{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":191,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":191,"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":"f050aeaf760a","filters":{"topic":"Survey Sampling and Estimation Techniques"}},"results":[{"id":"W2019293164","doi":"10.1198/016214501750333054","title":"A Model-Calibration Approach to Using Complete Auxiliary Information From Survey Data","year":2001,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":336,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Estimator; Calibration; Mathematics; Population; Applied mathematics; Statistics; Function (biology); Linear model; Linear regression","retraction":null,"screen_n_in":null,"score":{"opus":0.3089299026417691,"gpt":0.4014814388274089,"spread":0.09255153618563983,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002824621,0.0001130429,0.0003449031,0.00009679256,0.0001239815,0.0001209957,0.0004660152,0.00004537626,0.000008002173],"category_scores_gemma":[0.01071689,0.00008451095,0.00004859948,0.0004255622,0.00003657742,0.0006706823,0.000133723,0.000226319,0.000004276264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003603123,"about_ca_system_score_gemma":0.0001206336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009407515,"about_ca_topic_score_gemma":0.00004882612,"domain_scores_codex":[0.9976723,0.0006195566,0.0007398689,0.0001119735,0.0006878681,0.0001684382],"domain_scores_gemma":[0.9953274,0.002175279,0.001649378,0.0003621212,0.0003976223,0.00008815846],"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":[0.002103656,0.001673304,0.4865821,0.0001144482,0.001259837,0.000005246992,0.005232117,0.08409233,0.002384069,0.0161042,0.3186665,0.08178215],"study_design_scores_gemma":[0.0001771308,0.00004387918,0.08570918,0.00002672313,0.0000793587,0.000006839372,0.00008444121,0.8708206,0.00001745347,0.04274637,0.0001699948,0.000117979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1515126,0.000002186878,0.8468643,0.0002768721,0.00009050858,0.0001256284,0.0009861162,0.00002842749,0.0001133628],"genre_scores_gemma":[0.5034769,0.00000513539,0.4958002,0.0003995742,0.00007737453,0.000001606551,0.0002154912,0.00001097327,0.00001274894],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7867283,"threshold_uncertainty_score":0.9976163,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144914506","doi":"10.1111/j.1541-0420.2008.01018.x","title":"Estimating the Encounter Rate Variance in Distance Sampling","year":2008,"lang":"en","type":"article","venue":"Biometrics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":162,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Raincoast Conservation Foundation; Leverhulme Trust","keywords":"Statistics; Distance sampling; Variance (accounting); Sampling (signal processing); Mathematics; Econometrics; Computer science; Biology; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.2002806603232994,"gpt":0.3769286227303718,"spread":0.1766479624070724,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001785089,0.0001200856,0.0001692879,0.0004471248,0.0001920294,0.00004331832,0.0002575045,0.00006713731,0.00001687103],"category_scores_gemma":[0.005433443,0.00008840264,0.0000413565,0.003015846,0.00007506601,0.000111702,0.00004576402,0.000158635,0.00001981715],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008394072,"about_ca_system_score_gemma":0.00003352409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005463718,"about_ca_topic_score_gemma":0.000008179956,"domain_scores_codex":[0.9989206,0.00008920021,0.0003496928,0.0001930264,0.0002206269,0.0002268671],"domain_scores_gemma":[0.9971696,0.002218243,0.0001519492,0.0003363963,0.00009187405,0.00003191609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003193603,0.002756371,0.5086824,0.002016729,0.0002800346,0.0003282479,0.02370803,0.008896714,0.01100656,0.1706892,0.06201492,0.2093014],"study_design_scores_gemma":[0.002083669,0.0002203556,0.2146627,0.0009807297,0.00006004104,0.0002177712,0.0003374816,0.2665408,0.007853024,0.4801893,0.02474275,0.002111307],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1852697,0.0001530676,0.8133558,0.0001180381,0.0002395588,0.0001425591,0.000008921882,0.0001822747,0.0005300757],"genre_scores_gemma":[0.6773989,0.00002521451,0.3222573,0.00008301457,0.0000670521,0.00002390955,0.000003745774,0.00001651086,0.0001243601],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4921292,"threshold_uncertainty_score":0.6504732,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1997934667","doi":"10.1111/j.0006-341x.2005.030833.x","title":"Bias‐Corrected Maximum Likelihood Estimator of the Negative Binomial Dispersion Parameter","year":2005,"lang":"en","type":"article","venue":"Biometrics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Statistics; Estimator; Negative binomial distribution; Restricted maximum likelihood; Quasi-likelihood; Bias of an estimator; Maximum likelihood; Minimum-variance unbiased estimator; Poisson distribution","retraction":null,"screen_n_in":null,"score":{"opus":0.1103639924210811,"gpt":0.3339578366602562,"spread":0.2235938442391751,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006798297,0.0001587684,0.0002453805,0.0006928359,0.0001092206,0.00003494575,0.0003123102,0.0001417139,0.0000593019],"category_scores_gemma":[0.009915211,0.0001070646,0.0001472535,0.003249811,0.00009935313,0.00009906333,0.0001134504,0.0001411982,0.00002650674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009735299,"about_ca_system_score_gemma":0.00005420262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006420394,"about_ca_topic_score_gemma":0.000008140232,"domain_scores_codex":[0.9986742,0.0001213708,0.0004106979,0.0001954371,0.0003766155,0.000221655],"domain_scores_gemma":[0.9967009,0.002278084,0.000307954,0.000434788,0.0002110037,0.00006720794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002165288,0.001976212,0.05287379,0.0003871524,0.000236464,0.000002864613,0.002512862,0.00004927542,0.009580364,0.00375367,0.08264417,0.8457667],"study_design_scores_gemma":[0.00321439,0.000717809,0.07941839,0.0006005928,0.0003865924,0.00004247117,0.0005374598,0.04579126,0.6816632,0.1712273,0.01476064,0.001639855],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9246709,0.00009100787,0.07303534,0.0003806346,0.0004957547,0.0003976255,0.00006892129,0.0003014606,0.0005583411],"genre_scores_gemma":[0.7826254,0.00001537769,0.217069,0.00005663754,0.00007618321,0.00001336907,0.000008232404,0.00002471529,0.0001111228],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8441268,"threshold_uncertainty_score":0.9984247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1995436618","doi":"10.1007/bf02926010","title":"Imputation by power transformation","year":2003,"lang":"en","type":"article","venue":"Statistical Papers","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":110,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Imputation (statistics); Estimator; Mean squared error; Statistics; Population mean; Mathematics; Econometrics; Missing data","retraction":null,"screen_n_in":null,"score":{"opus":0.0340552416612756,"gpt":0.3409253376143045,"spread":0.3068700959530289,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004046882,0.00008982679,0.0001063771,0.00003066248,0.00008404861,0.00002637385,0.00003914064,0.00005748694,0.0007879881],"category_scores_gemma":[0.001251409,0.00008125253,0.0000250443,0.00007940989,0.00004208368,0.00007557609,0.000002017466,0.00008086848,0.00005031871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003263979,"about_ca_system_score_gemma":0.00001830557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007902128,"about_ca_topic_score_gemma":0.000002059329,"domain_scores_codex":[0.9992285,0.0001004664,0.0002242607,0.0001169728,0.0001772232,0.0001525242],"domain_scores_gemma":[0.9990957,0.0006630918,0.00004035489,0.00009330513,0.0000411926,0.0000663824],"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":[0.000009844766,0.00005417182,0.00005534008,0.00003169173,0.00001147094,8.906965e-7,0.0004723515,0.000003932321,0.0009930589,0.9669734,0.02247981,0.008914012],"study_design_scores_gemma":[0.0004525382,0.0001337157,0.000572064,0.00002136986,0.00002776492,0.000009055773,0.0003392585,0.000480069,0.003674764,0.9702014,0.0237881,0.0002998981],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005987993,0.00001125548,0.9076915,0.0001083748,0.00007253298,0.0001456377,0.00008466328,0.00023981,0.08565822],"genre_scores_gemma":[0.8523476,0.000003911035,0.1472603,0.0001140537,0.000003973832,0.00001723122,0.00006814477,0.00001478918,0.000170013],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8463596,"threshold_uncertainty_score":0.8627917,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028182691","doi":"10.1007/s11336-005-1495-y","title":"Item Randomized-Response Models for Measuring Noncompliance: Risk-Return Perceptions, Social Influences, and Self-Protective Responses","year":2007,"lang":"en","type":"article","venue":"Psychometrika","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":101,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Respondent; Psychology; Econometrics; CLARITY; Univariate; Multivariate statistics; Sample (material); Statistics; Multivariate analysis; Randomized response; Covariate; Social psychology; Actuarial science; Mathematics; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.1451726260714991,"gpt":0.4003350211667268,"spread":0.2551623950952276,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01748587,0.0002743799,0.0006368996,0.0008876199,0.0006162119,0.0001111272,0.0002064893,0.0002269096,0.00002016632],"category_scores_gemma":[0.01884266,0.0002488313,0.0002312633,0.00080231,0.0001721009,0.0002602181,0.00003828015,0.0003039818,0.000006131445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001566417,"about_ca_system_score_gemma":0.00005116911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000560429,"about_ca_topic_score_gemma":0.00001514741,"domain_scores_codex":[0.9972401,0.0008285922,0.0006799683,0.0004353407,0.0004046663,0.000411354],"domain_scores_gemma":[0.9771682,0.02163415,0.0004122327,0.000278491,0.000388178,0.0001187527],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.7221716,0.002146511,0.02720794,0.001309364,0.001758649,0.00001008402,0.04956802,0.000102645,0.004860946,0.01475199,0.008653676,0.1674586],"study_design_scores_gemma":[0.0896052,0.0005754211,0.1183372,0.0004391973,0.0005152808,0.00005396938,0.002560592,0.01444007,0.003944437,0.7664378,0.001408645,0.001682244],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5319895,0.0002679181,0.4658361,0.00009843422,0.0001031245,0.001006889,0.00005481592,0.0004699439,0.0001732522],"genre_scores_gemma":[0.8083631,0.0001250086,0.1908294,0.00005142466,0.0001468977,0.0003236261,0.000003544097,0.00004510479,0.0001118755],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7516858,"threshold_uncertainty_score":0.9999964,"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":"W2132467996","doi":"10.1111/j.1541-0420.2006.00576.x","title":"Adaptive Web Sampling","year":2006,"lang":"en","type":"article","venue":"Biometrics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":79,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Los Alamos National Laboratory; National Science Foundation","keywords":"Resampling; Computer science; Inference; Sampling (signal processing); Markov chain; Sampling design; Sample (material); Statistic; Population; Markov chain Monte Carlo; Adaptive sampling; Data mining; Statistics; Machine learning; Artificial intelligence; Mathematics; Monte Carlo method","retraction":null,"screen_n_in":null,"score":{"opus":0.241440605869536,"gpt":0.3821246386598277,"spread":0.1406840327902917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006217014,0.0001008351,0.0001390021,0.0009010043,0.00007986619,0.00004185054,0.0001219404,0.00008743429,0.00004056284],"category_scores_gemma":[0.001052521,0.00009386849,0.00005548689,0.002394259,0.00002929503,0.00005964688,0.00003255848,0.00007319105,0.00005502031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006145189,"about_ca_system_score_gemma":0.0000257718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008045082,"about_ca_topic_score_gemma":0.000005668208,"domain_scores_codex":[0.9991734,0.00003015034,0.0002338685,0.0001529488,0.0002303699,0.0001792655],"domain_scores_gemma":[0.9986134,0.0009224286,0.0000993924,0.0002042249,0.0001255606,0.00003495357],"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":[0.00006669637,0.00121093,0.02536292,0.0002458992,0.0001022929,0.00001821638,0.0002058155,0.00008625613,0.009529148,0.5895335,0.2195154,0.154123],"study_design_scores_gemma":[0.0007426996,0.0002170045,0.01654248,0.00009244306,0.00006090942,0.00002069223,0.0001060298,0.007093769,0.01491876,0.9007625,0.05857314,0.0008695485],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1147171,0.0002860928,0.8688769,0.0000704332,0.0002537638,0.0001814881,0.00004372298,0.001080218,0.01449028],"genre_scores_gemma":[0.6407796,0.000008886102,0.3586218,0.0000199468,0.0001072109,0.000009139138,0.00001233254,0.00001811081,0.0004229357],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5260625,"threshold_uncertainty_score":0.3827846,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2029555586","doi":"10.1198/016214506000000195","title":"Estimation in Multiple-Frame Surveys","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Social Sciences and Humanities Research Council","funders":"","keywords":"Estimator; Frame (networking); Sampling (signal processing); Variance (accounting); Sampling frame; Statistics; Mathematics; Population; Maximum likelihood; M-estimator; Computer science; Econometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.03637944048334951,"gpt":0.3404737711573941,"spread":0.3040943306740446,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003951653,0.00009004686,0.0003075605,0.0001047896,0.00005985514,0.00004044904,0.00015524,0.0000420744,0.00001158036],"category_scores_gemma":[0.01442054,0.00006474803,0.00007629745,0.0003619509,0.0000568738,0.0001069428,0.00002119535,0.0002627268,0.00000514343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005018514,"about_ca_system_score_gemma":0.00005396576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006276786,"about_ca_topic_score_gemma":0.0001885952,"domain_scores_codex":[0.9976638,0.0009319886,0.0006662408,0.00007709691,0.0004950229,0.0001658374],"domain_scores_gemma":[0.9926225,0.005438537,0.001576448,0.0001158195,0.0002166403,0.00003006737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006794787,0.0004671587,0.9052087,0.00003027862,0.00005819692,0.000006301643,0.0001663158,0.002294594,0.0006057966,0.01540548,0.02538719,0.05030203],"study_design_scores_gemma":[0.0002629557,0.0000605823,0.7566481,0.00003740126,0.00002451215,0.000006132951,0.00002579363,0.01319135,0.0003182429,0.2292855,0.00006115594,0.00007821687],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4460922,0.000004725511,0.5529909,0.0005528631,0.0001101873,0.00007417675,0.00002466206,0.00002402682,0.0001263153],"genre_scores_gemma":[0.8758515,0.000002709637,0.1239271,0.00005019986,0.00006046839,0.000002726196,0.000004552671,0.00001111196,0.0000896346],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4297592,"threshold_uncertainty_score":0.9938814,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2295376133","doi":"10.2501/jar-2015-006","title":"Accounting for Social-Desirability Bias in Survey Sampling","year":2015,"lang":"en","type":"article","venue":"Journal of Advertising Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":70,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Advantage Forensics (Canada)","funders":"","keywords":"Social desirability; Accounting; Sampling (signal processing); Social desirability bias; Survey research; Business; Reporting bias; Marketing; Psychology; Social psychology; Political science; MEDLINE; Computer science; Business administration; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.8263005776308638,"gpt":0.5848368616876762,"spread":0.2414637159431876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0784379,0.00009893085,0.0004062312,0.0005257816,0.0001798343,0.0001327144,0.0003024221,0.000121472,0.0000054096],"category_scores_gemma":[0.1270383,0.00008618097,0.0001084656,0.0006119648,0.00008633058,0.0003003607,0.0000683528,0.0006008325,0.000002122885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000441605,"about_ca_system_score_gemma":0.0004476677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002952352,"about_ca_topic_score_gemma":0.0001518639,"domain_scores_codex":[0.9962991,0.000973399,0.001276325,0.0001496482,0.0009004004,0.0004011093],"domain_scores_gemma":[0.9865317,0.009466498,0.0007211439,0.0001675896,0.003001939,0.0001111118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001623283,0.0008486798,0.883852,0.0007376543,0.00009239181,0.00001989779,0.008312438,0.0003593185,0.002220508,0.002207206,0.02833327,0.07139338],"study_design_scores_gemma":[0.001982853,0.0004284532,0.4148106,0.0008253676,0.00001473134,0.00004116319,0.00169419,0.002246952,0.004230944,0.5726693,0.0007457055,0.000309813],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9236098,0.00008366675,0.07544386,0.0003118742,0.0001308302,0.0002170663,0.000006071795,0.00003092307,0.0001659356],"genre_scores_gemma":[0.9137856,0.00000654333,0.08594173,0.00001167162,0.0001792918,0.000005380376,0.00000242956,0.00002518301,0.00004220889],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.570462,"threshold_uncertainty_score":0.9489421,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1976410238","doi":"10.1037/a0029314","title":"Asking sensitive questions: A statistical power analysis of randomized response models.","year":2012,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":70,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"World Anti-Doping Agency","keywords":"Randomized response; Statistical power; Statistics; Statistical model; Sample size determination; Wald test; Goodness of fit; Statistical hypothesis testing; Power (physics); Item response theory; Sample (material); Econometrics; Computer science; Statistical analysis; Mathematics; Psychology; Psychometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.2830794992700697,"gpt":0.5610199716537944,"spread":0.2779404723837247,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02763968,0.0001685913,0.001138731,0.000376155,0.00005866047,0.00001660254,0.0001158213,0.0001874217,0.000268394],"category_scores_gemma":[0.03870296,0.00012023,0.0003038017,0.00075517,0.000256503,0.00008071489,0.00004143719,0.0002157427,0.000004522795],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003082035,"about_ca_system_score_gemma":0.000007417488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001398473,"about_ca_topic_score_gemma":4.90843e-7,"domain_scores_codex":[0.9886039,0.009971418,0.0006515309,0.0002523098,0.0002378621,0.0002830023],"domain_scores_gemma":[0.9624132,0.03660262,0.0002808561,0.00037958,0.0001979962,0.0001257626],"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":[0.07299909,0.001805387,0.0004419874,0.00003709911,0.002799557,0.000007961973,0.00389297,0.0002943806,0.004385406,0.8743543,0.001058118,0.03792374],"study_design_scores_gemma":[0.009072223,0.0001949745,0.009526278,0.00005918928,0.002366689,0.0000181036,0.0001879915,0.03295132,0.002191025,0.9429097,0.0001161744,0.0004063649],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05282803,0.00008622889,0.9440926,0.0001264345,0.0001164802,0.0002723632,0.00004331428,0.000232701,0.002201839],"genre_scores_gemma":[0.4364423,0.000008866628,0.5633656,0.00008824457,0.00001078227,0.00004378366,0.000006551431,0.000008405446,0.00002539527],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3836143,"threshold_uncertainty_score":0.9693944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2059158409","doi":"10.1111/1467-842x.00153","title":"Median Estimation Using Double Sampling","year":2001,"lang":"en","type":"article","venue":"Australian & New Zealand Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":69,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor; University of Saskatchewan","funders":"","keywords":"Mathematics; Estimator; Statistics; Minimum-variance unbiased estimator; Sampling (signal processing); Stratified sampling","retraction":null,"screen_n_in":null,"score":{"opus":0.2384222707548125,"gpt":0.4195964561187449,"spread":0.1811741853639324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007992019,0.000165474,0.0003290574,0.0002032967,0.0000989203,0.0001014925,0.0001710492,0.0001011883,0.0001843427],"category_scores_gemma":[0.0005030899,0.0001470608,0.00006585829,0.0002001527,0.00004110437,0.0002374695,0.00001485889,0.0002667477,0.000009534154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008396827,"about_ca_system_score_gemma":0.0001675404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003300371,"about_ca_topic_score_gemma":0.00005285188,"domain_scores_codex":[0.9984095,0.0000489309,0.0007840516,0.0001093219,0.0003840397,0.0002641938],"domain_scores_gemma":[0.9981418,0.0004861614,0.0006743363,0.0001620199,0.000292149,0.0002435009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001057277,0.0007113472,0.05109418,0.0003717548,0.0005415264,0.0005974785,0.00509248,0.014709,0.002448402,0.03464984,0.6991301,0.1895967],"study_design_scores_gemma":[0.003790534,0.0006215969,0.006170118,0.0008423992,0.0004496417,0.002346525,0.0003122489,0.009938086,0.002450081,0.9518733,0.02050398,0.0007014961],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1065807,0.00001372918,0.892115,0.0006783838,0.0003493974,0.0001033676,0.00003391358,0.00005608453,0.00006938529],"genre_scores_gemma":[0.1116942,0.00005920809,0.8858274,0.00003036106,0.0003325918,5.967438e-7,0.00001811411,0.00003056287,0.00200701],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9172235,"threshold_uncertainty_score":0.5996965,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1989279378","doi":"10.1111/j.1751-5823.2006.00002.x","title":"On the Construction of Imputation Classes in Surveys","year":2007,"lang":"en","type":"article","venue":"International Statistical Review","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":64,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Statistics Canada; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Estimator; Statistics; Mathematics; Conditional expectation; Homogeneous; Econometrics; Population; Computer science; Missing data; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1188360583858608,"gpt":0.449637914926509,"spread":0.3308018565406482,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004249643,0.00006582683,0.000151706,0.00006258357,0.0000175054,0.000008931787,0.0001138603,0.00002823546,0.0004015425],"category_scores_gemma":[0.01203212,0.00004491701,0.00003085667,0.000133719,0.00006704356,0.00003507457,0.00001387778,0.000102493,0.00001681789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005258906,"about_ca_system_score_gemma":0.0000192712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004673599,"about_ca_topic_score_gemma":0.00003621069,"domain_scores_codex":[0.9988203,0.0002266457,0.000479639,0.0000977925,0.0002938005,0.00008178838],"domain_scores_gemma":[0.9917873,0.007773685,0.0001578625,0.0000961886,0.0001643496,0.00002068357],"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":[0.000007127347,0.00004434106,0.0008311929,0.0001543721,0.000008641142,0.000001720865,0.000009841471,0.000001330366,0.000007812171,0.896796,0.001954968,0.1001827],"study_design_scores_gemma":[0.0001023445,0.00004199491,0.02616556,0.001633546,0.00001140329,0.000008792817,0.00001357031,0.0004176149,0.000360113,0.9699813,0.001185584,0.00007816041],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007495061,0.0002570094,0.9858387,0.0009075199,0.0001505024,0.0002327285,0.00005182965,0.00003477602,0.005031857],"genre_scores_gemma":[0.8740861,0.001744576,0.1235169,0.0004679085,0.00003564031,0.00002699694,0.00006757084,0.00001339321,0.00004095625],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.866591,"threshold_uncertainty_score":0.99629,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1827082642","doi":"10.1080/00028487.2014.901252","title":"Cluster Sampling: A Pervasive, Yet Little Recognized Survey Design in Fisheries Research","year":2014,"lang":"en","type":"article","venue":"Transactions of the American Fisheries Society","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":62,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"U.S. Fish and Wildlife Service; Memorial University of Newfoundland; Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"Cluster sampling; Estimator; Sampling (signal processing); Sampling design; Simple random sample; Cluster (spacecraft); Independence (probability theory); Statistics; Fishery; Sample (material); Population; Sample size determination; Population dynamics of fisheries; Fisheries management; Fish <Actinopterygii>; Computer science; Econometrics; Biology; Mathematics; Fishing; Demography","retraction":null,"screen_n_in":null,"score":{"opus":0.3296738258219308,"gpt":0.398959574295874,"spread":0.0692857484739432,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005437206,0.0001906695,0.0004770553,0.00007572,0.0003551936,0.00006325275,0.0005048321,0.00009816602,0.0001088924],"category_scores_gemma":[0.002717657,0.0001553786,0.0002757639,0.001206968,0.001190787,0.000175419,0.00003841344,0.0005255574,0.000004160435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001124022,"about_ca_system_score_gemma":0.0001198072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004348124,"about_ca_topic_score_gemma":0.001093264,"domain_scores_codex":[0.9964866,0.001922977,0.000492643,0.0003009563,0.0004154131,0.0003813978],"domain_scores_gemma":[0.9905169,0.008073438,0.0002524354,0.0007156769,0.0003837653,0.00005778215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.004051141,0.00374394,0.3526989,0.001901087,0.001535162,0.000001151858,0.09952853,0.003361326,0.004982221,0.0009181043,0.3795454,0.147733],"study_design_scores_gemma":[0.004850218,0.002644112,0.650511,0.001064717,0.0003479549,0.00003693969,0.02746703,0.02513953,0.03443434,0.233065,0.01763046,0.002808755],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.42434,0.00001364385,0.5727534,0.00161438,0.000135937,0.0005031716,0.0000575794,0.0001886724,0.0003932597],"genre_scores_gemma":[0.7539457,0.0001284746,0.2448746,0.0001880532,0.00002244096,0.0001400789,0.000008395493,0.00005423657,0.0006380456],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.361915,"threshold_uncertainty_score":0.6573092,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4247186967","doi":"10.1007/978-0-387-70782-2","title":"Indirect Sampling","year":2007,"lang":"en","type":"book","venue":"Springer series in statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Statistics Canada","funders":"","keywords":"Sampling (signal processing); Environmental science; Computer science; Statistics; Psychology; Mathematics; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.1362042396617562,"gpt":0.3843215157834575,"spread":0.2481172761217014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001361197,0.0004200803,0.0006876156,0.0004597708,0.00008669719,0.00007318531,0.0003126674,0.0004959471,0.0002365689],"category_scores_gemma":[0.001843621,0.000467287,0.0000694855,0.0001436731,0.0001825025,0.00008810934,0.0001477894,0.0007729352,0.00006035616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003856679,"about_ca_system_score_gemma":0.0002636064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002388242,"about_ca_topic_score_gemma":0.000291977,"domain_scores_codex":[0.9978325,0.00005490399,0.0008356698,0.0004025461,0.0004372938,0.0004370215],"domain_scores_gemma":[0.996853,0.001918835,0.000395688,0.0005737247,0.0001768745,0.00008187705],"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":[0.00007719491,0.00008029552,0.0005622325,0.001479186,0.0001045406,0.0001536197,0.00110009,0.0000137243,0.000006502739,0.8330483,0.1248301,0.03854419],"study_design_scores_gemma":[0.0001218055,0.00005247591,0.0002905813,0.0006122569,0.00004235965,0.00001482097,0.00002528413,0.00002591917,0.000158606,0.8480011,0.1501033,0.0005514766],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00009147884,0.0002623938,0.6790626,0.00001495247,0.0009081084,0.0004481948,0.0007257178,0.0007151371,0.3177714],"genre_scores_gemma":[0.00008213292,0.000178711,0.7248927,0.00004147417,0.0002217762,0.00002490365,0.0002330316,0.0001450719,0.2741802],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04583005,"threshold_uncertainty_score":0.9997779,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1973354056","doi":"10.1093/biomet/asp041","title":"A unified approach to linearization variance estimation from survey data after imputation for item nonresponse","year":2009,"lang":"en","type":"article","venue":"Biometrika","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Imputation (statistics); Categorical variable; Missing data; Statistics; Mathematics; Estimator; Econometrics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2424406556858648,"gpt":0.4131986451287096,"spread":0.1707579894428448,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00307501,0.0001703602,0.0002365473,0.000644822,0.00008690816,0.0001528079,0.0003459728,0.0001514548,0.000009794518],"category_scores_gemma":[0.01591346,0.0001688399,0.00003558355,0.001843548,0.00001387379,0.0003088937,0.00005468393,0.00006443539,0.00002002868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006523801,"about_ca_system_score_gemma":0.00005954139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001308532,"about_ca_topic_score_gemma":0.00001259846,"domain_scores_codex":[0.9983777,0.0002487428,0.0004355748,0.0004709163,0.0002664122,0.0002006341],"domain_scores_gemma":[0.996249,0.002418948,0.0001789591,0.0007679109,0.0002959242,0.000089313],"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":[0.00918272,0.004493954,0.009976326,0.0005330578,0.0003928946,0.000005763821,0.005179761,0.003540413,0.01051716,0.009267675,0.06491435,0.8819959],"study_design_scores_gemma":[0.0009257192,0.0002949385,0.2667957,0.00007878217,0.00006132107,0.000002171941,0.00002824828,0.6856663,0.00298009,0.04183242,0.0007927615,0.0005416005],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0582667,0.0000350017,0.939199,0.0001282788,0.0001060433,0.0007786096,0.001091689,0.0003292076,0.0000655293],"genre_scores_gemma":[0.4660248,0.000002105708,0.5298397,0.0001154572,0.00005714012,0.00005239021,0.003818207,0.00001742982,0.00007277972],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8814543,"threshold_uncertainty_score":0.9923759,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2052097769","doi":"10.1093/biomet/87.4.929","title":"Empirical likelihood inference under stratified random sampling using auxiliary population information","year":2000,"lang":"en","type":"article","venue":"Biometrika","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Carleton University","funders":"","keywords":"Mathematics; Stratified sampling; Inference; Population; Statistics; Library science; Sampling (signal processing); Demography; Computer science; Artificial intelligence; Sociology; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.2299445286686772,"gpt":0.4337713915434576,"spread":0.2038268628747805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009920598,0.0001723862,0.0002514217,0.0006600269,0.0001828787,0.0001624117,0.0001365875,0.0001830736,0.000420792],"category_scores_gemma":[0.001069071,0.0001604507,0.0001015648,0.001312652,0.00002956917,0.0006856583,0.00002188377,0.0001388024,0.00007213051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001142684,"about_ca_system_score_gemma":0.00006268917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002753092,"about_ca_topic_score_gemma":0.00001017832,"domain_scores_codex":[0.9985105,0.0001086754,0.0006019009,0.0001687434,0.0003564443,0.0002537761],"domain_scores_gemma":[0.9984671,0.000866935,0.0001706514,0.0002806453,0.0001271079,0.00008757682],"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":[0.0006655673,0.000645387,0.0493063,0.0004819865,0.0002377818,0.000002379437,0.002110092,0.003148264,0.002524223,0.005506203,0.002671288,0.9327005],"study_design_scores_gemma":[0.006746276,0.0003887061,0.2662083,0.0006721167,0.0003141653,0.00005451989,0.0005550217,0.1057829,0.007678512,0.6034858,0.005809528,0.002304087],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6201614,0.00002949375,0.3785087,0.00005563779,0.00008735928,0.000224438,0.00001715963,0.0003844119,0.0005314275],"genre_scores_gemma":[0.8815958,0.00001698868,0.1180035,0.0001200561,0.00006369535,0.00001174969,0.0001386741,0.00001509181,0.00003441936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9303964,"threshold_uncertainty_score":0.6542988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2971819817","doi":"10.1039/c9em00215d","title":"Theory and modelling approaches to passive sampling","year":2019,"lang":"en","type":"review","venue":"Environmental Science Processes & Impacts","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Regional Municipality of Waterloo; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sampling (signal processing); Interpretation (philosophy); Sampling theory; Computer science; Environmental science; Mathematics; Statistics; Telecommunications; Sample size determination","retraction":null,"screen_n_in":null,"score":{"opus":0.433973485328245,"gpt":0.3977896918861622,"spread":0.03618379344208278,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002210071,0.0004504509,0.0008570347,0.0002956582,0.000319695,0.0002552246,0.0005689677,0.0001616584,0.00002890364],"category_scores_gemma":[0.001152079,0.0003429738,0.00009060755,0.0005594781,0.0003599926,0.0004739191,0.0003581982,0.0002728467,0.00008319712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002998798,"about_ca_system_score_gemma":0.0003223878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004787811,"about_ca_topic_score_gemma":5.880129e-7,"domain_scores_codex":[0.9975724,0.000102142,0.0004535348,0.000769058,0.0005538515,0.0005490216],"domain_scores_gemma":[0.9975404,0.001349248,0.0003532114,0.0004315329,0.00001125823,0.0003144249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001258013,0.0001217125,0.00001319561,0.01848856,0.0000401095,0.00000154127,0.001671328,0.000286933,0.00001435958,0.002422967,0.00003677561,0.97689],"study_design_scores_gemma":[0.0008039524,0.001513089,0.00005163774,0.1028077,0.003241778,0.0007199002,0.003762399,0.00435203,0.002877295,0.3026902,0.5673148,0.00986524],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001814371,0.9219408,0.07442214,0.00001576252,0.00007932642,0.001247984,0.00006235677,0.0001675367,0.0002497177],"genre_scores_gemma":[0.006037609,0.9421055,0.05141674,0.00003654398,0.0000556584,0.0001245519,0.00002221885,0.00007105285,0.0001300846],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9670247,"threshold_uncertainty_score":0.9999022,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1999057766","doi":"10.1016/s0378-3758(99)00092-0","title":"Some alternative strategies to Moors’ model in randomized response sampling","year":2000,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":52,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Randomized response; Moors; Mathematics; Efficiency; Statistics; Econometrics; Sampling (signal processing); Mathematical economics; Geography; Computer science; Archaeology","retraction":null,"screen_n_in":null,"score":{"opus":0.1514197559372908,"gpt":0.4420925287823689,"spread":0.2906727728450781,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002889216,0.0001164778,0.0005183451,0.0001947178,0.00004801325,0.00009693664,0.0001034788,0.00005115604,0.00003964537],"category_scores_gemma":[0.006274376,0.00008954072,0.0000350269,0.00007926658,0.00006931012,0.0002698838,0.00001544534,0.0002704663,0.000002669914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002935845,"about_ca_system_score_gemma":0.00009796278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003105032,"about_ca_topic_score_gemma":0.000001291442,"domain_scores_codex":[0.9985901,0.0002826206,0.0006408191,0.0001094783,0.0002163628,0.0001606622],"domain_scores_gemma":[0.9914947,0.008049512,0.0001636041,0.00007111318,0.0001071277,0.0001139046],"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":[0.1449924,0.0003233948,0.0008316622,0.0001854785,0.000151691,0.0002073168,0.02291864,0.2953005,0.0008262912,0.5010056,0.001402383,0.03185464],"study_design_scores_gemma":[0.005818464,0.0001671732,0.001029438,0.0004933984,0.00001816951,0.00002241377,0.000234048,0.1345531,0.0000828563,0.8574381,0.0000146951,0.0001280476],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.424747,0.00005775482,0.5748519,0.00009180007,0.00001926985,0.0000640171,0.00001398132,0.00001544049,0.0001388648],"genre_scores_gemma":[0.7276586,0.00004626848,0.2721678,0.00005769545,0.00002849161,0.00000419738,9.449612e-7,0.000006595727,0.00002942475],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3564326,"threshold_uncertainty_score":0.7511467,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2048788123","doi":"10.1002/jae.1052","title":"Do randomized‐response designs eliminate response biases? An empirical study of non‐compliance behavior","year":2009,"lang":"en","type":"article","venue":"Journal of Applied Econometrics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Ministerie van Sociale Zaken en Werkgelegenheid","keywords":"Econometrics; Toolbox; Response bias; Computer science; Multivariate statistics; Randomized response; Statistics; Contrast (vision); Mathematics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.3630646595252005,"gpt":0.4522586192882325,"spread":0.08919395976303202,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01776595,0.0002550249,0.001265961,0.002031898,0.00009845116,0.00009138035,0.0004959191,0.0001491513,0.00006620734],"category_scores_gemma":[0.007328023,0.0002182592,0.0002505989,0.001244476,0.00007811992,0.0002351055,0.00003615754,0.0003649264,0.000007822817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001519346,"about_ca_system_score_gemma":0.0001333273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000242116,"about_ca_topic_score_gemma":6.31165e-7,"domain_scores_codex":[0.9965349,0.000683423,0.00182215,0.0002606379,0.0004295023,0.0002694063],"domain_scores_gemma":[0.9869756,0.01016818,0.001730041,0.0005120203,0.0003980055,0.000216127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"observational","study_design_scores_codex":[0.8802097,0.01968161,0.006219082,0.00009953098,0.0004117143,0.0001800398,0.01231035,0.002278063,0.005244079,0.0006508272,0.002418467,0.07029654],"study_design_scores_gemma":[0.2979317,0.03632412,0.4914407,0.0006697566,0.002698539,0.0005540734,0.01353516,0.008724275,0.03848344,0.1063367,0.0003510524,0.002950547],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9638949,0.00004608857,0.03488408,0.00007593746,0.00009758069,0.0007814998,0.000009715164,0.00005359593,0.0001566001],"genre_scores_gemma":[0.934663,0.000025422,0.06510547,0.00007137004,0.00005223089,0.00002941507,0.000001105577,0.00002879845,0.00002319082],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.582278,"threshold_uncertainty_score":0.8900353,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159263306","doi":"10.1177/0049124107301944","title":"Log-Linear Randomized-Response Models Taking Self-Protective Response Behavior Into Account","year":2007,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Randomized response; Respondent; Log-linear model; Response bias; Item response theory; Statistics; Outcome (game theory); Psychology; Social psychology; Econometrics; Response time; Linear model; Mathematics; Computer science; Psychometrics","retraction":null,"screen_n_in":null,"score":{"opus":0.5305748280486128,"gpt":0.619559010240721,"spread":0.08898418219210824,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3028316,0.0003590689,0.001076235,0.000582255,0.0008272186,0.00009351878,0.000728001,0.0008983272,0.0001681802],"category_scores_gemma":[0.137613,0.0002607276,0.0004226833,0.0007843976,0.001305566,0.0001899803,0.0004816111,0.002170064,0.00005473913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005444169,"about_ca_system_score_gemma":0.0002539333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002346718,"about_ca_topic_score_gemma":0.000004556497,"domain_scores_codex":[0.9439008,0.05170805,0.001114808,0.0008693488,0.001167216,0.001239807],"domain_scores_gemma":[0.8583457,0.1391865,0.0003199466,0.0007348845,0.001149022,0.0002639683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.6701828,0.001991803,0.0005465531,0.0002256462,0.0004231035,0.0002747211,0.03205694,0.00009294083,0.09996552,0.07139529,0.000568355,0.1222763],"study_design_scores_gemma":[0.008625555,0.0005252612,0.001641182,0.00006434925,0.00005292947,0.00001802497,0.001861858,0.004200716,0.01816597,0.9642385,0.0001971536,0.0004084816],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4441288,0.0001310081,0.5529666,0.0003278074,0.00007262213,0.00145276,0.000004814413,0.0006374893,0.000278107],"genre_scores_gemma":[0.3979232,0.000018929,0.6010001,0.0000609021,0.0001068974,0.0007197568,0.000002452512,0.00004038458,0.0001273314],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8928432,"threshold_uncertainty_score":0.9999845,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2001784416","doi":"10.1139/f07-138","title":"Estimating abundance of spatially aggregated populations: comparing adaptive sampling with other survey designs","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Fisheries and Aquatic Sciences","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Marine Fisheries Service","keywords":"Estimator; Cluster sampling; Sampling (signal processing); Simple random sample; Survey research; Stratified sampling; Statistics; Population; Survey methodology; Pollock; Survey data collection; Cluster (spacecraft); Sampling design; Systematic sampling; Abundance (ecology); Computer science; Mathematics; Ecology; Fishery; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.376136716516481,"gpt":0.3471438643809633,"spread":0.02899285213551767,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001488101,0.0001020772,0.0002901729,0.0001818515,0.0004424977,0.00007108012,0.0001712178,0.00003151183,0.00001863584],"category_scores_gemma":[0.00164342,0.00007736771,0.00002633489,0.000349534,0.0006309046,0.0002790838,0.000006140027,0.00008894697,2.057541e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002954195,"about_ca_system_score_gemma":0.0006544754,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02473779,"about_ca_topic_score_gemma":0.05883915,"domain_scores_codex":[0.9989415,0.0001096448,0.0004423546,0.0001051065,0.0002221089,0.0001792194],"domain_scores_gemma":[0.9983582,0.0006796053,0.0005543304,0.00008113007,0.0001727621,0.0001539038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002746187,0.0000149188,0.9893712,0.00003009035,0.00003052956,0.000008018254,0.003496931,0.002492339,0.00002927659,0.00119068,0.0001645794,0.003143971],"study_design_scores_gemma":[0.001061064,0.001984977,0.6637278,0.003638625,0.0001045002,0.000790361,0.00231032,0.2266798,0.001103832,0.09763332,0.0001035131,0.000861855],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7165608,0.0001306599,0.2829663,0.00005765655,0.00006410406,0.00006110912,0.000004156813,0.00000833246,0.0001468976],"genre_scores_gemma":[0.6330124,0.000002781909,0.3669403,0.00001407922,0.00001469404,8.224195e-7,5.393238e-7,0.000005595052,0.000008785847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3256434,"threshold_uncertainty_score":0.9817566,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2022391270","doi":"10.1111/j.1467-842x.2005.00402.x","title":"MODEL-ASSISTED HIGHER-ORDER CALIBRATION OF ESTIMATORS OF VARIANCE","year":2005,"lang":"en","type":"article","venue":"Australian & New Zealand Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Estimator; Mathematics; Variance (accounting); Population variance; Statistics; Variable (mathematics); Calibration; Inference; Population; Extremum estimator; Set (abstract data type); Econometrics; M-estimator; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1129439387624059,"gpt":0.3607645240760187,"spread":0.2478205853136128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000499557,0.0001425743,0.0004411865,0.0001372309,0.00002888457,0.00001976161,0.0001665246,0.0001048061,0.0001353821],"category_scores_gemma":[0.0004144648,0.0001237952,0.00006465478,0.000186638,0.00006760234,0.0001940005,0.00001284735,0.0001781559,0.000001054512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003534779,"about_ca_system_score_gemma":0.0002140507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007451464,"about_ca_topic_score_gemma":0.00001825514,"domain_scores_codex":[0.9982535,0.00006400453,0.001070116,0.00008978751,0.0003655867,0.0001570674],"domain_scores_gemma":[0.997617,0.0004039705,0.00119924,0.0001770501,0.0004755487,0.000127169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004144146,0.001010378,0.01023631,0.0006102505,0.0004071241,0.00002698079,0.001954446,0.03851588,0.00469039,0.1021869,0.8044478,0.03549918],"study_design_scores_gemma":[0.00512543,0.001712997,0.02907577,0.001655038,0.0009218488,0.0002753684,0.0001257395,0.1241483,0.03826176,0.7895849,0.008145046,0.0009677994],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03173934,0.00002062933,0.9667552,0.0009416619,0.0001333031,0.00009631016,0.0001950963,0.00002900862,0.00008950279],"genre_scores_gemma":[0.345132,0.00002308162,0.6520427,0.00001660233,0.00007505194,5.334594e-7,0.00001095745,0.0000164954,0.002682549],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7963027,"threshold_uncertainty_score":0.504822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1497865302","doi":"10.6092/issn.1973-2201/1004","title":"Random non-response on study variable versus on study as well as auxiliary variables","year":2013,"lang":"en","type":"article","venue":"Università degli Studi di Bologna","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Estimator; Statistics; Mathematics; Simple random sample; Random variable; Variable (mathematics); Population mean; Population; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.05283423966777031,"gpt":0.3211686688882726,"spread":0.2683344292205023,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002199018,0.0004924827,0.0007130514,0.0004438319,0.0006517806,0.0001022316,0.0006078235,0.0001983749,0.001383302],"category_scores_gemma":[0.002394979,0.0004478076,0.0001279289,0.0005349391,0.00009931035,0.0002513421,0.0003185565,0.0004421703,0.002608756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003052754,"about_ca_system_score_gemma":0.0001578144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001305689,"about_ca_topic_score_gemma":0.00003029002,"domain_scores_codex":[0.9964767,0.001157776,0.0004502519,0.0007459563,0.0006293813,0.0005400088],"domain_scores_gemma":[0.9913504,0.006927477,0.0002443452,0.0009747805,0.0003199996,0.0001829698],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"qualitative","study_design_scores_codex":[0.1997132,0.1128552,0.1495819,0.0003712986,0.01190532,0.002623503,0.04908631,0.005538059,0.002111948,0.07139052,0.3886877,0.006134982],"study_design_scores_gemma":[0.1878516,0.1401516,0.1574511,0.001046137,0.00444273,0.00005571885,0.3957497,0.00404767,0.005289959,0.06529512,0.03112871,0.007489937],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.897724,0.00001036076,0.001754633,0.0001233103,0.0003954585,0.002826065,0.00001436556,0.0006600049,0.09649184],"genre_scores_gemma":[0.9835827,0.000007846002,0.002379683,0.0001437614,0.00006730005,0.0001081447,0.000009390103,0.00005962401,0.0136415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.357559,"threshold_uncertainty_score":0.9997973,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2759870632","doi":"10.1093/biomet/asx007","title":"OUP accepted manuscript","year":2017,"lang":"en","type":"article","venue":"Biometrika","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Jackknife resampling; Imputation (statistics); Robustness (evolution); Estimator; Mathematics; Covariate; Missing data; Statistics; Simple random sample; Econometrics; Population; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.358109777955419,"gpt":0.4504804658716225,"spread":0.09237068791620356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006713538,0.00009888109,0.0001544008,0.0003637893,0.0003250542,0.0002105359,0.0004471335,0.00008696086,0.0003938185],"category_scores_gemma":[0.003613899,0.00008706934,0.0000624182,0.0002127374,0.00006509606,0.0001571377,0.00009834506,0.00006911591,0.0001769452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002744075,"about_ca_system_score_gemma":0.00001284672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007008482,"about_ca_topic_score_gemma":0.000003362522,"domain_scores_codex":[0.9992781,0.00002571664,0.0001800796,0.0001607129,0.0001850776,0.0001703648],"domain_scores_gemma":[0.9986687,0.0001995922,0.0001790198,0.0008096413,0.00008189676,0.00006111529],"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":[0.00005028961,0.0004152218,0.02442503,0.0001983456,0.0001322302,0.00002242238,0.0003304223,1.615451e-7,0.008576501,0.0373375,0.3649647,0.5635472],"study_design_scores_gemma":[0.001628979,0.0002627626,0.2514065,0.0002059098,0.00009086757,0.00002825008,0.0001193975,0.0005350619,0.2035578,0.3492999,0.1916814,0.001183158],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6911315,0.0002867348,0.164702,0.001775613,0.002123744,0.0007111898,0.00008286113,0.002740205,0.1364462],"genre_scores_gemma":[0.9217978,0.0000145826,0.07524982,0.00004982149,0.0001040764,0.00001574121,0.000007692578,0.00002056632,0.002739936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.562364,"threshold_uncertainty_score":0.4326436,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2993287308","doi":"","title":"Multi-objective optimisation for optimum allocation in multivariate stratified sampling","year":2008,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Stratified sampling; Multivariate statistics; Statistics; Sampling (signal processing); Mathematics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.6825131120236855,"gpt":0.5037334109630854,"spread":0.1787797010606,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01482643,0.0002081149,0.0004818099,0.0002781261,0.000162774,0.00001457812,0.0001701209,0.0002779681,0.00001917022],"category_scores_gemma":[0.03186441,0.0002136872,0.00007927205,0.0003042045,0.00008716888,0.0001410596,0.00003224974,0.0002106098,0.000004987093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001095123,"about_ca_system_score_gemma":0.0001162634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002218652,"about_ca_topic_score_gemma":0.001305849,"domain_scores_codex":[0.9945441,0.003906262,0.0006463013,0.0004412328,0.00012781,0.0003343262],"domain_scores_gemma":[0.9772353,0.0217331,0.0002765864,0.0003134114,0.0003888634,0.0000527616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.01167889,0.006318099,0.2578678,0.00163076,0.001328742,0.00004159192,0.08525735,0.0973061,0.3555956,0.06803167,0.003711846,0.1112315],"study_design_scores_gemma":[0.003391148,0.0003101794,0.7806591,0.00007418545,0.00003735372,0.00003424034,0.0004660024,0.08433104,0.03517011,0.09467565,0.00005309381,0.0007979132],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2215482,0.00001779344,0.7772363,0.00003990226,0.0002221245,0.0006591398,0.00004278956,0.0001919226,0.0000418493],"genre_scores_gemma":[0.2940463,0.00001009644,0.7053984,0.00002912504,0.00003220807,0.0001932597,0.0001733695,0.00003008917,0.00008722288],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5227913,"threshold_uncertainty_score":0.9762906,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1994123841","doi":"10.1071/wr11105","title":"Assessment of bias in US waterfowl harvest estimates","year":2012,"lang":"en","type":"article","venue":"Wildlife Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Waterfowl; Anas; Goose; Branta; Geography; Context (archaeology); Anatidae; Fishery; Biology; Ecology; Habitat; Archaeology","retraction":null,"screen_n_in":null,"score":{"opus":0.4965470248049577,"gpt":0.5373102824956577,"spread":0.04076325769069999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009859075,0.0001112162,0.0002700376,0.000430303,0.00007662933,0.00003974892,0.0002425993,0.00009921117,0.0001149146],"category_scores_gemma":[0.003447335,0.00009170917,0.00004629689,0.0004616401,0.0001366919,0.0002180105,0.0001368868,0.0003685954,0.00003863566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001060377,"about_ca_system_score_gemma":0.00009779554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005466916,"about_ca_topic_score_gemma":0.00003296821,"domain_scores_codex":[0.9976752,0.0004802094,0.0004119242,0.0001603456,0.0007113149,0.0005610304],"domain_scores_gemma":[0.9963273,0.002846611,0.00007445231,0.00040372,0.0002246955,0.0001232453],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007515992,0.0003703609,0.9782779,0.0002101433,0.00001236005,0.000001586639,0.0003066687,0.00001530496,0.0003895172,0.0153002,0.004039554,0.001068895],"study_design_scores_gemma":[0.0003583711,0.0001322351,0.9495958,0.0003818839,0.000007482669,0.000007760479,0.0001745207,0.003769465,0.007220076,0.03637221,0.001769521,0.0002106786],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896984,0.00007340335,0.004332013,0.0002398891,0.00005706264,0.0003066281,0.000008991366,0.0001158201,0.005167819],"genre_scores_gemma":[0.9211788,0.00003170419,0.07838404,0.00001938462,0.00005931046,0.00006994104,0.00001045895,0.00002466688,0.0002217119],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07405203,"threshold_uncertainty_score":0.4127031,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2027764114","doi":"10.1198/016214502760047069","title":"Efficient Estimation of Quadratic Finite Population Functions in the Presence of Auxiliary Information","year":2002,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Estimator; Mathematics; Population; Covariance; Quadratic equation; Applied mathematics; Correctness; Linear model; Variance (accounting); Mathematical optimization; Statistics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.0370660623633208,"gpt":0.3227786959343425,"spread":0.2857126335710217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002119925,0.00007543639,0.0002673946,0.0001506314,0.00006219118,0.00002095134,0.0001764516,0.00003561394,0.00001987993],"category_scores_gemma":[0.01603248,0.00004736289,0.00008014838,0.0005612082,0.00006618707,0.0001571265,0.00001702192,0.0001948071,0.000002811354],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001709239,"about_ca_system_score_gemma":0.00002418293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001679915,"about_ca_topic_score_gemma":0.00001240402,"domain_scores_codex":[0.9976603,0.000541033,0.0009539846,0.0000463917,0.0006956128,0.000102686],"domain_scores_gemma":[0.9916686,0.005150951,0.002687934,0.0001577698,0.0003149657,0.00001972527],"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":[0.0003684757,0.002274027,0.2419314,0.0006308251,0.0002885135,0.00000239832,0.0187067,0.5115259,0.0003507017,0.05073839,0.0292564,0.1439263],"study_design_scores_gemma":[0.0002979961,0.0002343132,0.4312798,0.0001549616,0.0001056425,0.00000655061,0.0006660962,0.5322846,0.0001037012,0.03475854,0.00002294106,0.00008485698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5939885,0.000007716496,0.4049319,0.0006119962,0.0001053471,0.0001752467,0.00004798564,0.000009860402,0.0001213459],"genre_scores_gemma":[0.9742144,0.00000494835,0.02568477,0.00004572996,0.00001839523,0.000005067262,0.000006865932,0.000004310383,0.00001546274],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3802259,"threshold_uncertainty_score":0.9922559,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2072591790","doi":"10.1007/s11336-013-9390-9","title":"Modeling Motivated Misreports to Sensitive Survey Questions","year":2013,"lang":"en","type":"article","venue":"Psychometrika","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Kellogg's (Canada)","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Response bias; Psychology; Scale (ratio); Item response theory; Computer science; Process (computing); Data science; Econometrics; Social psychology; Cognitive psychology; Psychometrics; Mathematics; Developmental psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1796379956968289,"gpt":0.3932901266850871,"spread":0.2136521309882582,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00155666,0.0001809692,0.0002703494,0.0006226461,0.0001174109,0.00009492541,0.0001316334,0.0001056591,0.0001815047],"category_scores_gemma":[0.01127985,0.0001714552,0.00006435902,0.0015503,0.00001843187,0.0001475069,0.00003557574,0.0001564461,0.0003639125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006061894,"about_ca_system_score_gemma":0.00002436886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00227919,"about_ca_topic_score_gemma":0.00007093402,"domain_scores_codex":[0.9984263,0.000195507,0.0004615991,0.0003388341,0.0002822277,0.0002955289],"domain_scores_gemma":[0.9971516,0.001381832,0.00009044173,0.0004818855,0.0006947075,0.0001996068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0003163958,0.004201014,0.2697806,0.0004406384,0.001112842,0.00004413164,0.009615591,0.014648,0.01506258,0.01289583,0.4899549,0.1819274],"study_design_scores_gemma":[0.001265805,0.0004612421,0.587975,0.0007385868,0.00009693243,0.00009591252,0.0006377325,0.1430803,0.01448403,0.2473788,0.001115798,0.002670004],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5936413,0.00001330321,0.4040367,0.0001905453,0.000181538,0.0003881548,0.00001854865,0.0005365712,0.0009933314],"genre_scores_gemma":[0.9026964,0.000007492201,0.09651274,0.0001652574,0.00004670583,0.00008099536,0.00003640481,0.00003842801,0.0004155727],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4888391,"threshold_uncertainty_score":0.9970486,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2607179242","doi":"10.1017/pan.2017.8","title":"The Statistical Analysis of Misreporting on Sensitive Survey Questions","year":2017,"lang":"en","type":"article","venue":"Political Analysis","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Context (archaeology); Variety (cybernetics); Prejudice (legal term); Computer science; Survey data collection; Ideology; Multivariate statistics; Scale (ratio); Social psychology; Psychology; Econometrics; Statistics; Political science; Artificial intelligence; Mathematics; Law; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1787294437969652,"gpt":0.4678313315530983,"spread":0.2891018877561331,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00315354,0.0001308013,0.0005907174,0.0003245408,0.0006906826,0.0001381631,0.0002423328,0.0000699776,0.0000536216],"category_scores_gemma":[0.03736738,0.00008923789,0.0003872846,0.0006443645,0.0003845009,0.00004179091,0.00006422396,0.0001450892,0.000007598313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005131245,"about_ca_system_score_gemma":0.00003644843,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006992076,"about_ca_topic_score_gemma":0.003342981,"domain_scores_codex":[0.9979013,0.0004700862,0.0006508237,0.0002483938,0.0003822526,0.0003471056],"domain_scores_gemma":[0.9872943,0.01063414,0.0004531493,0.001005569,0.0004582285,0.0001546522],"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":[0.00002091013,0.0001093694,0.2053142,0.000007857054,0.006196771,0.000005728913,0.000050302,0.00009806174,0.000007810782,0.7871761,0.0001615175,0.0008513677],"study_design_scores_gemma":[0.00004017401,0.00002353017,0.8759353,0.000009388193,0.007186271,5.158951e-7,0.00005444144,0.03352608,0.0004563013,0.08264272,0.0000119667,0.0001132752],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4838129,0.000006145529,0.5064443,0.00105552,0.0000509544,0.0001202111,0.0007325468,0.0001361237,0.007641261],"genre_scores_gemma":[0.9918908,0.000002608187,0.007741719,0.00004043418,0.0000224359,0.00000831799,0.00009224276,0.000009176497,0.0001922889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7045333,"threshold_uncertainty_score":0.9996204,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2276203798","doi":"","title":"Design effects for the weighted mean and total estimators under complex survey sampling","year":2006,"lang":"en","type":"article","venue":"Quality Engineering","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Statistics Canada","funders":"","keywords":"Estimator; Statistics; Sampling (signal processing); Weighted arithmetic mean; Mathematics; Survey research; Sampling design; Econometrics; Computer science; Psychology; Demography; Telecommunications; Sociology; Applied psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.2423895262211679,"gpt":0.3902083630001223,"spread":0.1478188367789544,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002852673,0.0001665178,0.0002411735,0.00005453396,0.0001513945,0.00007523859,0.00009369233,0.00007053692,0.000003713628],"category_scores_gemma":[0.0009995472,0.0001321827,0.00004733697,0.0001198943,0.00002825574,0.00005876854,0.00002712729,0.00009754262,0.000001133176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003779056,"about_ca_system_score_gemma":0.0000118059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003642792,"about_ca_topic_score_gemma":0.00003092144,"domain_scores_codex":[0.9989974,0.0001439715,0.0003139619,0.0001780198,0.0001424433,0.0002242411],"domain_scores_gemma":[0.9861484,0.01344288,0.00007701176,0.0002237946,0.00006931799,0.00003860813],"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":[0.000311529,0.0005146649,0.009325238,0.005140475,0.0007475454,0.00000365636,0.002491577,0.5050279,0.02730979,0.4220442,0.009339706,0.01774377],"study_design_scores_gemma":[0.0006040314,0.00005700609,0.1472156,0.0001201746,0.00005942164,0.000009761214,0.00003573785,0.7929826,0.006530828,0.05178824,0.00008673141,0.00050979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1738979,0.00007234204,0.8250809,0.00004684832,0.00008519588,0.000382994,0.00001384807,0.0004123769,0.00000756419],"genre_scores_gemma":[0.6470011,0.000001462817,0.352812,0.00001545277,0.00004478509,0.00005326563,0.00002495318,0.00003012282,0.00001686666],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4731032,"threshold_uncertainty_score":0.5390255,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2079857135","doi":"10.1016/j.zool.2005.10.002","title":"Filter-feeding dabbling ducks (Anas spp.) can actively select particles by size","year":2006,"lang":"en","type":"article","venue":"Zoology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Biology; Predation; Interspecific competition; Anas; Botany; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.05375368357893183,"gpt":0.3150422963113493,"spread":0.2612886127324175,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005033197,0.000153269,0.0002519678,0.00006503386,0.0001399146,0.0000395607,0.0001468645,0.0001375026,0.0001712705],"category_scores_gemma":[0.001076774,0.0001478695,0.00005366644,0.0001672692,0.00007238854,0.00007718357,0.00003906041,0.0001663798,0.00002934806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006097821,"about_ca_system_score_gemma":0.00003349836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007336822,"about_ca_topic_score_gemma":0.0002959561,"domain_scores_codex":[0.9988494,0.0001186737,0.0002996803,0.0002516838,0.0001203308,0.0003602262],"domain_scores_gemma":[0.9980723,0.001455778,0.0001434359,0.0002001382,0.00007894092,0.00004938355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002039848,0.0009542665,0.1371127,0.0002704336,0.0002191951,0.00005702246,0.002146122,0.0001608395,0.3677246,0.05412556,0.4157197,0.02130558],"study_design_scores_gemma":[0.0009112676,0.0002670568,0.0231113,0.00008385023,0.00009985221,0.00009148751,0.0003050191,0.002073532,0.4775437,0.4892997,0.005424333,0.0007888923],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9598435,0.00005861069,0.03542392,0.0007316671,0.0001269249,0.000139534,0.0000220496,0.0005971676,0.003056608],"genre_scores_gemma":[0.9655035,0.000005111005,0.03341982,0.0001292444,0.0001222979,0.00002923569,0.00001805848,0.00003046064,0.0007422668],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4351741,"threshold_uncertainty_score":0.6029945,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061337431","doi":"10.1080/01621459.2000.10474281","title":"Jackknife Variance Estimation under Imputation for Estimators Using Poststratification Information","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University; Statistics Canada","funders":"","keywords":"Jackknife resampling; Estimator; Statistics; Imputation (statistics); Mathematics; Weighting; Econometrics; Missing data","retraction":null,"screen_n_in":null,"score":{"opus":0.03967785128842156,"gpt":0.3694318726392187,"spread":0.3297540213507971,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001720962,0.0001351117,0.000304561,0.0001054202,0.0002142848,0.0001324901,0.0001740541,0.00006763786,0.00004094302],"category_scores_gemma":[0.004948184,0.0001058752,0.0001162723,0.0003627849,0.00006184535,0.0007034547,0.000009324329,0.0001783466,0.000009303857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006259481,"about_ca_system_score_gemma":0.0001590035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000557648,"about_ca_topic_score_gemma":0.000003055802,"domain_scores_codex":[0.997983,0.0002532016,0.0009214663,0.00009524191,0.0005550035,0.0001920363],"domain_scores_gemma":[0.9946814,0.002066616,0.002356651,0.0001539678,0.0006790932,0.00006225061],"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":[0.001078399,0.0005855127,0.008501122,0.0002854895,0.0005369393,0.000001272338,0.001978449,0.1324833,0.00187909,0.1608324,0.02749919,0.6643388],"study_design_scores_gemma":[0.000647723,0.0002706399,0.05774311,0.0001052742,0.000269986,0.00003504593,0.0001665956,0.3846382,0.000796358,0.5547248,0.0003537343,0.0002485141],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1995094,0.000003120371,0.7991226,0.0007901847,0.0001459471,0.0002542356,0.00007430896,0.00004163563,0.00005853648],"genre_scores_gemma":[0.5180125,0.000004159617,0.481631,0.0001924664,0.00007081398,0.000008675926,0.00002477655,0.00001279453,0.00004279703],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6640902,"threshold_uncertainty_score":0.5923796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2043586387","doi":"10.1139/f06-063","title":"Improving the precision of design-based scallop drag surveys using adaptive allocation methods","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Fisheries and Aquatic Sciences","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Stratified sampling; Scallop; Sampling design; Sampling (signal processing); Stratum; Population; Fishery; Boom; Variance (accounting); Sample size determination; Environmental science; Statistics; Computer science; Engineering; Mathematics; Biology; Environmental engineering; Filter (signal processing)","retraction":null,"screen_n_in":null,"score":{"opus":0.1693764944447455,"gpt":0.354224719654368,"spread":0.1848482252096225,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01000094,0.00007883534,0.0001776568,0.0001656731,0.0003350518,0.0001275547,0.0002016037,0.00003913066,0.00001401023],"category_scores_gemma":[0.002351434,0.00005050176,0.00004106233,0.0003183936,0.0004751571,0.0002010617,0.000006405479,0.00007262675,7.213972e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000415323,"about_ca_system_score_gemma":0.0008957988,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01738075,"about_ca_topic_score_gemma":0.004954776,"domain_scores_codex":[0.99849,0.0006652974,0.0004094108,0.00008824878,0.0002023896,0.0001445925],"domain_scores_gemma":[0.9968011,0.002416337,0.0004582639,0.000088742,0.0001540054,0.00008148616],"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":[0.00007865322,0.0001150143,0.07113938,0.0002122707,0.00009435541,0.00001587817,0.005505352,0.01315175,0.01517714,0.01188996,0.002945996,0.8796743],"study_design_scores_gemma":[0.0003595411,0.0007630095,0.01794816,0.0005524703,0.0001042379,0.00005871582,0.002322832,0.7134148,0.03332409,0.2307204,0.0001122804,0.000319399],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1914651,0.0001794297,0.807884,0.0002150771,0.00008392694,0.00008334887,0.000001317321,0.000004379646,0.00008340707],"genre_scores_gemma":[0.553485,0.000001408314,0.4464694,0.00001410296,0.00001794643,7.739878e-7,1.739918e-7,0.000003305394,0.00000795448],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8793548,"threshold_uncertainty_score":0.9891626,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1511896087","doi":"10.1002/0470867205.ch7","title":"Analysis of Categorical Response Data from Complex Surveys: An Appraisal and Update","year":2003,"lang":"en","type":"other","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Categorical variable; Logistic regression; Statistics; Binary data; Computer science; Sample (material); Log-linear model; Domain (mathematical analysis); Regression analysis; Data mining; Linear model; Mathematics; Econometrics; Binary number","retraction":null,"screen_n_in":null,"score":{"opus":0.3042676196341385,"gpt":0.4512353789808296,"spread":0.1469677593466911,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003647692,0.00024159,0.0008277392,0.0005734779,0.00002586173,0.00003866086,0.0004713882,0.0002857143,0.006128648],"category_scores_gemma":[0.001628454,0.0002071494,0.00006059607,0.0004661204,0.0001000787,0.00005743153,0.0001465017,0.0001248282,0.00001559905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001106281,"about_ca_system_score_gemma":0.00004309349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004773768,"about_ca_topic_score_gemma":0.002776591,"domain_scores_codex":[0.9969435,0.00171943,0.0004251327,0.0005141656,0.0002513138,0.0001464364],"domain_scores_gemma":[0.9953337,0.002441021,0.0003221557,0.001757793,0.000054181,0.00009116745],"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":[0.00008708152,0.0002530585,0.004076757,0.00005610418,0.00195438,0.000004119127,0.00007922547,0.000001511594,0.00004121811,0.002626152,0.9892182,0.001602225],"study_design_scores_gemma":[0.002099777,0.0003992436,0.1117554,0.0002248527,0.01291225,0.00001394914,0.0004807512,0.07895484,0.000311797,0.04254623,0.7464365,0.003864457],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00344882,0.0001963401,0.9330668,0.00006112619,0.0001284129,0.0002982436,0.006211888,0.0009694746,0.05561882],"genre_scores_gemma":[0.02619788,0.0002326233,0.8256921,0.0001404575,0.0001356272,0.00002137889,0.03147843,0.0008297189,0.1152718],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2427817,"threshold_uncertainty_score":0.9947799,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121049202","doi":"10.1007/s10342-005-0074-6","title":"Adaptive cluster sampling for estimation of deforestation rates","year":2005,"lang":"en","type":"article","venue":"European Journal of Forest Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"Government of Canada","keywords":"Statistics; Sample size determination; Sampling (signal processing); Estimator; Mean squared error; Cluster sampling; Efficiency; Population; Deforestation (computer science); Mathematics; Population size; Sample (material); Simple random sample; Sampling design; Econometrics; Computer science; Demography; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.346117542520027,"gpt":0.4815740246007563,"spread":0.1354564820807293,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0116831,0.00009427586,0.0002078339,0.0004286677,0.0001286321,0.00005041757,0.0002596176,0.00002867993,0.00001615687],"category_scores_gemma":[0.005140733,0.00007630615,0.0001083051,0.0002198189,0.0001020444,0.0002881452,0.00004266217,0.0002753789,0.00001131437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007483159,"about_ca_system_score_gemma":0.00008477996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004763007,"about_ca_topic_score_gemma":0.00001187769,"domain_scores_codex":[0.9977204,0.0006715347,0.0007476643,0.0001055347,0.0005261349,0.0002287339],"domain_scores_gemma":[0.9952319,0.002619317,0.0004662902,0.0001664804,0.001437883,0.00007814725],"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":[0.003478808,0.001069814,0.007525777,0.0009886593,0.0003346063,0.00002264868,0.009672112,0.1646773,0.002033195,0.08356556,0.03680135,0.6898302],"study_design_scores_gemma":[0.005856703,0.006661463,0.06240076,0.002838608,0.0001360864,0.0002265638,0.001662727,0.3186208,0.03787796,0.5575467,0.005471112,0.0007005641],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3442555,0.00005568327,0.6544144,0.0002308662,0.00003785987,0.0002220676,0.000006224265,0.00001966629,0.0007576913],"genre_scores_gemma":[0.6250743,0.00001158676,0.3746681,0.00000755986,0.0001393539,0.000003370973,0.000004364361,0.00002343538,0.00006797009],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6891297,"threshold_uncertainty_score":0.6154308,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135885901","doi":"","title":"On sample allocation for efficient domain estimation","year":2013,"lang":"en","type":"article","venue":"Quality Engineering","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Statistics; Sample (material); Estimator; Sample size determination; Population; Econometrics; Context (archaeology); Simple random sample; Stratified sampling; Stratum; Mathematics; Reliability (semiconductor); Estimation; Sampling design; Survey sampling; Aggregate (composite); Computer science; Geography; Economics; Engineering; Demography","retraction":null,"screen_n_in":null,"score":{"opus":0.08950316587032563,"gpt":0.3695666906709428,"spread":0.2800635248006171,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009272079,0.0001002533,0.0001290013,0.00007481929,0.00005519162,0.00004122989,0.00006959661,0.00005536194,0.00003120877],"category_scores_gemma":[0.003358305,0.00009847627,0.00004765718,0.00008263099,0.000006789488,0.00005493127,0.000009020659,0.00005684617,0.00002573453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006844961,"about_ca_system_score_gemma":0.000007892781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001012777,"about_ca_topic_score_gemma":0.000001483897,"domain_scores_codex":[0.9992729,0.00002935425,0.0002747025,0.000134838,0.0001404031,0.0001477991],"domain_scores_gemma":[0.9972758,0.002318313,0.00006933497,0.0002132244,0.00008293116,0.00004034579],"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":[0.00001206308,0.0001336829,0.00003925019,0.0004501646,0.00002308542,5.244466e-8,0.0008020814,0.1580592,0.003214797,0.8231781,0.002211433,0.0118761],"study_design_scores_gemma":[0.0001983781,0.00004296486,0.0009503398,0.00006997654,0.000005271735,4.311441e-7,0.00003979657,0.6913927,0.005836907,0.3011352,0.0001454685,0.000182539],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2808356,0.000002695196,0.7181526,0.0001288385,0.00007180384,0.0003476675,0.000008606806,0.000399358,0.00005288193],"genre_scores_gemma":[0.5444871,1.953038e-7,0.4551944,0.00002357051,0.00002230007,0.0002117273,0.00003020745,0.00001538312,0.00001509688],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5333335,"threshold_uncertainty_score":0.4020448,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174992558","doi":"10.3389/fpsyg.2021.655592","title":"Functionality of the Crosswise Model for Assessing Sensitive or Transgressive Behavior: A Systematic Review and Meta-Analysis","year":2021,"lang":"en","type":"review","venue":"Frontiers in Psychology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"World Anti-Doping Agency","keywords":"Meta-analysis; Psychology; Transgressive; Empirical research; Population; Systematic review; Misconduct; Warrant; Protocol (science); Statistics; Econometrics; Social psychology; Mathematics; MEDLINE; Demography; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.4327622624312232,"gpt":0.5249382097685608,"spread":0.09217594733733753,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002582028,0.0003743571,0.007913406,0.0002777247,0.00008121831,0.00002944558,0.0002647121,0.0003750842,0.00002133129],"category_scores_gemma":[0.001442121,0.0002099691,0.002346719,0.0008230887,0.0001761399,0.00005884179,0.00004023269,0.0003141084,1.578757e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006044565,"about_ca_system_score_gemma":0.0001562284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000041853,"about_ca_topic_score_gemma":0.00001450238,"domain_scores_codex":[0.9959091,0.001593125,0.001574165,0.0005348298,0.0001955226,0.0001932751],"domain_scores_gemma":[0.9961222,0.001252572,0.001423681,0.0008823326,0.0002829026,0.00003629794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.000008160138,0.0001870693,0.000007323434,0.9307951,0.0564204,0.000005377173,0.0001759889,0.000003712748,3.002934e-8,0.000236516,0.005126015,0.007034295],"study_design_scores_gemma":[0.0001222935,0.00001287136,0.000002229794,0.03132898,0.9611009,0.00005278751,0.00004460637,0.0003876043,3.313922e-7,0.006032811,0.0006391987,0.0002754322],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[2.584362e-7,0.5873677,0.4102134,0.00004405054,0.00009309511,0.00192825,0.0003225461,0.00001754753,0.00001311124],"genre_scores_gemma":[0.000005766788,0.8688332,0.1282796,0.0002062074,0.000006874398,0.002313521,0.0000765595,0.00003751888,0.0002407975],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9046804,"threshold_uncertainty_score":0.856229,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2188992153","doi":"","title":"Simulation-based randomized systematic PPS sampling under substitution of units","year":2008,"lang":"en","type":"article","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Substitution (logic); Computer science; Sampling (signal processing); Econometrics; Statistics; Mathematics; Filter (signal processing)","retraction":null,"screen_n_in":null,"score":{"opus":0.2725552137362245,"gpt":0.3808668996483965,"spread":0.108311685912172,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001781396,0.0001333256,0.0006601536,0.0001700739,0.0001213392,0.00001124003,0.00009730265,0.00008763445,0.00006827101],"category_scores_gemma":[0.01134331,0.0001014638,0.0001127637,0.000336851,0.0001213212,0.0000808661,0.000009992449,0.00006603661,0.00001142007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003948942,"about_ca_system_score_gemma":0.00009661162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004559204,"about_ca_topic_score_gemma":0.000004347838,"domain_scores_codex":[0.9983768,0.0003278929,0.000758605,0.0001298827,0.0002838271,0.0001229581],"domain_scores_gemma":[0.9832842,0.01556802,0.000331921,0.0002932581,0.000483473,0.00003912457],"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":[0.002361472,0.0002292864,0.0003798417,0.01237497,0.0001718008,0.000001809555,0.0007186987,0.7636365,0.0002593551,0.2197502,0.00008399626,0.00003203979],"study_design_scores_gemma":[0.02226167,0.00002521261,0.00006091055,0.002491748,0.0001607843,0.00000385098,0.0001004571,0.8903996,0.006559209,0.07766095,0.000003504866,0.0002720533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1139541,0.00004755347,0.8843165,0.00001923349,0.00005420925,0.0007181088,0.000002993053,0.0003820731,0.000505179],"genre_scores_gemma":[0.9075334,0.000003334728,0.09220254,0.00003552185,0.00001288695,0.00004925653,0.0000157745,0.00001529661,0.0001319964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7935793,"threshold_uncertainty_score":0.9969845,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2792032639","doi":"10.1177/0049124117747302","title":"Optimizing Count Responses in Surveys: A Machine-learning Approach","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Social Science Research Institute, Duke University; University of British Columbia; University of Victoria","keywords":"Censoring (clinical trials); Count data; Poisson distribution; Computer science; Bayesian probability; Multinomial distribution; Machine learning; Statistics; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.6338353326777821,"gpt":0.602291176727981,"spread":0.03154415594980109,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1261021,0.0001904357,0.0004656975,0.0003745437,0.0005024675,0.00008879659,0.0004856974,0.0004130476,0.0002064663],"category_scores_gemma":[0.05589541,0.0001430688,0.00009891347,0.0008085016,0.000969517,0.00008159902,0.0003317444,0.001772408,0.00004022306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000191631,"about_ca_system_score_gemma":0.00009760294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002810711,"about_ca_topic_score_gemma":0.00001158774,"domain_scores_codex":[0.955602,0.04200788,0.0004989511,0.0005541374,0.0005520859,0.0007849384],"domain_scores_gemma":[0.9716456,0.02725698,0.00009520695,0.0003874686,0.0004944387,0.0001202895],"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":[0.002355199,0.003171595,0.1410369,0.000897144,0.0003104213,0.0001102425,0.05720783,0.0002073723,0.0311086,0.2061031,0.004343772,0.5531478],"study_design_scores_gemma":[0.0007691116,0.001309059,0.01869172,0.0001479116,0.00001117462,0.00002038859,0.003937999,0.04373372,0.006092307,0.9214723,0.003159029,0.0006553271],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.19576,0.0003434719,0.7935063,0.0002308245,0.0000624135,0.0004630191,0.000006438911,0.0004840971,0.00914351],"genre_scores_gemma":[0.2974737,0.00006040674,0.7017583,0.00002837145,0.000109146,0.0001304164,0.000007948908,0.00002433994,0.0004073707],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7153691,"threshold_uncertainty_score":0.9520572,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1535801153","doi":"10.6092/issn.1973-2201/1118","title":"Regression type estimators for random non-response in survey sampling","year":2013,"lang":"en","type":"article","venue":"Università degli Studi di Bologna","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Estimator; Statistics; Mathematics; Mean squared error; Population mean; Estimation; Simple random sample; Sampling (signal processing); Regression analysis; Population; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1240701557875457,"gpt":0.3648473016630667,"spread":0.2407771458755209,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00196552,0.0002130628,0.0004121341,0.0002903542,0.0002114788,0.00003432711,0.0002424667,0.0001649154,0.00005745927],"category_scores_gemma":[0.004660191,0.0001881366,0.0000789045,0.0003798378,0.00007407035,0.0001861758,0.0001162974,0.0001575184,0.00004001683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001254067,"about_ca_system_score_gemma":0.00007165755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003893432,"about_ca_topic_score_gemma":0.00007686207,"domain_scores_codex":[0.9985459,0.0003491196,0.0003022206,0.0003120205,0.0001547136,0.0003360627],"domain_scores_gemma":[0.9934455,0.005673715,0.0001596109,0.0003024182,0.0003388246,0.00007998137],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.02172448,0.001437827,0.8484682,0.0004802603,0.0004800324,0.00005721143,0.008161875,0.001285968,0.006017583,0.005991444,0.09041622,0.01547889],"study_design_scores_gemma":[0.01303493,0.001341422,0.9112442,0.0008902628,0.0001564121,0.0000139521,0.002812034,0.01977329,0.003825661,0.04355112,0.001794626,0.001562119],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9005959,0.00004326953,0.0977264,0.0001000668,0.0001911786,0.0007993807,0.00002094211,0.0002230716,0.0002997641],"genre_scores_gemma":[0.9534552,0.00001653766,0.04575325,0.00003546912,0.00002011116,0.00003094709,0.00003596638,0.00003122988,0.0006212703],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08862159,"threshold_uncertainty_score":0.7671989,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2048495621","doi":"10.1081/sta-200026577","title":"Estimating Function Jackknife Variance Estimators Under Stratified Multistage Sampling","year":2004,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; Carleton University","funders":"","keywords":"Jackknife resampling; Estimator; Mathematics; Statistics; Resampling; Consistency (knowledge bases); Population; Variance (accounting); Sampling (signal processing); Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1651102996378727,"gpt":0.4869650309381574,"spread":0.3218547313002846,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008594423,0.0002168153,0.0003232891,0.0001525314,0.000371052,0.0001111556,0.0002606578,0.0001525901,0.00004663933],"category_scores_gemma":[0.006292435,0.0002248376,0.00003083121,0.0002383517,0.0002299595,0.0002148796,0.0001076149,0.000416286,0.00000483495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009798806,"about_ca_system_score_gemma":0.00007212436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008486614,"about_ca_topic_score_gemma":0.00003730641,"domain_scores_codex":[0.9967474,0.001916653,0.000666705,0.000291925,0.0001446424,0.0002326875],"domain_scores_gemma":[0.9902505,0.008463891,0.000320002,0.0007462368,0.0001374755,0.00008191166],"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":[0.0000645418,0.00008027142,0.0001181586,0.0001165194,0.00001942931,6.794542e-7,0.001083725,0.003505096,0.0004168635,0.9408812,0.00002853866,0.05368496],"study_design_scores_gemma":[0.0005322266,0.00003930082,0.002837854,0.0002959374,0.00003870857,0.000008814364,0.0004215551,0.01127658,0.0005691118,0.9836768,0.00006639734,0.0002367064],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007887201,0.000293571,0.9904574,0.00007512327,0.0001753479,0.0003011329,0.00003575936,0.0002638515,0.0005106789],"genre_scores_gemma":[0.2095673,0.00004068496,0.7900683,0.00009450455,0.00001914671,0.00007146263,0.00004897096,0.0000299766,0.00005966877],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.20168,"threshold_uncertainty_score":0.9168613,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159217576","doi":"10.5705/ss.2011.024a","title":"On variance estimation under auxiliary value imputation in sample surveys","year":2011,"lang":"en","type":"article","venue":"Statistica Sinica","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Statistics; Imputation (statistics); Variance (accounting); Estimation; Value (mathematics); Econometrics; Sample (material); Mathematics; Missing data; Economics; Accounting","retraction":null,"screen_n_in":null,"score":{"opus":0.1502522325956184,"gpt":0.3878844082013983,"spread":0.2376321756057799,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002526857,0.0001776678,0.0002577647,0.0001590282,0.00008571764,0.0000315125,0.0001543426,0.0001136183,0.0003962509],"category_scores_gemma":[0.007776434,0.0001774348,0.0000381077,0.0002624391,0.00007737227,0.0001359068,0.0000289016,0.000194275,0.00008443012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009502571,"about_ca_system_score_gemma":0.00009014354,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007602309,"about_ca_topic_score_gemma":0.00009886297,"domain_scores_codex":[0.9979504,0.0006635654,0.0005495725,0.0003240465,0.0002560024,0.0002564316],"domain_scores_gemma":[0.9923103,0.006961266,0.0001893844,0.0003712036,0.00009666755,0.00007119167],"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":[0.00006217029,0.0003664655,0.000736568,0.00006730012,0.00002018537,0.000007021419,0.0008267007,0.0006252352,0.00001493799,0.9628624,0.002110025,0.03230096],"study_design_scores_gemma":[0.0002963548,0.0001400924,0.06935138,0.00008229098,0.00001434429,0.000002253679,0.00002964838,0.03657145,0.0001806577,0.8931369,0.00001033721,0.0001843338],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01033049,0.000005136188,0.9846942,0.00007412928,0.0001473811,0.0002743106,0.0001656553,0.0002938898,0.004014767],"genre_scores_gemma":[0.5342607,0.000003350389,0.4654927,0.00007476491,0.000009857053,0.00003012281,0.00007640255,0.00002204172,0.00003010004],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5239302,"threshold_uncertainty_score":0.930968,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1999617781","doi":"10.1577/m06-293.1","title":"Evaluation of Sampling Designs for Red Sea Urchins Strongylocentrotus franciscanus in British Columbia","year":2008,"lang":"en","type":"article","venue":"North American Journal of Fisheries Management","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Quadrat; Transect; Sampling (signal processing); Environmental science; Distance sampling; Statistics; Cluster sampling; Sampling design; Oceanography; Ecology; Mathematics; Biology; Geology; Computer science; Population; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.1448837546196176,"gpt":0.3330629434748082,"spread":0.1881791888551906,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002341484,0.0001031728,0.0004517818,0.0001385176,0.0001045064,0.00005470604,0.0002108854,0.00002267158,0.00005080721],"category_scores_gemma":[0.0007206281,0.0001469835,0.0001266167,0.0003277166,0.0001492049,0.0001580831,0.00002902283,0.0001270889,1.85606e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001882741,"about_ca_system_score_gemma":0.0001096029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001643894,"about_ca_topic_score_gemma":0.01195091,"domain_scores_codex":[0.9978001,0.0002113408,0.0008216925,0.0001496933,0.0007819972,0.0002352098],"domain_scores_gemma":[0.9978481,0.0002550136,0.0009324211,0.0001936523,0.0007010612,0.00006975717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001096169,0.0002841016,0.547258,0.0001479893,0.0002225875,0.00001768729,0.0006348909,0.002186805,0.000004705531,0.00001397247,0.005948436,0.4431712],"study_design_scores_gemma":[0.001604984,0.0007627704,0.9865565,0.0002087996,0.000254592,0.0000553874,0.0009137469,0.002524415,0.0000345132,0.006140744,0.0007162789,0.0002272325],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8339805,0.0000355731,0.1650744,0.00004611792,0.00008572164,0.0005261628,0.00002393535,0.0000249212,0.0002026276],"genre_scores_gemma":[0.8128556,0.00007642994,0.1868984,0.00002131396,0.00003926459,0.0000459823,0.000008948962,0.00002053785,0.00003357908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4429439,"threshold_uncertainty_score":0.6668888,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134587091","doi":"10.2307/3316078","title":"Variance estimation for the finite population distribution function with complete auxiliary information","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"Simon Fraser University; University of Waterloo","funders":"","keywords":"Jackknife resampling; Estimator; Consistency (knowledge bases); Statistics; Variance (accounting); Mathematics; Population; Population variance; Sample (material); Econometrics; Applied mathematics; Computer science; Discrete mathematics; Demography","retraction":null,"screen_n_in":null,"score":{"opus":0.06617314236239594,"gpt":0.2869820243308996,"spread":0.2208088819685037,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007415807,0.00009567239,0.0001352703,0.0001102175,0.0003286607,0.0001152765,0.00009893586,0.0000525678,0.00002819781],"category_scores_gemma":[0.001919759,0.00007024293,0.00003017502,0.0001770164,0.00004400309,0.0004567385,0.00000250124,0.0001253394,0.000003554122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001697932,"about_ca_system_score_gemma":0.0002518083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001313556,"about_ca_topic_score_gemma":0.003413707,"domain_scores_codex":[0.9991285,0.00004270544,0.0004435676,0.00005089693,0.0001769592,0.0001574097],"domain_scores_gemma":[0.9974539,0.001122739,0.0005039949,0.0001239307,0.0006761542,0.0001193072],"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":[0.0007296446,0.0000524505,0.01689719,0.0003535908,0.000253195,0.00001950696,0.001367397,0.08319321,0.000007936567,0.4616289,0.09558755,0.3399094],"study_design_scores_gemma":[0.001141023,0.0006575186,0.1061196,0.0002748418,0.0003456858,0.0002163773,0.0002542086,0.4463851,0.00001617473,0.3994758,0.04478154,0.0003321694],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002544947,0.00002407385,0.9957545,0.0003400923,0.0002498976,0.0002448684,0.0007853165,0.00002081654,0.00003549569],"genre_scores_gemma":[0.7457036,0.0000129992,0.2531875,0.0001173977,0.00009351051,0.00001442663,0.000826121,0.00001249797,0.00003195288],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7431586,"threshold_uncertainty_score":0.2864423,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042186389","doi":"10.1191/1471082x06st121oa","title":"Modelling repeated ordinal reports from multiple informants","year":2006,"lang":"en","type":"article","venue":"Statistical Modelling","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Université de Montréal","funders":"Economic and Social Research Council","keywords":"Multivariate statistics; Psychology; Multilevel model; Random effects model; Aggression; Continuation; Ordinal regression; Multivariate analysis; Mathematics; Longitudinal data; Demography; Repeated measures design; Generalized linear model; Statistics; Developmental psychology; Econometrics; Medicine; Computer science; Meta-analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.1125577140103702,"gpt":0.3249784066077078,"spread":0.2124206925973376,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006002291,0.0002258848,0.0003344255,0.00009378857,0.0001879756,0.00009110993,0.0001047865,0.0001381426,0.000102258],"category_scores_gemma":[0.0004179021,0.000217181,0.00006225141,0.0001330756,0.00005973502,0.0001787508,0.0000423434,0.000248524,0.00002752619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005722988,"about_ca_system_score_gemma":0.00003926958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004329609,"about_ca_topic_score_gemma":0.00002975733,"domain_scores_codex":[0.9979057,0.00005909886,0.0008867746,0.0003829113,0.0003891384,0.0003763822],"domain_scores_gemma":[0.9975485,0.001544785,0.0002277314,0.0003993228,0.0001772513,0.0001023825],"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":[0.00005936948,0.0001085234,0.001258812,0.00005008452,0.00002545537,0.00009321272,0.0001480532,0.952279,0.00005753896,0.04262565,0.00196006,0.001334293],"study_design_scores_gemma":[0.0001006868,0.00001202138,0.00002401394,0.00004976186,0.00002007626,0.00000827669,0.00001060218,0.573535,0.0003481487,0.4255992,0.0001367947,0.0001554518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1196241,0.00002570236,0.8775758,0.00001338802,0.0001108145,0.0001681685,0.0001176308,0.0005831733,0.001781222],"genre_scores_gemma":[0.5248088,0.000003684076,0.4747592,0.00001044717,0.00007250979,0.00001308555,0.0002194103,0.00002597025,0.00008688525],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4051847,"threshold_uncertainty_score":0.8856384,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096274285","doi":"10.2307/3315854","title":"On quasi‐likelihood inference in generalized linear mixed models with two components of dispersion","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Mathematics; Statistics; Estimator; Quasi-maximum likelihood; Generalized linear model; Dispersion (optics); Variance components; Generalized linear mixed model; Maximum likelihood; Mixed model; Applied mathematics; Likelihood function; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.103847777655825,"gpt":0.3234960585517568,"spread":0.2196482808959318,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005824628,0.0001106699,0.0002900997,0.0002899407,0.00004321147,0.00001550217,0.000118233,0.00004478297,0.00003734846],"category_scores_gemma":[0.001299563,0.00009265215,0.000026405,0.0001473425,0.00005934892,0.0000680174,0.000002905758,0.0001846067,0.000001332547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001117418,"about_ca_system_score_gemma":0.0004930106,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003371548,"about_ca_topic_score_gemma":0.01460337,"domain_scores_codex":[0.9989085,0.0001462953,0.000466491,0.00007730955,0.0002114041,0.0001900031],"domain_scores_gemma":[0.9982952,0.0006806621,0.0003213249,0.0001353963,0.0003210632,0.0002463132],"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":[0.0002179179,0.0003722173,0.01834113,0.00021955,0.0001046754,0.000268257,0.002473043,0.02667931,0.0002791032,0.9426416,0.003958654,0.004444614],"study_design_scores_gemma":[0.002691998,0.0008416085,0.002037637,0.001007609,0.00006189179,0.00005050032,0.0002417568,0.05198482,0.001870259,0.9387286,0.0001474718,0.0003358207],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4100065,0.00002449548,0.5895357,0.00002007507,0.00006723007,0.00006697058,0.0001258603,0.000004535434,0.0001487086],"genre_scores_gemma":[0.6818112,0.0000112058,0.3181182,0.00002167066,0.000006570724,8.285451e-7,0.000008761873,0.0000120239,0.000009569264],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2718047,"threshold_uncertainty_score":0.8149022,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3025393907","doi":"10.1017/psrm.2020.18","title":"Placebo statements in list experiments: Evidence from a face-to-face survey in Singapore","year":2020,"lang":"en","type":"article","venue":"Political Science Research and Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Treatment and control groups; Face (sociological concept); Psychology; Placebo; Inflation (cosmology); Interpretation (philosophy); Statement (logic); Survey data collection; Social psychology; Econometrics; Actuarial science; Statistics; Computer science; Economics; Medicine; Sociology; Political science; Alternative medicine; Mathematics; Social science","retraction":null,"screen_n_in":null,"score":{"opus":0.7576034810771761,"gpt":0.6772032127523472,"spread":0.08040026832482894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02698747,0.0001175288,0.000256887,0.0002882396,0.0001402637,0.0002028831,0.0004858776,0.00005811231,0.00004912437],"category_scores_gemma":[0.08303034,0.0001015385,0.00001374878,0.001635409,0.0006014148,0.0004009557,0.000439959,0.0003770988,0.00001184621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002956979,"about_ca_system_score_gemma":0.0003007977,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01154804,"about_ca_topic_score_gemma":0.0002961939,"domain_scores_codex":[0.994758,0.002222027,0.000390425,0.0005750349,0.0008584583,0.001196016],"domain_scores_gemma":[0.9887938,0.009783581,0.00002878648,0.0002456022,0.000192559,0.0009555919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001808619,0.001379406,0.5460016,0.0005100414,0.00002911117,0.0001124207,0.04164416,0.00004405853,0.1907691,0.1348323,0.001976907,0.08089229],"study_design_scores_gemma":[0.001082334,0.0008984194,0.2734185,0.001016607,0.000003610393,0.000002410098,0.005431377,0.02003367,0.2822681,0.415054,0.000174991,0.0006160445],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8349637,0.00007879937,0.161494,0.002470804,0.00002862318,0.0004904058,0.00002811441,0.00005268044,0.0003928299],"genre_scores_gemma":[0.7316325,0.00001478529,0.2681306,0.0001193833,0.00001487617,0.00005181131,0.000002088133,0.000007563238,0.00002643237],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2802217,"threshold_uncertainty_score":0.9950342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2024395005","doi":"10.1007/s00338-004-0377-y","title":"Has random sampling been neglected in coral reef faunal surveys?","year":2004,"lang":"en","type":"article","venue":"Coral Reefs","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Coral reef; Coral; Reef; Oceanography; Sampling (signal processing); Fishery; Cnidaria; Geography; Ecology; Geology; Environmental science; Biology; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2515569302831572,"gpt":0.3873813148324256,"spread":0.1358243845492684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001569249,0.0002443347,0.0004692161,0.0002285547,0.0001702522,0.0001200802,0.0002818975,0.0001898619,0.00007385925],"category_scores_gemma":[0.003089562,0.0002356823,0.0001140598,0.0005357402,0.0001140455,0.0001784352,0.00007313021,0.0003652873,0.00006764211],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001890445,"about_ca_system_score_gemma":0.0001359601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000979238,"about_ca_topic_score_gemma":0.0006475254,"domain_scores_codex":[0.9979628,0.0003417017,0.0005925952,0.0003459702,0.0003228979,0.0004340229],"domain_scores_gemma":[0.9982218,0.0008903799,0.0001809786,0.0004197273,0.0001719358,0.0001152274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.005533494,0.005563734,0.4948469,0.001699109,0.0005963754,0.0006420636,0.01378079,0.006603271,0.03788955,0.1202044,0.02991395,0.2827264],"study_design_scores_gemma":[0.01062756,0.000471819,0.2650332,0.001017661,0.00006258931,0.00006141362,0.0001652828,0.002617066,0.008713504,0.7088031,0.001193981,0.001232857],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5853269,0.00008283232,0.4126037,0.0002481927,0.0002020595,0.0003673942,0.00002228989,0.000572147,0.0005744965],"genre_scores_gemma":[0.9311887,0.0000134731,0.06829223,0.00007353226,0.00009026637,0.00003736588,0.00007828718,0.00004635198,0.0001797951],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5885987,"threshold_uncertainty_score":0.9610845,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1926189568","doi":"10.1111/j.1467-9574.2012.00524.x","title":"A true simulation study of three estimators at equal protection of respondents in randomized response sampling","year":2012,"lang":"en","type":"article","venue":"Statistica Neerlandica","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Stephen's University","funders":"","keywords":"Estimator; Randomized response; Statistics; Mathematics; Sampling (signal processing); Econometrics; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2050738640456224,"gpt":0.4267861853967717,"spread":0.2217123213511492,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006354621,0.0001629938,0.0007092667,0.0004452363,0.00006629925,0.000009548156,0.0001045309,0.00009853977,0.00007832158],"category_scores_gemma":[0.01717331,0.0001425145,0.00006550127,0.0003277315,0.00007791023,0.0001045063,0.00005321619,0.0001348726,0.000004681786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001011326,"about_ca_system_score_gemma":0.00004033871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002724669,"about_ca_topic_score_gemma":0.00009985892,"domain_scores_codex":[0.9970082,0.001107525,0.001003735,0.0001767257,0.0004633798,0.0002404385],"domain_scores_gemma":[0.9889137,0.01007263,0.0005368903,0.0002939161,0.0001131513,0.00006973173],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.7430341,0.007446895,0.1400001,0.00141088,0.0005754548,0.00001341355,0.04866882,0.01476751,0.007791858,0.0212627,0.0001505208,0.0148777],"study_design_scores_gemma":[0.1743326,0.002667914,0.2799138,0.001052386,0.0006194005,0.0000152849,0.001529712,0.2976586,0.00556825,0.2355046,0.00004066058,0.001096847],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5536481,0.00001156922,0.4452966,0.000005141048,0.00004667889,0.0008910361,0.00003078453,0.00005214749,0.00001794812],"genre_scores_gemma":[0.947091,0.00000103754,0.05268116,0.000001894623,0.00001524147,0.0001506644,0.00001188206,0.00002604955,0.00002109329],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5687015,"threshold_uncertainty_score":0.9911054,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165564908","doi":"10.1016/j.jmva.2007.08.005","title":"Confidence intervals for marginal parameters under fractional linear regression imputation for missing data","year":2007,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Health Information; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Mathematics; Statistics; Confidence interval; Missing data; Imputation (statistics); Estimator; Quantile; Linear regression; Sample size determination; Asymptotic distribution; Empirical likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.2789950480778123,"gpt":0.4912235056502935,"spread":0.2122284575724812,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006306276,0.0001328667,0.0004325719,0.0005056121,0.0001427273,0.00006650383,0.0002884103,0.0001055369,0.00002112189],"category_scores_gemma":[0.004678964,0.0001027487,0.0003394573,0.0003262531,0.00002821221,0.0004176998,0.0000353135,0.0001507796,5.947879e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008711018,"about_ca_system_score_gemma":0.00006996052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005544761,"about_ca_topic_score_gemma":0.00001852292,"domain_scores_codex":[0.9982908,0.00009650558,0.0009166892,0.0001962252,0.0003203429,0.0001793772],"domain_scores_gemma":[0.9922902,0.005181833,0.001331083,0.0002850838,0.0008247918,0.00008700295],"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":[0.02549402,0.005678051,0.01631043,0.002711527,0.05589212,0.0001353697,0.008865993,0.1956446,0.08626926,0.06735052,0.05087956,0.4847686],"study_design_scores_gemma":[0.001546945,0.0002490796,0.004168421,0.0003760666,0.003476455,0.00004192742,0.0004511407,0.749907,0.009831808,0.2290054,0.0006491371,0.0002967058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02546611,0.00003861603,0.9736031,0.0005061772,0.0001413746,0.0001619522,0.00004528595,0.0000275335,0.000009894011],"genre_scores_gemma":[0.3652187,0.000007138767,0.6344638,0.00005815446,0.0001206161,0.000002562692,0.0000764911,0.00001283074,0.00003973651],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5542623,"threshold_uncertainty_score":0.5601495,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}