{"meta":{"query_hash":"5f78ad9233b1","filters":{"venue":"Journal of Statistical Software"},"cohort_total":24,"direct_labels_cover":0,"predictions_cover":24,"exported":24,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/5f78ad9233b1","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Statistical+Software"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.026138770459304822,"score_gpt":0.3101626526354363,"score_spread":0.2840238821761315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1486450196","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0670562,0.000021799624,0.9321252,0.0004888421,0.00006209196,0.00009744676,0.00011622188,0.000018047085,0.000014145482],"genre_scores_gemma":[0.7557872,0.0000019668225,0.24377422,0.000334274,0.000049030717,0.0000016229156,8.777165e-7,0.000008151104,0.000042655534],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99835974,0.00017254466,0.0005003291,0.00025221586,0.00048436128,0.0002308064],"domain_scores_gemma":[0.99813396,0.00091009785,0.00016128957,0.00032882753,0.00012939042,0.0003364618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048288843,0.00012103939,0.00028761674,0.00021492278,0.000060443723,0.00013574853,0.0005501485,0.000032850465,0.00018528254],"category_scores_gemma":[0.0009009088,0.00007595955,0.000028917793,0.00028736633,0.00005609051,0.00069478224,0.00015555516,0.00013448806,0.000024405148],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011885574,0.0012824875,0.72118634,0.0000129416685,0.00016294072,0.00055377727,0.001761117,0.0017415517,0.0003026386,0.018791763,0.0013334982,0.2527521],"study_design_scores_gemma":[0.0023667037,0.0013583361,0.96097577,0.0000873117,0.00007601031,0.00007468704,0.00012467094,0.0060394243,0.000012325073,0.024107529,0.0044362964,0.000340957],"about_ca_topic_score_codex":0.000046313282,"about_ca_topic_score_gemma":0.0001749647,"teacher_disagreement_score":0.688731,"about_ca_system_score_codex":0.000052253195,"about_ca_system_score_gemma":0.00007227833,"threshold_uncertainty_score":0.30975404},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; 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","score_opus":0.243031611199427,"score_gpt":0.48486226510205405,"score_spread":0.24183065390262704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1630835083","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010298882,0.00056376104,0.98525685,0.000019112802,0.00058789254,0.00029212522,0.0029641176,0.000013199413,0.000004088828],"genre_scores_gemma":[0.28942916,0.000033781685,0.71008825,0.000022178763,0.0003228139,0.000010138088,0.000058837504,0.00002595265,0.000008871629],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996954,0.00025632003,0.0012682033,0.00026922376,0.00074341876,0.0005088022],"domain_scores_gemma":[0.97703373,0.020833269,0.0007301969,0.00071885984,0.00036254883,0.00032138155],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022000778,0.00023915141,0.0010222073,0.00034102553,0.00009585828,0.0000376576,0.000743563,0.00011814435,0.00016603296],"category_scores_gemma":[0.029741615,0.00015475624,0.00018243256,0.0008146411,0.00016254888,0.0005601262,0.00017390994,0.00036586443,0.0000010585727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005254267,0.009776946,0.32755336,0.0012606869,0.008677704,0.00017730982,0.005066594,0.0015072168,0.00074299687,0.33842567,0.009774415,0.29178283],"study_design_scores_gemma":[0.0061818794,0.002176841,0.24573879,0.00026025675,0.012156409,0.00005817561,0.0010707711,0.014906264,0.0008309653,0.71321,0.0021506,0.0012590624],"about_ca_topic_score_codex":0.000030882205,"about_ca_topic_score_gemma":0.000021284684,"teacher_disagreement_score":0.37478432,"about_ca_system_score_codex":0.000100069985,"about_ca_system_score_gemma":0.00008318007,"threshold_uncertainty_score":0.9784313},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.020547289171397226,"score_gpt":0.2583351193331463,"score_spread":0.23778783016174906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1868578820","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07083259,0.00023946767,0.9278357,0.000044857723,0.000385706,0.000159191,0.000366275,0.00011208861,0.000024121939],"genre_scores_gemma":[0.17213821,0.000036540077,0.82730025,0.00007411666,0.00032462674,0.0000069644357,0.00001989427,0.000065351735,0.000034037737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986449,0.00001184689,0.0005499383,0.00012137821,0.00029654682,0.0003754068],"domain_scores_gemma":[0.9990223,0.00024490734,0.00013283356,0.00014365166,0.00018873226,0.0002675939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021788642,0.0001999393,0.0003721394,0.000083150895,0.00015261282,0.000067794266,0.0001982501,0.00011239101,0.00016264265],"category_scores_gemma":[0.00026490606,0.00016655734,0.00011554252,0.00014461827,0.000043995842,0.00027846277,0.000027946635,0.00037812715,0.000015689879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002530539,0.00018246472,0.0013161993,0.0017419166,0.00019435248,0.00030303397,0.00095736684,0.9367894,0.0039016663,0.0013669555,0.013251162,0.03974242],"study_design_scores_gemma":[0.053492546,0.006681427,0.025276836,0.015352609,0.0023423035,0.009399853,0.0035153378,0.45886406,0.052640043,0.2808676,0.08130898,0.010258394],"about_ca_topic_score_codex":0.000010830175,"about_ca_topic_score_gemma":0.0000033285112,"teacher_disagreement_score":0.47792533,"about_ca_system_score_codex":0.00024819397,"about_ca_system_score_gemma":0.00015619161,"threshold_uncertainty_score":0.67920107},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.022667416435603303,"score_gpt":0.3016473060079822,"score_spread":0.27897988957237885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1914588449","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010837569,0.00037852922,0.9975265,0.000382064,0.00012670926,0.0002815928,0.00012341166,0.00005504869,0.0000423652],"genre_scores_gemma":[0.27791572,0.00004419649,0.7216993,0.00019336722,0.000081284656,0.000005720613,0.000015714215,0.000020462758,0.000024250401],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99755037,0.00007727622,0.00080979633,0.0004137419,0.0006443329,0.00050447544],"domain_scores_gemma":[0.99660355,0.0014152176,0.0005443805,0.00025017193,0.00057750795,0.00060917315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010473392,0.0002715984,0.0004373622,0.00029702828,0.0002441567,0.00028697704,0.0006973373,0.00015269093,0.000015823629],"category_scores_gemma":[0.00079857634,0.00020322412,0.00006540014,0.00062087784,0.00013032032,0.0014687871,0.000061986706,0.0003245507,0.000001717587],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013624066,0.0015980052,0.0024926176,0.0009351452,0.0001420148,0.00069790747,0.0028041378,0.0011282361,0.0010008246,0.06165798,0.014256533,0.9119242],"study_design_scores_gemma":[0.003926696,0.004583565,0.0038420316,0.000610692,0.00014247917,0.0010280065,0.0004338151,0.45055735,0.004622402,0.52843916,0.0006572892,0.0011565019],"about_ca_topic_score_codex":0.000004553065,"about_ca_topic_score_gemma":0.0000021869546,"teacher_disagreement_score":0.9107677,"about_ca_system_score_codex":0.00006146475,"about_ca_system_score_gemma":0.00030166862,"threshold_uncertainty_score":0.8287239},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.01069729842721405,"score_gpt":0.2481134082660615,"score_spread":0.23741610983884748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1947760575","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021999533,0.0001824587,0.9980267,0.00070481416,0.00062455935,0.00008083745,0.000009942041,0.00004115682,0.00010949628],"genre_scores_gemma":[0.099877656,0.0000034759705,0.89879256,0.0007017149,0.0005002862,0.0000027179349,0.0000010302963,0.00001572708,0.00010482828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981723,0.00022046584,0.00040784795,0.00016884768,0.00057955796,0.0004509734],"domain_scores_gemma":[0.9981726,0.00071310526,0.0002605646,0.00023500252,0.00027444167,0.00034431188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010648316,0.00017811632,0.00030002368,0.00006991405,0.00025592832,0.00014014497,0.0004841047,0.00007509237,0.00014089336],"category_scores_gemma":[0.00024036107,0.00010205493,0.000055794677,0.00034998346,0.00008105119,0.0006750577,0.00013624127,0.00048917026,0.00000982468],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022759278,0.0003944675,0.0024964241,0.000088705434,0.00023542235,0.00016447557,0.0007403185,0.0021057862,0.0003567246,0.78579915,0.020540465,0.18685047],"study_design_scores_gemma":[0.007143085,0.0044375747,0.04506832,0.0009666519,0.000759886,0.023276739,0.00009489867,0.12404591,0.00276952,0.7561005,0.032706946,0.00262999],"about_ca_topic_score_codex":0.00001885726,"about_ca_topic_score_gemma":0.000003331293,"teacher_disagreement_score":0.18422048,"about_ca_system_score_codex":0.000074184005,"about_ca_system_score_gemma":0.00017047157,"threshold_uncertainty_score":0.4161679},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"R package; Computer science; Series (stratigraphy); Software package; Time series; Algorithm; Base (topology); Software; Linear regression; Mathematics; Computational science; Machine learning","score_opus":0.025272372543365618,"score_gpt":0.2633249778170461,"score_spread":0.2380526052736805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1948959238","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022798182,0.00047347377,0.9755864,0.000111732115,0.000109818706,0.00009143221,0.0006974376,0.000014590888,0.00011692701],"genre_scores_gemma":[0.2481713,0.00004437646,0.7509409,0.00011182105,0.0003184337,0.0000022852519,0.00003376781,0.000025200474,0.0003518866],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998525,0.000007111233,0.00091397733,0.00018290436,0.00008234336,0.0002886648],"domain_scores_gemma":[0.9986158,0.00038500933,0.00048649078,0.00013327386,0.00022490528,0.00015451357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011692435,0.00012661614,0.0005974493,0.0002576861,0.00010160474,0.000041413823,0.0001442717,0.000085269174,0.00017603608],"category_scores_gemma":[0.0008950868,0.000112815855,0.00018353708,0.0003503085,0.000069684334,0.00024317382,0.000017029157,0.00018482374,0.000040317344],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005711521,0.0012863951,0.5738457,0.00052602554,0.0048033157,0.0005756772,0.0025779374,0.0073713316,0.00007646221,0.30419493,0.0072583677,0.091772325],"study_design_scores_gemma":[0.005881044,0.0054003843,0.42742848,0.0001918504,0.0014912351,0.00015039214,0.0003816368,0.06915335,0.0004523724,0.40027067,0.08741236,0.0017862162],"about_ca_topic_score_codex":0.000025684652,"about_ca_topic_score_gemma":0.000020035823,"teacher_disagreement_score":0.22537312,"about_ca_system_score_codex":0.00006439594,"about_ca_system_score_gemma":0.000036442976,"threshold_uncertainty_score":0.46004972},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.057098437824987656,"score_gpt":0.30913463259089435,"score_spread":0.2520361947659067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1951724000","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005111812,0.00021281918,0.99392706,0.00011722918,0.00047910624,0.000051017378,0.00002071698,0.000044639095,0.000035606212],"genre_scores_gemma":[0.1532665,0.0000044457097,0.84629977,0.00019347982,0.00020338039,5.3572876e-7,0.000003158393,0.000012634245,0.000016074066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779475,0.00017099112,0.0006136706,0.00022276919,0.00087018474,0.00032764566],"domain_scores_gemma":[0.997327,0.00082556385,0.0004153922,0.00034065233,0.00058145536,0.00050989375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009528171,0.00015747662,0.00041066788,0.00016318496,0.000082033526,0.0001787019,0.00086817326,0.00006818924,0.000008848665],"category_scores_gemma":[0.0028021843,0.00012539543,0.00009875629,0.000386668,0.000058495592,0.0011764723,0.00028602,0.00033951458,0.00002376487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018765073,0.0009706601,0.01076648,0.00041397774,0.0007772641,0.006939227,0.0027036087,0.20797412,0.00041200168,0.19518892,0.060494956,0.51317114],"study_design_scores_gemma":[0.0006922987,0.00026203104,0.00043069865,0.00012788607,0.000099281904,0.00032461665,0.00004015134,0.9297093,0.00017294964,0.06743106,0.0004911469,0.00021855797],"about_ca_topic_score_codex":0.000024467381,"about_ca_topic_score_gemma":0.0000016874143,"teacher_disagreement_score":0.7217352,"about_ca_system_score_codex":0.00013705021,"about_ca_system_score_gemma":0.00025972453,"threshold_uncertainty_score":0.5113477},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.00885045248584295,"score_gpt":0.251482053128426,"score_spread":0.24263160064258302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135892144","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029194798,0.000022758428,0.9701558,0.0003313259,0.00007329058,0.00012199264,0.000044523873,0.00004196188,0.000013571229],"genre_scores_gemma":[0.57729447,0.000008567083,0.4225658,0.000061267725,0.000044654495,0.0000026996318,0.000010714714,0.000008285996,0.0000035637977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984395,0.00004504651,0.00044092405,0.0003615305,0.00042146535,0.00029156302],"domain_scores_gemma":[0.99819183,0.0002699805,0.00038980469,0.00024803935,0.00053737406,0.0003629555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042941887,0.00019484713,0.00041867702,0.00017840136,0.00019784232,0.00029482768,0.00030736948,0.00010914427,0.0000143776015],"category_scores_gemma":[0.00024558962,0.00014194807,0.00006179349,0.00056407624,0.00011104916,0.0014724709,0.00005523206,0.00035512535,4.1263985e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021718594,0.0029013858,0.22505221,0.0024043352,0.0018709613,0.0032607182,0.0070211417,0.36143288,0.00638457,0.276996,0.0010980595,0.1094059],"study_design_scores_gemma":[0.0010558094,0.00074299984,0.01727372,0.000045775876,0.00030965896,0.00047005588,0.000073404546,0.9522681,0.0005898789,0.026722627,0.000028308024,0.00041966577],"about_ca_topic_score_codex":0.000010225647,"about_ca_topic_score_gemma":0.000060951512,"teacher_disagreement_score":0.5908352,"about_ca_system_score_codex":0.000031149422,"about_ca_system_score_gemma":0.0002005246,"threshold_uncertainty_score":0.5788474},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.033844006603445616,"score_gpt":0.3084657004614797,"score_spread":0.2746216938580341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512875827","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00033361156,0.00009500085,0.99828714,0.0006310376,0.0002733649,0.00015850387,0.00015309542,0.00006111642,0.000007142326],"genre_scores_gemma":[0.0039340183,0.00006315737,0.9954907,0.00010404449,0.00024053085,0.000009092897,0.0000014639207,0.000027678501,0.00012931647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99804986,0.00008658684,0.0004928761,0.00033641013,0.00053299265,0.00050129154],"domain_scores_gemma":[0.99709547,0.0014405621,0.00020828958,0.00032886225,0.0004284634,0.0004983586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062444387,0.00018241405,0.00034270814,0.00014136602,0.00015089664,0.00017845619,0.00068444415,0.0000749302,0.000023210972],"category_scores_gemma":[0.0012378943,0.00012241036,0.0000640147,0.00014959488,0.00015533851,0.0010296287,0.00031650305,0.00021424763,0.0000069052103],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054378168,0.00006938931,0.000106422325,0.00004848534,0.000026923215,0.00022277333,0.0001412652,0.00023752694,0.00040973138,0.001164303,0.00042867826,0.9970901],"study_design_scores_gemma":[0.009139725,0.0061507537,0.0089109475,0.0008803841,0.0000845441,0.0034839557,0.00017790716,0.87037826,0.0015938944,0.0860487,0.011792129,0.0013588076],"about_ca_topic_score_codex":0.0000050348476,"about_ca_topic_score_gemma":0.000005809253,"teacher_disagreement_score":0.9957313,"about_ca_system_score_codex":0.000117581396,"about_ca_system_score_gemma":0.000111130255,"threshold_uncertainty_score":0.49917495},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Period (music); Scaling; Multidimensional scaling; Computer science; History; Mathematics; Art; Machine learning","score_opus":0.012775728765790148,"score_gpt":0.2838603270710328,"score_spread":0.2710845983052427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515705452","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02084496,0.000047952304,0.9781627,0.0007423414,0.00008309336,0.00003827943,0.000028441384,0.000010822168,0.000041397278],"genre_scores_gemma":[0.44815913,0.000040715484,0.55137914,0.00003980085,0.000057481608,0.0000010505096,1.6962464e-7,0.000009344552,0.00031315957],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99896353,0.000042032094,0.0002680243,0.00013199402,0.00040703866,0.00018736297],"domain_scores_gemma":[0.99828583,0.0009527828,0.00016661303,0.00015095025,0.00024566893,0.00019815392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013670333,0.00008126407,0.00018703479,0.000096888965,0.000044686196,0.000041910105,0.00028672046,0.00002248225,0.000060625047],"category_scores_gemma":[0.00047966556,0.00004623168,0.000025172509,0.00011329687,0.00018337264,0.0006098609,0.00012654149,0.00017438355,0.000008495708],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018422745,0.00012177304,0.0061970074,0.00006225516,0.000102836755,0.0003896009,0.00043980766,0.000040332903,0.0031689191,0.012277083,0.00034010393,0.97667605],"study_design_scores_gemma":[0.014548596,0.018753208,0.768164,0.0044106706,0.00021102841,0.0062364107,0.00052430294,0.0058759297,0.011697601,0.14466743,0.022877142,0.0020337088],"about_ca_topic_score_codex":0.000008198306,"about_ca_topic_score_gemma":0.0000028914199,"teacher_disagreement_score":0.97464234,"about_ca_system_score_codex":0.000065859866,"about_ca_system_score_gemma":0.000078879064,"threshold_uncertainty_score":0.18852732},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.05011962462799613,"score_gpt":0.3917699605443133,"score_spread":0.34165033591631716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2577537660","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004052805,0.000056633555,0.9945754,0.00021128419,0.000263792,0.00016359802,0.00011811288,0.00003427111,0.00052410475],"genre_scores_gemma":[0.09834418,0.000005574368,0.9012851,0.000046032972,0.00021592075,0.0000058959426,0.0000013593354,0.000024558673,0.000071384646],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981489,0.00012099687,0.0006905821,0.00017804162,0.0005147245,0.00034675724],"domain_scores_gemma":[0.9949358,0.0032423502,0.0007584486,0.00043702844,0.00033400522,0.0002923604],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00091022754,0.00017969028,0.00051672006,0.000050410665,0.00030217745,0.00028466745,0.00052454724,0.00008582782,0.00037896665],"category_scores_gemma":[0.046169642,0.00013005489,0.00010603006,0.000048116886,0.00032067506,0.00018677438,0.000102068254,0.00041331045,0.0000135626315],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088349625,0.0002058261,0.0019252531,0.00030195154,0.000053906897,0.00077449175,0.00027933554,1.8091885e-7,0.000054660723,0.48325488,0.0023174495,0.51074374],"study_design_scores_gemma":[0.0006205324,0.00038170218,0.008532214,0.00028789171,0.00014381601,0.00020518963,0.00012061685,0.00006645682,0.00007319434,0.98790044,0.0014562923,0.0002116362],"about_ca_topic_score_codex":0.000015025561,"about_ca_topic_score_gemma":0.00000945792,"teacher_disagreement_score":0.5105321,"about_ca_system_score_codex":0.0000619938,"about_ca_system_score_gemma":0.000120694225,"threshold_uncertainty_score":0.9618649},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.011747742803746464,"score_gpt":0.27645266921670414,"score_spread":0.2647049264129577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801007199","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02466681,0.000060372517,0.97463363,0.0002487954,0.00014814637,0.000036112255,0.000115615745,0.00001584388,0.00007465028],"genre_scores_gemma":[0.7287952,0.000006322825,0.27097607,0.00012662364,0.00006320373,5.079624e-7,0.00000992399,0.0000059223275,0.000016262542],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975657,0.00014129482,0.0010449348,0.00024147869,0.00071480736,0.0002917866],"domain_scores_gemma":[0.9975651,0.00066095404,0.00065390684,0.00044926468,0.00046347032,0.00020728612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008289578,0.00014201034,0.0006928263,0.00090178987,0.000051063944,0.00008692711,0.00097533443,0.00006215694,0.00026461808],"category_scores_gemma":[0.0012784844,0.000117026815,0.00019342918,0.0022050382,0.00017924157,0.0004925092,0.00022557043,0.0002381936,0.000014764777],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018002225,0.00079535425,0.80248034,0.00006475028,0.0022318058,0.00078775093,0.001642515,0.0010231436,0.00060447655,0.020120237,0.006582755,0.16348684],"study_design_scores_gemma":[0.0013987926,0.0011103065,0.82404435,0.00017559066,0.001604397,0.00006354679,0.00013626888,0.14953645,0.00076404616,0.019045753,0.0015648319,0.0005556513],"about_ca_topic_score_codex":0.0007530392,"about_ca_topic_score_gemma":0.0010545506,"teacher_disagreement_score":0.7041284,"about_ca_system_score_codex":0.000077480916,"about_ca_system_score_gemma":0.00018908877,"threshold_uncertainty_score":0.47722152},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Zigzag; R package; Computer science; Mathematics; Statistics; Geometry","score_opus":0.027513842080723605,"score_gpt":0.2768311213842509,"score_spread":0.24931727930352732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089708264","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014246358,0.00074960117,0.9720363,0.011665697,0.0004846358,0.00027706922,0.00040421222,0.000048966725,0.00008715396],"genre_scores_gemma":[0.8991207,0.00016730068,0.09170708,0.0081462655,0.00072495354,0.0000052829987,0.00006385883,0.00004393486,0.00002066266],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9940091,0.00092858763,0.0018047834,0.00054950704,0.0020568904,0.0006511643],"domain_scores_gemma":[0.9949969,0.0022317641,0.0010730067,0.00064472406,0.00046864434,0.00058494665],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016568692,0.00041026124,0.00089685374,0.00016083675,0.0001909389,0.00080672046,0.0027561127,0.00017396794,0.00017388644],"category_scores_gemma":[0.0034130525,0.00028591935,0.00026972702,0.0016187358,0.00024594698,0.0013252844,0.00036128442,0.001465834,0.00026674435],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017388847,0.003942244,0.045219745,0.001902997,0.0012802487,0.0314415,0.08514687,0.0022141526,0.0028670484,0.04839608,0.43241414,0.3434361],"study_design_scores_gemma":[0.035933964,0.021388553,0.4335301,0.0082232235,0.005738098,0.0073396917,0.019493585,0.17525269,0.0038341733,0.11210247,0.16822463,0.008938817],"about_ca_topic_score_codex":0.000042274958,"about_ca_topic_score_gemma":0.000014067697,"teacher_disagreement_score":0.8848743,"about_ca_system_score_codex":0.0001252119,"about_ca_system_score_gemma":0.0003673326,"threshold_uncertainty_score":0.9999593},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16605877105624625,"score_gpt":0.3275761359707859,"score_spread":0.16151736491453964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094281686","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041854626,0.00031366682,0.99579376,0.0006585303,0.0007955568,0.00010151967,0.0017322026,0.00007406436,0.0001121803],"genre_scores_gemma":[0.011461131,0.0003498798,0.98732454,0.00019380085,0.00025633845,0.0000073995207,0.00030385124,0.000018540071,0.000084538646],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965489,0.00016519567,0.0009543177,0.00072212884,0.0012285303,0.00038095162],"domain_scores_gemma":[0.99460065,0.0010766559,0.000835727,0.0025659655,0.00059301796,0.00032800503],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008792033,0.00034521488,0.0008649179,0.00036797315,0.00009353971,0.000524183,0.006344751,0.00011703314,0.000055024633],"category_scores_gemma":[0.0016194785,0.0002542805,0.000101320176,0.00044996644,0.000102646234,0.0017802729,0.005508028,0.0013681332,0.000023251978],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033258655,0.0008459655,0.017350838,0.0018445005,0.0030451831,0.008691052,0.0009148361,0.006362213,0.0000062132526,0.060933977,0.11856276,0.78110987],"study_design_scores_gemma":[0.010791885,0.003448606,0.22256751,0.025344208,0.009797005,0.0033226782,0.0006478024,0.26922932,0.0004518871,0.2091658,0.23533365,0.009899644],"about_ca_topic_score_codex":0.00006468037,"about_ca_topic_score_gemma":0.000045875713,"teacher_disagreement_score":0.77121025,"about_ca_system_score_codex":0.00013894645,"about_ca_system_score_gemma":0.0009907254,"threshold_uncertainty_score":0.99999094},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03152622886809661,"score_gpt":0.24885392766239722,"score_spread":0.2173276987943006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123059542","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3042232,0.0008535141,0.6926445,0.00035242888,0.00024529346,0.00013260382,0.000106976666,0.0000065806985,0.0014349215],"genre_scores_gemma":[0.9718545,0.00013501632,0.027486559,0.00034137035,0.00010300002,0.0000023246034,0.0000039195343,0.000017171673,0.00005611104],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99830383,0.000052831925,0.0009888345,0.00019770725,0.00014029832,0.0003164723],"domain_scores_gemma":[0.99857163,0.0007089794,0.0003497631,0.00022750189,0.00006447197,0.00007764843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019065513,0.00012753547,0.0004525925,0.0001659659,0.00006465697,0.00008123033,0.00038655818,0.00008376558,0.00022378919],"category_scores_gemma":[0.00070897874,0.00010126962,0.000116894604,0.00019419081,0.00003229371,0.00032486752,0.00004916598,0.00064328953,0.00011462857],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029313,0.00035444822,0.33001953,0.00018889474,0.0000448353,0.00015522656,0.004357736,0.0034513944,0.00002410714,0.6185455,0.0019047471,0.040660467],"study_design_scores_gemma":[0.0010428872,0.00026820684,0.11191697,0.00010499975,0.000009415534,0.000042021587,0.00028259162,0.051067963,0.000003602917,0.8309583,0.0040436415,0.00025940136],"about_ca_topic_score_codex":0.00015082843,"about_ca_topic_score_gemma":0.000021973223,"teacher_disagreement_score":0.6676313,"about_ca_system_score_codex":0.00007820853,"about_ca_system_score_gemma":0.000048011803,"threshold_uncertainty_score":0.41296554},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.059603865856036185,"score_gpt":0.34019560006606203,"score_spread":0.28059173421002587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138858220","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30983505,0.00039683477,0.6892758,0.0001496793,0.00003714702,0.000059024365,0.00024094898,0.0000014644897,0.0000040409304],"genre_scores_gemma":[0.39786533,0.00009195728,0.60063356,0.0007363842,0.00020589698,0.000004440668,0.00038624884,0.000016357284,0.000059787813],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889076,0.00014205168,0.00043188204,0.00023845749,0.00009555111,0.00020129106],"domain_scores_gemma":[0.9991731,0.00015500179,0.00011189467,0.00021527239,0.00019436593,0.00015033329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075022364,0.000090799986,0.0002312529,0.0000283041,0.00005729772,0.000023938006,0.00015172148,0.00009160138,0.000015130227],"category_scores_gemma":[0.002699664,0.00008463779,0.000030910323,0.000048208665,0.000017789147,0.0000072483417,0.00013293137,0.00009363412,0.0000018044299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005069909,0.00080824713,0.040880233,0.00016062695,0.00036002637,0.00019701823,0.0003429735,0.09052911,0.66245985,0.00030477374,0.033130635,0.17031951],"study_design_scores_gemma":[0.008362959,0.0063377093,0.08741881,0.0003737702,0.0005159627,0.00065260613,0.0016888897,0.84583277,0.0065048514,0.016450724,0.02394012,0.0019208515],"about_ca_topic_score_codex":0.0000075284206,"about_ca_topic_score_gemma":0.000025257757,"teacher_disagreement_score":0.7553036,"about_ca_system_score_codex":0.000017468014,"about_ca_system_score_gemma":0.00015798362,"threshold_uncertainty_score":0.34514287},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.017611648276824543,"score_gpt":0.32921699603574767,"score_spread":0.3116053477589231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194665160","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01996706,0.0006574104,0.9753965,0.0031378886,0.00016644315,0.00007648762,0.000035951834,0.000014497574,0.0005477208],"genre_scores_gemma":[0.40319085,0.0004291772,0.5935204,0.0007842412,0.00060256873,0.0000032079406,0.000009824729,0.000017537306,0.0014421742],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981265,0.0002879419,0.00032863073,0.00013438998,0.00089743466,0.00022511726],"domain_scores_gemma":[0.9950793,0.0036129027,0.00017231164,0.000076893026,0.000702607,0.00035597855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011060495,0.00008664134,0.00021965189,0.00009270222,0.00050125766,0.00025278403,0.00015130386,0.000032430864,0.000091849724],"category_scores_gemma":[0.0024937908,0.00005308473,0.000054843807,0.0008837108,0.00021444344,0.00009202225,0.00007322339,0.00017244963,0.0000063864036],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020927997,0.0003088526,0.036242247,0.00003248741,0.00049505284,0.0010279824,0.0030202186,0.0005181176,0.000034362158,0.082867354,0.026180694,0.84906334],"study_design_scores_gemma":[0.0027810573,0.0015061017,0.3451328,0.00037645738,0.0007443082,0.00048901787,0.010125144,0.0009894442,0.0002326279,0.0720166,0.56480354,0.0008029312],"about_ca_topic_score_codex":0.00004925055,"about_ca_topic_score_gemma":0.00016583414,"teacher_disagreement_score":0.8482604,"about_ca_system_score_codex":0.000065631764,"about_ca_system_score_gemma":0.00028860173,"threshold_uncertainty_score":0.38553196},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Univariate; Statistics; Multivariate statistics; Multivariate normal distribution; Random variate; Quantile; Variance (accounting); Mathematics; Normal distribution; Random variable; Econometrics","score_opus":0.014305318521646985,"score_gpt":0.2654126965182635,"score_spread":0.25110737799661653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226403402","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017187474,0.0015986862,0.98961306,0.0036295976,0.0015099292,0.00025811876,0.0014894486,0.000025602027,0.00015683586],"genre_scores_gemma":[0.78696245,0.00014095537,0.20573922,0.0062485733,0.0005837149,0.000025010128,0.00006291286,0.000048886846,0.00018826181],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918651,0.0022769026,0.0017565698,0.0005756966,0.0026431975,0.00088256114],"domain_scores_gemma":[0.99344856,0.003637648,0.0012746253,0.0009998196,0.0003147197,0.0003246236],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004408532,0.00042603648,0.00086856924,0.000344197,0.0006651202,0.00066023576,0.0045394762,0.000102749036,0.001074944],"category_scores_gemma":[0.0023702565,0.00031228265,0.00030481198,0.0017994504,0.0002431715,0.0009854101,0.0012174385,0.002556309,0.000070871414],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023562303,0.00943911,0.025056599,0.00068271597,0.0013431156,0.058383867,0.036995187,0.023894293,0.00148126,0.17954089,0.40465504,0.2561717],"study_design_scores_gemma":[0.020299476,0.0102520585,0.31230003,0.0010155069,0.0027188077,0.013952494,0.007537322,0.09394126,0.00041418266,0.112518385,0.41983992,0.005210567],"about_ca_topic_score_codex":0.0002589341,"about_ca_topic_score_gemma":0.00003868975,"teacher_disagreement_score":0.78524375,"about_ca_system_score_codex":0.00027072607,"about_ca_system_score_gemma":0.000547595,"threshold_uncertainty_score":0.99993294},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Contiguity; Cluster analysis; Computer science; Hierarchical clustering; Theoretical computer science; Function (biology); Algorithm; Artificial intelligence","score_opus":0.01225028693388872,"score_gpt":0.2517438408299075,"score_spread":0.23949355389601876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294557430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006641724,0.000035963698,0.99219376,0.00077551237,0.00011803625,0.000054153476,0.00007355095,0.000019035317,0.0000882781],"genre_scores_gemma":[0.60345185,0.0000023201312,0.39607316,0.00042194675,0.000024672825,0.0000033876577,0.000004274366,0.000005791009,0.000012587968],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99810976,0.00020847037,0.0005004951,0.00019339712,0.00073545804,0.00025240073],"domain_scores_gemma":[0.9986761,0.0005873595,0.00022956486,0.000230153,0.00009571919,0.00018105573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079092116,0.0001025944,0.00032151886,0.00016958329,0.00010611723,0.00009456924,0.0008172485,0.000018936964,0.0001905066],"category_scores_gemma":[0.00038490217,0.00008022326,0.000048206843,0.00041330155,0.00011519981,0.00027980763,0.0004303651,0.00065222237,0.0000033382266],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011048722,0.0018850617,0.18138604,0.00016203069,0.00048203525,0.026764238,0.0026176989,0.029681128,0.0002350807,0.2091577,0.018965684,0.5275584],"study_design_scores_gemma":[0.01911152,0.010722378,0.47259003,0.0005444437,0.0003494361,0.020028222,0.0018232767,0.27085298,0.00017051293,0.14917934,0.051839184,0.0027886697],"about_ca_topic_score_codex":0.000023819706,"about_ca_topic_score_gemma":0.000034451943,"teacher_disagreement_score":0.59681016,"about_ca_system_score_codex":0.00014536861,"about_ca_system_score_gemma":0.00023176195,"threshold_uncertainty_score":0.32714096},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of 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","score_opus":0.07643798190945737,"score_gpt":0.38374974547277274,"score_spread":0.30731176356331535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402023001","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001218001,0.0011761199,0.98822355,0.00035558795,0.0037919558,0.0005026956,0.0044523645,0.00012557702,0.00015417216],"genre_scores_gemma":[0.023701299,0.0000841551,0.9733938,0.00025978909,0.0021177286,0.000021762447,0.00004954902,0.00017169691,0.00020022652],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945258,0.00050981576,0.0023504493,0.00060123875,0.0010545279,0.0009582045],"domain_scores_gemma":[0.9721697,0.024955114,0.0007307949,0.00044967473,0.0007340314,0.0009606956],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030548903,0.0006126707,0.0014228858,0.00022935616,0.00027239163,0.0008149575,0.0005907862,0.00037347653,0.0015379307],"category_scores_gemma":[0.032844443,0.0004949261,0.0004019125,0.00036454407,0.00037422645,0.0004994064,0.0001276866,0.0012995789,0.00010510072],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031276775,0.0007314539,0.00012983652,0.0045154886,0.00039184617,0.001299506,0.00081321626,0.000033351826,0.00029125734,0.48828378,0.037019674,0.46617782],"study_design_scores_gemma":[0.0011918178,0.0038068302,0.0005116715,0.0035021515,0.0014375056,0.0005261492,0.00033806247,0.083431266,0.00016557744,0.8961584,0.008169022,0.0007615647],"about_ca_topic_score_codex":0.0000167639,"about_ca_topic_score_gemma":0.000008402397,"teacher_disagreement_score":0.46541625,"about_ca_system_score_codex":0.00024865844,"about_ca_system_score_gemma":0.0004441225,"threshold_uncertainty_score":0.99975026},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Python (programming language); Computer science; Programming language","score_opus":0.021788826802131425,"score_gpt":0.2979243716317229,"score_spread":0.2761355448295915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404880964","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005427496,0.0003670434,0.9960543,0.0021095693,0.00028973175,0.0002162392,0.00035425622,0.000048590504,0.000017534512],"genre_scores_gemma":[0.23527765,0.000009224239,0.76414096,0.00036039072,0.00015988619,0.000010640187,0.0000063866855,0.000015908601,0.000018931112],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988523,0.000042549294,0.00030333863,0.0002674213,0.0003205293,0.00021385672],"domain_scores_gemma":[0.99628246,0.002963617,0.000057044657,0.0001394553,0.00025980358,0.000297645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029601023,0.0001390289,0.00024866138,0.000116216375,0.00009476318,0.0006930052,0.0002878252,0.0000365872,0.0000037044008],"category_scores_gemma":[0.0003310068,0.00011742932,0.0000652143,0.00024439907,0.000051620937,0.00048398465,0.00012771896,0.00018096167,0.0000026605883],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002362488,0.000037183894,0.000009450384,0.00012387894,0.000037601596,0.000046047557,0.00024403498,0.0014363665,0.0002956498,0.8544874,0.009046085,0.13421264],"study_design_scores_gemma":[0.00015150984,0.0002354602,0.000076133845,0.000106570056,0.000034062476,0.00014345064,0.00000779444,0.42175183,0.000044609085,0.5705971,0.0067204246,0.0001310368],"about_ca_topic_score_codex":0.000003598029,"about_ca_topic_score_gemma":7.805003e-7,"teacher_disagreement_score":0.42031547,"about_ca_system_score_codex":0.00005480586,"about_ca_system_score_gemma":0.00016420873,"threshold_uncertainty_score":0.66826653},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.027375578816853038,"score_gpt":0.37556120705876894,"score_spread":0.3481856282419159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409376239","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01758028,0.00015535156,0.98110336,0.00015341754,0.00042490967,0.00021364758,0.000070661314,0.000027832732,0.00027053506],"genre_scores_gemma":[0.24890465,0.000012510543,0.75069857,0.00021902997,0.00006414004,0.0000073366778,0.0000015174168,0.00001630536,0.00007598016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974759,0.00048792278,0.00104946,0.00019256542,0.00036287893,0.00043125154],"domain_scores_gemma":[0.9744352,0.024668371,0.00032965434,0.00016211251,0.00024442328,0.00016025563],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017385157,0.00020022066,0.00077351875,0.00018678594,0.00008683516,0.000055395245,0.00023811025,0.0001272847,0.00017123822],"category_scores_gemma":[0.061259396,0.00015312358,0.000108318156,0.00030612183,0.000076328695,0.00008421579,0.00008731305,0.0006255203,0.000008492806],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00073058624,0.00075322745,0.027335385,0.001060168,0.00015073277,0.0008926799,0.0005387215,0.000019058409,0.00013704407,0.82537025,0.0052211224,0.13779105],"study_design_scores_gemma":[0.005385196,0.0002159426,0.049058672,0.0010383639,0.00011959707,0.000018121778,0.00006648909,0.0022398,0.00013141753,0.94090456,0.0006354915,0.00018632732],"about_ca_topic_score_codex":0.000022515962,"about_ca_topic_score_gemma":0.000011403656,"teacher_disagreement_score":0.23132436,"about_ca_system_score_codex":0.00010385846,"about_ca_system_score_gemma":0.00013998064,"threshold_uncertainty_score":0.946648},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.06437155034120659,"score_gpt":0.3788384425209867,"score_spread":0.3144668921797801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125397753","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007073046,0.00009913787,0.9911184,0.0006295894,0.00030427048,0.00022672037,0.00042634853,0.000025594647,0.00009690777],"genre_scores_gemma":[0.036778092,0.0000063628718,0.9623893,0.0005098346,0.0001246908,0.0000101585765,0.00001380066,0.00002343154,0.00014430877],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979234,0.00020787651,0.00084434473,0.0002356082,0.00041448948,0.00037430692],"domain_scores_gemma":[0.99157554,0.007269652,0.00028900066,0.00019542304,0.00043560794,0.00023477386],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011788143,0.00021288612,0.00065833266,0.00017324048,0.00010233678,0.000064868625,0.00022413394,0.00016026416,0.00015545796],"category_scores_gemma":[0.016874464,0.00016264759,0.0001217745,0.00023395054,0.00011703279,0.00013285245,0.000047673406,0.0005964803,0.0000018519125],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008552249,0.00076231826,0.0042231823,0.0006080466,0.00013647859,0.0002994683,0.0002174281,0.000047937232,0.0014712445,0.75416106,0.049371455,0.18784615],"study_design_scores_gemma":[0.0017818066,0.00061456213,0.027163245,0.00067117694,0.00012197049,0.00005417529,0.000119039876,0.0015324181,0.0008330444,0.9656686,0.0011953769,0.00024456385],"about_ca_topic_score_codex":0.000010727766,"about_ca_topic_score_gemma":0.000013341602,"teacher_disagreement_score":0.21150756,"about_ca_system_score_codex":0.00006008713,"about_ca_system_score_gemma":0.00016833808,"threshold_uncertainty_score":0.9914068},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.008286097233459026,"score_gpt":0.24851377118353352,"score_spread":0.2402276739500745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7126223455","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09142857,0.00009233629,0.9077164,0.0001372288,0.00013070201,0.00028999944,0.00013237089,0.000016443124,0.000055960194],"genre_scores_gemma":[0.49611515,0.00004896178,0.5033403,0.0002822282,0.000058763067,0.000012242064,0.00002094577,0.000014887804,0.00010652982],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879676,0.00008178705,0.00036762503,0.00023764298,0.00026695637,0.0002492518],"domain_scores_gemma":[0.99859756,0.0008234616,0.00017174319,0.00011907526,0.000059255864,0.0002289298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003042139,0.00017741467,0.00038368063,0.00005169795,0.00016198405,0.00007683129,0.00010992736,0.00008580528,0.0000372348],"category_scores_gemma":[0.0003761274,0.00013294592,0.00003512615,0.00009452589,0.00019021917,0.0002293337,0.00008098054,0.00017953993,8.265658e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012567107,0.0008995355,0.118616596,0.0017362615,0.0005757784,0.0006193384,0.0015994794,0.01347812,0.001565802,0.048407007,0.04478128,0.7551537],"study_design_scores_gemma":[0.06673858,0.013288479,0.31612998,0.0014629815,0.0016772717,0.00033444125,0.00053787197,0.33026809,0.0048760967,0.2459763,0.016376747,0.00233316],"about_ca_topic_score_codex":0.00034116328,"about_ca_topic_score_gemma":0.00019528616,"teacher_disagreement_score":0.75282055,"about_ca_system_score_codex":0.000035121317,"about_ca_system_score_gemma":0.000038528175,"threshold_uncertainty_score":0.54213774},"labels":[],"label_agreement":null}]}