{"meta":{"query_hash":"141638cbfe58","filters":{"venue":"Survey methodology"},"cohort_total":26,"direct_labels_cover":0,"predictions_cover":26,"exported":26,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/141638cbfe58","api":"https://metacan.xera.ac/api/v1/cohort?venue=Survey+methodology"},"results":[{"id":"W1638540087","doi":"","title":"An Optimal Calibration Distance Leading to the Optimal Regresion Estimator","year":2005,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Estimator; Statistics; Mathematics; Calibration; Population; Optimal design; Best linear unbiased prediction; Population mean; Sampling (signal processing); Mean squared error; Computer science; Artificial intelligence; Medicine","score_opus":0.41918027327533336,"score_gpt":0.491450805124762,"score_spread":0.07227053184942867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1638540087","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17895456,0.00004657427,0.81903994,0.0009213587,0.00021478209,0.00027903638,0.000041020907,0.00037462995,0.00012812563],"genre_scores_gemma":[0.28185463,0.0000037562345,0.71736777,0.000222344,0.00017376032,0.000051298863,0.00006346089,0.000037057078,0.00022591522],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99234873,0.006076774,0.0005039181,0.0004415197,0.00023907493,0.00038998554],"domain_scores_gemma":[0.9900575,0.008728982,0.00018647156,0.0007124611,0.0001751587,0.00013941168],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017714733,0.00022278517,0.00039517556,0.00012888697,0.00030719937,0.00007902084,0.00045644448,0.00018179805,0.00011564887],"category_scores_gemma":[0.013150932,0.00016716975,0.00006509746,0.00034382244,0.000087985754,0.0002708258,0.00007385889,0.00025804434,0.000057827605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050262557,0.0012365459,0.031957522,0.00028710294,0.00030598746,0.000030415062,0.016649876,0.26217192,0.031002866,0.11660794,0.15951927,0.37520427],"study_design_scores_gemma":[0.0016460385,0.001944367,0.09091369,0.0002852721,0.00018558718,0.00021978072,0.0010567972,0.5962316,0.23040624,0.04052959,0.033639006,0.0029420792],"about_ca_topic_score_codex":0.00017766484,"about_ca_topic_score_gemma":0.0005922868,"teacher_disagreement_score":0.3722622,"about_ca_system_score_codex":0.000073033676,"about_ca_system_score_gemma":0.000057449386,"threshold_uncertainty_score":0.9951617},"labels":[],"label_agreement":null},{"id":"W20740463","doi":"","title":"Contact and cooperation in the Belgian fertility and family survey","year":2004,"lang":"en","type":"article","venue":"Survey methodology","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Vlaamse regering; Fonds Wetenschappelijk Onderzoek","keywords":"Fertility; Demographic economics; Geography; Demography; Sociology; Economics; Population","score_opus":0.6166600698174581,"score_gpt":0.48772756477543583,"score_spread":0.1289325050420223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W20740463","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9133794,0.00035388465,0.0853711,0.00039083228,0.0001646951,0.00014662185,0.00003543133,0.000010107093,0.0001479522],"genre_scores_gemma":[0.99582666,0.00006435641,0.0035183881,0.0005191528,0.000006313866,0.0000071382965,0.000036366822,0.0000046505693,0.000016948477],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.977358,0.02101287,0.0005553604,0.0004944081,0.00036217293,0.00021721312],"domain_scores_gemma":[0.9806264,0.018636905,0.000105958556,0.00032449263,0.00025639296,0.000049863636],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.09329619,0.00010697808,0.00030004318,0.0001682756,0.00014257636,0.00012846259,0.00022812099,0.00011652105,0.000010048241],"category_scores_gemma":[0.0232849,0.00006662874,0.000023443967,0.00067568634,0.00015006655,0.00014824948,0.00004574436,0.00017347938,0.0000075563025],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037918708,0.000049124723,0.963692,0.0000029441674,0.0000094126535,0.000003682226,0.0024171553,0.00037926293,0.0011151881,0.0018824848,0.00005276868,0.030016752],"study_design_scores_gemma":[0.00044220546,0.00008693066,0.9773788,0.0000026789912,0.000003203098,0.000004520469,0.0006210139,0.00069207296,0.000018303292,0.020642485,0.00003493811,0.00007284469],"about_ca_topic_score_codex":0.016808746,"about_ca_topic_score_gemma":0.06845113,"teacher_disagreement_score":0.08244731,"about_ca_system_score_codex":0.000010806783,"about_ca_system_score_gemma":0.00005512547,"threshold_uncertainty_score":0.9897384},"labels":[],"label_agreement":null},{"id":"W2133470535","doi":"","title":"A multivariate technique for multiply imputing missing values using a sequence of regression models","year":2001,"lang":"en","type":"article","venue":"Survey methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1995,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Missing data; Imputation (statistics); Statistics; Mathematics; Logistic regression; Multivariate statistics; Regression analysis; Regression; Computer science","score_opus":0.6952655713588801,"score_gpt":0.5554953450934195,"score_spread":0.13977022626546065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133470535","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017336449,0.000045475772,0.9815258,0.000026179896,0.00017659806,0.00061998423,0.000116021925,0.000057930443,0.00009557391],"genre_scores_gemma":[0.058593888,0.000006914779,0.94122446,0.000027912785,0.00004685922,0.000036888217,0.000008265373,0.00003867888,0.00001616592],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9910111,0.007218135,0.0007354728,0.00043423867,0.00015610056,0.0004449659],"domain_scores_gemma":[0.95468116,0.043969534,0.00049348804,0.0003654598,0.0004039466,0.000086404674],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017313741,0.00023206294,0.0007861007,0.00014981287,0.00014652923,0.000014988832,0.00024380603,0.00026382186,0.000019021987],"category_scores_gemma":[0.053226694,0.00018803078,0.00011697168,0.00029961238,0.0001884152,0.0000966208,0.000111163856,0.0002104684,3.008097e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005854881,0.000110426605,0.0017024156,0.00034943258,0.000061609826,0.00001554044,0.0008114954,0.00009653245,0.8243917,0.08490388,0.000019041938,0.08695244],"study_design_scores_gemma":[0.0003547673,0.00009055543,0.00076419796,0.0002566096,0.00003887838,0.000051393014,0.000047318405,0.1433366,0.03906141,0.8158058,0.000003571666,0.00018892862],"about_ca_topic_score_codex":0.00109249,"about_ca_topic_score_gemma":0.000022958082,"teacher_disagreement_score":0.7853303,"about_ca_system_score_codex":0.000051364485,"about_ca_system_score_gemma":0.000113484704,"threshold_uncertainty_score":0.9547484},"labels":[],"label_agreement":null},{"id":"W2136733697","doi":"","title":"Estimating agreement coefficients from sample survey data","year":2012,"lang":"en","type":"article","venue":"Survey methodology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Jackknife resampling; Statistics; Concordance; Mathematics; Cohen's kappa; Standard error; Correlation coefficient; Variance (accounting); Sampling (signal processing); Sample (material); Concordance correlation coefficient; Linearization; Computer science; Medicine; Nonlinear system; Accounting","score_opus":0.8726461020763974,"score_gpt":0.5551506380714631,"score_spread":0.3174954640049342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136733697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35562626,0.0002874872,0.6363247,0.00010997421,0.0046165916,0.00026945854,0.0024579326,0.00003000024,0.000277561],"genre_scores_gemma":[0.6076887,0.0000056937197,0.38948977,0.00039872422,0.00033315687,0.000011128115,0.0019001568,0.000017013237,0.00015562912],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93870497,0.053953607,0.0018541134,0.0015297029,0.002826548,0.0011310799],"domain_scores_gemma":[0.83284336,0.16014433,0.00078210875,0.0048683113,0.0009122931,0.0004496143],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.27626795,0.00029913746,0.00079911907,0.00018851642,0.00030197974,0.00016900203,0.003276782,0.00018647555,0.0034358057],"category_scores_gemma":[0.313595,0.00022431945,0.00009042594,0.00095671904,0.00022941305,0.0005006731,0.0016465529,0.00031467358,0.0011995353],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010664633,0.00025117066,0.9368598,0.0000029490698,0.00005658237,5.6634786e-7,0.0004150082,0.0006549975,0.00027240696,0.00003978461,0.011169594,0.05017048],"study_design_scores_gemma":[0.00036641624,0.000055115874,0.9806669,0.000008128782,0.000020158941,9.480149e-7,0.0001664747,0.0063349716,0.0001991232,0.004805822,0.007109928,0.00026605593],"about_ca_topic_score_codex":0.027789982,"about_ca_topic_score_gemma":0.008170281,"teacher_disagreement_score":0.25206247,"about_ca_system_score_codex":0.00008274973,"about_ca_system_score_gemma":0.000108289336,"threshold_uncertainty_score":0.9995781},"labels":[],"label_agreement":null},{"id":"W2143245567","doi":"","title":"Adjustment of unemployment estimates based on small area estimation in Korea","year":2003,"lang":"en","type":"article","venue":"Survey methodology","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Small area estimation; Statistics; Jackknife resampling; Estimator; Econometrics; Estimation; Unemployment; Mean squared error; Metropolitan area; Population; Efficiency; Mathematics; Geography; Economics; Demography; Economic growth","score_opus":0.32805697021142866,"score_gpt":0.332284060759851,"score_spread":0.004227090548422352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143245567","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42639986,0.0005212056,0.5688485,0.00012477815,0.0004443091,0.00023485329,0.0005081372,0.000019127985,0.0028992537],"genre_scores_gemma":[0.88063866,0.000037018213,0.11864882,0.0001820621,0.0000067755955,0.000029615683,0.00039500662,0.000013874006,0.000048171078],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980401,0.00076920167,0.000617237,0.00033572104,0.000030212037,0.00020752057],"domain_scores_gemma":[0.99688935,0.0024011228,0.00029500306,0.0003408503,0.000030479085,0.00004319556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005900272,0.0001331656,0.0005690483,0.00040926354,0.00002104502,0.000006896238,0.00013443234,0.00010315599,0.0005494704],"category_scores_gemma":[0.0043417905,0.00013866395,0.00007769171,0.00040186723,0.00004446768,0.000033565382,0.000016363061,0.00008930773,0.0000637676],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012142414,0.0002695146,0.8946408,0.000032010117,0.000064644846,0.0000029163623,0.00012878646,0.06953047,0.000050109826,0.031493302,0.000066752145,0.0035992768],"study_design_scores_gemma":[0.0007080305,0.00021653545,0.8575425,0.000015134043,0.000014856947,8.281948e-7,0.000014840411,0.11539801,0.0013964786,0.024117539,0.00037035043,0.00020488379],"about_ca_topic_score_codex":0.0072066495,"about_ca_topic_score_gemma":0.0020740451,"teacher_disagreement_score":0.45423877,"about_ca_system_score_codex":0.000060055096,"about_ca_system_score_gemma":0.000023199842,"threshold_uncertainty_score":0.99940443},"labels":[],"label_agreement":null},{"id":"W2148687539","doi":"","title":"Does the first impression count? : Examining the effect of the welcome screen design on the response rate","year":2013,"lang":"en","type":"article","venue":"Survey methodology","topic":"Psychology of Social Influence","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Impression; Psychology; Statistics; Mathematics; Computer science; World Wide Web","score_opus":0.30503771511793826,"score_gpt":0.43558759787378754,"score_spread":0.13054988275584928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148687539","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95794773,0.00009716289,0.00083754223,0.03665166,0.0018959318,0.0014086807,0.000014426349,0.00003688262,0.0011099896],"genre_scores_gemma":[0.99586564,0.000034663513,0.00028545476,0.0027477809,0.00017722255,0.00016448922,5.902101e-7,0.000016861046,0.0007072678],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.80878,0.18980038,0.00030493242,0.0003011407,0.00035303764,0.0004604654],"domain_scores_gemma":[0.7742524,0.22449322,0.00033137496,0.00074651977,0.00013579443,0.000040670628],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.160953,0.00019035388,0.00033828674,0.000037631053,0.0022412427,0.000064616775,0.0020476724,0.00027534532,0.00026908764],"category_scores_gemma":[0.06308688,0.000057202207,0.00010980518,0.00053454324,0.0036289496,0.00010507797,0.00022099762,0.00061627687,0.0000726359],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018405719,0.00013411134,0.6746953,0.0000356282,0.0007640341,0.000009082642,0.12723249,0.00063485984,0.06056893,0.008813795,0.0730785,0.035627555],"study_design_scores_gemma":[0.0002031774,0.00023157474,0.9877124,0.000026002805,0.000020940655,7.5242946e-7,0.0015643842,0.000011997651,0.0030874356,0.0029596486,0.004085199,0.000096490265],"about_ca_topic_score_codex":0.017668163,"about_ca_topic_score_gemma":0.0033513382,"teacher_disagreement_score":0.3130171,"about_ca_system_score_codex":0.00005590343,"about_ca_system_score_gemma":0.000119764285,"threshold_uncertainty_score":0.9990826},"labels":[],"label_agreement":null},{"id":"W2184159343","doi":"","title":"Confidence interval estimation of small area parameters shrinking both means and variances","year":2012,"lang":"en","type":"article","venue":"Survey methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Small area estimation; Statistics; Confidence interval; Mathematics; Mean squared error; Likelihood function; Maximum likelihood; Efficiency; Sampling (signal processing); Estimation; Applied mathematics; Computer science","score_opus":0.4756757551178532,"score_gpt":0.45104081200118146,"score_spread":0.024634943116671748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2184159343","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08368256,0.000103866914,0.9153627,0.00002786608,0.00033803028,0.0001209849,0.00003205623,0.000024143717,0.0003077551],"genre_scores_gemma":[0.2919642,0.000010759562,0.7079452,0.000035690096,0.000014772226,0.000007730523,0.000003639827,0.000009189609,0.000008775644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9932109,0.0057267323,0.00043919618,0.00020905088,0.00011176063,0.00030237134],"domain_scores_gemma":[0.9580892,0.04127865,0.00024705695,0.00021470881,0.00007808511,0.00009234507],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012709619,0.00014434088,0.00052430044,0.00007360885,0.000042062693,0.000014931364,0.00014606459,0.00011799632,0.00008195007],"category_scores_gemma":[0.034544032,0.00012186093,0.000039865357,0.00012863326,0.00026315116,0.00009202254,0.00007603449,0.00015700301,0.0000020237821],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114373004,0.000065073116,0.03351904,0.0002026605,0.00007178885,0.0000018412331,0.0014890159,0.000008875775,0.0006661206,0.8663871,0.000035628138,0.09743846],"study_design_scores_gemma":[0.00017288032,0.00011260606,0.13505912,0.00007394025,0.000055332683,0.00002345434,0.000109797686,0.0037833664,0.002061591,0.85838735,0.00000737635,0.00015316422],"about_ca_topic_score_codex":0.0005220682,"about_ca_topic_score_gemma":0.00013889794,"teacher_disagreement_score":0.20828164,"about_ca_system_score_codex":0.00001356391,"about_ca_system_score_gemma":0.000025467021,"threshold_uncertainty_score":0.9735884},"labels":[],"label_agreement":null},{"id":"W2189001323","doi":"","title":"Combining Synthetic Data with Subsampling to Create Public Use Microdata Files for Large Scale Surveys","year":2012,"lang":"en","type":"article","venue":"Survey methodology","topic":"demographic modeling and climate adaptation","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Microdata (statistics); Confidentiality; Computer science; Scale (ratio); Sample (material); Imputation (statistics); Statistics; Sample size determination; Statistical inference; Data file; Data science; Data mining; Econometrics; Database; Missing data; Mathematics; Census; Computer security; Geography; Machine learning","score_opus":0.7970682118326551,"score_gpt":0.5130019730252127,"score_spread":0.2840662388074424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189001323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4025036,0.000096106996,0.5941917,0.00021240574,0.00048546665,0.00024412722,0.0021722228,0.00004873278,0.000045685596],"genre_scores_gemma":[0.70308894,0.000013157342,0.294649,0.000232201,0.000060963437,0.000033359127,0.0016709234,0.000036651494,0.00021480219],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97717935,0.018728904,0.00094027875,0.001269312,0.0007121524,0.0011700296],"domain_scores_gemma":[0.9328368,0.06292264,0.00035593592,0.002564587,0.0009451943,0.0003748915],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.18209906,0.0002556976,0.0006893667,0.0005373491,0.00038362478,0.00044344124,0.0017492445,0.00016704986,0.00016718564],"category_scores_gemma":[0.081094794,0.00018921385,0.00007614737,0.001270708,0.00011163064,0.0012795927,0.00063844246,0.00018816174,0.0000941752],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039027876,0.00024954116,0.96330214,0.0000157522,0.00010555513,0.0000013859051,0.0013839094,0.00022400227,0.0011946252,0.0011925128,0.004748253,0.027192043],"study_design_scores_gemma":[0.0010398197,0.00022849803,0.96039885,0.000035357203,0.00007824395,0.000036089656,0.0021121972,0.015566759,0.00032509983,0.002274395,0.017281163,0.0006235259],"about_ca_topic_score_codex":0.0011533424,"about_ca_topic_score_gemma":0.009099188,"teacher_disagreement_score":0.30058536,"about_ca_system_score_codex":0.000017118964,"about_ca_system_score_gemma":0.000089614216,"threshold_uncertainty_score":0.9266455},"labels":[],"label_agreement":null},{"id":"W2189585271","doi":"","title":"Conservative variance estimation for sampling designs with zero pairwise inclusion probabilities","year":2012,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Pairwise comparison; Statistics; Mathematics; Variance (accounting); Standard error; Zero (linguistics); Population variance; Sampling (signal processing); Bias of an estimator; Econometrics; Minimum-variance unbiased estimator; Computer science","score_opus":0.6908408875368,"score_gpt":0.4942956986946006,"score_spread":0.19654518884219935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189585271","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12349749,0.00006596881,0.8748333,0.00011089952,0.00019921082,0.0008279035,0.000073346855,0.00032086912,0.00007101246],"genre_scores_gemma":[0.25415978,0.0000025219433,0.7451828,0.00009450139,0.000041532112,0.00027960463,0.00010456654,0.000036979447,0.000097714095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935906,0.0050026556,0.00046610885,0.00029754397,0.00018171786,0.00046137537],"domain_scores_gemma":[0.9486688,0.050080232,0.00031984158,0.00035611822,0.0004830523,0.00009200418],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.028883988,0.00023425663,0.00049990223,0.00012123385,0.0004151572,0.000021600288,0.00017936615,0.00019887002,0.000026612233],"category_scores_gemma":[0.03830421,0.0001919331,0.000059067053,0.0002515528,0.00017177925,0.00026896005,0.00014320127,0.00015950129,0.000004162281],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007405387,0.0017326772,0.20982057,0.0030218826,0.00074979255,0.0000025089835,0.05325132,0.0036552567,0.0055784583,0.6061436,0.009609051,0.09902951],"study_design_scores_gemma":[0.0007101329,0.00044210514,0.042364556,0.00012940285,0.00007319721,0.000021774107,0.00017673688,0.0044486783,0.010109881,0.9406498,0.00038556926,0.00048814696],"about_ca_topic_score_codex":0.00041542493,"about_ca_topic_score_gemma":0.00016500309,"teacher_disagreement_score":0.33450624,"about_ca_system_score_codex":0.0000904491,"about_ca_system_score_gemma":0.00010741819,"threshold_uncertainty_score":0.9999683},"labels":[],"label_agreement":null},{"id":"W2274680738","doi":"","title":"Small Area Estimation for Adjusting Subarea Unemployment and Its Application","year":2003,"lang":"en","type":"article","venue":"Survey methodology","topic":"Regional Economic and Spatial Analysis","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimation; Small area estimation; Unemployment; Statistics; Computer science; Mathematics; Economics; Economic growth","score_opus":0.4238741577399343,"score_gpt":0.32893561580293407,"score_spread":0.09493854193700024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274680738","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30773157,0.00078611815,0.6902084,0.00019311585,0.0001141689,0.00023045711,0.00007948288,0.0000143738,0.0006423784],"genre_scores_gemma":[0.94312054,0.00010884803,0.055880316,0.00017310392,0.000029025105,0.00013455047,0.00015168678,0.000017687458,0.00038423308],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986587,0.00027192096,0.00047264987,0.00039214952,0.000011376233,0.0001931678],"domain_scores_gemma":[0.99788016,0.0015484063,0.00030777205,0.00015094675,0.00005428381,0.000058412432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052102697,0.000112251844,0.0004116913,0.00013640322,0.0000945496,0.00001644228,0.00008285242,0.00010672988,0.000049962775],"category_scores_gemma":[0.0026889697,0.00012864568,0.00007037402,0.00012328356,0.000028894086,0.00006022841,0.000017742022,0.000056559464,0.00003937309],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007770346,0.000057138634,0.21629028,0.00006393213,0.00015704728,3.7591334e-7,0.00025542383,0.0054077497,0.00014733807,0.7626879,0.000104621504,0.014750496],"study_design_scores_gemma":[0.0013486753,0.00017827858,0.23947607,0.000008277905,0.00005578543,0.000012480566,0.000085017426,0.38680437,0.0008619716,0.35412815,0.016377222,0.00066370115],"about_ca_topic_score_codex":0.0007865758,"about_ca_topic_score_gemma":0.00055587303,"teacher_disagreement_score":0.635389,"about_ca_system_score_codex":0.000048131802,"about_ca_system_score_gemma":0.000015760244,"threshold_uncertainty_score":0.5246019},"labels":[],"label_agreement":null},{"id":"W2403892912","doi":"","title":"Dealing with non-ignorable nonresponse in survey sampling: A latent modeling approach","year":2015,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Covariate; Latent variable; Estimator; Latent variable model; Statistics; Econometrics; Computer science; Variable (mathematics); Mathematics","score_opus":0.8087179749783673,"score_gpt":0.522277081248507,"score_spread":0.28644089372986026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403892912","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5812443,0.00021482821,0.41614547,0.00009401891,0.00047129748,0.00035337903,0.0000299967,0.000071088856,0.0013756237],"genre_scores_gemma":[0.78100026,0.000046505174,0.217907,0.00019133656,0.000101834754,0.000061543826,0.00011057368,0.000055954242,0.00052499946],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6622247,0.33354878,0.0008926571,0.0011581078,0.00066977396,0.0015059874],"domain_scores_gemma":[0.90354055,0.0944768,0.00022716103,0.000561869,0.00071624044,0.000477402],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5002098,0.0003913028,0.001067325,0.0005821724,0.00040308503,0.000064967986,0.00069725997,0.0006675962,0.000055457695],"category_scores_gemma":[0.16100137,0.00035008157,0.00009450388,0.0016044037,0.0005815981,0.00024823964,0.00015075522,0.0007804485,0.00003387921],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.06748531,0.00030967078,0.8282226,0.00001757667,0.00013680906,0.000064836735,0.018931014,0.082004994,0.0002003177,0.00096000667,0.00010789705,0.0015589814],"study_design_scores_gemma":[0.0026495787,0.0003682242,0.97608626,0.00003257141,0.00003467438,0.000023068134,0.004443735,0.0121566905,0.000112803944,0.0027606408,0.00044531428,0.00088644406],"about_ca_topic_score_codex":0.11853335,"about_ca_topic_score_gemma":0.15928632,"teacher_disagreement_score":0.33920842,"about_ca_system_score_codex":0.00022689544,"about_ca_system_score_gemma":0.0015477234,"threshold_uncertainty_score":0.9998951},"labels":[],"label_agreement":null},{"id":"W2520722247","doi":"","title":"Modeling interviewer effects in panel surveys: - an application","year":2000,"lang":"en","type":"article","venue":"Survey methodology","topic":"Social Capital and Networks","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interview; Statistics; Econometrics; Computer science; Mathematics; Sociology","score_opus":0.3534255851812836,"score_gpt":0.44547318281231557,"score_spread":0.09204759763103199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520722247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9131666,0.0004254438,0.08285708,0.000102358965,0.00041735233,0.0002931374,0.0000040704736,0.00007257586,0.0026614214],"genre_scores_gemma":[0.9962117,0.00021395112,0.0026270838,0.0002314036,0.00027821853,0.000057238743,0.00005058838,0.00001438786,0.000315405],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9591468,0.039731022,0.00025036544,0.0003263056,0.00015189566,0.0003936358],"domain_scores_gemma":[0.9963159,0.0032818802,0.000037163536,0.00018473194,0.00007755477,0.00010278732],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03402236,0.0001072447,0.0002973919,0.00006364431,0.00016727202,0.000022513275,0.00028162048,0.00026364072,0.00028424524],"category_scores_gemma":[0.0015843506,0.00010908027,0.000050165545,0.00047879465,0.00014463352,0.00016094721,0.00002359567,0.00021462164,0.0000814311],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011606002,0.00013869532,0.044283226,0.00001483596,0.000016729316,0.0000046508057,0.02917706,0.0026580894,0.00010487746,0.0034198693,0.00005991993,0.920006],"study_design_scores_gemma":[0.00065536005,0.00016751725,0.90951437,0.000024332874,0.00001506238,0.0000012256259,0.0027860743,0.022831533,0.000034410292,0.06181586,0.001627493,0.00052673527],"about_ca_topic_score_codex":0.104055054,"about_ca_topic_score_gemma":0.18955189,"teacher_disagreement_score":0.91947925,"about_ca_system_score_codex":0.00006221983,"about_ca_system_score_gemma":0.000058378362,"threshold_uncertainty_score":0.99467725},"labels":[],"label_agreement":null},{"id":"W2552298465","doi":"","title":"Fence method for nonparametric small area estimation","year":2010,"lang":"en","type":"article","venue":"Survey methodology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fence (mathematics); Nonparametric statistics; Small area estimation; Estimation; Mathematics; Computer science; Function (biology); Statistics; Type (biology); Econometrics; Algorithm; Engineering; Combinatorics","score_opus":0.5702197929104776,"score_gpt":0.5181411432265587,"score_spread":0.052078649683918954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552298465","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03291788,0.000013473549,0.9644359,0.00011189202,0.001226511,0.00048545573,0.00014443678,0.000092916074,0.0005715727],"genre_scores_gemma":[0.007738334,0.0000025523489,0.9916192,0.00016351849,0.000077501754,0.00013410335,0.00003095109,0.000035412424,0.00019837091],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99293876,0.005378719,0.00056013843,0.00050642743,0.00014982541,0.00046610428],"domain_scores_gemma":[0.8418543,0.15688904,0.00024000605,0.00049745984,0.00038614555,0.00013308594],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.028552618,0.00022722405,0.00065179,0.00021185527,0.00011672064,0.00003425356,0.00036440318,0.00031880868,0.00030700592],"category_scores_gemma":[0.30470446,0.0001949066,0.00010833932,0.000534943,0.00013454317,0.000043911175,0.00007775646,0.00045611986,0.000019650939],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001874211,0.00011689227,0.0022127565,0.00012338508,0.00005054219,0.0000024275448,0.00018501548,0.000018676043,0.012512767,0.5414286,0.0006608452,0.44250065],"study_design_scores_gemma":[0.00037943447,0.0001855708,0.031493768,0.000007784338,0.0000536368,0.000022960654,0.000014038986,0.04643579,0.005298354,0.9153105,0.0005352149,0.00026291635],"about_ca_topic_score_codex":0.00039892332,"about_ca_topic_score_gemma":0.00060334726,"teacher_disagreement_score":0.44223773,"about_ca_system_score_codex":0.000018440438,"about_ca_system_score_gemma":0.00008945656,"threshold_uncertainty_score":0.9895824},"labels":[],"label_agreement":null},{"id":"W2553278379","doi":"","title":"A comparison of variance estimators for poststratification to estimated control totals","year":2010,"lang":"en","type":"article","venue":"Survey methodology","topic":"Control Systems and Identification","field":"Engineering","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Variance (accounting); Statistics; Mathematics; Econometrics; Economics","score_opus":0.20869940471011453,"score_gpt":0.4336219901237659,"score_spread":0.22492258541365137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553278379","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37556872,0.0000473074,0.62243897,0.00004936027,0.0011886298,0.00048317615,0.00010738123,0.000072791816,0.00004364287],"genre_scores_gemma":[0.90885264,4.4454765e-7,0.090829894,0.000009521004,0.00004880842,0.00013546775,0.000070622045,0.000019954547,0.000032628268],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99857557,0.0004748897,0.0005111425,0.00018603487,0.00007209131,0.00018029053],"domain_scores_gemma":[0.9967804,0.0024745786,0.0001169781,0.00030619022,0.0002564656,0.000065387074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004047683,0.000111255846,0.0004461491,0.00010194793,0.000034970875,0.000018423785,0.00014383992,0.0001528418,0.000021086147],"category_scores_gemma":[0.0037632827,0.000115161085,0.000047761496,0.0001799435,0.00002681577,0.000054139724,0.0000062738945,0.000113534916,0.000015629646],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010277673,0.000026583935,0.020808116,0.00006123013,0.000049142218,7.9407315e-8,0.00019207846,0.010164967,0.9564564,0.0020084833,0.00073169183,0.009398445],"study_design_scores_gemma":[0.0005915104,0.000081020844,0.7430015,0.000010735831,0.000029082985,0.000002856296,0.000019391371,0.21350302,0.041624807,0.00041292273,0.0005591443,0.00016401216],"about_ca_topic_score_codex":0.0003778152,"about_ca_topic_score_gemma":0.001060037,"teacher_disagreement_score":0.9148316,"about_ca_system_score_codex":0.000013828475,"about_ca_system_score_gemma":0.000022369444,"threshold_uncertainty_score":0.46961325},"labels":[],"label_agreement":null},{"id":"W2554863279","doi":"","title":"Observed best prediction via nested-error regression with potentially misspecified mean and variance","year":2015,"lang":"en","type":"article","venue":"Survey methodology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Small area estimation; Statistics; Mean squared error; Best linear unbiased prediction; Variance (accounting); Mean squared prediction error; Mathematics; Computer science; Linear regression; Regression; Econometrics; Machine learning","score_opus":0.6677220592976109,"score_gpt":0.45309889349637256,"score_spread":0.2146231658012383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2554863279","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13855183,0.00013891477,0.85989356,0.000103560786,0.00048963225,0.00022665308,0.000045773373,0.00007230747,0.00047776266],"genre_scores_gemma":[0.055293806,0.000017728726,0.9440192,0.000068055895,0.000102190555,0.000019618887,0.00002836277,0.000034774577,0.0004162898],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.989343,0.009209893,0.00041812367,0.0004671316,0.00025788284,0.0003039984],"domain_scores_gemma":[0.9893093,0.009379169,0.00023016914,0.000415421,0.00040863338,0.0002573175],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008995382,0.00022880224,0.0005563684,0.00006934922,0.00008803562,0.000028336888,0.00017300619,0.00024000471,0.000059096692],"category_scores_gemma":[0.018202202,0.00016228815,0.000028530952,0.00023933644,0.00020708746,0.00008553432,0.000087792105,0.0002877442,0.0000075106927],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.018357094,0.00212701,0.17056394,0.0012158155,0.0011184268,0.00058049645,0.013309554,0.00021559387,0.056330178,0.31192705,0.010924327,0.4133305],"study_design_scores_gemma":[0.003883353,0.0027142111,0.34324765,0.00027844924,0.00029580516,0.00031578395,0.00097043405,0.010006982,0.0023592222,0.63414496,0.00091429433,0.00086885813],"about_ca_topic_score_codex":0.00043588807,"about_ca_topic_score_gemma":0.0005068254,"teacher_disagreement_score":0.41246164,"about_ca_system_score_codex":0.00003019003,"about_ca_system_score_gemma":0.000090852154,"threshold_uncertainty_score":0.9900679},"labels":[],"label_agreement":null},{"id":"W2573621420","doi":"","title":"A short note on quantile and expectile estimation in unequal probability samples","year":2016,"lang":"en","type":"article","venue":"Survey methodology","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Quantile; Estimator; Mathematics; Quantile regression; Statistics; Econometrics; Generalization","score_opus":0.6814941744892106,"score_gpt":0.5625075198466303,"score_spread":0.11898665464258029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2573621420","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40076002,0.000018927049,0.5986572,0.00009399857,0.00023932221,0.00011112885,0.000044135333,0.000020051368,0.000055241064],"genre_scores_gemma":[0.73297083,0.0000030538936,0.26692727,0.000016040773,0.00001947618,0.000021839458,0.0000022909821,0.000007440435,0.000031735795],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9913634,0.006474609,0.0006392887,0.00074242835,0.00046854594,0.0003117178],"domain_scores_gemma":[0.90292007,0.09629017,0.00011042563,0.00039790908,0.00019228633,0.00008914858],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021932377,0.00013985626,0.00043555684,0.00020498162,0.000071321105,0.000031188378,0.00026182365,0.0001140468,0.000061162886],"category_scores_gemma":[0.22318938,0.00008647359,0.000026608743,0.0004355986,0.0002673745,0.00022031966,0.000118170305,0.00013973004,0.000040143943],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005527586,0.00005107555,0.21777664,0.0000068629006,0.000003543304,0.000005455206,0.00040035576,0.00063658325,0.0023571427,0.0067020096,0.000037530157,0.77147007],"study_design_scores_gemma":[0.00017839798,0.000099741155,0.69749,0.0000119751385,0.0000013717811,0.0000017090503,0.00005818762,0.0009538662,0.0016882815,0.2993432,0.00006988418,0.00010341607],"about_ca_topic_score_codex":0.00025484408,"about_ca_topic_score_gemma":0.0013196171,"teacher_disagreement_score":0.77136666,"about_ca_system_score_codex":0.000073422736,"about_ca_system_score_gemma":0.000044842618,"threshold_uncertainty_score":0.78335404},"labels":[],"label_agreement":null},{"id":"W2612643943","doi":"","title":"Some contributions to jackknifing two-phase sampling estimators","year":2010,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Statistics; Mathematics; Sampling (signal processing); Econometrics; Computer science","score_opus":0.4680701557935121,"score_gpt":0.5642361375453836,"score_spread":0.09616598175187152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612643943","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38789624,0.00001545979,0.60984015,0.00022532606,0.0009712826,0.0002509817,0.0002409244,0.0004823824,0.00007725915],"genre_scores_gemma":[0.2453654,0.000002042299,0.75384897,0.00022333204,0.00026262956,0.00007245092,0.00010769626,0.00004520011,0.000072291754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949763,0.0031288043,0.0006529075,0.0004701948,0.0002001463,0.0005716886],"domain_scores_gemma":[0.9706113,0.027713457,0.00020760324,0.00068762933,0.0005150047,0.00026500452],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02572515,0.00026110167,0.0006176886,0.00032993636,0.00028631667,0.000058491674,0.00036022632,0.0002621946,0.00015646828],"category_scores_gemma":[0.11266426,0.00025704736,0.00011243788,0.00044144876,0.00012602775,0.0001361381,0.00012875856,0.0006190824,0.00012107818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005485725,0.0007492684,0.013308451,0.000110944624,0.00022731572,0.000019777834,0.0014848529,0.00026587004,0.2624787,0.66481906,0.009480405,0.046506763],"study_design_scores_gemma":[0.0016876397,0.00023056929,0.015013118,0.000044470467,0.000066109475,0.00007874656,0.000061292834,0.0009950942,0.07592414,0.9025037,0.0026099398,0.00078512594],"about_ca_topic_score_codex":0.0010254333,"about_ca_topic_score_gemma":0.0007695263,"teacher_disagreement_score":0.23768467,"about_ca_system_score_codex":0.0000500245,"about_ca_system_score_gemma":0.00012490869,"threshold_uncertainty_score":0.9999882},"labels":[],"label_agreement":null},{"id":"W2618479281","doi":"","title":"An Approximate Design Effect for Unequal Weighting When Measurements May Correlate with Selection Probabilities","year":2000,"lang":"en","type":"article","venue":"Survey methodology","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Selection (genetic algorithm); Weighting; Statistics; Mathematics; Computer science; Artificial intelligence; Physics","score_opus":0.6404714675082755,"score_gpt":0.5156032129815941,"score_spread":0.12486825452668149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618479281","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25035864,0.0000780136,0.7465387,0.000024278193,0.00037697118,0.0015543107,0.000021139394,0.0001291338,0.0009188364],"genre_scores_gemma":[0.16219676,0.0000015455298,0.8358517,0.00007189196,0.00007144724,0.0003505485,0.000022603474,0.0000510908,0.0013823935],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9249417,0.07100408,0.00095328107,0.0012823114,0.0010453943,0.000773208],"domain_scores_gemma":[0.9584668,0.039705217,0.00035780953,0.0006851662,0.0005804582,0.00020453642],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1411556,0.00042574987,0.0010342028,0.00030521277,0.00038865968,0.0002275762,0.00080785085,0.00028561574,0.0009832893],"category_scores_gemma":[0.012244051,0.0002939175,0.00013727359,0.0007900334,0.00030640006,0.0005859789,0.00004463154,0.00027721992,0.00008585351],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.041142963,0.00067277736,0.10279235,0.00010169689,0.00049223274,0.00001007151,0.009266234,0.06138249,0.21646984,0.0010542908,0.0011935881,0.56542146],"study_design_scores_gemma":[0.008704267,0.029703602,0.07245251,0.00009944568,0.00028451093,0.00018743784,0.001189755,0.1512279,0.6366047,0.095089585,0.0018215256,0.0026347155],"about_ca_topic_score_codex":0.0004897322,"about_ca_topic_score_gemma":0.00015359002,"teacher_disagreement_score":0.56278676,"about_ca_system_score_codex":0.0001367479,"about_ca_system_score_gemma":0.0001518569,"threshold_uncertainty_score":0.9999513},"labels":[],"label_agreement":null},{"id":"W2733262089","doi":"","title":"Mixed Methods in Value Research: An Analysis of the Validity of the Russian Version of the Schwartz Value Survey (SVS) Using Cognitive Interviewing, Multidimensional Scaling (MDS), and Confirmatory Factor Analysis (CFA)","year":2013,"lang":"en","type":"article","venue":"Survey methodology","topic":"Customer Service Quality and Loyalty","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Confirmatory factor analysis; Psychology; Multidimensional scaling; Cognitive interview; Value (mathematics); Cognition; Statistics; Structural equation modeling; Mathematics; Psychiatry","score_opus":0.5546124260343751,"score_gpt":0.480816874291878,"score_spread":0.07379555174249708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2733262089","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898897,0.00009948833,0.008684767,0.00016602955,0.00045860617,0.0004740026,0.0001797005,0.000008947028,0.00003880098],"genre_scores_gemma":[0.9948004,0.0000063520324,0.004855065,0.00020673459,0.000033496046,0.0000070482038,0.00006334693,0.000018941582,0.000008624319],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9427273,0.054665934,0.0010320735,0.0005153075,0.00066524005,0.00039411135],"domain_scores_gemma":[0.981253,0.015677145,0.0011304803,0.00088799436,0.0010165236,0.000034831395],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06302185,0.0002548037,0.0012002707,0.0010655208,0.00034556567,0.00004590077,0.00081226695,0.00024828906,0.00024093445],"category_scores_gemma":[0.011246984,0.0001519993,0.0005241354,0.0067222985,0.0008531819,0.0003968119,0.0012659163,0.00058058277,0.0000017672397],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015094243,0.00014960556,0.9876066,0.00017401991,0.0012507915,2.3068445e-7,0.0010446047,0.0024102607,0.0053797383,0.00082135265,0.000005744631,0.0010061329],"study_design_scores_gemma":[0.00038821038,0.0000130546105,0.92575383,0.00009476508,0.0013406709,3.0909126e-7,0.0015966087,0.0659535,0.004313058,0.00037940967,0.000018860712,0.00014771165],"about_ca_topic_score_codex":0.17493242,"about_ca_topic_score_gemma":0.04210218,"teacher_disagreement_score":0.13283023,"about_ca_system_score_codex":0.000052091145,"about_ca_system_score_gemma":0.00011299429,"threshold_uncertainty_score":0.9970817},"labels":[],"label_agreement":null},{"id":"W2803428860","doi":"","title":"Application of Markov Latent Class Analysis to the CPS","year":2001,"lang":"en","type":"article","venue":"Survey methodology","topic":"Technology and Data Analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Latent class model; Markov chain; Class (philosophy); Computer science; Mathematics; Statistics; Artificial intelligence","score_opus":0.13075832751608424,"score_gpt":0.3678946917757851,"score_spread":0.23713636425970086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803428860","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036598016,0.00006933522,0.959652,0.0033011197,0.00008489634,0.000091749855,0.000018754079,0.000063525484,0.00012061531],"genre_scores_gemma":[0.77222663,0.000026525986,0.22702916,0.00049863703,0.000014575366,0.000026806338,0.000047703896,0.0000034964444,0.00012647739],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959746,0.0030146742,0.00028477304,0.0003908197,0.00012820827,0.00020689995],"domain_scores_gemma":[0.996216,0.002052171,0.00014169302,0.0014118907,0.0001346006,0.000043651264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00852092,0.00008906293,0.00033859175,0.00041511536,0.00007314757,0.000011988984,0.0014158124,0.00012694288,0.000026437006],"category_scores_gemma":[0.0011308558,0.00006291822,0.00012266704,0.0041098287,0.00008037533,0.00006910332,0.00037076502,0.00012630477,0.00005418416],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075808304,0.00008153494,0.64604855,0.000003243117,0.0012333351,0.0000055235987,0.0002544709,0.0026225464,0.0019343892,0.042737424,0.001477358,0.30352584],"study_design_scores_gemma":[0.00006956689,0.000039756622,0.966,3.9387555e-7,0.00016344312,0.000005904727,0.000013250991,0.0227028,0.0008012456,0.0026987325,0.007411856,0.00009301915],"about_ca_topic_score_codex":0.0019151416,"about_ca_topic_score_gemma":0.0052803354,"teacher_disagreement_score":0.7356286,"about_ca_system_score_codex":0.000014698931,"about_ca_system_score_gemma":0.000019598741,"threshold_uncertainty_score":0.29531977},"labels":[],"label_agreement":null},{"id":"W2943998842","doi":"","title":"Sample survey theory and methods: Past, present, and future directions","year":2017,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Estimator; Survey data collection; Imputation (statistics); Survey sampling; Weighting; Sample (material); Statistics; Inference; Sampling (signal processing); Software; Data mining; Survey methodology; Data collection; Sampling design; Resampling; Sample size determination; Consistency (knowledge bases); Econometrics; Missing data; Mathematics; Algorithm; Machine learning; Artificial intelligence","score_opus":0.4722577731315136,"score_gpt":0.5515094383971101,"score_spread":0.07925166526559646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943998842","genre_codex":"empirical","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59200037,0.009177697,0.3755795,0.007315317,0.0090428805,0.0009312549,0.000773315,0.00027108,0.004908604],"genre_scores_gemma":[0.06433979,0.010398629,0.9093444,0.0009766059,0.0072896522,0.0001717395,0.0001980891,0.00014187863,0.0071392283],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.4471824,0.5508302,0.00036652124,0.0007571624,0.00018506256,0.0006786636],"domain_scores_gemma":[0.67840064,0.320276,0.0002538229,0.0006208229,0.00021498135,0.0002337261],"candidate_categories":["metaresearch","sts"],"consensus_categories":["metaresearch","sts"],"category_scores_codex":[0.48071703,0.0002695537,0.0007264594,0.00018760048,0.0032094235,0.00017441851,0.0005808262,0.0005912596,0.00031738743],"category_scores_gemma":[0.28783953,0.00024287026,0.00008034556,0.00023230242,0.0027390015,0.00029795387,0.00036020298,0.00047463895,0.000006632217],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052530123,0.00004965047,0.66363704,0.000011087542,0.00019339035,0.000006037239,0.0067544603,1.8168242e-7,0.0001622567,0.017016847,0.0011908098,0.30572522],"study_design_scores_gemma":[0.00027887916,0.000049610102,0.8119867,0.0000027221743,0.000029584091,0.0000062746667,0.0009189647,0.0000021597316,0.000079615194,0.023192976,0.16323441,0.00021813784],"about_ca_topic_score_codex":0.052036915,"about_ca_topic_score_gemma":0.042379815,"teacher_disagreement_score":0.5337649,"about_ca_system_score_codex":0.000027195685,"about_ca_system_score_gemma":0.00018346657,"threshold_uncertainty_score":0.99997497},"labels":[],"label_agreement":null},{"id":"W2963777145","doi":"","title":"Multiple Imputation of Missing Values in Household Data with Structural Zeros","year":2017,"lang":"en","type":"article","venue":"Survey methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Categorical variable; Imputation (statistics); Multivariate statistics; Missing data; Statistics; Econometrics; Gibbs sampling; Multivariate normal distribution; Population; Mathematics; Latent variable; Computer science; Demography; Bayesian probability","score_opus":0.6315137670957544,"score_gpt":0.5150164246912262,"score_spread":0.11649734240452814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963777145","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28446916,0.000013041863,0.7149218,0.000033507527,0.00012187305,0.000109998655,0.00026046074,0.000013568073,0.00005664375],"genre_scores_gemma":[0.39774314,0.0000013571465,0.6021873,0.0000077282675,0.000016823928,0.0000017883532,0.000025631212,0.000011789916,0.0000044496996],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99477714,0.0041390834,0.00038229703,0.000335642,0.00013923802,0.0002265856],"domain_scores_gemma":[0.9759409,0.022452869,0.00039419904,0.001074445,0.000090685055,0.00004689089],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00852286,0.00013002653,0.000517503,0.00006816249,0.00011282552,0.00003814481,0.0006090778,0.00010359157,0.000020334459],"category_scores_gemma":[0.06458776,0.000097866556,0.00001821636,0.00006834964,0.00030009288,0.00016080077,0.00021898771,0.00017144071,5.428428e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065640826,0.0000663485,0.67215097,0.0002516089,0.00007719824,0.000040547264,0.0006958908,0.000011921394,0.005055412,0.03660261,0.000112128226,0.28427896],"study_design_scores_gemma":[0.00039145723,0.000053796866,0.5879843,0.00003218968,0.000014598,0.000008902123,0.00002643118,0.0031389296,0.0016424875,0.406617,0.0000014114374,0.00008849205],"about_ca_topic_score_codex":0.0025538362,"about_ca_topic_score_gemma":0.0012891694,"teacher_disagreement_score":0.37001437,"about_ca_system_score_codex":0.000013329147,"about_ca_system_score_gemma":0.00006329553,"threshold_uncertainty_score":0.9432916},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Stratified sampling; Multivariate statistics; Statistics; Sampling (signal processing); Mathematics; Computer science","score_opus":0.6825131120236855,"score_gpt":0.5037334109630854,"score_spread":0.17877970106060004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993287308","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2215482,0.000017793438,0.7772363,0.000039902265,0.00022212451,0.00065913977,0.000042789557,0.00019192265,0.000041849304],"genre_scores_gemma":[0.29404625,0.000010096444,0.7053984,0.000029125038,0.000032208067,0.00019325974,0.00017336945,0.000030089166,0.00008722288],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9945441,0.0039062616,0.0006463013,0.00044123278,0.00012781002,0.00033432618],"domain_scores_gemma":[0.97723526,0.0217331,0.00027658642,0.0003134114,0.00038886335,0.000052761603],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014826429,0.0002081149,0.00048180993,0.00027812607,0.000162774,0.000014578123,0.0001701209,0.00027796807,0.000019170218],"category_scores_gemma":[0.03186441,0.00021368719,0.00007927205,0.00030420453,0.00008716888,0.00014105963,0.000032249736,0.00021060981,0.0000049870932],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0116788875,0.0063180993,0.25786784,0.0016307599,0.0013287419,0.000041591917,0.08525735,0.0973061,0.35559565,0.06803167,0.0037118462,0.11123145],"study_design_scores_gemma":[0.0033911483,0.0003101794,0.7806591,0.00007418545,0.000037353715,0.000034240336,0.00046600244,0.08433104,0.035170108,0.09467565,0.000053093805,0.0007979132],"about_ca_topic_score_codex":0.0022186516,"about_ca_topic_score_gemma":0.001305849,"teacher_disagreement_score":0.52279127,"about_ca_system_score_codex":0.000109512286,"about_ca_system_score_gemma":0.00011626337,"threshold_uncertainty_score":0.9762906},"labels":[],"label_agreement":null},{"id":"W3041227018","doi":"","title":"“Optimal” calibration weights under unit nonresponse in survey sampling","year":2019,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Statistics; Estimator; Calibration; Sampling (signal processing); Sample (material); Variance (accounting); Population; Survey sampling; Econometrics; Non-response bias; Mathematics; Computer science; Demography; Physics; Economics","score_opus":0.6246140539733327,"score_gpt":0.49634499195555926,"score_spread":0.12826906201777344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041227018","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5688576,0.000026755555,0.4301544,0.000040857194,0.00030539613,0.00025096748,0.00005108533,0.00016124059,0.00015166264],"genre_scores_gemma":[0.53429186,0.000012581954,0.46434993,0.00013472645,0.00003145093,0.000028946986,0.00034667895,0.00006032348,0.00074353616],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96960396,0.0283122,0.0007878898,0.00055164093,0.00024948426,0.0004948271],"domain_scores_gemma":[0.93241453,0.066392176,0.00024717496,0.00062184455,0.0002411807,0.00008308396],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051632814,0.0002738963,0.00069452095,0.00047053333,0.00007267875,0.00004379086,0.00031283192,0.00038605015,0.00040037357],"category_scores_gemma":[0.023171866,0.00026230354,0.000078523626,0.0007110535,0.00007503028,0.00018085544,0.00009730448,0.00040242018,0.000091477144],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020651296,0.00025493826,0.97451794,0.00010779008,0.00009171698,0.0000058851156,0.0009265218,0.0032261708,0.0031790715,0.013416221,0.0006580393,0.0015505857],"study_design_scores_gemma":[0.00053095905,0.00010523377,0.9351648,0.00003985982,0.0000084723415,0.000009781493,0.00007832022,0.003209205,0.0028618248,0.057530064,0.00011184313,0.00034962417],"about_ca_topic_score_codex":0.0063724057,"about_ca_topic_score_gemma":0.008610399,"teacher_disagreement_score":0.044113845,"about_ca_system_score_codex":0.00007611829,"about_ca_system_score_gemma":0.00015583422,"threshold_uncertainty_score":0.9999829},"labels":[],"label_agreement":null},{"id":"W3048692611","doi":"","title":"An assessment of accuracy improvement by adaptive survey design : [Une évaluation de l’amélioration de l’exactitude au moyen d’un plan de sondage adaptatif]","year":2019,"lang":"fr","type":"article","venue":"Survey methodology","topic":"Census and Population Estimation","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.43361672778826854,"score_gpt":0.47828446764394816,"score_spread":0.04466773985567962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048692611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45496324,0.000088153225,0.54295915,0.00015014476,0.0004336335,0.00086472585,0.00044317375,0.00002832812,0.00006942321],"genre_scores_gemma":[0.5495072,0.00005949864,0.44879416,0.00007200793,0.00006262582,0.000044463028,0.001203543,0.000048909584,0.00020762988],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.94636357,0.050059456,0.001399017,0.00067219004,0.0005831802,0.0009225902],"domain_scores_gemma":[0.9718388,0.025069637,0.0014517561,0.0006740989,0.00072473066,0.00024100066],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0711055,0.0004341656,0.00089889666,0.0002246681,0.00018895793,0.000060244838,0.00034176506,0.0006692222,0.00052792294],"category_scores_gemma":[0.009548865,0.0004869015,0.00012059465,0.0005085749,0.00012189491,0.0004895787,0.00006816075,0.000509869,0.000020019117],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022574754,0.001872262,0.4749681,0.0005899101,0.00073192845,0.000009736225,0.017996233,0.13815439,0.1970846,0.014093745,0.0014143861,0.15082723],"study_design_scores_gemma":[0.00095551537,0.0010241101,0.63347346,0.000049086466,0.00015266263,0.000011674918,0.00038828867,0.34344637,0.009105771,0.01104394,0.00004113797,0.00030799737],"about_ca_topic_score_codex":0.064284295,"about_ca_topic_score_gemma":0.01316822,"teacher_disagreement_score":0.20529199,"about_ca_system_score_codex":0.0012999362,"about_ca_system_score_gemma":0.0019456722,"threshold_uncertainty_score":0.99975824},"labels":[],"label_agreement":null},{"id":"W3148502279","doi":"","title":"A grouping genetic algorithm for joint stratification and sample allocation designs","year":2019,"lang":"en","type":"article","venue":"Survey methodology","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematical optimization; Cartesian product; Selection (genetic algorithm); Genetic algorithm; Algorithm; Population stratification; Population; Sample size determination; Multivariate statistics; Mathematics; Computer science; Statistics; Artificial intelligence; Combinatorics","score_opus":0.6926526353938932,"score_gpt":0.5259590208262171,"score_spread":0.16669361456767606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3148502279","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.072807506,0.00023090377,0.925258,0.00008504971,0.00061008136,0.0008307349,0.00005404353,0.000029594894,0.00009411509],"genre_scores_gemma":[0.049631543,0.000011061066,0.949787,0.00014369421,0.00004889657,0.00008476043,0.00003594809,0.000021124859,0.00023597875],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9857646,0.011922876,0.00076240726,0.0008227359,0.00040641718,0.0003209584],"domain_scores_gemma":[0.9548246,0.04381722,0.00031287718,0.00055868557,0.00038439926,0.000102187165],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04159457,0.00017204815,0.00048707597,0.00025083884,0.00011284356,0.00011341471,0.00031264,0.00016257846,0.00021102533],"category_scores_gemma":[0.026597185,0.0001482143,0.000078486475,0.00045140123,0.00011923323,0.00019855647,0.00008854775,0.00010577614,0.000067748224],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009803681,0.000038363934,0.0069626886,0.000008204789,0.000024852414,3.8599188e-7,0.0004910755,0.00019509392,0.25860268,0.0024806357,0.00013500822,0.730963],"study_design_scores_gemma":[0.0009891202,0.0008692655,0.62079054,0.000008959852,0.00002266672,0.000026714828,0.00095227326,0.16246624,0.064211845,0.14853145,0.0006713975,0.0004595217],"about_ca_topic_score_codex":0.00057721656,"about_ca_topic_score_gemma":0.000058736758,"teacher_disagreement_score":0.73050344,"about_ca_system_score_codex":0.000046385863,"about_ca_system_score_gemma":0.000079261714,"threshold_uncertainty_score":0.98688006},"labels":[],"label_agreement":null}]}