{"meta":{"query_hash":"478ad34d6f7d","filters":{"venue":"Journal of Survey Statistics and Methodology"},"cohort_total":25,"direct_labels_cover":0,"predictions_cover":25,"exported":25,"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/478ad34d6f7d","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Survey+Statistics+and+Methodology"},"results":[{"id":"W2102082048","doi":"10.1093/jssam/smu011","title":"Small Area Prediction of Proportions with Applications to the Canadian Labour Force Survey","year":2014,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Estimator; Statistics; Small area estimation; Econometrics; Mathematics; Mean squared error; Multinomial distribution; Census; Estimation; Current Population Survey; Standard error; Table (database); Population; Benchmarking; Computer science; Demography; Economics; Data mining","score_opus":0.3842642301409165,"score_gpt":0.4131436403482028,"score_spread":0.028879410207286293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102082048","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068053612,0.00009573777,0.99025655,0.00012950184,0.00006391813,0.00024461746,0.00056329474,0.0005937765,0.0012471796],"genre_scores_gemma":[0.15310803,0.00031841066,0.8375044,0.00009362943,0.00007464361,0.0011850485,0.0018722772,0.0002551051,0.00558846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99365777,0.0036477188,0.00019261986,0.00088144874,0.001407348,0.00021310299],"domain_scores_gemma":[0.97692966,0.016163155,0.0009167995,0.0026482115,0.0031169474,0.00022531724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011066184,0.0007956003,0.0010958591,0.0023906184,0.0011851235,0.0012029593,0.002148845,0.0006350814,0.008678866],"category_scores_gemma":[0.070549406,0.0005132234,0.0011451293,0.0049161683,0.001052401,0.0010132655,0.0017500486,0.0021434145,0.0013245959],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024301649,0.0001296868,0.03525268,0.0002495291,0.00023494368,0.00030856972,0.0008919213,0.29180664,0.0010837727,0.18474744,0.013419494,0.4716323],"study_design_scores_gemma":[0.000049261056,0.00007527692,0.012299835,0.00007297634,0.0000392161,0.00009110229,0.00020067184,0.9040748,0.0009538796,0.06959777,0.012478753,0.000066429624],"about_ca_topic_score_codex":0.3221852,"about_ca_topic_score_gemma":0.30559093,"teacher_disagreement_score":0.67781484,"about_ca_system_score_codex":0.0032582406,"about_ca_system_score_gemma":0.007476464,"threshold_uncertainty_score":0.64061975},"labels":[],"label_agreement":null},{"id":"W2196855157","doi":"10.1093/jssam/smv022","title":"Clarifying Some Aspects of Variance Estimation in Two-Phase Sampling","year":2015,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Estimator; Jackknife resampling; Variance (accounting); Mathematics; Statistics; Sampling (signal processing); Bias of an estimator; Minimum-variance unbiased estimator; Computer science; Applied mathematics","score_opus":0.6371680919234616,"score_gpt":0.5436168220745937,"score_spread":0.09355126984886786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2196855157","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004781648,0.0006666347,0.991342,0.001232965,0.00010835676,0.000071469476,0.00003466063,0.000034334364,0.0017280752],"genre_scores_gemma":[0.23784725,0.0020115527,0.75301456,0.0021336994,0.001110062,0.00093561324,0.00015666921,0.00012014984,0.0026704485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94368804,0.045586087,0.0018343674,0.0032536031,0.004759948,0.0008779557],"domain_scores_gemma":[0.80314815,0.16878761,0.008373334,0.012504604,0.0066455165,0.0005407486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07277423,0.0011409101,0.0020489653,0.0019794162,0.0009978085,0.0028714084,0.0027527958,0.0033440178,0.0038608063],"category_scores_gemma":[0.23359299,0.0009895831,0.0018464598,0.003289538,0.0063316063,0.0061910413,0.0034404264,0.005256986,0.00052068377],"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":[0.000042163017,0.000041518007,0.0014763838,0.00027893615,0.000067772184,0.00015564807,0.000551512,0.012349974,0.0006658935,0.9547664,0.0011759903,0.028427683],"study_design_scores_gemma":[0.000067765824,0.00013803095,0.001311825,0.00015479197,0.00004113189,0.00013972197,0.00013928706,0.07387768,0.0009372903,0.9166383,0.0065098573,0.000044326487],"about_ca_topic_score_codex":0.0015688026,"about_ca_topic_score_gemma":0.0008983193,"teacher_disagreement_score":0.07277423,"about_ca_system_score_codex":0.0018023357,"about_ca_system_score_gemma":0.0022431763,"threshold_uncertainty_score":0.38487154},"labels":[],"label_agreement":null},{"id":"W2464696916","doi":"10.1093/jssam/smaa042","title":"Estimating the Size and Distribution of Networked Populations with Snowball Sampling","year":2020,"lang":"en","type":"preprint","venue":"Journal of Survey Statistics and Methodology","topic":"Census and Population Estimation","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Snowball sampling; Sample size determination; Inference; Computer science; Population; Sampling (signal processing); Population size; Graph; Sample (material); Selection (genetic algorithm); Statistics; Sampling design; Econometrics; Mathematics; Theoretical computer science; Machine learning; Artificial intelligence; Demography; Telecommunications","score_opus":0.5549742675041466,"score_gpt":0.47497496643355197,"score_spread":0.07999930107059461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2464696916","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11679395,0.000084770254,0.88163525,0.00010682364,0.000020437288,0.00011331208,0.00019570322,0.00010103486,0.0009487265],"genre_scores_gemma":[0.76970655,0.00018159961,0.22780804,0.000070084236,0.000041218944,0.0003025161,0.0006531052,0.000038414055,0.001198553],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976997,0.0014550074,0.00006993666,0.0003957729,0.0002863569,0.000093201445],"domain_scores_gemma":[0.9868217,0.009924386,0.001083132,0.0013259035,0.00063209387,0.00021286844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063865744,0.0004639976,0.0008241511,0.0016127072,0.0003728932,0.0011172147,0.0015618035,0.0005779675,0.0018458395],"category_scores_gemma":[0.02821905,0.0005676949,0.0005765164,0.0011297481,0.0011954375,0.0015140682,0.0018024327,0.0006840465,0.00021698345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004972031,0.00016517586,0.05230464,0.00015034241,0.0003062573,0.00035767144,0.0005109439,0.70622253,0.00517732,0.13549101,0.0021012696,0.096715674],"study_design_scores_gemma":[0.00003369175,0.000050243812,0.00364651,0.000026199503,0.000020276015,0.00005387224,0.00009212627,0.93252075,0.0010866101,0.06171593,0.0007416775,0.00001214029],"about_ca_topic_score_codex":0.0047331084,"about_ca_topic_score_gemma":0.00429237,"teacher_disagreement_score":0.0063865744,"about_ca_system_score_codex":0.00072554935,"about_ca_system_score_gemma":0.00058801466,"threshold_uncertainty_score":0.033775866},"labels":[],"label_agreement":null},{"id":"W2521098594","doi":"10.1093/jssam/smw013","title":"The Pseudo-EBLUP Estimator for a Weighted Average with an Application to the Canadian Survey of Employment, Payrolls and Hours","year":2016,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics; Estimator; Mean squared error; Statistics; Heteroscedasticity; Small area estimation; Bias of an estimator; Best linear unbiased prediction; Mixed model; Monte Carlo method; Minimum-variance unbiased estimator; Computer science","score_opus":0.18778461691358378,"score_gpt":0.33631120036945816,"score_spread":0.14852658345587438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2521098594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009093446,0.000480683,0.9881953,0.00021587397,0.0000609453,0.00012315363,0.00047837337,0.00021589578,0.0011363717],"genre_scores_gemma":[0.2231642,0.0009157456,0.768112,0.0003843725,0.00011264625,0.00084341405,0.0016890576,0.00021171045,0.0045668795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9908922,0.005041022,0.00032002828,0.0011018399,0.00238755,0.0002573791],"domain_scores_gemma":[0.97797716,0.012346451,0.0012595308,0.003922235,0.004281663,0.00021290875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012999402,0.0005717196,0.0010120098,0.0016413289,0.0006564235,0.001172336,0.0024869351,0.00080502237,0.0035106828],"category_scores_gemma":[0.06711335,0.00043144147,0.0010825188,0.0033098608,0.0011340556,0.0018263533,0.0014121587,0.0017470572,0.0005660167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020107834,0.00012801879,0.039949223,0.00074970647,0.00083531695,0.00024696725,0.0006341988,0.16447085,0.0021884146,0.22196054,0.015075137,0.5535605],"study_design_scores_gemma":[0.000112742,0.000255981,0.044936284,0.00035460741,0.00024208524,0.000371308,0.00029822037,0.74068165,0.0036015804,0.16848817,0.040513672,0.00014358594],"about_ca_topic_score_codex":0.07717991,"about_ca_topic_score_gemma":0.0846097,"teacher_disagreement_score":0.9979098,"about_ca_system_score_codex":0.0020902168,"about_ca_system_score_gemma":0.0069648214,"threshold_uncertainty_score":0.15346134},"labels":[],"label_agreement":null},{"id":"W2599342551","doi":"10.1093/jssam/smw035","title":"Adaptive and Network Sampling for Inference and Interventions in Changing Populations","year":2016,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"HIV, Drug Use, Sexual Risk","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sampling (signal processing); Sampling design; Inference; Computer science; Population; Adaptive sampling; Sample (material); Smoothing; Data mining; Simple random sample; Tracing; Machine learning; Statistics; Artificial intelligence; Mathematics","score_opus":0.6918727978663437,"score_gpt":0.5395960375672009,"score_spread":0.15227676029914283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599342551","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026569967,0.0003018832,0.99503833,0.00057545485,0.00008374419,0.00022416645,0.00004847172,0.000056719626,0.0010142291],"genre_scores_gemma":[0.13195764,0.0009371111,0.86134315,0.0005748388,0.0003079689,0.003551678,0.00016590301,0.000058125348,0.0011035152],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8744895,0.11596197,0.0015383778,0.003681037,0.0038957107,0.00043333502],"domain_scores_gemma":[0.6631449,0.30877423,0.007659683,0.015190883,0.004365028,0.0008653486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08948983,0.0012078413,0.0017974826,0.0026379144,0.0013366592,0.0022982683,0.0032346467,0.0023433988,0.0054118824],"category_scores_gemma":[0.26934674,0.0010374587,0.0021189686,0.00239683,0.007183936,0.0042887293,0.003731557,0.0049878755,0.00031535153],"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":[0.00017578552,0.00011494604,0.0040691444,0.00047742238,0.00045294888,0.0001036234,0.0006251532,0.09926884,0.0003093452,0.8261264,0.0015956935,0.066680714],"study_design_scores_gemma":[0.00012424111,0.00016681265,0.0008906093,0.0001762333,0.00006603564,0.00004492421,0.00009847936,0.2842137,0.0003568563,0.709453,0.004374321,0.000034796743],"about_ca_topic_score_codex":0.0041682627,"about_ca_topic_score_gemma":0.0032937808,"teacher_disagreement_score":0.08948983,"about_ca_system_score_codex":0.0026915735,"about_ca_system_score_gemma":0.0025113893,"threshold_uncertainty_score":0.4732731},"labels":[],"label_agreement":null},{"id":"W3018909183","doi":"10.1093/jssam/smaa004","title":"Multiply Robust Bootstrap Variance Estimation in the Presence of Singly Imputed Survey Data","year":2020,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; Université de Montréal","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Estimator; Quantile; Imputation (statistics); Statistics; Robustness (evolution); Variance (accounting); Point estimation; Econometrics; Mathematics; Robust statistics; Population; Computer science; Missing data","score_opus":0.6810327651611238,"score_gpt":0.4918226381347552,"score_spread":0.18921012702636858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018909183","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006676668,0.00026870723,0.9924636,0.00007617315,0.000017295873,0.000037489644,0.000026676506,0.00017921095,0.00025415057],"genre_scores_gemma":[0.19025904,0.00044308355,0.80771524,0.000117566466,0.00011931449,0.00034171614,0.00024430902,0.00012262355,0.00063719385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9813107,0.014436008,0.0005640582,0.0011343688,0.002280458,0.00027441754],"domain_scores_gemma":[0.95577806,0.03187373,0.0030469242,0.0069419728,0.0021288672,0.00023053377],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01627766,0.0008134197,0.0015357053,0.0019625057,0.0005729265,0.0010883838,0.002615853,0.0019276455,0.0016099841],"category_scores_gemma":[0.09556707,0.0006758928,0.0014850604,0.0018985629,0.0014114045,0.0015463239,0.0025308717,0.001773666,0.0006660212],"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":[0.00053356186,0.00021563582,0.014459787,0.00070427207,0.0010782507,0.0005529055,0.0007916652,0.11118942,0.008747135,0.17594434,0.0037114783,0.68207145],"study_design_scores_gemma":[0.0001286178,0.00048623665,0.008841,0.00022992212,0.00027560728,0.0010069092,0.00015203869,0.7462594,0.012778971,0.21960746,0.0100933295,0.00014055046],"about_ca_topic_score_codex":0.00071819715,"about_ca_topic_score_gemma":0.00075066945,"teacher_disagreement_score":0.9837223,"about_ca_system_score_codex":0.00043249375,"about_ca_system_score_gemma":0.00085875863,"threshold_uncertainty_score":0.0860855},"labels":[],"label_agreement":null},{"id":"W3041151490","doi":"10.1093/jssam/smab004","title":"Imputation Procedures in Surveys Using Nonparametric and Machine Learning Methods: An Empirical Comparison","year":2021,"lang":"en","type":"preprint","venue":"Journal of Survey Statistics and Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Imputation (statistics); Nonparametric statistics; Computer science; Machine learning; Artificial intelligence; Data mining; Data set; Econometrics; Missing data; Mathematics","score_opus":0.5742043220523099,"score_gpt":0.5636730961020205,"score_spread":0.010531225950289325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041151490","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32929245,0.017117992,0.6415478,0.002442937,0.00022136835,0.0005806891,0.00070205843,0.00036012125,0.0077345585],"genre_scores_gemma":[0.85371083,0.0028980179,0.14080372,0.00033790054,0.00018740511,0.00040797144,0.0007185184,0.00013200227,0.00080369663],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8072861,0.17839079,0.0026522358,0.002510478,0.008475523,0.00068490766],"domain_scores_gemma":[0.3414253,0.60348046,0.018713519,0.02414095,0.01141555,0.00082414865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13889143,0.0005960376,0.0013421898,0.0034564063,0.0007205585,0.0024127583,0.001953996,0.0017580244,0.0030771128],"category_scores_gemma":[0.39221826,0.00049115246,0.0017220769,0.0065948335,0.0025340288,0.004810079,0.0025196846,0.0021493388,0.00046337876],"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":[0.0024492415,0.0011714072,0.15394971,0.0025342675,0.003943099,0.00021432852,0.0027624548,0.122623086,0.0004608427,0.18345319,0.009550793,0.5168876],"study_design_scores_gemma":[0.0007252959,0.0024201537,0.18940221,0.0026082778,0.0012730506,0.0010992073,0.0032979806,0.51567876,0.001814469,0.26231688,0.019024592,0.0003392057],"about_ca_topic_score_codex":0.0013993017,"about_ca_topic_score_gemma":0.001115916,"teacher_disagreement_score":0.13889143,"about_ca_system_score_codex":0.0011207627,"about_ca_system_score_gemma":0.0015827714,"threshold_uncertainty_score":0.7345369},"labels":[],"label_agreement":null},{"id":"W3095502049","doi":"10.1093/jssam/smaa023","title":"Machine Learning for Occupation Coding—A Comparison Study","year":2020,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Koch Institute for Integrative Cancer Research, Massachusetts Institute of Technology; Robert Koch Institut; Universität Mannheim; Social Sciences and Humanities Research Council of Canada; Deutsche Forschungsgemeinschaft; Institut für Arbeitsmarkt- und Berufsforschung","keywords":"Computer science; Coding (social sciences); Machine learning; Artificial intelligence; Multinomial distribution; Data mining; Statistics; Mathematics","score_opus":0.40040143944183104,"score_gpt":0.47051340662495067,"score_spread":0.07011196718311963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095502049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.964805,0.002601005,0.022625115,0.001633907,0.00029784927,0.00031596379,0.0012869291,0.00035723374,0.0060769855],"genre_scores_gemma":[0.9811615,0.00039646716,0.0147958705,0.00015736796,0.000102390346,0.00018276376,0.0022790295,0.000063862666,0.0008607627],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9881981,0.008676227,0.00046077734,0.001105959,0.0011823723,0.00037667152],"domain_scores_gemma":[0.9058338,0.07850874,0.0028032558,0.0048511615,0.0070319194,0.00097111677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016942155,0.00085015694,0.0008303429,0.0029422406,0.0008997315,0.0019965598,0.0018563361,0.0014488361,0.0037453193],"category_scores_gemma":[0.06901777,0.00028472987,0.0012256486,0.0029851699,0.0010623398,0.002800574,0.0013081041,0.0022369768,0.001336861],"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":[0.006119942,0.0044771996,0.33913112,0.0018139206,0.0015624271,0.0002549437,0.0022522556,0.08193183,0.001026108,0.012912861,0.02636205,0.5221554],"study_design_scores_gemma":[0.0006985183,0.0027241933,0.2539698,0.0007449757,0.0006943414,0.00033830397,0.0049619055,0.7021742,0.0027090204,0.014903416,0.015891852,0.00018952318],"about_ca_topic_score_codex":0.011154591,"about_ca_topic_score_gemma":0.0068100956,"teacher_disagreement_score":0.98305786,"about_ca_system_score_codex":0.0025131055,"about_ca_system_score_gemma":0.0016008797,"threshold_uncertainty_score":0.08959979},"labels":[],"label_agreement":null},{"id":"W3097049086","doi":"10.1093/jssam/smaa016","title":"Targeting Key Survey Variables at the Unit Nonresponse Treatment Stage","year":2020,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Estimator; Non-response bias; Weighting; Missing data; Statistics; Propensity score matching; Computer science; Econometrics; Inverse probability weighting; Set (abstract data type); Mathematics; Medicine","score_opus":0.6424708043159415,"score_gpt":0.4784392389837912,"score_spread":0.1640315653321503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097049086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030456113,0.0003371737,0.9629795,0.0010539995,0.00022841233,0.0016668602,0.0003884945,0.00021233999,0.0026770798],"genre_scores_gemma":[0.5502732,0.0005201657,0.43587494,0.0011106502,0.00024143948,0.0059976033,0.00072641793,0.00010143227,0.0051541314],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9643867,0.029897664,0.0010309702,0.001954475,0.0020505618,0.000679477],"domain_scores_gemma":[0.9640807,0.020430027,0.0044750846,0.007896169,0.0027356595,0.00038241394],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.034617614,0.00072104036,0.0015263467,0.001352248,0.0010679679,0.0014827529,0.00251941,0.0018146901,0.0075283386],"category_scores_gemma":[0.09535882,0.0004901005,0.0014916728,0.0030429214,0.0013762343,0.0016479613,0.0026393912,0.0025589583,0.001525198],"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":[0.00071025704,0.0011693368,0.059109047,0.0015378107,0.00080013345,0.000267492,0.0016839061,0.03711893,0.0042279935,0.25310305,0.01307106,0.62720096],"study_design_scores_gemma":[0.00080670294,0.0019000245,0.06569655,0.00103821,0.00089194684,0.00031019753,0.0015179935,0.45784047,0.026197292,0.3909906,0.052622132,0.00018785028],"about_ca_topic_score_codex":0.0016687186,"about_ca_topic_score_gemma":0.001826222,"teacher_disagreement_score":0.9653824,"about_ca_system_score_codex":0.0011404016,"about_ca_system_score_gemma":0.0027114644,"threshold_uncertainty_score":0.18307763},"labels":[],"label_agreement":null},{"id":"W3132157226","doi":"10.1093/jssam/smaa046","title":"Who Counts? Measuring Disability Cross-Nationally in Census Data","year":2021,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Health disparities and outcomes","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Toronto","funders":"","keywords":"Microdata (statistics); Standardization; Terminology; Census; Harmonization; International Classification of Functioning, Disability and Health; Medical model of disability; Psychology; Gerontology; Actuarial science; Medicine; Political science; Environmental health; Business; Population; Psychiatry; Physical therapy","score_opus":0.6228852929621991,"score_gpt":0.5393534200347042,"score_spread":0.08353187292749487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132157226","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.633811,0.011979007,0.07043922,0.026056971,0.0014478075,0.0017543836,0.19188556,0.00045974492,0.062166322],"genre_scores_gemma":[0.89921993,0.0043173586,0.04791232,0.0019237883,0.00030685333,0.0022416997,0.042579792,0.00012826742,0.0013699537],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9836369,0.00959858,0.0028174731,0.0011451746,0.0022850924,0.0005167509],"domain_scores_gemma":[0.9799446,0.0069177533,0.006155436,0.0026619227,0.0038908855,0.00042947347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013908801,0.00031623183,0.0005018019,0.0043993294,0.00043111687,0.0017738036,0.0008564432,0.0004053759,0.002516471],"category_scores_gemma":[0.059572063,0.00027580373,0.0005270666,0.008681746,0.0005788217,0.0028415164,0.0019936962,0.001050684,0.0006422422],"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":[0.000044070053,0.00009140057,0.7735083,0.001191517,0.00063687784,0.00005920103,0.007670299,0.0010278017,0.00025267864,0.018617682,0.06743923,0.12946084],"study_design_scores_gemma":[0.00004052572,0.00010567789,0.8171711,0.0039012586,0.00025069827,0.00030402496,0.01640746,0.0040183356,0.0012191666,0.016311346,0.14013049,0.00013982234],"about_ca_topic_score_codex":0.029088972,"about_ca_topic_score_gemma":0.02784789,"teacher_disagreement_score":0.029088972,"about_ca_system_score_codex":0.0012494744,"about_ca_system_score_gemma":0.0017766587,"threshold_uncertainty_score":0.073557675},"labels":[],"label_agreement":null},{"id":"W3186908110","doi":"10.1093/jssam/smab007","title":"Lack of Replication or Generalization? Cultural Values Explain a Question Wording Effect","year":2021,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Cultural Differences and Values","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"Economic and Social Research Council","keywords":"Replication (statistics); Generalization; Epistemology; Econometrics; Mathematical economics; Computer science; Psychology; Positive economics; Mathematics; Statistics; Economics; Philosophy","score_opus":0.5870137882448033,"score_gpt":0.5534318512773253,"score_spread":0.03358193696747802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186908110","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6773633,0.006479692,0.20696452,0.026765078,0.003461801,0.0060936273,0.0016804525,0.0013691427,0.06982235],"genre_scores_gemma":[0.981834,0.00025185235,0.011969561,0.002929011,0.0002872793,0.0013036425,0.0002267202,0.00021947123,0.000978493],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.6465013,0.2544641,0.02206345,0.033250574,0.03997155,0.0037489627],"domain_scores_gemma":[0.12546088,0.705332,0.03559264,0.115097634,0.017226802,0.0012899947],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3319109,0.0013920466,0.002126631,0.0028996305,0.0018469968,0.0035402353,0.005230397,0.0030262908,0.010358024],"category_scores_gemma":[0.6974455,0.0014924791,0.0027535406,0.002489725,0.015326354,0.009144391,0.006254712,0.004667397,0.0013422916],"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":[0.005493981,0.0019500371,0.5647778,0.0068933032,0.0051557897,0.0017999602,0.068443574,0.0035315373,0.012477309,0.12435281,0.018644465,0.18647942],"study_design_scores_gemma":[0.0017115936,0.002842512,0.56992495,0.0036878583,0.0028587687,0.0017704394,0.024553126,0.021331066,0.023303382,0.30943203,0.03799847,0.00058579806],"about_ca_topic_score_codex":0.005206643,"about_ca_topic_score_gemma":0.0028542737,"teacher_disagreement_score":0.6680891,"about_ca_system_score_codex":0.0029240851,"about_ca_system_score_gemma":0.002593202,"threshold_uncertainty_score":0.8238728},"labels":[],"label_agreement":null},{"id":"W3190138084","doi":"10.1093/jssam/smab022","title":"A Model-Assisted Approach for Finding Coding Errors in Manual Coding of Open-Ended Questions","year":2021,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Actua; University of Waterloo; Roche (Canada)","funders":"","keywords":"Coding (social sciences); Computer science; Statistics; Natural language processing; Artificial intelligence; Mathematics","score_opus":0.7870611956524755,"score_gpt":0.5441244124235828,"score_spread":0.24293678322889267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3190138084","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017919995,0.0000631522,0.97781473,0.00032393046,0.00004360281,0.00039988518,0.00013746093,0.0028527325,0.00044448616],"genre_scores_gemma":[0.22544034,0.000041468746,0.77140886,0.0002798273,0.00003612025,0.0012336562,0.00052815274,0.00020907499,0.0008225068],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9337932,0.0496453,0.0027495623,0.0066561974,0.0062668645,0.0008888423],"domain_scores_gemma":[0.765063,0.1815021,0.014771248,0.018925797,0.018238237,0.0014996376],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.056063138,0.0025578921,0.002239944,0.0063928114,0.0019061529,0.0033269878,0.004967253,0.0031894722,0.0028086905],"category_scores_gemma":[0.1579796,0.001601642,0.002124382,0.0032263862,0.0017897647,0.0032414477,0.0043911147,0.0041755764,0.001588715],"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":[0.001521416,0.001233367,0.029882614,0.00070201716,0.0009402582,0.00036128372,0.004892926,0.16117808,0.00865052,0.011804199,0.010961448,0.7678719],"study_design_scores_gemma":[0.00007303025,0.00014277657,0.0021780236,0.00007859848,0.000046066452,0.000118861964,0.00035011754,0.9820195,0.0029865985,0.010770242,0.001165308,0.00007074501],"about_ca_topic_score_codex":0.0091786515,"about_ca_topic_score_gemma":0.014512525,"teacher_disagreement_score":0.9439369,"about_ca_system_score_codex":0.0032818771,"about_ca_system_score_gemma":0.005248129,"threshold_uncertainty_score":0.2964937},"labels":[],"label_agreement":null},{"id":"W3193938275","doi":"10.1093/jssam/smab029","title":"Bootstrap Estimation of the Conditional Bias for Measuring Influence in Complex Surveys","year":2021,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Estimator; Statistics; Sampling (signal processing); Variance (accounting); Sampling design; Conditional variance; Sample (material); Econometrics; Mathematics; Estimation; Population; Computer science; Autoregressive conditional heteroskedasticity","score_opus":0.7007546710550773,"score_gpt":0.5016242371275665,"score_spread":0.19913043392751073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193938275","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017763639,0.00034683806,0.9798472,0.00015333094,0.000054448403,0.00012931612,0.00010062826,0.00017490715,0.0014296452],"genre_scores_gemma":[0.5966239,0.00055994536,0.39989507,0.00031583544,0.00020345509,0.0009868597,0.0005149719,0.00021105743,0.00068895484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.94924015,0.04064842,0.0015248432,0.002259632,0.0058214166,0.0005055041],"domain_scores_gemma":[0.6821668,0.26756537,0.015250076,0.022962946,0.011129583,0.0009252589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05431816,0.00086077565,0.0015883732,0.0040486157,0.0008987564,0.0016876743,0.0023569355,0.0017582857,0.003384317],"category_scores_gemma":[0.33559042,0.00063483353,0.0017277359,0.0040812264,0.0034372313,0.0028433844,0.003249537,0.0023842654,0.00062098727],"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":[0.0005819841,0.00024137019,0.09318882,0.00086350663,0.0014370348,0.0005838199,0.0014381452,0.17717451,0.0037367167,0.4577108,0.0049423003,0.25810093],"study_design_scores_gemma":[0.00010831399,0.0003053213,0.026085285,0.00053756306,0.0002754661,0.0004495257,0.00030290624,0.6222063,0.005314244,0.33653164,0.007760551,0.00012284076],"about_ca_topic_score_codex":0.0028535163,"about_ca_topic_score_gemma":0.001819096,"teacher_disagreement_score":0.05431816,"about_ca_system_score_codex":0.0013807681,"about_ca_system_score_gemma":0.0011854781,"threshold_uncertainty_score":0.2872653},"labels":[],"label_agreement":null},{"id":"W4206410105","doi":"10.1093/jssam/smab057","title":"Neighborhood Bootstrap for Respondent-Driven Sampling","year":2021,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"HIV, Drug Use, Sexual Risk","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Resampling; Estimator; Leverage (statistics); Sampling (signal processing); Statistics; Consistency (knowledge bases); Computer science; Variance (accounting); Econometrics; Respondent; Tree (set theory); Bootstrap aggregating; Sample (material); Mathematics; Artificial intelligence","score_opus":0.5731953672614928,"score_gpt":0.5175135239374811,"score_spread":0.055681843324011715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206410105","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009167859,0.00022880829,0.9885039,0.00025780033,0.00006941634,0.00019449009,0.00015338436,0.00019356454,0.0012307097],"genre_scores_gemma":[0.3985195,0.00042725855,0.5955581,0.0004812927,0.00026993695,0.0014341803,0.0008556653,0.0001657818,0.0022883706],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97232866,0.02307852,0.00048819665,0.0014644783,0.0022759151,0.00036419937],"domain_scores_gemma":[0.85501415,0.11923984,0.004464358,0.012889462,0.007300717,0.0010915019],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.039106574,0.00079688744,0.0016744822,0.0020661307,0.0013147553,0.0014801535,0.0038238713,0.002106114,0.0053315507],"category_scores_gemma":[0.16429494,0.00068456726,0.0016551156,0.002181126,0.0026196826,0.0019123389,0.0030179664,0.0027688488,0.0010555831],"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":[0.0006470848,0.000230059,0.017200083,0.00052127434,0.00042833923,0.00060897827,0.00085695094,0.28522444,0.0013616207,0.5858139,0.006418095,0.10068923],"study_design_scores_gemma":[0.00006655122,0.00008866259,0.0011463844,0.000107249725,0.000033057535,0.00010532117,0.0000806938,0.8854811,0.00056267396,0.10910791,0.0031931747,0.000027273629],"about_ca_topic_score_codex":0.0057193954,"about_ca_topic_score_gemma":0.003291787,"teacher_disagreement_score":0.96089345,"about_ca_system_score_codex":0.0013742173,"about_ca_system_score_gemma":0.0016892483,"threshold_uncertainty_score":0.2068178},"labels":[],"label_agreement":null},{"id":"W4226069045","doi":"10.1093/jssam/smac023","title":"Augmenting Survey Data with Digital Trace Data: Is There a Threat to Panel Retention?","year":2022,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft","keywords":"Panel data; Panel survey; Panel discussion; German; Quarter (Canadian coin); Survey data collection; Data retention; TRACE (psycholinguistics); Worry; Computer science; Psychology; Econometrics; Computer security; Advertising; Business; Statistics; Mathematics; Economics; Demographic economics; Geography","score_opus":0.7842892671678372,"score_gpt":0.5220393702231063,"score_spread":0.2622498969447309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226069045","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75131017,0.0017777683,0.13192177,0.061674524,0.0013892187,0.0028591643,0.0021715665,0.0011041262,0.045791645],"genre_scores_gemma":[0.95930225,0.00029804854,0.024951838,0.009016387,0.0003626865,0.0018649367,0.00057209877,0.00012240371,0.003509242],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.69448125,0.26283234,0.006975172,0.007051365,0.024423972,0.004235863],"domain_scores_gemma":[0.26109996,0.5606416,0.054878175,0.0836899,0.03570382,0.0039866315],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22723463,0.00046163469,0.00085558067,0.001260664,0.0029277867,0.004779514,0.0033276428,0.002279633,0.010780631],"category_scores_gemma":[0.5621638,0.00083525147,0.0011254712,0.0027535981,0.0034101135,0.005741832,0.0048595266,0.0039113034,0.0024620336],"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":[0.0025464965,0.002058869,0.46304247,0.0018357396,0.0011813686,0.00034321522,0.022805095,0.0030512095,0.00362783,0.015619385,0.02806612,0.4558221],"study_design_scores_gemma":[0.0009037677,0.010770316,0.60758126,0.008343349,0.0016123445,0.0016685283,0.054800738,0.036901988,0.026331045,0.063376695,0.18719165,0.00051837676],"about_ca_topic_score_codex":0.0060109473,"about_ca_topic_score_gemma":0.0056364224,"teacher_disagreement_score":0.7727654,"about_ca_system_score_codex":0.0019860684,"about_ca_system_score_gemma":0.0044411905,"threshold_uncertainty_score":0.9529573},"labels":[],"label_agreement":null},{"id":"W4248615235","doi":"10.1093/jssam/smab047","title":"A Rescaling Bootstrap Approach For Imputed Survey Data","year":2021,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Estimator; Statistics; Mathematics; Econometrics; Variance (accounting); Computer science; Missing data","score_opus":0.8566941241856907,"score_gpt":0.5528146051570141,"score_spread":0.3038795190286766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248615235","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002481619,0.00013821045,0.9968208,0.00005513504,0.000026896438,0.000027798456,0.000040137234,0.00017423416,0.00023519716],"genre_scores_gemma":[0.1884731,0.0004660548,0.8088207,0.00018921531,0.00018044308,0.0004274081,0.00043239837,0.00018020955,0.00083038537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9890282,0.0078977235,0.00041432423,0.00091416115,0.0015224355,0.00022309505],"domain_scores_gemma":[0.98704404,0.0077598304,0.00077469193,0.0026858295,0.00155455,0.00018096589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009453639,0.0006697754,0.0013438687,0.0023422674,0.0005600858,0.0007783429,0.0027040283,0.0010208436,0.0025156885],"category_scores_gemma":[0.042208258,0.00045764976,0.0010394611,0.0030210756,0.0010383663,0.0013121658,0.0018236196,0.0017605611,0.0007151063],"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":[0.00029898007,0.00021905413,0.008560794,0.0005754995,0.000511213,0.0008226168,0.0007146913,0.16413228,0.008979416,0.1914281,0.0060956897,0.61766154],"study_design_scores_gemma":[0.00004976302,0.000120338394,0.0025737104,0.000083410516,0.0000686132,0.0003031907,0.00008599492,0.9018056,0.0033618787,0.08369855,0.007789481,0.000059443344],"about_ca_topic_score_codex":0.001068551,"about_ca_topic_score_gemma":0.0008008559,"teacher_disagreement_score":0.009453639,"about_ca_system_score_codex":0.00047084887,"about_ca_system_score_gemma":0.0006441947,"threshold_uncertainty_score":0.049996197},"labels":[],"label_agreement":null},{"id":"W4309622736","doi":"10.1093/jssam/smac027","title":"Jackknife Bias-Corrected Generalized Regression Estimator in Survey Sampling","year":2022,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Jackknife resampling; Estimator; Statistics; Mathematics; Mean squared error; Bias of an estimator; Population; Minimum-variance unbiased estimator; Sample size determination; Sample (material); Variance (accounting); Econometrics","score_opus":0.7039901809482423,"score_gpt":0.5070651107249131,"score_spread":0.19692507022332917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309622736","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008054975,0.00025303077,0.9908744,0.00006606098,0.000029747409,0.00005153217,0.00004990075,0.00020971608,0.00041072103],"genre_scores_gemma":[0.27570164,0.00039298434,0.7210756,0.00021840833,0.00007814714,0.00038488396,0.00030692943,0.0001651136,0.0016761806],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9709872,0.0241124,0.0005299925,0.0016634815,0.0022652699,0.00044162298],"domain_scores_gemma":[0.9586712,0.027835423,0.003977719,0.0051900945,0.0039849393,0.00034063382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025143238,0.00086615974,0.0018622148,0.001852541,0.00053721596,0.00082272926,0.0028289063,0.001548239,0.001866535],"category_scores_gemma":[0.10219341,0.00060575345,0.00096964336,0.002518096,0.0012676724,0.0017155943,0.0016924604,0.0015517961,0.00066547876],"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":[0.00045576648,0.00017710867,0.026789732,0.0007083539,0.00083978433,0.0003889695,0.00060803245,0.49888888,0.0036967874,0.16641061,0.006494174,0.29454184],"study_design_scores_gemma":[0.00009805144,0.00023809339,0.0055444627,0.00019769135,0.00011979374,0.00036755283,0.0001260768,0.9083502,0.0035861123,0.07462406,0.0066636326,0.00008412466],"about_ca_topic_score_codex":0.004361883,"about_ca_topic_score_gemma":0.003593879,"teacher_disagreement_score":0.025143238,"about_ca_system_score_codex":0.0009220726,"about_ca_system_score_gemma":0.0014514184,"threshold_uncertainty_score":0.1329717},"labels":[],"label_agreement":null},{"id":"W4378232119","doi":"10.1093/jssam/smad015","title":"Automated Classification for Open-Ended Questions with BERT","year":2023,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Topic Modeling","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Social Sciences and Humanities Research Council; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Coding (social sciences); Artificial intelligence; Boosting (machine learning); Natural language processing; Machine learning; Language model; Training set; Statistics","score_opus":0.48587528374401967,"score_gpt":0.4643715025409455,"score_spread":0.021503781203074168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378232119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55544287,0.0009808594,0.41260457,0.0016896646,0.00035074208,0.00080106047,0.0059223785,0.013896588,0.008311239],"genre_scores_gemma":[0.8951675,0.00009474348,0.09531221,0.00020271224,0.000078450925,0.00037581392,0.0061345287,0.00018565111,0.0024483253],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9930335,0.004431301,0.0003845817,0.00093502435,0.00084858853,0.0003670184],"domain_scores_gemma":[0.9385139,0.04560056,0.00287909,0.006273583,0.0057350774,0.0009978196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009821454,0.0009717103,0.00075563666,0.0024421075,0.0004476257,0.0012810187,0.0015218678,0.001466596,0.0042967983],"category_scores_gemma":[0.05542549,0.00033721264,0.00065036135,0.0015656651,0.0006401632,0.002610463,0.0016496527,0.002226998,0.0036219745],"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":[0.0019803115,0.0010556334,0.09056731,0.0009987942,0.00014893213,0.000266471,0.0022777927,0.06424219,0.01685926,0.009624635,0.043751307,0.76822746],"study_design_scores_gemma":[0.00006830709,0.00030633147,0.029977754,0.00012002933,0.000031288837,0.00016755113,0.0007839292,0.9298141,0.013790926,0.014504878,0.010371138,0.000063738706],"about_ca_topic_score_codex":0.0020516748,"about_ca_topic_score_gemma":0.002885373,"teacher_disagreement_score":0.009821454,"about_ca_system_score_codex":0.0012091104,"about_ca_system_score_gemma":0.0009440864,"threshold_uncertainty_score":0.051941454},"labels":[],"label_agreement":null},{"id":"W4392712152","doi":"10.1093/jssam/smae002","title":"Estimation of a Population Total Under Nonresponse Using Follow-up","year":2024,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Estimation; Statistics; Econometrics; Computer science; Population; Mathematics; Medicine; Environmental health; Economics","score_opus":0.554927493029936,"score_gpt":0.5121732745467844,"score_spread":0.04275421848315164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392712152","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062339727,0.0001992264,0.93536335,0.00022638866,0.000030490968,0.00032893397,0.00014211911,0.00015712457,0.0012125608],"genre_scores_gemma":[0.6120263,0.00034236495,0.38306373,0.00026770166,0.00007309697,0.0013989214,0.00061623985,0.000047240752,0.0021644114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9753203,0.020113945,0.00064778194,0.0016013907,0.002034655,0.00028197074],"domain_scores_gemma":[0.94258183,0.041599844,0.005178969,0.0073068053,0.0029893355,0.00034319787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03570823,0.00056815334,0.0013860533,0.0029143323,0.00048915163,0.0010571651,0.0019946517,0.0009670279,0.0024173614],"category_scores_gemma":[0.10983529,0.0004771174,0.00094827206,0.0025106943,0.00086526095,0.0019657088,0.0019184063,0.0009622602,0.00033721342],"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":[0.0004420873,0.0006067135,0.08236342,0.00073918153,0.0009976077,0.00016086812,0.0016538259,0.087262444,0.002300905,0.105759144,0.0026106841,0.7151032],"study_design_scores_gemma":[0.00039779063,0.0020847162,0.08719757,0.00044877248,0.00076779036,0.00036931006,0.0009956377,0.6739724,0.0126343435,0.20438465,0.016593942,0.0001529985],"about_ca_topic_score_codex":0.0013252376,"about_ca_topic_score_gemma":0.0014471263,"teacher_disagreement_score":0.03570823,"about_ca_system_score_codex":0.0008023783,"about_ca_system_score_gemma":0.0011624979,"threshold_uncertainty_score":0.18884546},"labels":[],"label_agreement":null},{"id":"W4392953941","doi":"10.1093/jssam/smae003","title":"Text Messages to Facilitate the Transition to Web-First Sequential Mixed-Mode Designs in Longitudinal Surveys","year":2024,"lang":"en","type":"article","venue":"Journal of Survey Statistics and 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":false,"route_about_ca":true,"ca_institutions":"","funders":"Economic and Social Research Council; University of Essex","keywords":"Web survey; Sample (material); World Wide Web; Mode (computer interface); Computer science; Quarter (Canadian coin); Mixed mode; Psychology; Geography; Human–computer interaction","score_opus":0.6092991703284136,"score_gpt":0.5016061607140164,"score_spread":0.1076930096143972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392953941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.53781945,0.00038367417,0.40978432,0.0016681161,0.00081848225,0.034552503,0.0015042769,0.0032371585,0.010232],"genre_scores_gemma":[0.43277916,0.00015698862,0.4975649,0.0010829178,0.00031999694,0.064489506,0.00037570036,0.0002612524,0.0029695968],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.93721294,0.055892836,0.0025504709,0.0017284609,0.001987636,0.0006276486],"domain_scores_gemma":[0.76536983,0.19068232,0.013782917,0.02088692,0.00696677,0.0023111668],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.053171862,0.0010379396,0.00079502957,0.0011483906,0.00092130544,0.0018182686,0.0013564683,0.0015840642,0.014037897],"category_scores_gemma":[0.14485882,0.0010738259,0.0007942292,0.001020564,0.0009533288,0.0018928797,0.002156841,0.0018043476,0.0020536059],"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":[0.034425728,0.02755745,0.03687182,0.0049725086,0.0006429399,0.0002838606,0.019936224,0.013388898,0.046258163,0.021755636,0.01139524,0.7825116],"study_design_scores_gemma":[0.050327063,0.260322,0.2307256,0.0036642898,0.0021557014,0.0006536182,0.0066305497,0.115886584,0.12651785,0.07742117,0.12438542,0.0013101225],"about_ca_topic_score_codex":0.00037027328,"about_ca_topic_score_gemma":0.0007308,"teacher_disagreement_score":0.9468281,"about_ca_system_score_codex":0.0007008924,"about_ca_system_score_gemma":0.0010353744,"threshold_uncertainty_score":0.28120303},"labels":[],"label_agreement":null},{"id":"W4396570341","doi":"10.1093/jssam/smae021","title":"Should We Offer Web, Paper, or Both? A Comparison of Single- and Mixed-Response Mode Treatments in a Mail Survey","year":2024,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Methodology and Nonresponse","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Center for Science and Engineering Statistics; U.S. Census Bureau; Washington State University; American Institutes for Research; McMaster University; U.S. Department of Education; National Science Foundation","keywords":"Mixed mode; The Internet; Web survey; Mode (computer interface); Consistency (knowledge bases); Sample (material); Response time; Incentive; Response bias; Psychology; Computer science; Advertising; World Wide Web; Social psychology; Business; Artificial intelligence; Economics; Human–computer interaction","score_opus":0.6823083142602526,"score_gpt":0.5520341180469343,"score_spread":0.13027419621331837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396570341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.971797,0.00024888414,0.009720054,0.0014132948,0.0005010347,0.008322372,0.000469103,0.00034796834,0.0071802987],"genre_scores_gemma":[0.94669974,0.00019669929,0.020330446,0.0019065393,0.0003811428,0.027269498,0.00029265264,0.00006143917,0.0028618975],"study_design_codex":"design_other","study_design_gemma":"nonrandomized_trial","domain_scores_codex":[0.9079624,0.07728196,0.0037649083,0.0035544261,0.0056225187,0.0018138216],"domain_scores_gemma":[0.7960584,0.16418284,0.018935941,0.013632785,0.003499316,0.0036906498],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.05662949,0.0012364638,0.0016198077,0.0014182546,0.001528024,0.002990016,0.0024167302,0.003983324,0.012608792],"category_scores_gemma":[0.15939733,0.0013442994,0.001628072,0.00090403104,0.0022401304,0.0032229193,0.0017872058,0.003384129,0.0029574626],"study_design_candidate":"nonrandomized_trial","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":[0.3360558,0.17195573,0.052429996,0.0035756107,0.002576306,0.00024842127,0.011234234,0.008618061,0.013415232,0.014179432,0.0075832945,0.37812793],"study_design_scores_gemma":[0.13041227,0.510956,0.18841924,0.0018287776,0.0036329702,0.00024249256,0.009338362,0.066589914,0.027524287,0.03333931,0.02667935,0.001037025],"about_ca_topic_score_codex":0.00084756734,"about_ca_topic_score_gemma":0.0007073649,"teacher_disagreement_score":0.9433705,"about_ca_system_score_codex":0.001926146,"about_ca_system_score_gemma":0.0020162957,"threshold_uncertainty_score":0.29948896},"labels":[],"label_agreement":null},{"id":"W4402591820","doi":"10.1093/jssam/smae032","title":"Model-Based Prediction for Small Domains Using Covariates: A Comparison of Four Methods","year":2024,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Work & Health; McGill University; McGill University Health Centre","funders":"Institut de Valorisation des Données","keywords":"Covariate; Computer science; Statistics; Econometrics; Artificial intelligence; Data mining; Machine learning; Mathematics","score_opus":0.7662515417175665,"score_gpt":0.5679552565310851,"score_spread":0.19829628518648135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402591820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033331003,0.0017103516,0.96302074,0.0005040528,0.000058827743,0.00011425305,0.00011232125,0.00045878952,0.00068962184],"genre_scores_gemma":[0.5508233,0.001988514,0.44406545,0.00035248545,0.00024314654,0.00043808765,0.0007521375,0.000280139,0.0010567325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934047,0.0050281826,0.00022380141,0.0005706307,0.00064614916,0.0001265408],"domain_scores_gemma":[0.9579965,0.035250608,0.0016999021,0.0025835172,0.0019899094,0.0004796731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018444328,0.0011659698,0.0022365544,0.0015105214,0.00052747637,0.0015712723,0.0026526684,0.0015537292,0.0013609676],"category_scores_gemma":[0.040273562,0.0006304921,0.0016258275,0.0015452722,0.0008757801,0.002719437,0.0022508502,0.0028482,0.00033654604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065154245,0.00036322483,0.015266181,0.00033700926,0.0008226472,0.00012822244,0.0003371258,0.72523874,0.0009646729,0.020547694,0.0019681521,0.23337477],"study_design_scores_gemma":[0.000029919367,0.000056703284,0.00086385367,0.00003483142,0.00002779928,0.000020205553,0.000022952625,0.99284184,0.00016654187,0.0055630915,0.0003575002,0.000014762143],"about_ca_topic_score_codex":0.0048087053,"about_ca_topic_score_gemma":0.00254553,"teacher_disagreement_score":0.018444328,"about_ca_system_score_codex":0.0007306555,"about_ca_system_score_gemma":0.0013415369,"threshold_uncertainty_score":0.097544074},"labels":[],"label_agreement":null},{"id":"W4417210052","doi":"10.1093/jssam/smaf023","title":"Analyzing List-Style Open-Ended Questions: Combining Texts from Individual Answer Boxes Improves Classification with Language Models","year":2025,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Classifier (UML); Factorial; Transformer; Language model; Encoder; Question answering","score_opus":0.1819431608627828,"score_gpt":0.3925421491784883,"score_spread":0.21059898831570548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417210052","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68798774,0.00043952648,0.30162558,0.0008992046,0.00015562554,0.00047997863,0.0012917059,0.0031625573,0.003958044],"genre_scores_gemma":[0.889342,0.00008131956,0.10671594,0.0001974179,0.0000836684,0.00030210023,0.0016400535,0.00016380993,0.0014737553],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9864066,0.009822274,0.00063785136,0.0015180345,0.0012468407,0.00036843237],"domain_scores_gemma":[0.85148835,0.12985285,0.0050208685,0.0047253342,0.0075901835,0.0013223919],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0120942015,0.00091549597,0.000964469,0.0021773477,0.00061363535,0.0026940643,0.0009943836,0.0015958027,0.0037622256],"category_scores_gemma":[0.07694288,0.00029345087,0.0008439714,0.0014864341,0.0006095132,0.0036184073,0.0018151754,0.0018397857,0.0021927457],"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":[0.0046343505,0.0023906846,0.14412019,0.0012020796,0.00043594936,0.00022937125,0.0035191425,0.031262748,0.046536703,0.0036236418,0.011937998,0.75010717],"study_design_scores_gemma":[0.0001918038,0.001718379,0.0763791,0.00029994483,0.00028755155,0.00018623107,0.0022585567,0.84214526,0.056125503,0.013262848,0.006967902,0.00017694752],"about_ca_topic_score_codex":0.0011683746,"about_ca_topic_score_gemma":0.0017378266,"teacher_disagreement_score":0.9879058,"about_ca_system_score_codex":0.00081497844,"about_ca_system_score_gemma":0.00066869694,"threshold_uncertainty_score":0.06396103},"labels":[],"label_agreement":null},{"id":"W7119808922","doi":"10.1093/jssam/smaf043","title":"Correcting Selection Bias in Non-Probability Two-Phase Payment Survey","year":2025,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bank of Canada","funders":"","keywords":"Selection (genetic algorithm); Selection bias; Variance (accounting); Calibration; Payment; Estimation","score_opus":0.47385081697316495,"score_gpt":0.5186313866550564,"score_spread":0.044780569681891425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7119808922","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022521302,0.00008502519,0.9755367,0.0003346114,0.000044948283,0.00022861412,0.00009272679,0.00014770421,0.001008474],"genre_scores_gemma":[0.5543257,0.0002528156,0.44139758,0.0004304781,0.00011905593,0.0009232375,0.00034705835,0.00006841293,0.0021355662],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9550615,0.038388673,0.0009245457,0.0019927467,0.003066132,0.0005662702],"domain_scores_gemma":[0.81292355,0.15450853,0.010309489,0.015442993,0.0063038464,0.0005115237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0488295,0.0006711688,0.0012137995,0.0014825439,0.0006055344,0.0017898916,0.0026223387,0.0016781634,0.0042049545],"category_scores_gemma":[0.25024796,0.00085653417,0.0010448706,0.00245824,0.0015406361,0.003672973,0.002484631,0.0018345637,0.000574153],"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":[0.00037381722,0.00037416624,0.03889026,0.00057840993,0.000297427,0.0003948653,0.000946632,0.11790386,0.00159833,0.5983975,0.004685098,0.23555979],"study_design_scores_gemma":[0.00016299692,0.00030147648,0.010135101,0.0001262406,0.000081412196,0.00021669563,0.00016472494,0.663299,0.002045761,0.3173563,0.0060531003,0.00005716707],"about_ca_topic_score_codex":0.0018391397,"about_ca_topic_score_gemma":0.0014828128,"teacher_disagreement_score":0.0488295,"about_ca_system_score_codex":0.0009561467,"about_ca_system_score_gemma":0.0018457869,"threshold_uncertainty_score":0.25823814},"labels":[],"label_agreement":null},{"id":"W7133121762","doi":"10.1093/jssam/smaf036","title":"Smoothed pseudo-population bootstrap methods with applications to finite population quantiles","year":2025,"lang":"en","type":"article","venue":"Journal of Survey Statistics and 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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Estimator; Resampling; Confidence interval; Bootstrapping (finance); Quantile; Jackknife resampling; Poisson sampling; Population; CDF-based nonparametric confidence interval; Sampling (signal processing)","score_opus":0.4880688058564743,"score_gpt":0.5424089670887016,"score_spread":0.05434016123222729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133121762","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028288863,0.000116117684,0.9964844,0.00005174743,0.00001896853,0.000023731838,0.000020631147,0.0001930827,0.00026245325],"genre_scores_gemma":[0.2742997,0.00049544114,0.72231096,0.00020141815,0.00013528598,0.00057471765,0.0002841214,0.00029307342,0.0014053163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99418855,0.004428512,0.00014192375,0.00031191783,0.00081614725,0.00011298532],"domain_scores_gemma":[0.96575713,0.02732205,0.0012673304,0.0029322507,0.0024515928,0.00026963008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00960835,0.0005820905,0.0009761308,0.0021012963,0.00047908505,0.0010998846,0.0019677174,0.0009794052,0.004324331],"category_scores_gemma":[0.05820232,0.0005416679,0.0010268253,0.0020219157,0.0014540345,0.0015218533,0.0019063951,0.0020239737,0.00094508636],"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":[0.00025370755,0.00013520155,0.004621275,0.00037863688,0.00024154471,0.00035241817,0.00051762164,0.35880193,0.003215226,0.3979915,0.0034019146,0.23008908],"study_design_scores_gemma":[0.000042473443,0.00007740106,0.0011466125,0.000054800483,0.000025261968,0.0000924636,0.00004631059,0.8518042,0.0013362691,0.14078012,0.004567918,0.000026102525],"about_ca_topic_score_codex":0.0015161551,"about_ca_topic_score_gemma":0.0012386687,"teacher_disagreement_score":0.00960835,"about_ca_system_score_codex":0.0006293656,"about_ca_system_score_gemma":0.0009509239,"threshold_uncertainty_score":0.05081439},"labels":[],"label_agreement":null}]}