.000003919534,0.00001717167,0.00005611104],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6676313,"threshold_uncertainty_score":0.4129655,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2512875827","doi":"10.18637/jss.v072.i05","title":"<b>RSKC</b>: An<i>R</i>Package for a Robust and Sparse K-Means Clustering Algorithm","year":2016,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":58,"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":"Outlier; Cluster analysis; Computer science; Data mining; R package; Identification (biology); Algorithm; Monte Carlo method; Artificial intelligence; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03384400660344562,"gpt":0.3084657004614797,"spread":0.2746216938580341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006244439,0.000182414,0.0003427081,0.000141366,0.0001508966,0.0001784562,0.0006844442,0.0000749302,0.00002321097],"category_scores_gemma":[0.001237894,0.0001224104,0.0000640147,0.0001495949,0.0001553385,0.001029629,0.0003165031,0.0002142476,0.00000690521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001175814,"about_ca_system_score_gemma":0.0001111303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005034848,"about_ca_topic_score_gemma":0.000005809253,"domain_scores_codex":[0.9980499,0.00008658684,0.0004928761,0.0003364101,0.0005329926,0.0005012915],"domain_scores_gemma":[0.9970955,0.001440562,0.0002082896,0.0003288623,0.0004284634,0.0004983586],"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":[0.00005437817,0.00006938931,0.0001064223,0.00004848534,0.00002692322,0.0002227733,0.0001412652,0.0002375269,0.0004097314,0.001164303,0.0004286783,0.9970901],"study_design_scores_gemma":[0.009139725,0.006150754,0.008910947,0.0008803841,0.0000845441,0.003483956,0.0001779072,0.8703783,0.001593894,0.0860487,0.01179213,0.001358808],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003336116,0.00009500085,0.9982871,0.0006310376,0.0002733649,0.0001585039,0.0001530954,0.00006111642,0.000007142326],"genre_scores_gemma":[0.003934018,0.00006315737,0.9954907,0.0001040445,0.0002405308,0.000009092897,0.000001463921,0.0000276785,0.0001293165],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9957313,"threshold_uncertainty_score":0.499175,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1948959238","doi":"10.18637/jss.v023.i05","title":"Algorithms for Linear Time Series Analysis: With<i>R</i>Package","year":2007,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"R package; Computer science; Series (stratigraphy); Software package; Time series; Algorithm; Base (topology); Software; Linear regression; Mathematics; Computational science; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02527237254336562,"gpt":0.2633249778170461,"spread":0.2380526052736805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001169243,0.0001266161,0.0005974493,0.0002576861,0.0001016047,0.00004141382,0.0001442717,0.00008526917,0.0001760361],"category_scores_gemma":[0.0008950868,0.0001128159,0.0001835371,0.0003503085,0.00006968433,0.0002431738,0.00001702916,0.0001848237,0.00004031734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006439594,"about_ca_system_score_gemma":0.00003644298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002568465,"about_ca_topic_score_gemma":0.00002003582,"domain_scores_codex":[0.998525,0.000007111233,0.0009139773,0.0001829044,0.00008234336,0.0002886648],"domain_scores_gemma":[0.9986158,0.0003850093,0.0004864908,0.0001332739,0.0002249053,0.0001545136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005711521,0.001286395,0.5738457,0.0005260255,0.004803316,0.0005756772,0.002577937,0.007371332,0.00007646221,0.3041949,0.007258368,0.09177233],"study_design_scores_gemma":[0.005881044,0.005400384,0.4274285,0.0001918504,0.001491235,0.0001503921,0.0003816368,0.06915335,0.0004523724,0.4002707,0.08741236,0.001786216],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02279818,0.0004734738,0.9755864,0.0001117321,0.0001098187,0.00009143221,0.0006974376,0.00001459089,0.000116927],"genre_scores_gemma":[0.2481713,0.00004437646,0.7509409,0.000111821,0.0003184337,0.000002285252,0.00003376781,0.00002520047,0.0003518866],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2253731,"threshold_uncertainty_score":0.4600497,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4294557430","doi":"10.18637/jss.v103.i07","title":"Hierarchical Clustering with Contiguity Constraint in <i>R</i>","year":2022,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Contiguity; Cluster analysis; Computer science; Hierarchical clustering; Theoretical computer science; Function (biology); Algorithm; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01225028693388872,"gpt":0.2517438408299075,"spread":0.2394935538960188,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007909212,0.0001025944,0.0003215189,0.0001695833,0.0001061172,0.00009456924,0.0008172485,0.00001893696,0.0001905066],"category_scores_gemma":[0.0003849022,0.00008022326,0.00004820684,0.0004133015,0.0001151998,0.0002798076,0.0004303651,0.0006522224,0.000003338227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001453686,"about_ca_system_score_gemma":0.000231762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002381971,"about_ca_topic_score_gemma":0.00003445194,"domain_scores_codex":[0.9981098,0.0002084704,0.0005004951,0.0001933971,0.000735458,0.0002524007],"domain_scores_gemma":[0.9986761,0.0005873595,0.0002295649,0.000230153,0.00009571919,0.0001810557],"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":[0.001104872,0.001885062,0.181386,0.0001620307,0.0004820352,0.02676424,0.002617699,0.02968113,0.0002350807,0.2091577,0.01896568,0.5275584],"study_design_scores_gemma":[0.01911152,0.01072238,0.47259,0.0005444437,0.0003494361,0.02002822,0.001823277,0.270853,0.0001705129,0.1491793,0.05183918,0.00278867],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006641724,0.0000359637,0.9921938,0.0007755124,0.0001180363,0.00005415348,0.00007355095,0.00001903532,0.0000882781],"genre_scores_gemma":[0.6034518,0.000002320131,0.3960732,0.0004219468,0.00002467283,0.000003387658,0.000004274366,0.000005791009,0.00001258797],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5968102,"threshold_uncertainty_score":0.327141,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1947760575","doi":"10.18637/jss.v047.i05","title":"High-Dimensional Bayesian Clustering with Variable Selection: The<i>R</i>Package<b>bclust</b>","year":2012,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Neuchâtel; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"R package; Cluster analysis; Computer science; Bayesian probability; Hierarchical clustering; Bayes' theorem; Bayes factor; Parametric statistics; Variable (mathematics); Data mining; Mathematics; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01069729842721405,"gpt":0.2481134082660615,"spread":0.2374161098388475,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001064832,0.0001781163,0.0003000237,0.00006991405,0.0002559283,0.000140145,0.0004841047,0.00007509237,0.0001408934],"category_scores_gemma":[0.0002403611,0.0001020549,0.00005579468,0.0003499835,0.00008105119,0.0006750577,0.0001362413,0.0004891703,0.00000982468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000074184,"about_ca_system_score_gemma":0.0001704716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001885726,"about_ca_topic_score_gemma":0.000003331293,"domain_scores_codex":[0.9981723,0.0002204658,0.000407848,0.0001688477,0.000579558,0.0004509734],"domain_scores_gemma":[0.9981726,0.0007131053,0.0002605646,0.0002350025,0.0002744417,0.0003443119],"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":[0.0002275928,0.0003944675,0.002496424,0.00008870543,0.0002354224,0.0001644756,0.0007403185,0.002105786,0.0003567246,0.7857991,0.02054046,0.1868505],"study_design_scores_gemma":[0.007143085,0.004437575,0.04506832,0.0009666519,0.000759886,0.02327674,0.00009489867,0.1240459,0.00276952,0.7561005,0.03270695,0.00262999],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002199953,0.0001824587,0.9980267,0.0007048142,0.0006245594,0.00008083745,0.000009942041,0.00004115682,0.0001094963],"genre_scores_gemma":[0.09987766,0.000003475971,0.8987926,0.0007017149,0.0005002862,0.000002717935,0.000001030296,0.00001572708,0.0001048283],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1842205,"threshold_uncertainty_score":0.4161679,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1868578820","doi":"10.18637/jss.v010.i01","title":"<b>MATCH</b>- A Software Package for Robust Profile Matching Using<i>S-PLUS</i>","year":2004,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Vehicle emissions and performance","field":"Engineering","cited_by":35,"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":"Listing (finance); Computer science; Software; Matching (statistics); Set (abstract data type); Graphical user interface; Programming language; Data mining; Software engineering; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02054728917139723,"gpt":0.2583351193331463,"spread":0.2377878301617491,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002178864,0.0001999393,0.0003721394,0.0000831509,0.0001526128,0.00006779427,0.0001982501,0.000112391,0.0001626427],"category_scores_gemma":[0.0002649061,0.0001665573,0.0001155425,0.0001446183,0.00004399584,0.0002784628,0.00002794663,0.0003781272,0.00001568988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000248194,"about_ca_system_score_gemma":0.0001561916,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001083017,"about_ca_topic_score_gemma":0.000003328511,"domain_scores_codex":[0.9986449,0.00001184689,0.0005499383,0.0001213782,0.0002965468,0.0003754068],"domain_scores_gemma":[0.9990223,0.0002449073,0.0001328336,0.0001436517,0.0001887323,0.0002675939],"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":[0.0002530539,0.0001824647,0.001316199,0.001741917,0.0001943525,0.000303034,0.0009573668,0.9367894,0.003901666,0.001366955,0.01325116,0.03974242],"study_design_scores_gemma":[0.05349255,0.006681427,0.02527684,0.01535261,0.002342304,0.009399853,0.003515338,0.4588641,0.05264004,0.2808676,0.08130898,0.01025839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07083259,0.0002394677,0.9278357,0.00004485772,0.000385706,0.000159191,0.000366275,0.0001120886,0.00002412194],"genre_scores_gemma":[0.1721382,0.00003654008,0.8273003,0.00007411666,0.0003246267,0.000006964436,0.00001989427,0.00006535173,0.00003403774],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4779253,"threshold_uncertainty_score":0.6792011,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3194665160","doi":"10.18637/jss.v099.i02","title":"The <i>R</i> Package <b>sentometrics</b> to Compute, Aggregate, and Predict with Textual Sentiment","year":2021,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institut de Valorisation des Données; Innoviris; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"R package; Computer science; Aggregate (composite); Indexation; Sentiment analysis; Workflow; Index (typography); Volatility (finance); Series (stratigraphy); Information retrieval; Econometrics; Natural language processing; Mathematics; World Wide Web; Database; Programming language; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.01761164827682454,"gpt":0.3292169960357477,"spread":0.3116053477589231,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00110605,0.00008664134,0.0002196519,0.00009270222,0.0005012577,0.000252784,0.0001513039,0.00003243086,0.00009184972],"category_scores_gemma":[0.002493791,0.00005308473,0.00005484381,0.0008837108,0.0002144434,0.00009202225,0.00007322339,0.0001724496,0.000006386404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006563176,"about_ca_system_score_gemma":0.0002886017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004925055,"about_ca_topic_score_gemma":0.0001658341,"domain_scores_codex":[0.9981265,0.0002879419,0.0003286307,0.00013439,0.0008974347,0.0002251173],"domain_scores_gemma":[0.9950793,0.003612903,0.0001723116,0.00007689303,0.000702607,0.0003559786],"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":[0.00020928,0.0003088526,0.03624225,0.00003248741,0.0004950528,0.001027982,0.003020219,0.0005181176,0.00003436216,0.08286735,0.02618069,0.8490633],"study_design_scores_gemma":[0.002781057,0.001506102,0.3451328,0.0003764574,0.0007443082,0.0004890179,0.01012514,0.0009894442,0.0002326279,0.0720166,0.5648035,0.0008029312],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01996706,0.0006574104,0.9753965,0.003137889,0.0001664431,0.00007648762,0.00003595183,0.00001449757,0.0005477208],"genre_scores_gemma":[0.4031909,0.0004291772,0.5935204,0.0007842412,0.0006025687,0.000003207941,0.000009824729,0.00001753731,0.001442174],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8482604,"threshold_uncertainty_score":0.385532,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1486450196","doi":"10.18637/jss.v069.i04","title":"Parallel and Other Simulations in<i>R</i>Made Easy: An End-to-End Study","year":2016,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Eidgenössische Technische Hochschule Zürich","keywords":"Computer science; Graphics; Computation; Set (abstract data type); Table (database); Scale (ratio); Contrast (vision); Contingency table; Algorithm; Computational science; Data mining; Computer graphics (images); Artificial intelligence; Programming language; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02613877045930482,"gpt":0.3101626526354363,"spread":0.2840238821761315,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004828884,0.0001210394,0.0002876167,0.0002149228,0.00006044372,0.0001357485,0.0005501485,0.00003285046,0.0001852825],"category_scores_gemma":[0.0009009088,0.00007595955,0.00002891779,0.0002873663,0.00005609051,0.0006947822,0.0001555552,0.0001344881,0.00002440515],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000522532,"about_ca_system_score_gemma":0.00007227833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004631328,"about_ca_topic_score_gemma":0.0001749647,"domain_scores_codex":[0.9983597,0.0001725447,0.0005003291,0.0002522159,0.0004843613,0.0002308064],"domain_scores_gemma":[0.998134,0.0009100978,0.0001612896,0.0003288275,0.0001293904,0.0003364618],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001188557,0.001282488,0.7211863,0.00001294167,0.0001629407,0.0005537773,0.001761117,0.001741552,0.0003026386,0.01879176,0.001333498,0.2527521],"study_design_scores_gemma":[0.002366704,0.001358336,0.9609758,0.0000873117,0.00007601031,0.00007468704,0.0001246709,0.006039424,0.00001232507,0.02410753,0.004436296,0.000340957],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0670562,0.00002179962,0.9321252,0.0004888421,0.00006209196,0.00009744676,0.0001162219,0.00001804709,0.00001414548],"genre_scores_gemma":[0.7557872,0.000001966823,0.2437742,0.000334274,0.00004903072,0.000001622916,8.777165e-7,0.000008151104,0.00004265553],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.688731,"threshold_uncertainty_score":0.309754,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2801007199","doi":"10.18637/jss.v084.c01","title":"<b>stampr</b>: Spatial-Temporal Analysis of Moving Polygons in <i>R</i>","year":2018,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Polygon (computer graphics); Computer science; R package; Core (optical fiber); Computer graphics (images); Algorithm; Computational science","retraction":null,"screen_n_in":null,"score":{"opus":0.01174774280374646,"gpt":0.2764526692167041,"spread":0.2647049264129577,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008289578,0.0001420103,0.0006928263,0.0009017899,0.00005106394,0.00008692711,0.0009753344,0.00006215694,0.0002646181],"category_scores_gemma":[0.001278484,0.0001170268,0.0001934292,0.002205038,0.0001792416,0.0004925092,0.0002255704,0.0002381936,0.00001476478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007748092,"about_ca_system_score_gemma":0.0001890888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007530392,"about_ca_topic_score_gemma":0.001054551,"domain_scores_codex":[0.9975657,0.0001412948,0.001044935,0.0002414787,0.0007148074,0.0002917866],"domain_scores_gemma":[0.9975651,0.000660954,0.0006539068,0.0004492647,0.0004634703,0.0002072861],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001800223,0.0007953543,0.8024803,0.00006475028,0.002231806,0.0007877509,0.001642515,0.001023144,0.0006044765,0.02012024,0.006582755,0.1634868],"study_design_scores_gemma":[0.001398793,0.001110306,0.8240443,0.0001755907,0.001604397,0.00006354679,0.0001362689,0.1495364,0.0007640462,0.01904575,0.001564832,0.0005556513],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02466681,0.00006037252,0.9746336,0.0002487954,0.0001481464,0.00003611225,0.0001156157,0.00001584388,0.00007465028],"genre_scores_gemma":[0.7287952,0.000006322825,0.2709761,0.0001266236,0.00006320373,5.079624e-7,0.00000992399,0.000005922328,0.00001626254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7041284,"threshold_uncertainty_score":0.4772215,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7126223455","doi":"10.18637/jss.v115.i02","title":"<b>sdmTMB</b> : An <i>R</i> Package for Fast, Flexible, and User-Friendly Generalized Linear Mixed Effects Models with Spatial and Spatiotemporal Random Fields","year":2025,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Fisheries and Oceans Canada; Bird Studies Canada","keywords":"Random field; Inference; Gaussian; Flexibility (engineering); Bayesian probability; Markov random field; Random effects model; Generalized linear mixed model; Spatial analysis; Spatial correlation","retraction":null,"screen_n_in":null,"score":{"opus":0.008286097233459026,"gpt":0.2485137711835335,"spread":0.2402276739500745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003042139,0.0001774147,0.0003836806,0.00005169795,0.000161984,0.00007683129,0.0001099274,0.00008580528,0.0000372348],"category_scores_gemma":[0.0003761274,0.0001329459,0.00003512615,0.00009452589,0.0001902192,0.0002293337,0.00008098054,0.0001795399,8.265658e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003512132,"about_ca_system_score_gemma":0.00003852817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003411633,"about_ca_topic_score_gemma":0.0001952862,"domain_scores_codex":[0.9987968,0.00008178705,0.000367625,0.000237643,0.0002669564,0.0002492518],"domain_scores_gemma":[0.9985976,0.0008234616,0.0001717432,0.0001190753,0.00005925586,0.0002289298],"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":[0.01256711,0.0008995355,0.1186166,0.001736262,0.0005757784,0.0006193384,0.001599479,0.01347812,0.001565802,0.04840701,0.04478128,0.7551537],"study_design_scores_gemma":[0.06673858,0.01328848,0.31613,0.001462981,0.001677272,0.0003344413,0.000537872,0.3302681,0.004876097,0.2459763,0.01637675,0.00233316],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09142857,0.00009233629,0.9077164,0.0001372288,0.000130702,0.0002899994,0.0001323709,0.00001644312,0.00005596019],"genre_scores_gemma":[0.4961151,0.00004896178,0.5033403,0.0002822282,0.00005876307,0.00001224206,0.00002094577,0.0000148878,0.0001065298],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7528206,"threshold_uncertainty_score":0.5421377,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402023001","doi":"10.18637/jss.v110.i06","title":"<b>sparsegl</b>: An <i>R</i> Package for Estimating Sparse Group Lasso","year":2024,"lang":"ru","type":"article","venue":"Journal of Statistical Software","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; Carnegie Mellon University; National Institutes of Health; National Science Foundation","keywords":"R package; Lasso (programming language); Group (periodic table); Computer science; Statistics; Mathematics; Chemistry; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.07643798190945737,"gpt":0.3837497454727727,"spread":0.3073117635633154,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00305489,0.0006126707,0.001422886,0.0002293562,0.0002723916,0.0008149575,0.0005907862,0.0003734765,0.001537931],"category_scores_gemma":[0.03284444,0.0004949261,0.0004019125,0.0003645441,0.0003742265,0.0004994064,0.0001276866,0.001299579,0.0001051007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002486584,"about_ca_system_score_gemma":0.0004441225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000167639,"about_ca_topic_score_gemma":0.000008402397,"domain_scores_codex":[0.9945258,0.0005098158,0.002350449,0.0006012387,0.001054528,0.0009582045],"domain_scores_gemma":[0.9721697,0.02495511,0.0007307949,0.0004496747,0.0007340314,0.0009606956],"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":[0.0003127677,0.0007314539,0.0001298365,0.004515489,0.0003918462,0.001299506,0.0008132163,0.00003335183,0.0002912573,0.4882838,0.03701967,0.4661778],"study_design_scores_gemma":[0.001191818,0.00380683,0.0005116715,0.003502151,0.001437506,0.0005261492,0.0003380625,0.08343127,0.0001655774,0.8961584,0.008169022,0.0007615647],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001218001,0.00117612,0.9882236,0.000355588,0.003791956,0.0005026956,0.004452365,0.000125577,0.0001541722],"genre_scores_gemma":[0.0237013,0.0000841551,0.9733938,0.0002597891,0.002117729,0.00002176245,0.00004954902,0.0001716969,0.0002002265],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4654163,"threshold_uncertainty_score":0.9997503,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4226403402","doi":"10.18637/jss.v102.i02","title":"Multivariate Normal Variance Mixtures in <i>R</i>: The <i>R</i> Package <b>nvmix</b>","year":2022,"lang":"ja","type":"article","venue":"Journal of Statistical Software","topic":"Data Analysis with R","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Univariate; Statistics; Multivariate statistics; Multivariate normal distribution; Random variate; Quantile; Variance (accounting); Mathematics; Normal distribution; Random variable; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.01430531852164699,"gpt":0.2654126965182635,"spread":0.2511073779966165,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004408532,0.0004260365,0.0008685692,0.000344197,0.0006651202,0.0006602358,0.004539476,0.000102749,0.001074944],"category_scores_gemma":[0.002370256,0.0003122826,0.000304812,0.00179945,0.0002431715,0.0009854101,0.001217438,0.002556309,0.00007087141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002707261,"about_ca_system_score_gemma":0.000547595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002589341,"about_ca_topic_score_gemma":0.00003868975,"domain_scores_codex":[0.9918651,0.002276903,0.00175657,0.0005756966,0.002643198,0.0008825611],"domain_scores_gemma":[0.9934486,0.003637648,0.001274625,0.0009998196,0.0003147197,0.0003246236],"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":[0.00235623,0.00943911,0.0250566,0.000682716,0.001343116,0.05838387,0.03699519,0.02389429,0.00148126,0.1795409,0.404655,0.2561717],"study_design_scores_gemma":[0.02029948,0.01025206,0.3123,0.001015507,0.002718808,0.01395249,0.007537322,0.09394126,0.0004141827,0.1125184,0.4198399,0.005210567],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001718747,0.001598686,0.9896131,0.003629598,0.001509929,0.0002581188,0.001489449,0.00002560203,0.0001568359],"genre_scores_gemma":[0.7869624,0.0001409554,0.2057392,0.006248573,0.0005837149,0.00002501013,0.00006291286,0.00004888685,0.0001882618],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7852437,"threshold_uncertainty_score":0.9999329,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2515705452","doi":"10.18637/jss.v073.i07","title":"My Early Interactions with Jan and Some of His Lost Papers","year":2016,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Period (music); Scaling; Multidimensional scaling; Computer science; History; Mathematics; Art; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01277572876579015,"gpt":0.2838603270710328,"spread":0.2710845983052427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001367033,0.00008126407,0.0001870348,0.00009688897,0.0000446862,0.00004191011,0.0002867205,0.00002248225,0.00006062505],"category_scores_gemma":[0.0004796656,0.00004623168,0.00002517251,0.0001132969,0.0001833726,0.0006098609,0.0001265415,0.0001743835,0.000008495708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006585987,"about_ca_system_score_gemma":0.00007887906,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008198306,"about_ca_topic_score_gemma":0.00000289142,"domain_scores_codex":[0.9989635,0.00004203209,0.0002680243,0.000131994,0.0004070387,0.000187363],"domain_scores_gemma":[0.9982858,0.0009527828,0.000166613,0.0001509502,0.0002456689,0.0001981539],"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":[0.0001842275,0.000121773,0.006197007,0.00006225516,0.0001028368,0.0003896009,0.0004398077,0.0000403329,0.003168919,0.01227708,0.0003401039,0.976676],"study_design_scores_gemma":[0.0145486,0.01875321,0.768164,0.004410671,0.0002110284,0.006236411,0.0005243029,0.00587593,0.0116976,0.1446674,0.02287714,0.002033709],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02084496,0.0000479523,0.9781627,0.0007423414,0.00008309336,0.00003827943,0.00002844138,0.00001082217,0.00004139728],"genre_scores_gemma":[0.4481591,0.00004071548,0.5513791,0.00003980085,0.00005748161,0.00000105051,1.696246e-7,0.000009344552,0.0003131596],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9746423,"threshold_uncertainty_score":0.1885273,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3089708264","doi":"10.18637/jss.v095.i04","title":"Zigzag Expanded Navigation Plots in <i>R</i>: The <i>R</i> Package <b>zenplots</b>","year":2020,"lang":"ja","type":"article","venue":"Journal of Statistical Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Zigzag; R package; Computer science; Mathematics; Statistics; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.02751384208072361,"gpt":0.2768311213842509,"spread":0.2493172793035273,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001656869,0.0004102612,0.0008968537,0.0001608367,0.0001909389,0.0008067205,0.002756113,0.0001739679,0.0001738864],"category_scores_gemma":[0.003413053,0.0002859193,0.000269727,0.001618736,0.000245947,0.001325284,0.0003612844,0.001465834,0.0002667443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001252119,"about_ca_system_score_gemma":0.0003673326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004227496,"about_ca_topic_score_gemma":0.0000140677,"domain_scores_codex":[0.9940091,0.0009285876,0.001804783,0.000549507,0.00205689,0.0006511643],"domain_scores_gemma":[0.9949969,0.002231764,0.001073007,0.0006447241,0.0004686443,0.0005849467],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.001738885,0.003942244,0.04521975,0.001902997,0.001280249,0.0314415,0.08514687,0.002214153,0.002867048,0.04839608,0.4324141,0.3434361],"study_design_scores_gemma":[0.03593396,0.02138855,0.4335301,0.008223223,0.005738098,0.007339692,0.01949359,0.1752527,0.003834173,0.1121025,0.1682246,0.008938817],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01424636,0.0007496012,0.9720363,0.0116657,0.0004846358,0.0002770692,0.0004042122,0.00004896673,0.00008715396],"genre_scores_gemma":[0.8991207,0.0001673007,0.09170708,0.008146266,0.0007249535,0.000005282999,0.00006385883,0.00004393486,0.00002066266],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8848743,"threshold_uncertainty_score":0.9999593,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3138858220","doi":"10.18637/jss.v097.i07","title":"<b>FamEvent</b>: An <i>R</i> Package for Generating and Modeling Time-to-Event Data in Family Designs","year":2021,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Alberta Health Services; University of Calgary; Lunenfeld-Tanenbaum Research Institute; Western University","funders":"National Cancer Institute","keywords":"Penetrance; Pedigree chart; Missing data; Computer science; Event (particle physics); Population; Statistics; Covariate; Confidence interval; R package; Data mining; Mathematics; Genetics; Medicine; Biology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.05960386585603619,"gpt":0.340195600066062,"spread":0.2805917342100259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007502236,0.00009079999,0.0002312529,0.0000283041,0.00005729772,0.00002393801,0.0001517215,0.00009160138,0.00001513023],"category_scores_gemma":[0.002699664,0.00008463779,0.00003091032,0.00004820867,0.00001778915,0.000007248342,0.0001329314,0.00009363412,0.00000180443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001746801,"about_ca_system_score_gemma":0.0001579836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007528421,"about_ca_topic_score_gemma":0.00002525776,"domain_scores_codex":[0.9988908,0.0001420517,0.000431882,0.0002384575,0.00009555111,0.0002012911],"domain_scores_gemma":[0.9991731,0.0001550018,0.0001118947,0.0002152724,0.0001943659,0.0001503333],"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":[0.0005069909,0.0008082471,0.04088023,0.000160627,0.0003600264,0.0001970182,0.0003429735,0.09052911,0.6624599,0.0003047737,0.03313063,0.1703195],"study_design_scores_gemma":[0.008362959,0.006337709,0.08741881,0.0003737702,0.0005159627,0.0006526061,0.00168889,0.8458328,0.006504851,0.01645072,0.02394012,0.001920852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.309835,0.0003968348,0.6892758,0.0001496793,0.00003714702,0.00005902437,0.000240949,0.00000146449,0.00000404093],"genre_scores_gemma":[0.3978653,0.00009195728,0.6006336,0.0007363842,0.000205897,0.000004440668,0.0003862488,0.00001635728,0.00005978781],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7553036,"threshold_uncertainty_score":0.3451429,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3094281686","doi":"10.18637/jss.v114.i04","title":"Exploring Data Subsets with <b>vtree</b>","year":2025,"lang":"en","type":"preprint","venue":"Journal of Statistical Software","topic":"Data Analysis with R","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Agricultural Research Institute of Ontario","funders":"","keywords":"Venn diagram; Contingency table; Variable (mathematics); Computer science; Missing data; Data mining; Diagram; Tree (set theory); Algorithm; Theoretical computer science; Mathematics; Machine learning; Combinatorics; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.1660587710562463,"gpt":0.3275761359707859,"spread":0.1615173649145396,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008792033,0.0003452149,0.0008649179,0.0003679731,0.00009353971,0.000524183,0.006344751,0.0001170331,0.00005502463],"category_scores_gemma":[0.001619478,0.0002542805,0.0001013202,0.0004499664,0.0001026462,0.001780273,0.005508028,0.001368133,0.00002325198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001389464,"about_ca_system_score_gemma":0.0009907254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006468037,"about_ca_topic_score_gemma":0.00004587571,"domain_scores_codex":[0.9965489,0.0001651957,0.0009543177,0.0007221288,0.00122853,0.0003809516],"domain_scores_gemma":[0.9946007,0.001076656,0.000835727,0.002565966,0.000593018,0.000328005],"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":[0.0003325866,0.0008459655,0.01735084,0.001844501,0.003045183,0.008691052,0.0009148361,0.006362213,0.000006213253,0.06093398,0.1185628,0.7811099],"study_design_scores_gemma":[0.01079188,0.003448606,0.2225675,0.02534421,0.009797005,0.003322678,0.0006478024,0.2692293,0.0004518871,0.2091658,0.2353337,0.009899644],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004185463,0.0003136668,0.9957938,0.0006585303,0.0007955568,0.0001015197,0.001732203,0.00007406436,0.0001121803],"genre_scores_gemma":[0.01146113,0.0003498798,0.9873245,0.0001938008,0.0002563384,0.000007399521,0.0003038512,0.00001854007,0.00008453865],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7712103,"threshold_uncertainty_score":0.9999909,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W7125397753","doi":"10.18637/jss.v115.i08","title":"<b>SMLE</b> : An <i>R</i> Package for Joint Feature Screening in Ultrahigh-Dimensional GLMs","year":2025,"lang":"en","type":"article","venue":"Journal of Statistical Software","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"R package; Categorical variable; Feature selection; Feature (linguistics); Flexibility (engineering); Joint (building); Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.06437155034120659,"gpt":0.3788384425209867,"spread":0.3144668921797801,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001178814,0.0002128861,0.0006583327,0.0001732405,0.0001023368,0.00006486863,0.0002241339,0.0001602642,0.000155458],"category_scores_gemma":[0.01687446,0.0001626476,0.0001217745,0.0002339505,0.0001170328,0.0001328525,0.00004767341,0.0005964803,0.000001851913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006008713,"about_ca_system_score_gemma":0.0001683381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001072777,"about_ca_topic_score_gemma":0.0000133416,"domain_scores_codex":[0.9979234,0.0002078765,0.0008443447,0.0002356082,0.0004144895,0.0003743069],"domain_scores_gemma":[0.9915755,0.007269652,0.0002890007,0.000195423,0.0004356079,0.0002347739],"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":[0.0008552249,0.0007623183,0.004223182,0.0006080466,0.0001364786,0.0002994683,0.0002174281,0.00004793723,0.001471244,0.7541611,0.04937145,0.1878462],"study_design_scores_gemma":[0.001781807,0.0006145621,0.02716324,0.0006711769,0.0001219705,0.00005417529,0.0001190399,0.001532418,0.0008330444,0.9656686,0.001195377,0.0002445639],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007073046,0.00009913787,0.9911184,0.0006295894,0.0003042705,0.0002267204,0.0004263485,0.00002559465,0.00009690777],"genre_scores_gemma":[0.03677809,0.000006362872,0.9623893,0.0005098346,0.0001246908,0.00001015858,0.00001380066,0.00002343154,0.0001443088],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2115076,"threshold_uncertainty_score":0.9914068,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}