{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1050,"total_is_capped":false,"direct_labels_cover":18,"predictions_cover":1050,"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":"569ae49061c2","filters":{"venue":"Canadian Journal of Statistics"}},"results":[{"id":"W2077321682","doi":"10.2307/3316064","title":"A new class of multivariate skew distributions with applications to bayesian regression models","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":624,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Multivariate statistics; Skewness; Bayesian linear regression; Bayesian multivariate linear regression; Prior probability; Mathematics; Skew; Bayesian probability; Skew normal distribution; Class (philosophy); Statistics; Transformation (genetics); Regression analysis; Applied mathematics; Econometrics; Bayesian inference; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.05106965600890957,"gpt":0.3258112086798858,"spread":0.2747415526709763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002527807,0.000152841,0.000319997,0.0001755198,0.0001810204,0.00004408447,0.0002082864,0.00006506655,0.0004026116],"category_scores_gemma":[0.001151938,0.0001249681,0.00005213321,0.0004978828,0.00009634738,0.00008631354,0.000006063511,0.0001829587,0.00001313808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001700476,"about_ca_system_score_gemma":0.001961823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005074517,"about_ca_topic_score_gemma":0.002843275,"domain_scores_codex":[0.9984974,0.00007420697,0.000748987,0.0001423825,0.0002801631,0.0002568731],"domain_scores_gemma":[0.9967386,0.0004444731,0.0004847478,0.000294045,0.0008876199,0.001150495],"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":[0.000007781492,0.00003875908,0.00005964442,0.0000241386,0.00002819222,0.000008283009,0.0001526328,0.0002559484,0.00004232406,0.9634774,0.03353952,0.002365398],"study_design_scores_gemma":[0.000692073,0.0001371012,0.0009757815,0.0001522247,0.0001489803,0.00008894417,0.0001582024,0.002622377,0.000344822,0.9616539,0.03280197,0.0002236242],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001707447,0.00002298694,0.9938148,0.0006336633,0.00004117692,0.0003262696,0.003361642,0.000007812822,0.001620903],"genre_scores_gemma":[0.3323918,0.000002234955,0.6671355,0.00004765265,0.00002279972,0.00001649343,0.00006244667,0.00001604382,0.0003050197],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.332221,"threshold_uncertainty_score":0.5096052,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2002858652","doi":"10.1002/cjs.5550360302","title":"Bayesian analysis of elapsed times in continuous‐time Markov chains","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":344,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Prior probability; Frequentist inference; Bayesian probability; Posterior probability; Markov chain; Computer science; Mathematics; Bayesian inference; Econometrics; Statistics; Markov chain Monte Carlo","retraction":null,"screen_n_in":null,"score":{"opus":0.02815515843739064,"gpt":0.2897788057720888,"spread":0.2616236473346982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006578266,0.0001666123,0.000910152,0.001045478,0.00007226389,0.00002003577,0.0002644875,0.0000965951,0.001928563],"category_scores_gemma":[0.003440689,0.0001545699,0.0001331635,0.0008152457,0.000277885,0.00006163379,0.000009625639,0.0002696012,0.000005063014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001261072,"about_ca_system_score_gemma":0.0009806805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001753269,"about_ca_topic_score_gemma":0.009446041,"domain_scores_codex":[0.9980015,0.0002030117,0.001018298,0.0001332315,0.0002809426,0.0003630737],"domain_scores_gemma":[0.9965455,0.001730663,0.0005596856,0.0002133169,0.0004201994,0.0005306341],"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":[0.0001031504,0.0002101798,0.115421,0.0001788402,0.001814445,0.005021671,0.00370788,0.00007095946,0.0002353897,0.8044726,0.03158034,0.03718347],"study_design_scores_gemma":[0.002375837,0.0008900326,0.2464408,0.0004521901,0.002865439,0.0004277307,0.0006364592,0.04359719,0.0002850629,0.6997663,0.001285963,0.0009770457],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01465879,0.00007539492,0.9812043,0.0001070966,0.0001154435,0.0000988086,0.001272277,0.000004079326,0.002463749],"genre_scores_gemma":[0.3371997,0.00002329564,0.662316,0.00005372651,0.00003591991,9.797493e-7,0.000009682207,0.00001780736,0.0003428091],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3225409,"threshold_uncertainty_score":0.9989838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152401561","doi":"10.1002/cjs.10051","title":"Small area estimation of poverty indicators","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":314,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Small area estimation; Mean squared error; Statistics; Econometrics; Mathematics; Estimation; Parametric statistics; Population; Sample size determination; Poverty; Economics; Demography; Economic growth; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.0849120140259072,"gpt":0.3067622398761663,"spread":0.2218502258502591,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00147741,0.00006790508,0.0001881975,0.0008249916,0.00008213268,0.00008766646,0.000351371,0.00006624825,0.0003764008],"category_scores_gemma":[0.004177374,0.00005268656,0.00005440519,0.0004738593,0.0001199122,0.0001169831,0.000005446753,0.0002329295,0.00001160949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001865635,"about_ca_system_score_gemma":0.0009147639,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009851459,"about_ca_topic_score_gemma":0.02487232,"domain_scores_codex":[0.9984927,0.00004127905,0.0007302032,0.0000894631,0.0005000836,0.0001462539],"domain_scores_gemma":[0.9975387,0.0004864222,0.0007089291,0.0001844839,0.0006609011,0.0004205213],"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":[0.00003870234,0.00005397375,0.106025,0.00002438194,0.00007319359,0.000152796,0.003818745,0.01762376,0.000668138,0.07630616,0.04899891,0.7462162],"study_design_scores_gemma":[0.00116983,0.000496804,0.2442763,0.0001136736,0.0001649979,0.0002903789,0.002162956,0.2132778,0.0004375509,0.5037785,0.03336561,0.0004655535],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.593577,0.0000327545,0.4041492,0.0002389702,0.0008068251,0.0000343961,0.0002576525,0.000001954679,0.0009011674],"genre_scores_gemma":[0.9396779,0.000006522625,0.06009863,0.0001078545,0.00003000201,2.305716e-7,0.000006363138,0.000005711011,0.00006681099],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7457507,"threshold_uncertainty_score":0.9929212,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118036030","doi":"10.2307/3315951","title":"Exact and approximate sum representations for the Dirichlet process","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":275,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Dirichlet process; Hierarchical Dirichlet process; Dirichlet distribution; Latent Dirichlet allocation; Mathematics; Representation (politics); Context (archaeology); Bayesian probability; Metric (unit); Measure (data warehouse); Process (computing); Applied mathematics; Generalized Dirichlet distribution; Dirichlet's energy; Computer science; Statistics; Topic model; Mathematical analysis; Artificial intelligence; Data mining; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.04002486311540775,"gpt":0.2838017468158548,"spread":0.2437768837004471,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003044337,0.00006317952,0.0001028493,0.00007824734,0.0002133867,0.0001752156,0.0003277876,0.00002324055,0.00001621999],"category_scores_gemma":[0.0002567102,0.0000439187,0.00002272114,0.0001225727,0.00006918139,0.0001631905,0.000008341436,0.0001052453,6.42574e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001945213,"about_ca_system_score_gemma":0.0001691409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00014585,"about_ca_topic_score_gemma":0.0008468959,"domain_scores_codex":[0.9994149,0.00003363208,0.0001897119,0.0000903016,0.00009235777,0.0001791611],"domain_scores_gemma":[0.9988798,0.0003490124,0.0001316311,0.0001525612,0.0002157569,0.0002711703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003578427,0.00001668208,0.0006596954,0.00007004567,0.0000684078,0.0001266271,0.006040539,0.0002110776,0.00001480874,0.5565445,0.09335211,0.3428919],"study_design_scores_gemma":[0.0006879707,0.0001921384,0.002610317,0.00004915339,0.00008791906,0.0005655567,0.0002307988,0.5847171,0.00009044166,0.3839567,0.02654974,0.0002621513],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001263731,0.0008613637,0.9959174,0.002302044,0.0002223636,0.0001058904,0.00008452099,0.000002974183,0.0003770213],"genre_scores_gemma":[0.1297271,0.0001131159,0.869278,0.0004262706,0.0001105164,0.000005720392,9.115457e-7,0.000008662861,0.0003297623],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.584506,"threshold_uncertainty_score":0.1790952,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098381731","doi":"10.1002/cjs.10141","title":"Truncated regular vines in high dimensions with application to financial data","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":274,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft; Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"Vine copula; Copula (linguistics); Bivariate analysis; Multivariate statistics; Econometrics; Norwegian; Computer science; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.05266772801323331,"gpt":0.2215157529952169,"spread":0.1688480249819836,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000532212,0.00008516873,0.0002521297,0.0003262803,0.00007697813,0.00002559614,0.0002503605,0.00005527474,0.00003118556],"category_scores_gemma":[0.0005256948,0.00009012152,0.00001285275,0.0002934461,0.0000320373,0.000245028,0.0000176733,0.000150135,0.00003617882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001464386,"about_ca_system_score_gemma":0.0003429088,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01539181,"about_ca_topic_score_gemma":0.0535829,"domain_scores_codex":[0.9990249,0.00000902348,0.0005072455,0.0001346898,0.00003576409,0.0002883761],"domain_scores_gemma":[0.998964,0.00003683242,0.0002340479,0.0002876495,0.00009582051,0.0003816897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005933506,0.00006294725,0.5439586,0.00002490414,0.00002000537,0.00003540823,0.001159931,0.002336697,0.00001618506,0.4326532,0.01151588,0.008156857],"study_design_scores_gemma":[0.0007730768,0.0001851644,0.8359193,0.00007663698,0.00002226419,0.0000286901,0.00008064279,0.01358434,0.00001596527,0.0443581,0.104582,0.0003738228],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5189767,0.0008834525,0.4769949,0.0004734696,0.0003596816,0.0001397234,0.002051874,0.00000282269,0.000117328],"genre_scores_gemma":[0.9603472,0.00003122466,0.03919726,0.0001513765,0.0001616018,0.000002093472,0.00006693233,0.00001332394,0.00002901252],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4413705,"threshold_uncertainty_score":0.9911648,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137554980","doi":"10.1002/cjs.5550340403","title":"A unified view on skewed distributions arising from selections","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":201,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Skew; Selection (genetic algorithm); Multivariate statistics; Skew normal distribution; Parametric statistics; Multivariate normal distribution; Econometrics; Computer science; Distribution (mathematics); Mathematics; Statistics; Statistical physics; Artificial intelligence; Physics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.04966933493043046,"gpt":0.3036805044028415,"spread":0.254011169472411,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001470024,0.0001319531,0.0002257755,0.0001459226,0.000388739,0.0001039361,0.0001458702,0.00006807989,0.0007715622],"category_scores_gemma":[0.001356219,0.0001307945,0.00005929451,0.0003443627,0.0001237536,0.00005908852,0.000004235001,0.0002661884,0.00006816557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003174143,"about_ca_system_score_gemma":0.0007570421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002614717,"about_ca_topic_score_gemma":0.01092464,"domain_scores_codex":[0.9987642,0.00006193059,0.0006024917,0.0001158296,0.000202238,0.0002533717],"domain_scores_gemma":[0.9976727,0.0009104568,0.0003042785,0.0001691793,0.0005303525,0.0004129711],"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":[0.000002974451,0.00005202394,0.0001110752,0.000006915991,0.00002086928,0.00002636308,0.00002492419,0.00005154237,0.00004901434,0.8906765,0.1076645,0.001313252],"study_design_scores_gemma":[0.0004128315,0.00006107668,0.02225931,0.00008088495,0.0001370086,0.00003770214,0.00005764952,0.00132519,0.0001532706,0.9385331,0.03675947,0.0001824768],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003926131,0.00003723151,0.9807434,0.0008836234,0.0001891793,0.0001124717,0.01174942,0.00001886654,0.002339642],"genre_scores_gemma":[0.8806061,0.000005974834,0.1182083,0.0001271424,0.0001829694,0.000006590105,0.0006304102,0.00001898379,0.0002135582],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.87668,"threshold_uncertainty_score":0.8448065,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126022166","doi":"10.1002/cjs.5550340410","title":"Classification with reject option","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":194,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Class (philosophy); Binary number; Mathematical economics; Mathematics; Computer science; Econometrics; Actuarial science; Artificial intelligence; Economics; Arithmetic","retraction":null,"screen_n_in":null,"score":{"opus":0.4361016309661956,"gpt":0.4725475954723197,"spread":0.03644596450612408,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001307559,0.0001189128,0.0003550939,0.0001703111,0.00009220971,0.00006560223,0.000173605,0.00009014785,0.0002081689],"category_scores_gemma":[0.01506369,0.00009438465,0.00004408039,0.0001843871,0.0001969215,0.00006853988,0.000003621934,0.0002760263,0.00001252494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001808137,"about_ca_system_score_gemma":0.0008515169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006685427,"about_ca_topic_score_gemma":0.00651241,"domain_scores_codex":[0.9982729,0.0002388997,0.0008352472,0.0001154546,0.000290014,0.0002474649],"domain_scores_gemma":[0.9916123,0.006637946,0.0006269071,0.0001862509,0.0005824769,0.0003541829],"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":[0.00004466499,0.00003029036,0.003562667,0.00004132598,0.00003293604,0.0002220939,0.00003589481,0.00002434558,0.00006668834,0.9555516,0.03273604,0.007651477],"study_design_scores_gemma":[0.0005568257,0.0002869723,0.01977132,0.00009089297,0.0001253142,0.0001123981,0.00005686169,0.0002202811,0.00007876779,0.9750461,0.003520486,0.0001337803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00776162,0.0000386851,0.9879899,0.0003666513,0.000442362,0.0001347615,0.0003424951,0.000008947018,0.002914561],"genre_scores_gemma":[0.2017991,0.000005753207,0.7975348,0.0000494149,0.000361744,0.000001739293,0.000003580226,0.00002311484,0.0002208076],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1940375,"threshold_uncertainty_score":0.9932328,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1755019093","doi":"10.1002/cjs.11246","title":"A mixture of generalized hyperbolic distributions","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true},"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mixture model; Generalized inverse Gaussian distribution; Skew; Expectation–maximization algorithm; Cluster analysis; Generalized normal distribution; Mathematics; Gaussian; Applied mathematics; Mixture distribution; Multivariate statistics; Inverse distribution; Estimation theory; Inverse Gaussian distribution; Probability distribution; Distribution (mathematics); Statistics; Probability density function; Computer science; Heavy-tailed distribution; Normal distribution; Gaussian process; Maximum likelihood; Gaussian random field; Mathematical analysis; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03640317111091929,"gpt":0.2600045938295232,"spread":0.2236014227186039,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003970255,0.0000787313,0.0002124014,0.0001402542,0.00004715914,0.00005054902,0.0004672463,0.00005078143,0.00001230251],"category_scores_gemma":[0.0003311382,0.00006806271,0.00004673137,0.0002300585,0.00007223501,0.0001254801,0.0000153499,0.0001474651,0.000002365121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008070122,"about_ca_system_score_gemma":0.002230659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009420893,"about_ca_topic_score_gemma":0.001780374,"domain_scores_codex":[0.9991488,0.00009228957,0.0003167595,0.00007645611,0.000165445,0.0002002315],"domain_scores_gemma":[0.998098,0.00005354826,0.0002132937,0.0002006188,0.0006037947,0.0008307154],"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":[0.000003273919,0.00001140813,0.0002562269,0.00000860265,0.00002737577,0.0002049362,0.0007850758,0.00003462331,0.0001185234,0.8976118,0.06739569,0.03354247],"study_design_scores_gemma":[0.001489288,0.0004082291,0.002309088,0.00008340566,0.00008665471,0.0009924215,0.0000550485,0.009800901,0.00116715,0.8667476,0.1165001,0.0003600375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001342156,0.0006762969,0.9960006,0.0006358651,0.0005141838,0.00003402782,0.0002972911,0.000003077665,0.0004965115],"genre_scores_gemma":[0.1483334,0.00001461577,0.8513207,0.0001444088,0.00008858381,3.994939e-7,0.00000435427,0.000005115824,0.00008838029],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1469913,"threshold_uncertainty_score":0.3957093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147388240","doi":"10.1002/cjs.10046","title":"Estimation methods for time‐dependent AUC models with survival data","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":175,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Estimator; Covariate; Nonparametric statistics; Statistics; Receiver operating characteristic; Statistical inference; Asymptotic distribution; Mathematics; Inference; Econometrics; Gaussian; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.2761347095098711,"gpt":0.427944776573096,"spread":0.1518100670632249,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001854059,0.0001514183,0.0003899822,0.0001336401,0.000118233,0.00009789424,0.0004527578,0.00006354537,0.000127784],"category_scores_gemma":[0.005077964,0.0001210713,0.00002588133,0.0001039259,0.00007430401,0.0001934408,0.00001155145,0.0001957474,0.000003003164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001016387,"about_ca_system_score_gemma":0.001097742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001965869,"about_ca_topic_score_gemma":0.0007835352,"domain_scores_codex":[0.9985956,0.0001828446,0.000531415,0.0001640498,0.0002153652,0.0003107192],"domain_scores_gemma":[0.9957065,0.002527466,0.0003538707,0.0003730218,0.0005034615,0.0005356899],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004568805,0.0000240729,0.000007863659,0.0000397654,0.00005125763,0.00005119715,0.0001594196,0.0005774086,0.00003010316,0.6231424,0.0112455,0.3646254],"study_design_scores_gemma":[0.0003591033,0.0003924749,0.00007785619,0.00005894222,0.0001335295,0.00005951074,0.00003368967,0.2927234,0.00004174727,0.7054003,0.0005899399,0.0001295629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009924803,0.00006230497,0.9964279,0.0002919216,0.0001884937,0.0001804983,0.001880423,0.000006462355,0.0008627378],"genre_scores_gemma":[0.007737006,0.000006425689,0.9918359,0.000110055,0.00009040558,0.000001444173,0.00004539084,0.00002072386,0.0001526303],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3644958,"threshold_uncertainty_score":0.6079164,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106247158","doi":"10.1002/cjs.5550330407","title":"Cure rate models: A unified approach","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":170,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Markov chain Monte Carlo; Markov chain; Covariate; Class (philosophy); Population; Bayesian probability; Mathematics; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.591728175816646,"gpt":0.4805929130659556,"spread":0.1111352627506905,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003119936,0.0002002393,0.0006498409,0.0002212878,0.000116653,0.00008761769,0.0004354468,0.0001650677,0.0004448631],"category_scores_gemma":[0.03146145,0.0001746907,0.0001108962,0.0002170546,0.0002328709,0.0001417856,0.00001598028,0.000610286,0.00002250121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002085073,"about_ca_system_score_gemma":0.001334182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001446004,"about_ca_topic_score_gemma":0.001503648,"domain_scores_codex":[0.9972369,0.0005473512,0.001280016,0.000174968,0.0003080831,0.0004526669],"domain_scores_gemma":[0.9871792,0.01018391,0.0006143397,0.0002978341,0.0005957847,0.001128926],"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":[0.000038045,0.00005562306,0.00003702235,0.00007225697,0.0001016988,0.0001705578,0.000327796,0.0007588409,0.000008240489,0.8656822,0.09988312,0.0328646],"study_design_scores_gemma":[0.000809893,0.0001213436,0.00006739121,0.00006342542,0.0001581048,0.00009463121,0.0001287058,0.01281398,0.00002800239,0.9714946,0.01401293,0.0002070562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004390735,0.0001393906,0.9839337,0.0006723499,0.0005309316,0.0001694819,0.0007897561,0.00001153007,0.01331375],"genre_scores_gemma":[0.02553311,0.00004800376,0.9724364,0.0004229377,0.000702553,0.000002659525,0.0000028993,0.0000457805,0.0008056762],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1058123,"threshold_uncertainty_score":0.976697,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962877661","doi":"10.1002/cjs.11313","title":"Post‐selection inference for ‐penalized likelihood models","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":168,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; National Heart, Lung, and Blood Institute","keywords":"Lasso (programming language); Inference; Model selection; Selection (genetic algorithm); Logistic regression; Statistical inference; Statistics; Econometrics; Computer science; Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1315714462399989,"gpt":0.3746781688314629,"spread":0.243106722591464,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009015446,0.0001439021,0.0003888989,0.0001353586,0.0004943318,0.000300702,0.000452807,0.00008539417,0.0002932293],"category_scores_gemma":[0.02190477,0.0001248875,0.00007794405,0.00003596,0.0001461921,0.0002012021,0.00001334095,0.0002277327,0.000004974544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001091838,"about_ca_system_score_gemma":0.0016163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001935448,"about_ca_topic_score_gemma":0.01431614,"domain_scores_codex":[0.9986036,0.00007449983,0.0006275169,0.0001240232,0.0002047315,0.0003655751],"domain_scores_gemma":[0.9950643,0.001595379,0.0008106253,0.0002724286,0.001627226,0.0006300925],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000380899,0.0000165826,0.0005945899,0.00006786185,0.00004942161,0.00003640196,0.000236766,0.0000128676,0.0001116049,0.9467509,0.0103431,0.04174175],"study_design_scores_gemma":[0.0005910301,0.0003502273,0.001983525,0.00008772289,0.00008934175,0.00004265476,0.00005073125,0.009507819,0.0001404279,0.9853919,0.001607239,0.000157375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004382433,0.00003000285,0.9920011,0.000318081,0.0004868865,0.0001609222,0.001258684,0.000004045845,0.001357859],"genre_scores_gemma":[0.3175633,0.00001009382,0.6819974,0.0001007397,0.0001411137,0.000004067389,0.00000364233,0.00001899202,0.000160717],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3131808,"threshold_uncertainty_score":0.9863341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2046113245","doi":"10.1002/cjs.5550350205","title":"Nonparametric estimation of copula functions for dependence modelling","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Iowa State University","keywords":"Copula (linguistics); Estimator; Kernel smoother; Mathematics; Nonparametric statistics; Smoothing; Econometrics; Joint probability distribution; Statistics; Parametric statistics; Kernel method; Computer science; Artificial intelligence; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.1481917443454699,"gpt":0.3613164904895311,"spread":0.2131247461440612,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001143958,0.00008847268,0.0002550539,0.000350522,0.00009229029,0.00002316976,0.0001306145,0.00006316817,0.00008054524],"category_scores_gemma":[0.007203643,0.00008378903,0.00004893887,0.0002623895,0.00008536138,0.0000586881,0.000003660892,0.000154219,0.000001907649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001034056,"about_ca_system_score_gemma":0.0005918656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006162726,"about_ca_topic_score_gemma":0.001843569,"domain_scores_codex":[0.9987764,0.00002871192,0.0006846649,0.00007537246,0.0001927915,0.0002420986],"domain_scores_gemma":[0.9947494,0.003567956,0.0004369942,0.000107424,0.0007660704,0.0003721995],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004436573,0.00003665382,0.0005646533,0.0002184222,0.00005330117,0.00004769777,0.0003090166,0.01416755,0.00004124368,0.8838083,0.004853813,0.09585496],"study_design_scores_gemma":[0.0003526967,0.000321902,0.0006773074,0.0001175079,0.0001442081,0.00006127384,0.0001927501,0.2101814,0.0002904242,0.787096,0.0004302752,0.0001342286],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007611195,0.00007113052,0.9909383,0.00002058772,0.000347928,0.0001178231,0.0005735465,0.000002612631,0.0003168759],"genre_scores_gemma":[0.3667031,0.000003639181,0.6331857,0.00001357136,0.00003707637,7.52236e-7,0.000003321306,0.000009123955,0.0000437526],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3590919,"threshold_uncertainty_score":0.8623953,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124015892","doi":"10.1002/cjs.5550360110","title":"A multivariate von mises distribution with applications to bioinformatics","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":154,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Institute for Occupational Safety and Health; Engineering and Physical Sciences Research Council","keywords":"Bivariate analysis; Univariate; von Mises distribution; Multivariate statistics; Joint probability distribution; Mathematics; Extension (predicate logic); Marginal distribution; Distribution (mathematics); Maximum likelihood; Statistics; Multivariate normal distribution; von Mises yield criterion; Conditional probability distribution; Applied mathematics; Econometrics; Computer science; Random variable; Mathematical analysis; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.04651975538989457,"gpt":0.2705272366819816,"spread":0.224007481292087,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001510637,0.0001007024,0.0001884717,0.0001288437,0.0002387897,0.00003373704,0.000150408,0.00004801281,0.0001076473],"category_scores_gemma":[0.0005065377,0.00007599039,0.00002940906,0.0002938183,0.00007268661,0.00007943388,0.000006998966,0.0001472958,0.00002570271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001272115,"about_ca_system_score_gemma":0.0005832021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004413218,"about_ca_topic_score_gemma":0.001244468,"domain_scores_codex":[0.9991286,0.0000213928,0.0004083846,0.00006444826,0.0001651146,0.0002120099],"domain_scores_gemma":[0.9983857,0.0002225502,0.0002612413,0.0001423412,0.0004249177,0.0005631965],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005034641,0.0001799911,0.007375637,0.0001262977,0.0001735571,0.0006192501,0.001627619,0.0004516789,0.00006612282,0.7020602,0.2755368,0.0117325],"study_design_scores_gemma":[0.00506012,0.002968724,0.1394514,0.0005987816,0.0007716762,0.005875922,0.00244203,0.006892118,0.0006424117,0.1350721,0.6981516,0.002073091],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007831593,0.0000166408,0.9897295,0.0002522608,0.00005397978,0.0001862492,0.001430404,0.000007148148,0.0004921861],"genre_scores_gemma":[0.328275,0.000007893314,0.671281,0.0001395617,0.00007535862,0.000007861365,0.00004819128,0.00001098691,0.0001541632],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5669882,"threshold_uncertainty_score":0.3098798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042809187","doi":"10.2307/3316063","title":"The historical functional linear model","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Bivariate analysis; Mathematics; Acceleration; Covariate; Function (biology); Basis (linear algebra); Functional data analysis; Applied mathematics; Calibration; Domain (mathematical analysis); Regression analysis; Linear regression; Basis function; Linear model; Statistics; Mathematical analysis; Geometry; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.03208348061610872,"gpt":0.2109072855509716,"spread":0.1788238049348629,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002692112,0.00005142585,0.00006958435,0.00006343244,0.0003140196,0.0001158668,0.0002832236,0.00002245264,0.00001170239],"category_scores_gemma":[0.0004189392,0.0000371752,0.00002516555,0.0001189418,0.0000357418,0.0001291149,0.000004602749,0.0001643583,0.000007320657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000306501,"about_ca_system_score_gemma":0.002683238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006808143,"about_ca_topic_score_gemma":0.001147959,"domain_scores_codex":[0.9993607,0.00002256191,0.0001936007,0.0000585878,0.0001703143,0.0001942723],"domain_scores_gemma":[0.9990475,0.00009643351,0.0001156062,0.0001017135,0.0002706251,0.0003681632],"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":[0.000005398453,0.00001616532,0.001116725,0.000009185534,0.00003580933,0.0004252042,0.0004365823,0.01223205,0.0001157556,0.4361837,0.463375,0.08604845],"study_design_scores_gemma":[0.0005167376,0.0001579125,0.0007104527,0.00002883648,0.00002243128,0.0009202781,0.00005468426,0.09641036,0.00124413,0.2266452,0.673004,0.000284904],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002435064,0.0006874199,0.9962932,0.0009415864,0.000816159,0.00001139522,0.00000560879,0.000002776146,0.0009983605],"genre_scores_gemma":[0.1294224,0.0000342355,0.8675426,0.0006309598,0.0001818033,4.816548e-7,5.01389e-7,0.000008532878,0.002178561],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.209629,"threshold_uncertainty_score":0.4759948,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2080412783","doi":"10.1002/cjs.5540330306","title":"Pseudo-likelihood ratio tests for semiparametric multivariate copula model selection","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Science Foundation","keywords":"Copula (linguistics); Mathematics; Likelihood-ratio test; Multivariate statistics; Statistics; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.05184956655361838,"gpt":0.2562395954269246,"spread":0.2043900288733063,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005780095,0.0001276165,0.0003395261,0.0005426194,0.0001972275,0.00008864395,0.0001532243,0.0001069416,0.0000500912],"category_scores_gemma":[0.001180282,0.0001556159,0.00008401911,0.0002717603,0.00003045361,0.0002445285,0.000004762494,0.0002152786,0.00002858059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004108621,"about_ca_system_score_gemma":0.0006752629,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00359232,"about_ca_topic_score_gemma":0.02147074,"domain_scores_codex":[0.9985801,0.000008941362,0.000836794,0.0001666846,0.00004163053,0.0003658241],"domain_scores_gemma":[0.9985883,0.0001155361,0.0005147997,0.0001033079,0.0003120766,0.0003659653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009201522,0.000125062,0.05240949,0.000102696,0.0001379204,0.00001521294,0.001979393,0.361494,0.00009522843,0.4892122,0.0405369,0.05379991],"study_design_scores_gemma":[0.0005970065,0.0001075914,0.005093778,0.00001610415,0.00001731393,0.00001265072,0.00001726175,0.9098034,0.00002881214,0.07675322,0.007380527,0.0001723509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05739078,0.0006701843,0.9392787,0.0002756317,0.0003398845,0.0001564957,0.00164402,0.000005340986,0.0002389491],"genre_scores_gemma":[0.7585031,0.00005019099,0.2408631,0.0001366951,0.0002326012,0.00000370091,0.00001478328,0.00002092217,0.0001748618],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7011123,"threshold_uncertainty_score":0.9963849,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157533206","doi":"10.2307/3315952","title":"Linear functional regression: The case of fixed design and functional response","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":150,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Estimator; Consistency (knowledge bases); Linear regression; Mathematics; Simple linear regression; Simple (philosophy); Regression; Applied mathematics; Proper linear model; Fixed point; Regression analysis; Bayesian multivariate linear regression; Design matrix; Mathematical optimization; Computer science; Statistics; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2210371788422803,"gpt":0.3597806722117065,"spread":0.1387434933694262,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001063984,0.0001135298,0.0002306218,0.0001144573,0.0002240898,0.00001835862,0.00006675573,0.00005723474,0.0006827403],"category_scores_gemma":[0.005207673,0.00007504224,0.00003792782,0.0001017275,0.0002672114,0.00006420484,0.000009227268,0.0002591256,0.000002141661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005587511,"about_ca_system_score_gemma":0.0003054882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007085962,"about_ca_topic_score_gemma":0.0003426062,"domain_scores_codex":[0.9987363,0.000365573,0.0004563277,0.0000938911,0.0001641858,0.0001837416],"domain_scores_gemma":[0.9930329,0.005706654,0.000304887,0.0001362821,0.0004338311,0.0003854382],"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":[0.001272405,0.0001005385,0.000102476,0.0001502315,0.0002334562,0.01230519,0.002053642,0.003071785,0.0004910548,0.6330385,0.26719,0.07999075],"study_design_scores_gemma":[0.001496272,0.0007784577,0.0008708684,0.0001925162,0.0002612264,0.0156679,0.0007953815,0.06401775,0.0002106661,0.9069865,0.008423872,0.0002986168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00515782,0.0003433416,0.9932413,0.0005134837,0.0002572797,0.00009077237,0.000332491,0.00000241557,0.00006115947],"genre_scores_gemma":[0.1416101,0.00002959017,0.8575112,0.0001063426,0.0001220613,0.000001947905,0.000001291171,0.00001725306,0.0006002833],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.273948,"threshold_uncertainty_score":0.7475528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2031212901","doi":"10.1002/cjs.10047","title":"Model‐based clustering of longitudinal data","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true},"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Science Foundation Ireland","keywords":"Bayesian information criterion; Cluster analysis; Information Criteria; Model selection; Covariance; Convergence (economics); Computer science; Statistical model; Bayesian probability; Exponential family; Expectation–maximization algorithm; Mathematics; Data mining; Statistics; Maximum likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.09939433401187582,"gpt":0.2985575540033773,"spread":0.1991632199915015,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006256946,0.00008184599,0.0001826861,0.0001772934,0.00006030583,0.00007338684,0.001373337,0.00004975659,0.0000234646],"category_scores_gemma":[0.0002215398,0.00007561273,0.00002626573,0.0001218004,0.00007980759,0.0002660644,0.00005843075,0.0003026571,9.541334e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002073489,"about_ca_system_score_gemma":0.001967372,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006173212,"about_ca_topic_score_gemma":0.02157757,"domain_scores_codex":[0.9991363,0.00003126355,0.0003310634,0.0001302753,0.0001665322,0.0002045213],"domain_scores_gemma":[0.9983247,0.00009628603,0.0002392785,0.0006014713,0.0002771275,0.0004611425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001531585,0.00004298363,0.002397558,0.0001212717,0.00007321832,0.0009016725,0.0006887466,0.008561687,0.002311429,0.5728716,0.027976,0.3840385],"study_design_scores_gemma":[0.0001812348,0.00004629264,0.0006669075,0.0000257304,0.00001640465,0.000103712,0.000002143827,0.9689576,0.0001303815,0.02881806,0.0009627321,0.00008877712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005987664,0.00004995086,0.9977868,0.0002762499,0.0006123403,0.00002887947,0.0002953907,0.000002658211,0.0003489454],"genre_scores_gemma":[0.2895901,0.000002153959,0.7102405,0.00008669934,0.00005320163,1.042749e-7,0.000003212693,0.000005348157,0.00001875827],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9603959,"threshold_uncertainty_score":0.9962761,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2161686623","doi":"10.2307/3316042","title":"Robust linear discriminant analysis using S‐estimators","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":129,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Estimator; Outlier; M-estimator; Mathematics; Discriminant function analysis; Invariant estimator; Statistics; Linear discriminant analysis; Trimmed estimator; Robust statistics; Minimax estimator; Efficient estimator; Covariance matrix; Minimum-variance unbiased estimator","retraction":null,"screen_n_in":null,"score":{"opus":0.2383924046562461,"gpt":0.4046503756290366,"spread":0.1662579709727905,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000462082,0.0001654352,0.0005119725,0.0004496243,0.0001753432,0.0000437567,0.0001887352,0.00006546795,0.000263064],"category_scores_gemma":[0.002349066,0.0001417562,0.000120134,0.0004983255,0.0001399608,0.0001130535,0.00001046017,0.0002519136,0.000002677751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001910297,"about_ca_system_score_gemma":0.0006267464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001106087,"about_ca_topic_score_gemma":0.009579574,"domain_scores_codex":[0.9984725,0.00008952858,0.0006615862,0.0001366657,0.00023607,0.0004036852],"domain_scores_gemma":[0.997473,0.0006470565,0.0003882578,0.0001953413,0.0004287892,0.0008675277],"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":[0.0000735485,0.0001231934,0.01205079,0.0001730766,0.001514637,0.00797609,0.001854194,0.09450731,0.0001282342,0.8406318,0.005926208,0.03504088],"study_design_scores_gemma":[0.0005240525,0.0001878577,0.001928323,0.0001217927,0.003268634,0.0005889342,0.0005936797,0.3045098,0.00003291334,0.6845524,0.003215725,0.0004758573],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01387598,0.0000874049,0.985011,0.00005703889,0.0002403717,0.00005956919,0.000443957,0.000004948778,0.0002197308],"genre_scores_gemma":[0.09566579,0.00002423996,0.9039659,0.00005270574,0.0001110899,4.830596e-7,0.000005697538,0.00002747686,0.0001466368],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2100025,"threshold_uncertainty_score":0.5780651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096040912","doi":"10.1002/cjs.10029","title":"Robust small area estimation","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":128,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"Carleton University","funders":"","keywords":"Small area estimation; Estimator; Outlier; Statistics; Mean squared error; Mathematics; Robustness (evolution); Robust statistics; Parametric statistics; Covariance; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.1944350222287364,"gpt":0.3575785715294745,"spread":0.1631435493007382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003589226,0.000119594,0.0002644084,0.0001484169,0.0001015403,0.00004633501,0.0001467317,0.00005764592,0.0001252241],"category_scores_gemma":[0.003347903,0.0001078896,0.00004083547,0.00009720932,0.00005890535,0.00008402558,0.000002797897,0.0002249714,0.000004058667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001243131,"about_ca_system_score_gemma":0.0005154154,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009386674,"about_ca_topic_score_gemma":0.001883228,"domain_scores_codex":[0.9989679,0.00005135483,0.0004717452,0.00008919645,0.0001448321,0.0002749998],"domain_scores_gemma":[0.9980313,0.0005929938,0.0002776256,0.000129541,0.0003515645,0.0006170457],"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":[0.00001205188,0.00002255159,0.00003125745,0.0000258917,0.00001846868,0.0004155887,0.0003738615,0.003281338,0.00002536989,0.8076657,0.01034323,0.1777847],"study_design_scores_gemma":[0.000252609,0.0002187901,0.0004312331,0.00007157843,0.00005849927,0.0001325913,0.00005029918,0.01674877,0.00002677548,0.9801727,0.001706366,0.0001298088],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001387727,0.0000721421,0.9966629,0.0003023307,0.0002077602,0.00007095675,0.000235638,0.000006474694,0.001054061],"genre_scores_gemma":[0.07236881,0.00001028946,0.9271545,0.000218169,0.00007276103,4.419344e-7,0.000005351657,0.00001326287,0.0001563775],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1776549,"threshold_uncertainty_score":0.4399612,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1988889362","doi":"10.2307/3315976","title":"Penalized regression with model‐based penalties","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"McGill University; University of British Columbia","funders":"","keywords":"Smoothing spline; Smoothing; Spline (mechanical); Nonparametric regression; Mathematics; Computation; Applied mathematics; Nonparametric statistics; Parametric statistics; Regression; Function (biology); Parametric equation; Algorithm; Mathematical optimization; Statistics; Spline interpolation; Geometry; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.09599628667049624,"gpt":0.3328125964276031,"spread":0.2368163097571068,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003621975,0.0001539441,0.0003377528,0.0001359648,0.0001374726,0.00006730245,0.0001997506,0.00005591555,0.003899996],"category_scores_gemma":[0.0009503131,0.0001044412,0.00003953788,0.0001173019,0.0001820744,0.00006381983,0.000002673508,0.0002600971,0.0000079288],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000863313,"about_ca_system_score_gemma":0.001636227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004613093,"about_ca_topic_score_gemma":0.002648887,"domain_scores_codex":[0.9987589,0.0001020074,0.0004431728,0.0001025459,0.0002940481,0.0002993331],"domain_scores_gemma":[0.9978358,0.0007421075,0.000226591,0.0001701028,0.000374555,0.0006508123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005839247,0.0001049607,0.001375855,0.0003193766,0.0001377903,0.002087944,0.00146891,0.003845873,0.00006751133,0.709951,0.1124181,0.1676387],"study_design_scores_gemma":[0.001714882,0.0007052677,0.0005765474,0.000707093,0.0002019755,0.0002431249,0.0001442248,0.1358424,0.0001990619,0.8540906,0.005157119,0.0004176733],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01412361,0.00008012622,0.9810002,0.0002310256,0.00007253403,0.00008467437,0.0004173871,0.000006865736,0.003983562],"genre_scores_gemma":[0.1713806,0.0000143123,0.8274297,0.0002153914,0.00004826234,0.000001516411,0.00000361507,0.0000237721,0.0008828486],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.167221,"threshold_uncertainty_score":0.9970106,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109904733","doi":"10.2307/3315985","title":"Estimating the number of clusters","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Cancer Institute","keywords":"Estimator; Nonparametric statistics; Computation; Mathematics; Constant (computer programming); Random variate; Cluster (spacecraft); Set (abstract data type); Function (biology); Population; Data set; Algorithm; Applied mathematics; Probability density function; Statistics; Computer science; Combinatorics; Random variable","retraction":null,"screen_n_in":null,"score":{"opus":0.01626948947403848,"gpt":0.2627838807639077,"spread":0.2465143912898692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004266874,0.00005873208,0.00012464,0.00004200073,0.00008740363,0.00006050323,0.0005211158,0.00002478785,0.000198356],"category_scores_gemma":[0.00008647767,0.00004103359,0.00003403552,0.0001306333,0.00007866458,0.0001110852,0.000007258458,0.0001461414,0.000007479269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003012931,"about_ca_system_score_gemma":0.0005896848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007854907,"about_ca_topic_score_gemma":0.0006802859,"domain_scores_codex":[0.9992975,0.00007443649,0.0002796644,0.00005773209,0.000127794,0.0001628536],"domain_scores_gemma":[0.9991592,0.0001396606,0.0001551063,0.0001747864,0.0001355378,0.0002357708],"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":[0.000002296043,0.000004957738,0.0004482499,0.00001397379,0.00002465161,0.0001465761,0.001899905,0.001162404,0.000005765542,0.133256,0.01396492,0.8490703],"study_design_scores_gemma":[0.0006977001,0.0001591532,0.005304284,0.0002234156,0.00007421098,0.002103501,0.00006621882,0.4305762,0.0001116895,0.54,0.02032536,0.0003583523],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002592858,0.00006651093,0.993228,0.0005631827,0.000317164,0.00002592249,0.0000233783,0.000001687029,0.003181319],"genre_scores_gemma":[0.1156956,0.000004386557,0.8836773,0.0003350122,0.00006959558,1.858312e-7,2.518827e-7,0.000004344545,0.0002133853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8487119,"threshold_uncertainty_score":0.2171859,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061062996","doi":"10.2307/3315865","title":"Bayesian methods for generalized linear models with covariates missing at random","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Covariate; Bayesian linear regression; Mathematics; Bayesian probability; Statistics; Missing data; Generalized linear model; Conditional probability distribution; Bayesian inference; Joint probability distribution; Posterior probability; Linear model; Calibration","retraction":null,"screen_n_in":null,"score":{"opus":0.1071731295981301,"gpt":0.369493582037078,"spread":0.262320452438948,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001018887,0.0002221112,0.000629589,0.0001886148,0.0002866669,0.00009512765,0.0002232646,0.00009979172,0.0008042348],"category_scores_gemma":[0.003282674,0.0001717296,0.00008831116,0.0001523992,0.0001714198,0.0001057159,0.000009391058,0.0002262476,0.0000024581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001806529,"about_ca_system_score_gemma":0.0003844344,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003066269,"about_ca_topic_score_gemma":0.001362893,"domain_scores_codex":[0.9981744,0.0003056392,0.0007050561,0.0001704427,0.0001824399,0.0004620588],"domain_scores_gemma":[0.9939688,0.003937878,0.0004537903,0.0001994174,0.0005960347,0.0008441],"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":[0.000200401,0.00003376239,0.00008637796,0.0001992193,0.0001945343,0.0002211661,0.0009781241,0.0001863249,0.0001107573,0.8661702,0.01927364,0.1123455],"study_design_scores_gemma":[0.002125783,0.000241267,0.00001398445,0.0001112528,0.0002775675,0.0002098767,0.00003355766,0.2347843,0.000201095,0.7585059,0.003277033,0.0002183408],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00006973524,0.0003509496,0.9974965,0.0003755939,0.0002416626,0.0002359821,0.0006022701,0.000008567244,0.0006186828],"genre_scores_gemma":[0.002523884,0.00003436022,0.9967293,0.0001929163,0.0001796879,0.000006951917,0.000006575874,0.0000526546,0.0002736982],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.234598,"threshold_uncertainty_score":0.8805807,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152244463","doi":"10.2307/3316141","title":"The weighted likelihood","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":117,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National University of Singapore; University of Kent","keywords":"Estimator; Axiom; Maximum likelihood; Computer science; Mathematical economics; Mathematics; Econometrics; Applied mathematics; Statistics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.08607038839831196,"gpt":0.3346700070928898,"spread":0.2485996186945778,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004262732,0.0001048967,0.0001984063,0.00006986323,0.0003051403,0.00006722,0.0002327738,0.00004437524,0.0003594864],"category_scores_gemma":[0.002584172,0.00006961514,0.00004535901,0.0001020991,0.0001575493,0.00005871209,0.000006541572,0.0002739551,0.00001821211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008708182,"about_ca_system_score_gemma":0.0002058343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009521162,"about_ca_topic_score_gemma":0.004223521,"domain_scores_codex":[0.9988209,0.00008956297,0.0004570296,0.00007202277,0.0001916225,0.0003688607],"domain_scores_gemma":[0.9966867,0.001904719,0.000244855,0.000166641,0.0003572013,0.0006398677],"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":[0.000003905258,0.00001068063,0.00003459933,0.0000118047,0.00003402178,0.0002444595,0.0002871502,0.000002367691,0.000006179768,0.7449825,0.1005577,0.1538247],"study_design_scores_gemma":[0.0002117898,0.00009592915,0.00005595591,0.00002537916,0.00004277976,0.0001019624,0.00009321913,0.002424618,0.00001716897,0.9080171,0.08882132,0.00009277003],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003996887,0.0006949984,0.9944506,0.0006743189,0.0004889356,0.00006673462,0.000246746,0.000004581632,0.002973457],"genre_scores_gemma":[0.04330743,0.0002003675,0.9549896,0.0001675739,0.0001931847,0.000001525368,9.14685e-7,0.00002764439,0.001111832],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1630346,"threshold_uncertainty_score":0.3936124,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167589067","doi":"10.2307/3316146","title":"A pseudo‐empirical best linear unbiased prediction approach to small area estimation using survey weights","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Agricultural Economics and Policy","field":"Agricultural and Biological Sciences","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"Carleton University; Statistics Canada","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Best linear unbiased prediction; Mathematics; Mean squared error; Small area estimation; Estimator; Bias of an estimator; Statistics; Minimum-variance unbiased estimator; Stein's unbiased risk estimate; Efficient estimator; Consistent estimator; Consistency (knowledge bases); Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1621798992549481,"gpt":0.2476845372074379,"spread":0.08550463795248983,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002156708,0.0001127222,0.0001792357,0.00004249129,0.0002008797,0.00009841038,0.0001740182,0.00007940174,0.000172094],"category_scores_gemma":[0.0002006737,0.0000484099,0.00004318671,0.0002428197,0.00003570595,0.00008486161,0.000007970592,0.000140123,0.00002545999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001699059,"about_ca_system_score_gemma":0.00007295593,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0145752,"about_ca_topic_score_gemma":0.05183673,"domain_scores_codex":[0.9991208,0.00006412615,0.0003493371,0.0001198729,0.00009463166,0.0002512171],"domain_scores_gemma":[0.9987282,0.0001396339,0.0001782261,0.00003149151,0.0002264109,0.0006959985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001881921,0.0008626892,0.3446731,0.0001095632,0.0004505051,0.0003427318,0.009270744,0.08477454,0.007654916,0.006417682,0.3242182,0.2210372],"study_design_scores_gemma":[0.0004407801,0.001060162,0.4747666,0.00009465358,0.00009919702,0.0004168965,0.000364794,0.4878713,0.00006969571,0.001016667,0.03320463,0.0005946216],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9924627,0.00003759106,0.004814066,0.0003880948,0.0001814686,0.0001043391,0.001642924,0.000004154514,0.0003646564],"genre_scores_gemma":[0.9793531,0.00001894323,0.01949168,0.00033422,0.0004430486,0.000001008134,0.0001661486,0.000001706232,0.0001901757],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4030967,"threshold_uncertainty_score":0.9919868,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160535159","doi":"10.1002/cjs.5550340305","title":"Penalized contrast estimator for adaptive density deconvolution","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":98,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Independent and identically distributed random variables; Estimator; Adaptive estimator; Minimax; Minimax estimator; Mathematics; Contrast (vision); Deconvolution; Applied mathematics; Rate of convergence; Statistics; Mathematical optimization; Algorithm; Computer science; Random variable; Minimum-variance unbiased estimator; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.08179033237983849,"gpt":0.3198455344430373,"spread":0.2380552020631988,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005043829,0.0001255971,0.0003465005,0.0001123892,0.0001643263,0.00005219686,0.0001254783,0.00006694635,0.0001808598],"category_scores_gemma":[0.00430178,0.0001145775,0.0000635211,0.00006997887,0.0001458797,0.00005495379,0.00000415379,0.000145921,0.000004875737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001815872,"about_ca_system_score_gemma":0.0009956174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001873884,"about_ca_topic_score_gemma":0.01539889,"domain_scores_codex":[0.9988307,0.00007456841,0.0005439082,0.0000980633,0.0001450873,0.0003077229],"domain_scores_gemma":[0.996243,0.002028421,0.0003596579,0.0000952687,0.0008728961,0.0004007625],"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":[0.00004726803,0.00001690267,0.0007922944,0.00003523058,0.00002972247,0.00008133563,0.00004273983,0.000009862317,0.00006081534,0.9498033,0.04474565,0.004334883],"study_design_scores_gemma":[0.0008398229,0.0002481385,0.007314349,0.00006585481,0.0001313071,0.0001050067,0.00006923506,0.005522401,0.0001676255,0.9834821,0.001899834,0.0001543324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007142251,0.00007942667,0.9904211,0.00009256513,0.0003464043,0.00017193,0.001255684,0.000005138751,0.0004855321],"genre_scores_gemma":[0.2770692,0.000001664214,0.7226163,0.00004732961,0.0001452059,0.000002895389,0.000006900867,0.00001492776,0.00009568275],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2699269,"threshold_uncertainty_score":0.8592941,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1983074539","doi":"10.2307/3315967","title":"Kendall's tau for serial dependence","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":95,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation Francqui - Stichting","keywords":"Nonparametric statistics; Univariate; Mathematics; Statistics; Null hypothesis; Autocorrelation; Autoregressive model; Statistic; Monte Carlo method; Asymptotic distribution; Context (archaeology); Series (stratigraphy); Independence (probability theory); Null (SQL); Econometrics; Parametric statistics; Statistical hypothesis testing; Applied mathematics; Estimator; Multivariate statistics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.03796314985015479,"gpt":0.217070838835212,"spread":0.1791076889850572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003785377,0.0000809647,0.0002581213,0.0001398701,0.000133236,0.00006613824,0.0001804373,0.00006640354,0.001246667],"category_scores_gemma":[0.0003146559,0.0000982793,0.00006533397,0.00007488215,0.00004428977,0.0001378849,0.000002305112,0.0001292984,0.00006987387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001150017,"about_ca_system_score_gemma":0.0004228993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005040259,"about_ca_topic_score_gemma":0.01677427,"domain_scores_codex":[0.9990189,0.000005488484,0.0005717289,0.0001116671,0.00002667577,0.0002655342],"domain_scores_gemma":[0.9992132,0.00005741441,0.0002162156,0.00009937418,0.0001101841,0.000303596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001781991,0.00004561393,0.03775524,0.00009060546,0.0000965904,0.0001554599,0.002216299,0.005538615,0.000009418924,0.762678,0.0592956,0.1319403],"study_design_scores_gemma":[0.001257054,0.0003848705,0.01893356,0.00004619005,0.00002230071,0.0000575055,0.00007131299,0.02214611,0.00002223468,0.4142931,0.5423787,0.0003870661],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2840751,0.002363754,0.6978638,0.0005946478,0.002128326,0.0002486046,0.007613715,0.000007126504,0.005105029],"genre_scores_gemma":[0.9471067,0.0001659835,0.0511966,0.0001745996,0.0004147929,0.000001958423,0.00001419633,0.00001883876,0.0009063343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6630316,"threshold_uncertainty_score":0.9996663,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1981158530","doi":"10.1002/cjs.11162","title":"Q‐learning for estimating optimal dynamic treatment rules from observational data","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"McGill University","funders":"National Institute of Neurological Disorders and Stroke; Canadian Institutes of Health Research; Mailman School of Public Health, Columbia University; National Institutes of Health","keywords":"Observational study; Covariate; Randomized experiment; Propensity score matching; Causal inference; Randomized controlled trial; Computer science; Analysis of covariance; Machine learning; Inference; Econometrics; Vocabulary; Statistics; Set (abstract data type); Artificial intelligence; Medicine; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3868564774755924,"gpt":0.4250497342740967,"spread":0.03819325679850433,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003502975,0.0001390508,0.0002546372,0.00009731432,0.0001579825,0.00005092651,0.0002844944,0.00005748753,0.0001141517],"category_scores_gemma":[0.003098198,0.0001281263,0.00003226685,0.0000443607,0.00005921393,0.0003967207,0.00002011343,0.0001630766,0.000003946758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004049471,"about_ca_system_score_gemma":0.0006872784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006979037,"about_ca_topic_score_gemma":0.002712811,"domain_scores_codex":[0.9989473,0.00003799621,0.0004459952,0.00009976014,0.0001388876,0.0003300212],"domain_scores_gemma":[0.9971786,0.001513743,0.0004346197,0.0002206976,0.0002559044,0.0003964262],"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":[0.0001144117,0.0003173509,0.04155406,0.000286085,0.001025501,0.0002396723,0.008383714,0.006907481,0.0008335639,0.4556656,0.05155256,0.43312],"study_design_scores_gemma":[0.001096844,0.0008511296,0.007245143,0.0003595706,0.0005252986,0.0001286569,0.001005674,0.3361853,0.0002251953,0.6318231,0.01992542,0.0006286107],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03420352,0.000163111,0.961759,0.00008397058,0.0002641325,0.000133586,0.00333325,0.000016848,0.00004258737],"genre_scores_gemma":[0.1119761,0.00001124853,0.8870721,0.00002640157,0.0002588198,0.00000544862,0.0005491818,0.00002940848,0.00007122002],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4324914,"threshold_uncertainty_score":0.5224836,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2139539678","doi":"10.2307/3315958","title":"The estimating function bootstrap","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Studentized range; Resampling; Mathematics; Applied mathematics; Edgeworth series; Computation; Algorithm; Statistics; Standard error","retraction":null,"screen_n_in":null,"score":{"opus":0.1124458314299867,"gpt":0.337958186419868,"spread":0.2255123549898814,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006135238,0.00008655862,0.0001501835,0.00004525182,0.000327548,0.0001122474,0.000168329,0.00003793252,0.001566565],"category_scores_gemma":[0.002763491,0.00005935005,0.00003371838,0.00008911807,0.0001437598,0.00004512734,0.00000239627,0.000240796,0.00002505707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005954414,"about_ca_system_score_gemma":0.0005202339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003812943,"about_ca_topic_score_gemma":0.002508005,"domain_scores_codex":[0.9989873,0.00008749036,0.0004398273,0.00006010474,0.0001698763,0.0002554704],"domain_scores_gemma":[0.9972883,0.001809123,0.000175885,0.0001232528,0.0002278339,0.0003756114],"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":[0.00001122812,0.000005228435,0.0001625399,0.00001529128,0.00002817499,0.00006886319,0.0001449753,0.00004452726,0.000005401985,0.499285,0.03924828,0.4609805],"study_design_scores_gemma":[0.0001756643,0.0001933422,0.00225305,0.00005980263,0.00006646444,0.0001125226,0.0001067562,0.005475534,0.00001017891,0.9543276,0.03711616,0.000102939],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006402133,0.0001496689,0.9875072,0.0002742382,0.0007602925,0.00006368254,0.0001460178,0.000005632108,0.004691115],"genre_scores_gemma":[0.08074655,0.00002177268,0.9179458,0.0001437656,0.0002999245,0.000001259856,0.000001315276,0.00001766738,0.0008219632],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4608776,"threshold_uncertainty_score":0.9993461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2046745272","doi":"10.1002/cjs.10063","title":"Using temporal variability to improve spatial mapping with application to satellite data","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":85,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"","funders":"Office of Naval Research; National Aeronautics and Space Administration; National Science Foundation","keywords":"Computer science; Missing data; Satellite; Remote sensing; Grid; Filter (signal processing); Footprint; Statistical model; Kalman filter; Temporal resolution; Scalability; Component (thermodynamics); Data mining; Geography; Artificial intelligence; Geodesy","retraction":null,"screen_n_in":null,"score":{"opus":0.03034373005954589,"gpt":0.2439479229199173,"spread":0.2136041928603714,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006515354,0.000110185,0.0001503063,0.00008652663,0.000141628,0.00008316023,0.0004356896,0.00004092217,0.0002072816],"category_scores_gemma":[0.0004515618,0.0001024951,0.000009918734,0.000218156,0.0000945229,0.0001234167,0.00008101255,0.0002241424,0.00003941185],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001825879,"about_ca_system_score_gemma":0.0004022531,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05033315,"about_ca_topic_score_gemma":0.2586469,"domain_scores_codex":[0.9989001,0.00002521882,0.0003216709,0.0002360471,0.0002244469,0.0002925843],"domain_scores_gemma":[0.9982982,0.0000780081,0.0001750912,0.0004357217,0.00008133175,0.0009316014],"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":[0.00006137015,0.00004599764,0.4122644,0.00004577684,0.00005302225,0.0002447503,0.001960498,0.004953158,0.03692137,0.00333316,0.006752845,0.5333636],"study_design_scores_gemma":[0.0007463933,0.000460034,0.5710846,0.00008398372,0.0001206703,0.0002533231,0.0003994566,0.06017477,0.0004246656,0.007470007,0.3578814,0.000900685],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08248074,0.000002180202,0.9153908,0.0002185159,0.0003523817,0.0002132197,0.0008894042,0.000002942404,0.0004497987],"genre_scores_gemma":[0.5939872,4.293788e-7,0.4056477,0.0002099986,0.0001028041,0.000001176639,0.00002487177,0.00001048706,0.00001529392],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.532463,"threshold_uncertainty_score":0.9559907,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1990449216","doi":"10.2307/3315913","title":"A general class of hierarchical ordinal regression models with applications to correlated roc analysis","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Markov chain Monte Carlo; Ordinal regression; Statistics; Bayesian probability; Artificial intelligence; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01679690788041081,"gpt":0.2588644484062906,"spread":0.2420675405258798,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002569566,0.0001140653,0.0003213332,0.000472784,0.0001059628,0.00006169043,0.0005206199,0.00006187588,0.00008000921],"category_scores_gemma":[0.00001757617,0.00008851536,0.00006866243,0.001125361,0.00007230064,0.0001446912,0.00001194482,0.000243703,0.000002708741],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007604182,"about_ca_system_score_gemma":0.0009730385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007811091,"about_ca_topic_score_gemma":0.003195743,"domain_scores_codex":[0.9988272,0.00009554422,0.0004077492,0.0001711027,0.0002475883,0.000250872],"domain_scores_gemma":[0.9982519,0.00007151286,0.0001854831,0.0002985888,0.0003596694,0.0008328461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006036829,0.00004491424,0.0005612328,0.00001430811,0.0003432019,0.000283075,0.001156247,0.07401323,0.00006805145,0.496235,0.005086099,0.4221343],"study_design_scores_gemma":[0.0006647297,0.0006420831,0.002839078,0.0001083888,0.0005006688,0.000329922,0.0000184504,0.8476912,0.00008710329,0.1385653,0.008185777,0.0003673304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00352891,0.00008957901,0.9948117,0.0004537213,0.00003895396,0.00009262181,0.0001194826,0.000004482971,0.000860618],"genre_scores_gemma":[0.2116687,0.00001426707,0.787732,0.0001892947,0.00003904046,0.000002728861,0.000005096289,0.000007129253,0.0003416957],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7736779,"threshold_uncertainty_score":0.3609551,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1973353515","doi":"10.2307/3316054","title":"An adaptive randomized design with application to estimation","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Adaptive design; Estimation; Simple (philosophy); Computer science; Mathematics; Mathematical optimization; Population; Completely randomized design; Statistics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1074360952197745,"gpt":0.4002492733428469,"spread":0.2928131781230724,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004714634,0.0001175693,0.000404327,0.0005004883,0.0001288031,0.00023825,0.0004512281,0.00004121084,0.0002049518],"category_scores_gemma":[0.00300912,0.00008293283,0.00003718574,0.00059089,0.0001589978,0.0003599878,0.000004768621,0.0001164617,0.00006954601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001839879,"about_ca_system_score_gemma":0.000934999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00113039,"about_ca_topic_score_gemma":0.00190726,"domain_scores_codex":[0.9975308,0.0007427041,0.0006641314,0.0001783597,0.0006695469,0.0002144738],"domain_scores_gemma":[0.9955943,0.00177224,0.000453053,0.0002491232,0.0009646225,0.0009667091],"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":[0.03483181,0.00006707732,0.0006087323,0.000002408649,0.00008830046,0.0005600554,0.004149945,0.3955779,0.001787832,0.05298691,0.01171641,0.4976226],"study_design_scores_gemma":[0.02817354,0.003510204,0.002176408,0.00005892594,0.0001287106,0.0007048476,0.002268602,0.7939001,0.001785175,0.1636332,0.003145497,0.0005148315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002443089,0.00005066706,0.9961929,0.0001909107,0.0001196649,0.0004075426,0.0000389021,0.000003984752,0.0005523764],"genre_scores_gemma":[0.3818073,0.00000184988,0.6179112,0.000160247,0.00003388387,0.000007251043,0.000001600818,0.000009222777,0.00006743713],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4971077,"threshold_uncertainty_score":0.3602415,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2025635898","doi":"10.1002/cjs.5540330308","title":"A copula-graphic estimator for the conditional survival function under dependent censoring","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Mathematics; Copula (linguistics); Estimator; Statistics; Humanities; Econometrics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.03811143756602844,"gpt":0.292893316084848,"spread":0.2547818785188196,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00111441,0.00009916102,0.0001461878,0.0002057661,0.001050756,0.0001581044,0.000250137,0.00005265054,0.0002100193],"category_scores_gemma":[0.0002437143,0.00008661081,0.00009082583,0.00018408,0.0003221824,0.0001648164,0.000005593467,0.0001774552,0.000009709379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002693899,"about_ca_system_score_gemma":0.0008994979,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006514995,"about_ca_topic_score_gemma":0.3264522,"domain_scores_codex":[0.9986132,0.00009847098,0.0003447854,0.0001034615,0.0004721854,0.000367942],"domain_scores_gemma":[0.9984649,0.0003588211,0.0002497213,0.0001031733,0.0004598004,0.0003636235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002741436,0.00002349768,0.03142106,0.00001861418,0.0002292342,0.00003299573,0.0008416626,0.00711819,0.000002855652,0.9300192,0.01989612,0.01036918],"study_design_scores_gemma":[0.001462414,0.0002301459,0.4730835,0.0000511135,0.0005274952,0.00002409977,0.01079133,0.002030184,0.000006609859,0.09831763,0.4130356,0.0004399403],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02765941,0.001034707,0.9557315,0.004875819,0.005034497,0.0006986436,0.001666357,0.00002047,0.00327857],"genre_scores_gemma":[0.9921898,0.0001011076,0.006221766,0.0003844096,0.0008312188,0.000008485216,0.00001853623,0.00001403342,0.0002306957],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9645303,"threshold_uncertainty_score":0.9848768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2075601854","doi":"10.1002/cjs.5550350403","title":"Nonresponse weighting adjustment using estimated response probability","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":81,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Statistics; Estimator; Weighting; Inverse probability weighting; Non-response bias; Mathematics; Variance (accounting); Respondent; Probability sampling; Inverse probability; Econometrics; Bayesian probability; Posterior probability","retraction":null,"screen_n_in":null,"score":{"opus":0.2125820364407258,"gpt":0.3825614725344622,"spread":0.1699794360937364,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007946387,0.0001485319,0.0002731182,0.0004220651,0.0001894083,0.00005270599,0.0001776787,0.00009392296,0.0001129466],"category_scores_gemma":[0.01437464,0.0001414672,0.00005407901,0.0002422727,0.0001208965,0.0000989394,0.000009784739,0.0002596826,0.00000410656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000611575,"about_ca_system_score_gemma":0.001696255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00119288,"about_ca_topic_score_gemma":0.004014635,"domain_scores_codex":[0.9981179,0.00030502,0.0008191974,0.0001135325,0.0002565568,0.000387814],"domain_scores_gemma":[0.994634,0.003327453,0.0005000515,0.0002089987,0.0007469603,0.0005825747],"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":[0.0218826,0.00155982,0.1492674,0.002278668,0.001451884,0.01443998,0.03447308,0.006409411,0.03056439,0.2681455,0.1528129,0.3167144],"study_design_scores_gemma":[0.002444642,0.001606661,0.1974168,0.001852771,0.0004991298,0.003042589,0.001281149,0.02187587,0.01515724,0.7474858,0.005842481,0.001494862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4581069,0.00006832055,0.541267,0.00004792,0.0002278925,0.00009928373,0.0001075368,0.00002130473,0.00005389646],"genre_scores_gemma":[0.3881408,0.000001945223,0.6116987,0.00003979185,0.00005958012,5.146592e-7,0.000002931278,0.00002027407,0.00003539067],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4793403,"threshold_uncertainty_score":0.9939277,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102538225","doi":"10.2307/3315915","title":"Set estimation and nonparametric detection","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Mathematics; Estimator; Combinatorics; Statistics; Algorithm; Applied mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07493561435641664,"gpt":0.3645627467966709,"spread":0.2896271324402542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006944994,0.00007913374,0.0001762362,0.0004456438,0.0001782263,0.0002135412,0.0001853547,0.00004155378,0.0005277261],"category_scores_gemma":[0.007589788,0.00006767574,0.00001748113,0.0005793591,0.0001235954,0.0003180404,0.000004223577,0.0001877633,0.00006743411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001024872,"about_ca_system_score_gemma":0.0002943625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003570981,"about_ca_topic_score_gemma":0.00251248,"domain_scores_codex":[0.9986054,0.00005667215,0.0005380738,0.0001246579,0.000482726,0.0001925097],"domain_scores_gemma":[0.9974456,0.001206275,0.0002188526,0.0001076563,0.0004563767,0.0005652124],"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":[0.000009871439,0.000001663688,0.001099934,0.000003734864,0.000004521152,0.000106747,0.0002354575,0.002972466,0.00000765766,0.001038785,0.0009101424,0.993609],"study_design_scores_gemma":[0.0006979085,0.0004633697,0.05194042,0.000052871,0.00005815835,0.0008563122,0.0006747555,0.1319188,0.0002749341,0.7834688,0.02924837,0.0003452947],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08453143,0.0002050236,0.9141826,0.0000734812,0.0003263279,0.00003994829,0.0001665491,0.00000299832,0.0004716572],"genre_scores_gemma":[0.8913705,0.0000196296,0.1082302,0.0000381843,0.0000732474,4.168587e-7,0.000001104489,0.000007084672,0.0002596187],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9932637,"threshold_uncertainty_score":0.9086233,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1981569082","doi":"10.2307/3316100","title":"Penalized likelihood regression: General formulation and efficient approximation","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Applied mathematics; Mathematics; Regression; Cover (algebra); Simple (philosophy); Exponential function; Convergence (economics); Exponential family; Scale (ratio); Rate of convergence; Regression analysis; Computer science; Statistics; Mathematical optimization; Mathematical analysis; Key (lock)","retraction":null,"screen_n_in":null,"score":{"opus":0.08577174368814076,"gpt":0.3112195300394528,"spread":0.225447786351312,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003849402,0.0001069071,0.0002245453,0.0001439318,0.0001296248,0.0000676438,0.00008218003,0.00005710171,0.0006260092],"category_scores_gemma":[0.002115282,0.00008423867,0.00002703112,0.00009876464,0.00006056586,0.00005027284,0.000007056814,0.0001570621,0.000005278312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007751413,"about_ca_system_score_gemma":0.0001216272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001337369,"about_ca_topic_score_gemma":0.0003174688,"domain_scores_codex":[0.9989537,0.00008578331,0.0004494571,0.00008721081,0.0002031682,0.0002206776],"domain_scores_gemma":[0.9983513,0.000483466,0.0002912126,0.00009759452,0.0003051735,0.0004712259],"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":[0.00001417838,0.00003677667,0.0006294579,0.0001158368,0.0000316874,0.0001279588,0.001403373,0.00003422167,0.0001560802,0.848492,0.02012255,0.1288359],"study_design_scores_gemma":[0.001158486,0.0002838403,0.005636228,0.0002366989,0.000121482,0.0002978105,0.0001452053,0.1983312,0.0001605499,0.7906485,0.00270506,0.0002749319],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06502786,0.0002917343,0.9325936,0.0002251214,0.0002427321,0.0001163561,0.0001563903,0.000005420519,0.001340811],"genre_scores_gemma":[0.3334236,0.00002461522,0.6662642,0.00005975116,0.00009985767,0.000001152064,0.000002792553,0.00001176946,0.0001121715],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2683958,"threshold_uncertainty_score":0.6854362,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2048245747","doi":"10.2307/3315902","title":"On blest's measure of rank correlation","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Nonparametric statistics; Measure (data warehouse); Independence (probability theory); Mathematics; Statistics; Monte Carlo method; Rank (graph theory); Random variable; Rank correlation; Limiting; Asymptotic distribution; Correlation; Statistical physics; Distance correlation; Applied mathematics; Econometrics; Combinatorics; Physics; Computer science; Geometry; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03433118345733249,"gpt":0.1976021056044307,"spread":0.1632709221470982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005690676,0.0000673473,0.0002424094,0.0002513844,0.00006258366,0.00001781983,0.00008331711,0.00006275187,0.0002514611],"category_scores_gemma":[0.001521069,0.00007856332,0.00004953159,0.0001171739,0.00005132408,0.0000799472,0.00000116309,0.0001645548,0.00002796664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001074131,"about_ca_system_score_gemma":0.0003756281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001454111,"about_ca_topic_score_gemma":0.003278844,"domain_scores_codex":[0.9991399,0.00001551035,0.0005807324,0.00007784035,0.00003948921,0.0001465162],"domain_scores_gemma":[0.9990082,0.00008347737,0.0004421543,0.00010098,0.0001822096,0.0001829213],"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":[0.00001129634,0.00001239701,0.02403497,0.00001356239,0.00001656299,0.00001427011,0.0004088554,0.003151985,0.000002373282,0.9672859,0.003503183,0.001544632],"study_design_scores_gemma":[0.001406627,0.0004858375,0.03867123,0.0001567257,0.000031762,0.00003259821,0.0001728517,0.02045937,0.00008065529,0.901619,0.03654758,0.0003358279],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1126059,0.001938105,0.8678393,0.0000861805,0.001114193,0.00008167092,0.0007575531,0.000001903396,0.01557519],"genre_scores_gemma":[0.9899085,0.00004512133,0.009841193,0.00005125883,0.00003024262,2.503363e-7,0.00000339091,0.000009801726,0.0001103058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8773025,"threshold_uncertainty_score":0.320372,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015482051","doi":"10.2307/3316073","title":"The likelihood ratio test for homogeneity in finite mixture models","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Likelihood-ratio test; Statistics; Homogeneity (statistics); Applied mathematics; Infimum and supremum; Asymptotic distribution; Statistic; Parametric statistics; Score test; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.02403154402225908,"gpt":0.2514606562080007,"spread":0.2274291121857416,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011203,0.0001122879,0.0001930071,0.0001417095,0.0002319829,0.0002437712,0.0007382131,0.00006522823,0.000004859708],"category_scores_gemma":[0.0007926965,0.00008145822,0.00005952971,0.0002536265,0.0000552271,0.0002337751,0.00001491563,0.0002388266,0.000001454598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009595622,"about_ca_system_score_gemma":0.001456285,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004837408,"about_ca_topic_score_gemma":0.03933149,"domain_scores_codex":[0.9987801,0.00009199232,0.000457309,0.0001306384,0.0001542559,0.0003857382],"domain_scores_gemma":[0.997572,0.001116869,0.0002221989,0.0002772867,0.0003907373,0.0004209332],"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":[0.00001302378,0.00002918459,0.001243867,0.00001410249,0.00002714009,0.0005087298,0.001212318,0.001922302,0.00005324691,0.5756462,0.03457006,0.3847598],"study_design_scores_gemma":[0.0004402313,0.000163719,0.001229738,0.000030142,0.00001238516,0.0001575691,0.00002605793,0.2649454,0.00004797784,0.7106587,0.02213585,0.0001521735],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001974593,0.0006662369,0.996072,0.001960343,0.0004361955,0.000126214,0.0001782162,0.000002741626,0.0003605964],"genre_scores_gemma":[0.1386001,0.0001371453,0.8602794,0.0005812004,0.0001659537,0.000004550997,0.000002589243,0.0000116014,0.0002174162],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3846077,"threshold_uncertainty_score":0.9781982,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162490486","doi":"10.1002/cjs.5550340301","title":"Pseudo‐empirical likelihood ratio confidence intervals for complex surveys","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"Carleton University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Empirical likelihood; Mathematics; Confidence interval; Stratified sampling; CDF-based nonparametric confidence interval; Confidence distribution; Statistic; Coverage probability; Sampling (signal processing); Population; Sampling distribution; Likelihood function; Confidence region; Empirical distribution function; Maximum likelihood; Computer science; Demography","retraction":null,"screen_n_in":null,"score":{"opus":0.1281838857712769,"gpt":0.3805694175399234,"spread":0.2523855317686465,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001791926,0.0001855182,0.0004996243,0.0001730417,0.0001587915,0.000149032,0.0003056808,0.00009164303,0.0005751064],"category_scores_gemma":[0.005339959,0.000166594,0.00009511384,0.0001430238,0.0002205772,0.00008559951,0.00001042028,0.0002350404,0.0000101491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001440443,"about_ca_system_score_gemma":0.001246864,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001935348,"about_ca_topic_score_gemma":0.02093261,"domain_scores_codex":[0.9978283,0.0003666147,0.0009415622,0.0001549452,0.0002416121,0.0004669486],"domain_scores_gemma":[0.9937599,0.0040841,0.0004530379,0.0001780994,0.0009552657,0.0005696124],"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":[0.00001153857,0.00003347929,0.002500309,0.00009560635,0.00003465222,0.0001374756,0.0001160206,0.000002222147,0.0001374211,0.803075,0.1795846,0.01427174],"study_design_scores_gemma":[0.0005051537,0.0002936882,0.01734473,0.00009085579,0.00008293695,0.0001200001,0.00006760612,0.002221084,0.0001241101,0.9760135,0.002928291,0.0002080274],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006773936,0.00004417124,0.9948875,0.00047092,0.0004052564,0.0001942756,0.002538841,0.00000759659,0.0007740884],"genre_scores_gemma":[0.1457347,0.000003581922,0.853616,0.0002045122,0.0002817097,0.000004574506,0.00002303611,0.00002687575,0.0001050426],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1766563,"threshold_uncertainty_score":0.9969328,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167921963","doi":"10.1002/cjs.11197","title":"Nonparametric cure rate estimation with covariates","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":76,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true},"ca_institutions":"Cancer Care South East; Ontario Institute for Cancer Research; Cancer Care Ontario; Institute for Clinical Evaluative Sciences; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Nonparametric statistics; Cure rate; Estimator; Parametric statistics; Statistics; Sample size determination; Econometrics; Mathematics; Estimation; Medicine; Surgery; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.2739738524595979,"gpt":0.4499953593536981,"spread":0.1760215068941002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001666845,0.0001772225,0.0005441299,0.0003246529,0.0001074204,0.0001709412,0.000271756,0.0001138445,0.001627125],"category_scores_gemma":[0.07214209,0.0001176201,0.00005192979,0.0004497359,0.0002221921,0.000161586,0.000008890313,0.000412928,0.0000953679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001387645,"about_ca_system_score_gemma":0.001043793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001079571,"about_ca_topic_score_gemma":0.001024546,"domain_scores_codex":[0.9978547,0.000376795,0.000977142,0.0001389631,0.0002913278,0.0003610637],"domain_scores_gemma":[0.9746038,0.02247289,0.0007617449,0.0002318886,0.001054264,0.0008753912],"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":[0.00008909396,0.0001110384,0.005031074,0.0002954463,0.0004153645,0.0007239691,0.0004500853,0.0005300374,0.00003870456,0.6417283,0.2086191,0.1419677],"study_design_scores_gemma":[0.0007602937,0.0004215539,0.006200118,0.0001283926,0.0001774808,0.00009691917,0.00006066341,0.004397088,0.00006406646,0.9866705,0.0008321852,0.0001907266],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004596297,0.00003392947,0.9930028,0.0007052041,0.0005449732,0.0002898441,0.0003112534,0.000009813937,0.0005059302],"genre_scores_gemma":[0.06024728,0.00001247207,0.939168,0.0002033494,0.0001524732,0.000006010515,0.000002651475,0.00003476603,0.0001730236],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3449422,"threshold_uncertainty_score":0.9992855,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2092017416","doi":"10.2307/3316145","title":"Score tests for heterogeneity and overdispersion in zero‐inflated Poisson and binomial regression models","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":74,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Overdispersion; Negative binomial distribution; Count data; Mathematics; Poisson regression; Zero-inflated model; Statistics; Quasi-likelihood; Poisson distribution; Binomial test; Econometrics; Context (archaeology); Null hypothesis; Binomial (polynomial); Regression analysis; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.1040603929980713,"gpt":0.3351457339977928,"spread":0.2310853409997216,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003954861,0.000133015,0.0003314439,0.0001847283,0.00009960058,0.00006553334,0.00008039904,0.00009622452,0.00004386463],"category_scores_gemma":[0.00174968,0.0001082783,0.00002626821,0.00008110938,0.00010981,0.0001085129,0.00001192298,0.0001799286,4.834059e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008503613,"about_ca_system_score_gemma":0.0001058426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003453653,"about_ca_topic_score_gemma":0.004527687,"domain_scores_codex":[0.9989409,0.00007977358,0.0004704826,0.0001369992,0.0001254752,0.0002463204],"domain_scores_gemma":[0.9981148,0.0009146084,0.0002345968,0.00009873896,0.0001708764,0.0004663862],"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":[0.0001801686,0.00009439322,0.03900124,0.0005992501,0.00007599469,0.0008006834,0.002283374,0.00003589926,0.0007092019,0.6180879,0.03462387,0.303508],"study_design_scores_gemma":[0.001271712,0.0003555549,0.01549304,0.000426206,0.00005803439,0.0001742453,0.00005381243,0.04324409,0.0001094881,0.9383774,0.0002266235,0.0002097837],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.282329,0.0004352862,0.7160643,0.0001817923,0.0001373438,0.0001774188,0.0005778527,0.000002715066,0.0000942726],"genre_scores_gemma":[0.5304282,0.0000802361,0.4693926,0.00003881969,0.00003113989,0.000001118621,0.000002117585,0.00001258032,0.00001321499],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3202895,"threshold_uncertainty_score":0.4415459,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2076733016","doi":"10.1002/cjs.5550350410","title":"Nonlinear functional models for functional responses in reproducing kernel hilbert spaces","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Matrix Theory and Algorithms","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Reproducing kernel Hilbert space; Hilbert space; Kernel (algebra); Smoothing; Estimator; Nonlinear system; Applied mathematics; Kernel regression; Computer science; Extension (predicate logic); Kernel method; Mathematics; Representer theorem; Kernel smoother; Nonlinear regression; Nonparametric regression; Algorithm; Artificial intelligence; Regression analysis; Machine learning; Kernel embedding of distributions; Support vector machine; Statistics; Discrete mathematics; Pure mathematics; Radial basis function kernel","retraction":null,"screen_n_in":null,"score":{"opus":0.03725385583395897,"gpt":0.2508526050452271,"spread":0.2135987492112681,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001956573,0.0000958584,0.000150719,0.0004168779,0.0001413444,0.0001007661,0.0002525944,0.00004716908,0.00003592457],"category_scores_gemma":[0.0006720173,0.0000936232,0.00004634107,0.0002268201,0.00005844497,0.0003444299,0.00001367032,0.0001905677,0.000003550474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001515194,"about_ca_system_score_gemma":0.001419129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005335347,"about_ca_topic_score_gemma":0.006310643,"domain_scores_codex":[0.9988459,0.00004203919,0.0004122005,0.0001912966,0.0002033158,0.0003052228],"domain_scores_gemma":[0.9982645,0.0006530813,0.0001889754,0.0001823871,0.0003698345,0.0003412338],"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":[0.0005137454,0.00007834407,0.003096053,0.0000528999,0.00008445625,0.001015872,0.001606332,0.03681028,0.0001769801,0.8874505,0.0242371,0.04487748],"study_design_scores_gemma":[0.002731109,0.0007061586,0.03120483,0.0001877621,0.00004744154,0.001536511,0.0005678651,0.3999687,0.001020823,0.506687,0.05460605,0.0007356348],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01147984,0.0002061904,0.9861522,0.0006416238,0.001102765,0.00007060744,0.000126527,0.000005262449,0.0002149895],"genre_scores_gemma":[0.3307996,0.00001170364,0.6662937,0.000424555,0.0009154048,0.000002002458,0.00001326987,0.00001687528,0.001522929],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3807634,"threshold_uncertainty_score":0.3817843,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2074955526","doi":"10.2307/3316051","title":"Simple and accurate one‐sided inference from signed roots of likelihood ratios","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":68,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Statistic; Simple (philosophy); Inference; Mathematics; Statistics; Nuisance parameter; Scalar (mathematics); Null hypothesis; Statistical hypothesis testing; Statistical inference; Computer science; Applied mathematics; Algorithm; Estimator; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02637955835057473,"gpt":0.270371991212576,"spread":0.2439924328620013,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00007316918,0.0001191815,0.0003213534,0.0001772804,0.00007478138,0.00004233394,0.000176732,0.0000787993,0.002783637],"category_scores_gemma":[0.001069564,0.000120409,0.00003574748,0.0002409278,0.00009684651,0.000103415,0.00001000777,0.0001921057,0.000003576399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008603273,"about_ca_system_score_gemma":0.0008007668,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.008045722,"about_ca_topic_score_gemma":0.0260548,"domain_scores_codex":[0.9990225,0.00001424847,0.0004539739,0.0001042777,0.0001651612,0.0002398521],"domain_scores_gemma":[0.9982229,0.0004308181,0.0004080603,0.0001345848,0.0003081639,0.0004954668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002732516,0.000247914,0.6300902,0.0003069371,0.001948298,0.001965417,0.002241415,0.0004510866,0.3069716,0.004816134,0.02540509,0.02528255],"study_design_scores_gemma":[0.007988542,0.001106207,0.2632198,0.0007510724,0.003750957,0.0003468147,0.007216492,0.0041405,0.5128946,0.1856273,0.01074815,0.002209503],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.939452,0.001149881,0.0562249,0.0001537685,0.00006201259,0.0000325385,0.001262903,0.000005541934,0.001656445],"genre_scores_gemma":[0.9945302,0.0001741391,0.004962791,0.00007129472,0.0001025549,4.940766e-7,0.00004281735,0.00001214187,0.0001035773],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3668705,"threshold_uncertainty_score":0.9985598,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130364138","doi":"10.2307/3315917","title":"On the estimation of the marginal density of a moving average process","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":68,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Xunta de Galicia","keywords":"Estimator; Mathematics; Mean squared error; Kernel density estimation; Statistics; Applied mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05029668268010393,"gpt":0.3037736532078126,"spread":0.2534769705277087,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005299,0.00007878387,0.0002020371,0.0000491327,0.00009875279,0.00001691476,0.0002377856,0.00003372599,0.0009010869],"category_scores_gemma":[0.00503105,0.00004547571,0.00004085226,0.000132646,0.0001867562,0.00002872215,0.000004653882,0.0002165979,0.000002492601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004823431,"about_ca_system_score_gemma":0.0006046926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004092693,"about_ca_topic_score_gemma":0.0008200723,"domain_scores_codex":[0.9990035,0.0001307178,0.0004227963,0.00005216425,0.0002533527,0.0001374625],"domain_scores_gemma":[0.9973149,0.001724344,0.0003644789,0.0001590815,0.000308889,0.0001282684],"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":[0.00003570085,0.00003154854,0.001060641,0.0001768186,0.00003885954,0.00003222175,0.001324931,0.001461692,0.00002727925,0.9510816,0.003177422,0.04155123],"study_design_scores_gemma":[0.0001719608,0.0001467491,0.01487015,0.0003365639,0.00006412007,0.00004805924,0.0001150192,0.01326293,0.0007387651,0.9701228,0.00005064702,0.00007225465],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.666656,0.00001592562,0.3304287,0.0003056392,0.0001240097,0.0001302102,0.0003655652,0.00000146561,0.001972433],"genre_scores_gemma":[0.8891507,0.000003338703,0.1106617,0.00008405718,0.00001847662,5.938023e-7,4.209671e-7,0.00000741193,0.0000732522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2224947,"threshold_uncertainty_score":0.986627,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2049916971","doi":"10.1002/cjs.5550340106","title":"Empirical likelihood tests for two-sample problems via nonparametric density estimation","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Ministerio de Economía y Competitividad","keywords":"Mathematics; Empirical likelihood; Estimator; Statistics; Test statistic; Nonparametric statistics; Kernel density estimation; Statistical hypothesis testing","retraction":null,"screen_n_in":null,"score":{"opus":0.02904746549342792,"gpt":0.2929953656221195,"spread":0.2639479001286916,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006331964,0.0001257023,0.0002342215,0.0003487158,0.0001660525,0.0001874787,0.000389922,0.00006371919,0.000006229123],"category_scores_gemma":[0.0006593418,0.0001171659,0.00006238738,0.0004305823,0.00004820282,0.0002220842,0.00001396942,0.0001766043,0.00000341845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001665002,"about_ca_system_score_gemma":0.001119507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003610794,"about_ca_topic_score_gemma":0.01368057,"domain_scores_codex":[0.9987563,0.00006897844,0.0004418823,0.0001634812,0.0001938884,0.0003754802],"domain_scores_gemma":[0.997821,0.0006731711,0.00028305,0.0001991772,0.0005451336,0.0004784302],"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":[0.00001125913,0.0001013327,0.008404493,0.0001039254,0.0000520092,0.0002552958,0.0005506405,0.006145352,0.0001883887,0.1897874,0.0648245,0.7295754],"study_design_scores_gemma":[0.0004672805,0.0002083865,0.006022038,0.00002506055,0.00003099743,0.000191463,0.000001559402,0.3184083,0.0001519668,0.6723367,0.001986693,0.0001695418],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001267728,0.0001503069,0.9973222,0.0004694648,0.0004243982,0.000163303,0.000119201,0.000009201909,0.00007421851],"genre_scores_gemma":[0.1942338,0.000001440104,0.8053817,0.0002098201,0.000132473,0.000002373233,0.00000886309,0.000009728826,0.00001984688],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7294058,"threshold_uncertainty_score":0.763408,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2062452883","doi":"10.2307/3316009","title":"Empirical likelihood for linear regression models under imputation for missing responses","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":67,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Empirical likelihood; Mathematics; Statistics; Imputation (statistics); Confidence interval; Likelihood-ratio test; Linear regression; Missing data; Regression analysis; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.2585600432776193,"gpt":0.4361599736847908,"spread":0.1775999304071715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0008455259,0.0001418068,0.000316,0.0001879665,0.0002186031,0.00006871037,0.0001381497,0.0001049276,0.00004970678],"category_scores_gemma":[0.008435648,0.000116549,0.00008031397,0.0001073393,0.00007823467,0.00009654909,0.000005606554,0.0001582098,9.828166e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001512374,"about_ca_system_score_gemma":0.001405074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009643864,"about_ca_topic_score_gemma":0.00069534,"domain_scores_codex":[0.9986185,0.0001084622,0.0006038253,0.0001295399,0.0001724472,0.0003672077],"domain_scores_gemma":[0.9929287,0.005139811,0.0003442238,0.0001162226,0.0008843804,0.0005866853],"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":[0.000979365,0.0001089785,0.0007547056,0.000405432,0.0001443827,0.0002090304,0.001778682,0.0007660855,0.0002858152,0.6115716,0.1093172,0.2736787],"study_design_scores_gemma":[0.0006600607,0.0004155614,0.0003214566,0.0001734528,0.00009517974,0.00009070648,0.0001929465,0.07045411,0.00008057812,0.9238572,0.003516638,0.0001421354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005837768,0.0001141985,0.9914435,0.001102524,0.0003129828,0.0002297496,0.0008536218,0.000006331464,0.00009932232],"genre_scores_gemma":[0.04884772,0.00001915845,0.9503443,0.0003313499,0.0002488235,0.00000660549,0.00001241861,0.0000341482,0.0001554512],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3122856,"threshold_uncertainty_score":0.9999167,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2032156573","doi":"10.2307/3316098","title":"Testing circular symmetry","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Monte Carlo method; Test statistic; Mathematics; Statistic; Symmetry (geometry); Sample (material); Statistics; Statistical hypothesis testing; Sampling distribution; Applied mathematics; Geometry; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.04607588704548786,"gpt":0.233857456048734,"spread":0.1877815690032462,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003346891,0.00008070256,0.0001474501,0.0002000241,0.0001098543,0.0001372766,0.0004973885,0.00004119638,0.00005919178],"category_scores_gemma":[0.0005662205,0.00007632113,0.00003270149,0.0003060227,0.0000415525,0.0001749256,0.00001189496,0.0002058281,0.00001602758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007206012,"about_ca_system_score_gemma":0.0003329298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000329438,"about_ca_topic_score_gemma":0.0002213461,"domain_scores_codex":[0.9991648,0.00006056069,0.000267464,0.00009589986,0.0001505246,0.0002607535],"domain_scores_gemma":[0.9985908,0.0001692806,0.0001608621,0.0001903007,0.0002817354,0.0006070258],"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":[2.294017e-7,0.000008711614,0.001129361,0.00001814617,0.0000234953,0.001770283,0.0005182492,0.00002033729,0.00009963366,0.3544445,0.03316019,0.6088068],"study_design_scores_gemma":[0.0009894408,0.0005461397,0.01274854,0.0002591131,0.00009133288,0.005309376,0.00005133083,0.2035073,0.0002785284,0.6964086,0.07893298,0.0008772891],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003015301,0.0008421011,0.9939116,0.0003398908,0.0004976609,0.00002416636,0.00001997465,0.000005815935,0.004057261],"genre_scores_gemma":[0.1592055,0.000007928851,0.8401551,0.0004116859,0.0001110958,1.787978e-7,1.959493e-7,0.00000689824,0.0001014641],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6079296,"threshold_uncertainty_score":0.3112285,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1968782267","doi":"10.1002/cjs.5550360401","title":"Optimal scaling of Metropolis algorithms: Heading toward general target distributions","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":63,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Toronto; Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Heading (navigation); Simple (philosophy); Scaling; Independent and identically distributed random variables; Gaussian; Algorithm; Distribution (mathematics); Asymptotically optimal algorithm; Computer science; Mathematics; Mathematical optimization; Statistical physics; Applied mathematics; Random variable; Statistics; Mathematical analysis; Geometry; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.09391328041418588,"gpt":0.3312765790653092,"spread":0.2373632986511233,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006038198,0.0001487811,0.0004590616,0.000271686,0.000192498,0.0000222254,0.0002127039,0.00007878867,0.00009901622],"category_scores_gemma":[0.001676544,0.000141674,0.0001342456,0.0002083342,0.0002196784,0.00008128808,0.00001465643,0.0002696603,9.996607e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002862773,"about_ca_system_score_gemma":0.001186232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002112891,"about_ca_topic_score_gemma":0.0008939753,"domain_scores_codex":[0.9984569,0.0001119887,0.0007082264,0.0001015557,0.0002495016,0.0003718499],"domain_scores_gemma":[0.9977834,0.0003274938,0.0004195821,0.0001554375,0.0006244195,0.0006897292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009144593,0.0002468949,0.01254412,0.0006869725,0.001067754,0.005506177,0.01287535,0.002974241,0.001363246,0.6157585,0.3285169,0.01836832],"study_design_scores_gemma":[0.01709078,0.005611602,0.01319519,0.003036597,0.004004675,0.02279791,0.02481069,0.1971476,0.06628799,0.2776954,0.3607969,0.007524664],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08505029,0.0003932927,0.9112486,0.0001256659,0.0004733017,0.00006776381,0.002193364,0.000004745452,0.0004429825],"genre_scores_gemma":[0.2180873,0.00005737363,0.7813322,0.00002980999,0.0002619315,9.075584e-7,0.00002028874,0.00002151926,0.0001886929],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3380632,"threshold_uncertainty_score":0.5777298,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2084634105","doi":"10.2307/3315862","title":"Small area estimation using unmatched sampling and linking models","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"Carleton University; Statistics Canada","funders":"","keywords":"Markov chain Monte Carlo; Small area estimation; Sampling (signal processing); Bayes' theorem; Computer science; Estimation; Importance sampling; Hierarchical database model; Statistics; Monte Carlo method; Bayesian probability; Econometrics; Data mining; Artificial intelligence; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.4358124722805446,"gpt":0.3441380724064532,"spread":0.09167439987409137,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001647035,0.00009684084,0.0002329388,0.00053142,0.0002374314,0.0004193759,0.0002058044,0.00006064886,0.0001071914],"category_scores_gemma":[0.00134275,0.00008269634,0.00004265506,0.0003120298,0.00007424205,0.0002826406,0.000008299079,0.0001686341,0.000005338237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005853731,"about_ca_system_score_gemma":0.0001896421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008812208,"about_ca_topic_score_gemma":0.004968002,"domain_scores_codex":[0.9982828,0.00007588956,0.0008273881,0.0001432709,0.0004621285,0.0002085235],"domain_scores_gemma":[0.9975631,0.0006157496,0.0005466679,0.0001487224,0.0007188861,0.0004068655],"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":[0.000005796604,0.000009409376,0.006040524,0.00001357878,0.00002637337,0.00008520993,0.004939804,0.7766533,0.00007185742,0.009243202,0.0004504507,0.2024605],"study_design_scores_gemma":[0.0001347497,0.00003237731,0.0005773489,0.00005824991,0.00002530619,0.0001020272,0.0005184813,0.8300061,0.000001895234,0.1683069,0.0001609861,0.00007560688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2894633,0.0002743689,0.7097445,0.00009721206,0.0001914889,0.00002819605,0.00005257766,0.000002327097,0.0001460581],"genre_scores_gemma":[0.7197967,0.00003638223,0.2800213,0.00007600009,0.00003250518,1.456172e-7,0.000002543516,0.000007620594,0.00002677477],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4303333,"threshold_uncertainty_score":0.4044051,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106053216","doi":"10.2307/3315932","title":"Interval censoring: Model characterizations for the validity of the simplified likelihood","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Censoring (clinical trials); Mathematics; Statistics; Maximum likelihood; Likelihood function; Estimator; Nonparametric statistics; Equivalence (formal languages); Applied mathematics; Econometrics; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05963329131130263,"gpt":0.2945347630924245,"spread":0.2349014717811219,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007469585,0.00007694461,0.0001420775,0.00008689956,0.0006535075,0.00007579911,0.0005200502,0.0000403223,0.00001922917],"category_scores_gemma":[0.0005380929,0.00005385941,0.000118415,0.0002122145,0.000364354,0.00009422187,0.00001390166,0.0001487388,8.99718e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001662945,"about_ca_system_score_gemma":0.00152933,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005933848,"about_ca_topic_score_gemma":0.1252602,"domain_scores_codex":[0.9989368,0.00007282966,0.000360182,0.0000706811,0.0002802868,0.0002792733],"domain_scores_gemma":[0.9986199,0.0001539394,0.0003610405,0.0001686809,0.0004874127,0.0002090568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0000181774,0.00007991817,0.03456785,0.00007164509,0.0002275738,0.00001573762,0.02011085,0.01791127,0.00005662574,0.9115139,0.008381128,0.007045303],"study_design_scores_gemma":[0.001823719,0.000261271,0.5190978,0.0002549567,0.0007466289,0.00001107828,0.009304108,0.005362295,0.000226106,0.3680827,0.09429818,0.0005311599],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.187312,0.0001033206,0.7960927,0.0077535,0.003034996,0.0009065917,0.002821053,0.000009404643,0.001966516],"genre_scores_gemma":[0.9948649,0.00008144551,0.004469464,0.0002846638,0.0001921993,0.000004332222,0.000003445803,0.00001025945,0.00008928883],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8075529,"threshold_uncertainty_score":0.8970243,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2011917229","doi":"10.2307/3315941","title":"Deconvolution of supersmooth densities with smooth noise","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Independent and identically distributed random variables; Estimator; Mathematics; Pointwise; Deconvolution; Kernel density estimation; Random variable; Minimax; Probability density function; Rate of convergence; Applied mathematics; Context (archaeology); Statistics; Mathematical optimization; Mathematical analysis; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05511153463926723,"gpt":0.2821448764553929,"spread":0.2270333418161257,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002957528,0.000113525,0.0003094098,0.0001685445,0.0000671532,0.00002553572,0.0001323506,0.00005008736,0.000161676],"category_scores_gemma":[0.001601238,0.00009078795,0.00003376825,0.0001197113,0.0002822717,0.00006530689,0.00000455903,0.0001726004,0.000002766504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001662031,"about_ca_system_score_gemma":0.001777653,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002746122,"about_ca_topic_score_gemma":0.01496064,"domain_scores_codex":[0.9989883,0.00004796459,0.0004472676,0.00007456939,0.0002071241,0.0002347758],"domain_scores_gemma":[0.998055,0.0005065747,0.0002875846,0.0001269716,0.0006118584,0.0004120544],"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":[0.00003573894,0.00002586786,0.002722943,0.0001116855,0.00005639523,0.0002907142,0.001099395,0.000109894,0.0001122862,0.9887323,0.001548228,0.005154542],"study_design_scores_gemma":[0.001110669,0.0008871293,0.01615048,0.0004127842,0.0001760641,0.0002694751,0.001052724,0.0001391941,0.0007850854,0.9781857,0.0006006869,0.0002299881],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1522635,0.00009095827,0.8462785,0.000114057,0.0001596842,0.00006305394,0.0004022977,0.000003148423,0.000624734],"genre_scores_gemma":[0.4966654,0.000008582882,0.5032167,0.00003991772,0.0000333596,4.034476e-7,0.000001406944,0.00001158431,0.00002260376],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3444019,"threshold_uncertainty_score":0.8348389,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}