{"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":"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":[0.0028646,0.000014745366,0.98940456,0.00028367084,0.000101253325,0.00024325473,0.006984589,0.0000032694666,0.000100081365],"genre_scores_gemma":[0.04225738,0.000020108813,0.95736736,0.00014058113,0.00005512959,0.000016902512,0.000046043147,0.000013583812,0.00008292876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99612516,0.0027673985,0.0005978635,0.00013240581,0.00017325574,0.00020392818],"domain_scores_gemma":[0.9773777,0.020441331,0.0005085972,0.00019971795,0.001220647,0.0002519984],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011697215,0.00011251729,0.00042126953,0.0001436408,0.0001574609,0.000027624726,0.00016997433,0.00007676102,0.00006801052],"category_scores_gemma":[0.02319718,0.000068719295,0.000021782742,0.00025899144,0.0001609076,0.00002282569,0.000022817649,0.00023070634,6.884301e-7],"study_design_candidate":"theoretical_or_conceptual","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":[0.00023225775,0.00009927613,0.086111106,0.00014724866,0.00018591045,0.00000643101,0.0004194328,0.000028382901,0.00013156477,0.8194305,0.010388587,0.08281936],"study_design_scores_gemma":[0.00020208106,0.00053717423,0.6848664,0.000029092125,0.00006958405,0.00006678584,0.0000420575,0.00022907348,0.000032152704,0.31018117,0.003666296,0.000078084966],"about_ca_topic_score_codex":0.020891216,"about_ca_topic_score_gemma":0.4091819,"teacher_disagreement_score":0.59875536,"about_ca_system_score_codex":0.00003141021,"about_ca_system_score_gemma":0.00028120272,"threshold_uncertainty_score":0.9856287},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1063945,0.00021928054,0.8928836,0.000049847316,0.0002652155,0.000071473034,0.000070630944,0.000010035249,0.000035437766],"genre_scores_gemma":[0.27096868,0.000055877757,0.7288914,0.000028055203,0.000030593645,0.0000010820033,0.0000091108095,0.000011254989,0.0000039725487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99665755,0.0019270431,0.0009312939,0.00011450178,0.0002093521,0.00016025468],"domain_scores_gemma":[0.9859497,0.012357481,0.0008967757,0.000121217105,0.0005705126,0.00010433291],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021113599,0.00011424075,0.000585699,0.00029118662,0.000027634725,0.000018624782,0.000105831816,0.00008676919,0.0000047605718],"category_scores_gemma":[0.034877703,0.00010346493,0.000028016153,0.00016829779,0.00007747099,0.00014600356,0.000031153748,0.00029075867,3.1119882e-7],"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":[0.0022529045,0.0011895016,0.03576418,0.00077947,0.00032365127,0.00015857902,0.0067978883,0.0067164823,0.00490302,0.720599,0.0038100258,0.21670529],"study_design_scores_gemma":[0.0018318795,0.00037610938,0.013696328,0.00011221508,0.000038777816,0.00010851268,0.00010532478,0.008176624,0.0010161866,0.9743791,0.00003895656,0.00011998592],"about_ca_topic_score_codex":0.0003239981,"about_ca_topic_score_gemma":0.00015218396,"teacher_disagreement_score":0.2537801,"about_ca_system_score_codex":0.000044543558,"about_ca_system_score_gemma":0.00014608014,"threshold_uncertainty_score":0.97325194},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15934767,0.00017875912,0.838865,0.00047969818,0.0003511659,0.00015007726,0.0006191503,0.0000045046168,0.0000040166674],"genre_scores_gemma":[0.33852285,0.00005488702,0.66113937,0.000023655124,0.000110276276,0.0000013160815,0.0001324576,0.000012026328,0.000003157373],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99720556,0.0014286992,0.00089758454,0.00014702707,0.00019856472,0.00012254046],"domain_scores_gemma":[0.98474216,0.012543869,0.0019114716,0.00013567164,0.0005900256,0.00007682662],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0050041145,0.00016399504,0.00064417603,0.00003918966,0.00011152252,0.000036470563,0.000097358294,0.0001364627,0.0000062812464],"category_scores_gemma":[0.013614172,0.00010888451,0.000039631857,0.00009253312,0.00012678588,0.000034101788,0.000118014796,0.0004837913,4.1003435e-8],"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":[0.002232655,0.00027442136,0.40430167,0.0040632463,0.0015583087,0.000044094315,0.006247371,0.16557042,0.00029185097,0.29888254,0.0076857754,0.10884763],"study_design_scores_gemma":[0.00032108172,0.0001363702,0.58072466,0.00017899234,0.0003053357,0.00007888116,0.000034938508,0.054216962,0.0000029896469,0.36383793,0.000049982915,0.00011187501],"about_ca_topic_score_codex":0.00023636775,"about_ca_topic_score_gemma":0.00025073497,"teacher_disagreement_score":0.1791752,"about_ca_system_score_codex":0.000022989472,"about_ca_system_score_gemma":0.000082193714,"threshold_uncertainty_score":0.9946946},"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":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12784533,0.00027283837,0.86344,0.0010847262,0.00011124264,0.00016791122,0.0070687574,9.756568e-7,0.000008234193],"genre_scores_gemma":[0.89281523,0.000814209,0.10585026,0.00029615356,0.000055829092,0.000014152667,0.00007610457,0.000017429733,0.0000606464],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986579,0.00047381944,0.00050174893,0.00015325463,0.000039473118,0.00017379921],"domain_scores_gemma":[0.99413353,0.0046324823,0.0005838288,0.00018370779,0.00029243616,0.0001739879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00904877,0.000089614034,0.00038439166,0.00013618064,0.00018883336,0.000045877267,0.0001760531,0.00005081183,0.000009354675],"category_scores_gemma":[0.002024361,0.000045359462,0.000021704456,0.0001463932,0.00011133491,0.00006008872,0.00001861509,0.00006387853,0.0000011743555],"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":[0.0008113524,0.00002733198,0.9148454,0.000010627746,0.00030299617,0.0000022058337,0.00024717086,0.0000373807,0.00003993148,0.01788739,0.0022424255,0.06354576],"study_design_scores_gemma":[0.00047409258,0.0005850858,0.9816481,0.0000061748965,0.000029802466,0.000010863634,0.000017198334,0.0009314426,0.000016851536,0.01218371,0.0040093404,0.00008735142],"about_ca_topic_score_codex":0.16986245,"about_ca_topic_score_gemma":0.6759162,"teacher_disagreement_score":0.7649699,"about_ca_system_score_codex":0.00002782842,"about_ca_system_score_gemma":0.0000781353,"threshold_uncertainty_score":0.8356655},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16701785,0.00067195157,0.83162856,0.00028121183,0.00013827173,0.00010422352,0.00015038528,0.0000017178435,0.0000057981642],"genre_scores_gemma":[0.42516762,0.0006011048,0.5740307,0.00005048231,0.00007635034,0.0000024112965,0.000005903719,0.0000073706387,0.0000580737],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998763,0.00051467086,0.00039834634,0.00010068934,0.000054538217,0.00016872164],"domain_scores_gemma":[0.99157286,0.007835566,0.00023342446,0.000046072073,0.00021199339,0.000100113495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004403905,0.00007231625,0.0003660964,0.00024988843,0.000054744367,0.000008800292,0.000022838156,0.000054243614,0.0000052694986],"category_scores_gemma":[0.00737996,0.000050485538,0.00002050001,0.00011018805,0.00008478666,0.00005082906,0.000035687695,0.00011351383,9.0409024e-8],"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":[0.0007552806,0.000056980592,0.59203833,0.00015355076,0.00012197222,0.000021404205,0.0021526257,0.000049911996,0.0005918825,0.023591613,0.00036058552,0.38010585],"study_design_scores_gemma":[0.0015016757,0.0008040223,0.95554495,0.0004541148,0.00010155569,0.00012467561,0.00097106147,0.00065812067,0.000008042996,0.039569456,0.00018500512,0.00007730879],"about_ca_topic_score_codex":0.000056166275,"about_ca_topic_score_gemma":0.0007290594,"teacher_disagreement_score":0.38002855,"about_ca_system_score_codex":0.000017747156,"about_ca_system_score_gemma":0.000033330747,"threshold_uncertainty_score":0.88350344},"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":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":[0.005156936,0.000110353954,0.99213266,0.00035435392,0.00017890806,0.00014734438,0.0019031389,0.0000032513262,0.000013060021],"genre_scores_gemma":[0.08469648,0.00011319107,0.9149357,0.00015917262,0.000038693695,9.165747e-7,0.000043170578,0.000011212706,0.0000014811523],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9882589,0.009842767,0.0011207986,0.00024141814,0.00031838412,0.00021771571],"domain_scores_gemma":[0.9208776,0.07740146,0.0008593114,0.00030173644,0.00045619812,0.00010373511],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022140995,0.00014910653,0.0006822618,0.000075128635,0.000044025084,0.00003938386,0.0006143966,0.000097713055,0.000018534565],"category_scores_gemma":[0.14079185,0.00010326853,0.000023418956,0.00032959186,0.00021520774,0.00012694873,0.00012974482,0.00041177357,3.1682896e-7],"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":[0.0038634725,0.0010160751,0.21581118,0.0017052462,0.0005908215,0.00052896095,0.010115424,0.0012517148,0.0024635661,0.28063485,0.030425519,0.45159316],"study_design_scores_gemma":[0.0008138103,0.0005425329,0.6745058,0.00007211738,0.0000802963,0.000082352715,0.00015386636,0.103542455,0.00005048432,0.21995556,0.00004464167,0.00015609531],"about_ca_topic_score_codex":0.00052804593,"about_ca_topic_score_gemma":0.0004256068,"teacher_disagreement_score":0.4586946,"about_ca_system_score_codex":0.000009444954,"about_ca_system_score_gemma":0.00012994284,"threshold_uncertainty_score":0.8664456},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16003504,0.0016749107,0.837434,0.0000330233,0.00043432688,0.0001730224,0.00020388409,0.000007830613,0.0000039457423],"genre_scores_gemma":[0.05015587,0.00084008387,0.9487761,0.0000426537,0.00007825676,0.0000032767714,0.00005561064,0.00004476936,0.000003329933],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9461686,0.05052046,0.0019974865,0.000558166,0.00035842555,0.0003968604],"domain_scores_gemma":[0.93841547,0.058495738,0.0017403623,0.000191342,0.0008896432,0.00026745285],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.047908597,0.00039864893,0.0021652833,0.0007009712,0.00009850579,0.00020219546,0.00020363941,0.0005100399,0.000026889044],"category_scores_gemma":[0.117179364,0.00034888854,0.00007070966,0.00042504023,0.00022811306,0.000103602986,0.00035399102,0.0020870995,6.589477e-8],"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":[0.00032602897,0.00048746174,0.49929032,0.0018040491,0.00031946017,0.00025230146,0.0030784218,0.00084876566,0.00050441397,0.0035879435,0.000076355034,0.48942447],"study_design_scores_gemma":[0.0006599432,0.0005555781,0.46600226,0.0002594986,0.0002565804,0.00033776488,0.0004345798,0.1301763,0.0000866156,0.40082648,0.00000884672,0.0003955605],"about_ca_topic_score_codex":0.001264755,"about_ca_topic_score_gemma":0.0015269391,"teacher_disagreement_score":0.4890289,"about_ca_system_score_codex":0.00008679569,"about_ca_system_score_gemma":0.00046337568,"threshold_uncertainty_score":0.9998963},"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":"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":[0.11700769,0.00042613258,0.88102573,0.0004091716,0.00020812803,0.00027462537,0.00062676595,0.0000099749,0.000011772931],"genre_scores_gemma":[0.7581279,0.00012798277,0.24101159,0.0003649242,0.0001271412,0.000002003016,0.0002054664,0.0000149440975,0.000017999724],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973524,0.0016379914,0.00056850514,0.00014199916,0.00016639699,0.00013269908],"domain_scores_gemma":[0.99451214,0.004194802,0.0005120019,0.00006726004,0.0005013901,0.00021241033],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00437858,0.00010057451,0.0006789394,0.00007252662,0.000056712288,0.000014816246,0.000060802584,0.000040236067,0.000024896364],"category_scores_gemma":[0.01571069,0.00008350674,0.000040501054,0.00009597405,0.00004419174,0.000035811223,0.00003291967,0.00026296894,0.0000010943021],"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":[0.0033888328,0.00017226358,0.9656792,0.00010741817,0.00020934049,0.000049064194,0.0006244579,0.000086549364,0.0004411006,0.000119918135,0.0054607056,0.023661146],"study_design_scores_gemma":[0.003222549,0.0043178964,0.9726246,0.000013934061,0.00022055025,0.00004138786,0.0002994243,0.010798906,0.000040625757,0.00015339974,0.008177914,0.0000888016],"about_ca_topic_score_codex":0.0000794246,"about_ca_topic_score_gemma":0.000096625176,"teacher_disagreement_score":0.64112025,"about_ca_system_score_codex":0.000016276404,"about_ca_system_score_gemma":0.00006769545,"threshold_uncertainty_score":0.9925804},"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":"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":[0.1539377,0.00030502462,0.8437322,0.0003834176,0.00019133571,0.000121220524,0.0012875234,0.000020539474,0.000021081612],"genre_scores_gemma":[0.041500263,0.0009785846,0.9563224,0.00043197788,0.000117660515,0.000004404514,0.00011478269,0.000041898562,0.00048806923],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9863091,0.012241637,0.0008115711,0.00017749575,0.00022028528,0.00023988208],"domain_scores_gemma":[0.9308766,0.06755416,0.00072574115,0.00015101455,0.0005318898,0.00016058967],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027101794,0.00019053428,0.0006064836,0.00007622451,0.00019471273,0.000047683065,0.00017416319,0.000103283295,0.00014001704],"category_scores_gemma":[0.058773883,0.000120892095,0.00005089139,0.0001802816,0.00013809306,0.000049678245,0.000082486644,0.00023213794,0.0000028400793],"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":[0.018552871,0.0008536064,0.63552386,0.00074065384,0.0025716866,0.0004887176,0.022744525,0.0020176289,0.011272582,0.027997803,0.21771644,0.059519626],"study_design_scores_gemma":[0.0047396002,0.0058490457,0.8549815,0.000112655245,0.0007165655,0.0003904116,0.0016711041,0.0088962745,0.0061469697,0.06704681,0.048219044,0.0012300534],"about_ca_topic_score_codex":0.0009247941,"about_ca_topic_score_gemma":0.0006350459,"teacher_disagreement_score":0.21945761,"about_ca_system_score_codex":0.00004833603,"about_ca_system_score_gemma":0.00012643967,"threshold_uncertainty_score":0.94915444},"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":"methods","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":[0.6606619,0.009429136,0.2760573,0.023733187,0.010368489,0.00032826638,0.009072082,0.00001797188,0.010331684],"genre_scores_gemma":[0.43151137,0.011193203,0.55092627,0.0033929807,0.0010106751,0.0000013690491,0.00021873122,0.000023925239,0.0017214736],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9971143,0.0021615438,0.00031037195,0.0000870012,0.00018299728,0.00014381002],"domain_scores_gemma":[0.99310607,0.0062685227,0.00012419117,0.000085997366,0.00033213184,0.000083093946],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013784203,0.0000353803,0.00019909468,0.000020200723,0.000089857866,0.00003691071,0.00011832381,0.000051414005,0.00011437929],"category_scores_gemma":[0.021646408,0.000032439784,0.000010809318,0.000080589736,0.00017783184,0.000073888536,0.000048322054,0.00013747592,5.8198003e-7],"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":[0.000023225544,0.00002447902,0.9521439,0.00003656177,0.000011505237,0.000029069553,0.00034372398,0.0000053829394,0.0000010845579,0.028777681,0.003945085,0.014658303],"study_design_scores_gemma":[0.00013771318,0.0000064161623,0.9453973,0.000010431269,0.0000039732913,0.0000061663245,0.00021155008,0.000025945577,8.1860895e-7,0.0076981755,0.04646931,0.00003218056],"about_ca_topic_score_codex":0.0027414558,"about_ca_topic_score_gemma":0.021655904,"teacher_disagreement_score":0.27486897,"about_ca_system_score_codex":0.00004947798,"about_ca_system_score_gemma":0.00034612216,"threshold_uncertainty_score":0.9961963},"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":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":[0.753745,0.0009469129,0.24422674,0.00015984428,0.0007103629,0.00006314268,0.000094034855,0.000004309302,0.000049658604],"genre_scores_gemma":[0.7053883,0.0018610086,0.29010364,0.00024138698,0.00032209262,0.000006401423,0.00020412833,0.000019995874,0.0018530296],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99384785,0.005155104,0.00056477974,0.00018088927,0.00012216154,0.0001292273],"domain_scores_gemma":[0.9949663,0.0035262986,0.0005853669,0.0001486088,0.0007078051,0.00006557873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047632847,0.00010656888,0.00046184217,0.00006688416,0.000055189394,0.000024616913,0.00007416805,0.000098086115,0.0001974767],"category_scores_gemma":[0.005908405,0.000068395115,0.00004907878,0.00016454459,0.00007887673,0.00006696081,0.000027020065,0.00013385664,0.0000011274112],"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":[0.0031135266,0.00028020574,0.62244916,0.00031039427,0.0008745232,0.00019129897,0.008279519,0.000115617906,0.05742922,0.065506846,0.038856547,0.20259316],"study_design_scores_gemma":[0.0008784845,0.00085895264,0.9874936,0.000063948144,0.00012650064,0.00045417517,0.0007425883,0.00017636085,0.0023919933,0.006087219,0.00060362625,0.00012256774],"about_ca_topic_score_codex":0.00031646003,"about_ca_topic_score_gemma":0.00017705951,"teacher_disagreement_score":0.36504444,"about_ca_system_score_codex":0.000016942013,"about_ca_system_score_gemma":0.00003427541,"threshold_uncertainty_score":0.7073339},"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":"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":[0.071355864,0.00014066743,0.9273774,0.0002445166,0.0002861363,0.00016495815,0.0002880419,0.0000010531656,0.0001413317],"genre_scores_gemma":[0.33733797,0.0001228901,0.6623521,0.00005782419,0.000014757362,0.00000358836,0.0000103411485,0.000004355226,0.000096195436],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9933288,0.0041255536,0.0014844252,0.0002742765,0.00057789066,0.00020907079],"domain_scores_gemma":[0.98161906,0.015807202,0.0009172976,0.00018416054,0.0013780873,0.00009420297],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05333626,0.00010813313,0.0007419871,0.00028749663,0.00010964914,0.00011616508,0.00042355814,0.000086996115,0.000020472131],"category_scores_gemma":[0.043901175,0.00008432916,0.00006985809,0.00039386604,0.000109462846,0.00016619994,0.00017099184,0.0002289664,1.3080471e-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":[0.0039863065,0.0027080409,0.36854446,0.0007042751,0.00070526,0.00016460693,0.007477638,0.101188526,0.111069724,0.21183698,0.026978757,0.16463543],"study_design_scores_gemma":[0.0039705643,0.0006481734,0.5165039,0.00020619223,0.00013896497,0.0001586504,0.0046952646,0.19040418,0.0022212537,0.28018364,0.00050901127,0.0003602097],"about_ca_topic_score_codex":0.00008526182,"about_ca_topic_score_gemma":0.0004676698,"teacher_disagreement_score":0.2659821,"about_ca_system_score_codex":0.00005217147,"about_ca_system_score_gemma":0.0002605016,"threshold_uncertainty_score":0.97478956},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0755771,0.000048696667,0.9231042,0.00011599044,0.00014283945,0.00009305398,0.00090393826,0.0000013478731,0.000012832757],"genre_scores_gemma":[0.24477562,0.000026085858,0.7551068,0.00004781011,0.00001556867,0.0000020263374,0.000013643603,0.000006746243,0.000005668485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9925869,0.0060759606,0.00085243944,0.00011676735,0.00021584597,0.00015207556],"domain_scores_gemma":[0.9556696,0.042525206,0.00064840337,0.00011140959,0.0009900456,0.000055328015],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015400117,0.00009880014,0.00052096724,0.00007904705,0.000051898558,0.00001869187,0.00011842278,0.00007185709,0.000029957377],"category_scores_gemma":[0.08259728,0.00007246347,0.000050991093,0.00016881827,0.00019232981,0.000051662333,0.00004026341,0.00019347687,8.305851e-8],"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":[0.00020389198,0.00023802384,0.11759796,0.0006747896,0.00016328217,0.00003899301,0.0004182312,0.0006035738,0.005981202,0.78209436,0.0012841778,0.090701506],"study_design_scores_gemma":[0.00033631225,0.000060081562,0.5072963,0.000038264243,0.000023564024,0.000053710177,0.00002508746,0.0012397128,0.0006860149,0.49018145,0.000015686785,0.000043784534],"about_ca_topic_score_codex":0.00007594063,"about_ca_topic_score_gemma":0.00033520118,"teacher_disagreement_score":0.38969836,"about_ca_system_score_codex":0.000022007725,"about_ca_system_score_gemma":0.00018464436,"threshold_uncertainty_score":0.92513037},"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":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":[0.07749325,0.0008948554,0.9193943,0.00078717514,0.0006554489,0.00011639326,0.000568011,0.000005144572,0.000085378815],"genre_scores_gemma":[0.06700159,0.00088032166,0.9303576,0.0007662867,0.00033412193,0.0000021926433,0.00008389315,0.000032648626,0.0005413912],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99737674,0.0013409195,0.00064305053,0.00018224432,0.00020277385,0.00025427484],"domain_scores_gemma":[0.9867529,0.011381702,0.00037918455,0.00015083281,0.0010950763,0.00024026287],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0050174235,0.00012978517,0.0006921137,0.00015310486,0.00006407671,0.000022648112,0.00007171977,0.00012606889,0.0000566132],"category_scores_gemma":[0.018104117,0.000111422116,0.00007244357,0.00013366809,0.0000811062,0.000042876385,0.00003861075,0.00032651948,0.0000013168603],"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":[0.011689839,0.0008810004,0.33172306,0.00094463653,0.0023297602,0.0025809046,0.007077232,0.00020481323,0.16948505,0.01981834,0.050583903,0.40268147],"study_design_scores_gemma":[0.009084417,0.004119762,0.9004757,0.00018098459,0.0010233297,0.0059306263,0.0053654364,0.0008977995,0.0041996296,0.034126677,0.034142777,0.0004528762],"about_ca_topic_score_codex":0.00002331309,"about_ca_topic_score_gemma":0.00011984004,"teacher_disagreement_score":0.56875265,"about_ca_system_score_codex":0.000032717293,"about_ca_system_score_gemma":0.00033422414,"threshold_uncertainty_score":0.9901668},"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":"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":[0.4304503,0.001027845,0.5455537,0.0011213826,0.0011140191,0.00022043222,0.020380644,0.000011486761,0.00012025161],"genre_scores_gemma":[0.43304548,0.00094888516,0.5601956,0.0010885145,0.0003779306,0.000007725896,0.0017282636,0.0000664245,0.0025411553],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.90289736,0.094384015,0.00080809655,0.0006312118,0.0007399848,0.0005393071],"domain_scores_gemma":[0.91883475,0.07929695,0.000586382,0.0006163409,0.00043302082,0.00023254468],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21618347,0.00016115181,0.00057638227,0.00017392616,0.000765006,0.00012149083,0.0012217696,0.00008879008,0.00027976136],"category_scores_gemma":[0.07258289,0.00013200102,0.0000257257,0.00047342147,0.00032877436,0.00041677168,0.0008424136,0.0005068162,0.0000018778946],"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":[0.015887244,0.00024882623,0.85699254,0.000022654536,0.00064218126,0.0003106112,0.011477489,0.00004473302,0.000071729075,0.0005844488,0.048147473,0.06557007],"study_design_scores_gemma":[0.0005803332,0.0005546418,0.965002,0.000009550703,0.000081563034,0.000110009605,0.0048421673,0.000055843277,0.0000045463203,0.001295412,0.027269756,0.00019415871],"about_ca_topic_score_codex":0.0046202154,"about_ca_topic_score_gemma":0.012908186,"teacher_disagreement_score":0.14360057,"about_ca_system_score_codex":0.000045206347,"about_ca_system_score_gemma":0.00049824646,"threshold_uncertainty_score":0.9352291},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007225521,0.0003520289,0.9886755,0.000048480546,0.00030324972,0.00011081008,0.0032445728,0.000018149143,0.000021724176],"genre_scores_gemma":[0.009531194,0.00022721374,0.98898727,0.00007851456,0.00009723519,0.00000258549,0.0009941226,0.000027661345,0.00005420522],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99371064,0.004710618,0.00088399375,0.00026909742,0.00019116832,0.0002344963],"domain_scores_gemma":[0.957451,0.040012926,0.0006227634,0.00039964667,0.0013968558,0.00011684323],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.038688395,0.00014790299,0.00068038434,0.00012326206,0.00009672348,0.000060967937,0.0002879429,0.00014830897,0.000010006003],"category_scores_gemma":[0.079474635,0.00012945593,0.00004478391,0.00017987273,0.00008208538,0.00008987665,0.0001360906,0.00026226076,1.2950629e-7],"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":[0.0040752366,0.0017974772,0.16494556,0.0024904413,0.002757223,0.0002342544,0.0020349626,0.00031616903,0.0041594636,0.053953268,0.48636228,0.27687368],"study_design_scores_gemma":[0.0033270132,0.0008571694,0.4228768,0.00015047553,0.00048217722,0.0013847091,0.00043450817,0.042097848,0.002606212,0.52198297,0.002933248,0.0008668618],"about_ca_topic_score_codex":0.00023325422,"about_ca_topic_score_gemma":0.00029534704,"teacher_disagreement_score":0.483429,"about_ca_system_score_codex":0.000018200812,"about_ca_system_score_gemma":0.0002080744,"threshold_uncertainty_score":0.9898726},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39244065,0.00021703642,0.6060608,0.000053466203,0.00061921845,0.000101083126,0.00047661038,0.00002186258,0.000009289046],"genre_scores_gemma":[0.08660334,0.00019397584,0.91278076,0.000104755694,0.000041741947,0.000010057803,0.00015547838,0.000037794336,0.000072104376],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98513776,0.012695954,0.0012544186,0.00023117651,0.00038361718,0.0002970953],"domain_scores_gemma":[0.962586,0.03547962,0.0010959503,0.00019773557,0.0005177664,0.0001229625],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04224303,0.00020201385,0.00085991045,0.00048669009,0.00020466493,0.00003624533,0.00022956837,0.000103655126,0.00011489289],"category_scores_gemma":[0.050934307,0.00017436399,0.000055319335,0.00043228062,0.00008011036,0.00006781577,0.00015378627,0.00062972965,5.2199783e-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":[0.0038816207,0.0007523485,0.82358617,0.00025622797,0.00027370185,0.00024885754,0.00206686,0.0017026345,0.0029037655,0.009872948,0.0764718,0.07798307],"study_design_scores_gemma":[0.0017705902,0.00059771223,0.8491873,0.000088479086,0.00005213867,0.0004922578,0.00019945834,0.0046600103,0.00041501728,0.14128982,0.0008527058,0.0003944776],"about_ca_topic_score_codex":0.0016978763,"about_ca_topic_score_gemma":0.0008895681,"teacher_disagreement_score":0.30671996,"about_ca_system_score_codex":0.00009300444,"about_ca_system_score_gemma":0.00015950533,"threshold_uncertainty_score":0.9862124},"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":"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":[0.0044124867,0.00003078412,0.99395776,0.0010463354,0.00033723778,0.00010691247,0.000053174943,0.000036062233,0.000019222647],"genre_scores_gemma":[0.027823871,0.00006616203,0.97186285,0.00010749845,0.000027796668,0.0000052535756,0.000012154755,0.000005473625,0.00008894091],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985463,0.000786465,0.00030436917,0.00013527184,0.000096619675,0.0001310008],"domain_scores_gemma":[0.99527884,0.003793358,0.00027894336,0.00014026766,0.00044031508,0.00006827304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005758173,0.000060487702,0.00021991794,0.00012777346,0.000082842715,0.000086765,0.0003399874,0.000042897726,8.9995086e-7],"category_scores_gemma":[0.0019069519,0.000046084024,0.000012002482,0.00020842972,0.00003401298,0.0001483375,0.00008416952,0.0000900076,7.339621e-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":[0.00033613658,0.000104293555,0.014373542,0.00008335959,0.00023716096,0.00007285874,0.0012785745,0.0025237233,0.0034723077,0.7300373,0.03569883,0.21178192],"study_design_scores_gemma":[0.0007217293,0.00037194573,0.39346838,0.000017776332,0.000019786381,0.00011478836,0.000040772575,0.5618527,0.000046690988,0.041849136,0.0014033243,0.000092998656],"about_ca_topic_score_codex":0.00009544994,"about_ca_topic_score_gemma":0.00014243108,"teacher_disagreement_score":0.68818814,"about_ca_system_score_codex":0.000015117308,"about_ca_system_score_gemma":0.00012713211,"threshold_uncertainty_score":0.22829373},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38953173,0.00014592751,0.6097448,0.000025541023,0.000406195,0.000040333274,0.000090740265,0.000012003188,0.0000027300766],"genre_scores_gemma":[0.4339816,0.000027702345,0.5659048,0.000008928844,0.000024288162,4.244595e-7,0.000014555744,0.000011735853,0.000025938989],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99692494,0.0019693957,0.00070752954,0.00010336004,0.00018394878,0.00011085066],"domain_scores_gemma":[0.98266274,0.016496077,0.00040720438,0.00008978248,0.00029126173,0.00005290901],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012129693,0.000103229315,0.00040452625,0.00029850454,0.000041156727,0.00003256501,0.00005124239,0.00010074048,0.000017636721],"category_scores_gemma":[0.012558326,0.000087171786,0.00005347531,0.00016776625,0.000054958946,0.000106731335,0.000021815637,0.00016212129,3.061666e-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":[0.004928447,0.0004253655,0.02430021,0.0030678972,0.0015552966,0.000162155,0.0058633103,0.01978946,0.02090747,0.27661315,0.011935641,0.6304516],"study_design_scores_gemma":[0.0005556077,0.000448306,0.13835578,0.0003297581,0.00025625227,0.00064267643,0.00012605349,0.15740505,0.001327835,0.70030963,0.00003043249,0.00021259901],"about_ca_topic_score_codex":0.0004111711,"about_ca_topic_score_gemma":0.00005045414,"teacher_disagreement_score":0.630239,"about_ca_system_score_codex":0.000038569935,"about_ca_system_score_gemma":0.000075101365,"threshold_uncertainty_score":0.9957593},"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":"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":[0.31814525,0.00046225125,0.6750247,0.004117782,0.001583522,0.00017319286,0.0004431748,0.00000894491,0.000041206156],"genre_scores_gemma":[0.85046345,0.0008134718,0.14752094,0.00043099196,0.00026659356,0.000012447121,0.000013312413,0.000022415536,0.0004563651],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.85578305,0.14218564,0.00077880686,0.00034292656,0.0003923914,0.00051716145],"domain_scores_gemma":[0.90155405,0.09766591,0.00011523315,0.000114187285,0.00031076666,0.0002398534],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.23636335,0.00017397679,0.0005301369,0.00045313602,0.00030885744,0.00010271582,0.000276599,0.00017747615,0.000103486076],"category_scores_gemma":[0.04271167,0.00012727326,0.000076378165,0.0006799028,0.00036660634,0.00013135638,0.000046999514,0.0004642414,0.0000108941695],"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":[0.028049974,0.00049949746,0.15280347,0.0003642225,0.001428005,0.0028496364,0.31529006,0.0071133506,0.014106009,0.027454048,0.09123014,0.3588116],"study_design_scores_gemma":[0.0003806948,0.00053688604,0.97533065,0.000065518565,0.00006901724,0.000066173714,0.0024125127,0.00013207615,0.00015024618,0.0073702545,0.013257847,0.00022811469],"about_ca_topic_score_codex":0.008352245,"about_ca_topic_score_gemma":0.17139679,"teacher_disagreement_score":0.82252717,"about_ca_system_score_codex":0.00009208997,"about_ca_system_score_gemma":0.0004206005,"threshold_uncertainty_score":0.9982512},"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":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":[0.94660074,0.0058765155,0.044718195,0.00062574766,0.0011143435,0.00015032981,0.0008848496,0.000008808836,0.00002046784],"genre_scores_gemma":[0.8870919,0.0042971172,0.10776606,0.00011668824,0.000067764035,0.000004152514,0.000015684625,0.000027390719,0.00061327906],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.85389405,0.14393753,0.0010878372,0.00031324793,0.00034894535,0.000418372],"domain_scores_gemma":[0.80178046,0.19740808,0.0003146537,0.00010437144,0.00022145148,0.00017100791],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.13320191,0.0002136453,0.0010740662,0.00048418937,0.00012444734,0.000051835308,0.00017526608,0.00032812657,0.00010181598],"category_scores_gemma":[0.08465511,0.00015850556,0.0000621344,0.0004848222,0.0007050006,0.00015011789,0.00006130203,0.0004276845,8.4903087e-7],"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":[0.13078666,0.0008217083,0.68550813,0.00017606429,0.0007780528,0.0006180459,0.027400756,0.000044086315,0.01696466,0.001261262,0.007660812,0.12797977],"study_design_scores_gemma":[0.0011197736,0.0012634071,0.988532,0.00009659907,0.00010208918,0.000053972435,0.0015894573,0.0002191463,0.00031678236,0.0027018492,0.0038250026,0.00017991335],"about_ca_topic_score_codex":0.0047511947,"about_ca_topic_score_gemma":0.06303002,"teacher_disagreement_score":0.30302387,"about_ca_system_score_codex":0.00007987614,"about_ca_system_score_gemma":0.00065891584,"threshold_uncertainty_score":0.95406723},"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":"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":[0.010938033,0.00040364714,0.98595,0.000042820444,0.00076773384,0.00018362403,0.0016907898,0.000010225185,0.000013120829],"genre_scores_gemma":[0.019715546,0.00004419593,0.9800703,0.000036717116,0.000079392456,0.000004126418,0.000009128588,0.000029001532,0.00001157067],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99467915,0.003521758,0.0012172506,0.00019173534,0.00016660946,0.00022350744],"domain_scores_gemma":[0.9344904,0.063956976,0.00059099065,0.00012329688,0.00072101864,0.000117331845],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018785793,0.00016966792,0.00094686536,0.00023431268,0.00006342043,0.000036483063,0.000120419114,0.00015750474,0.000014273814],"category_scores_gemma":[0.030075062,0.00013448368,0.00009987164,0.00016718514,0.00015854544,0.000038354283,0.000030909603,0.000289467,7.157116e-8],"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":[0.0012975518,0.0003109982,0.004245936,0.0022653094,0.00071070186,0.000025196303,0.0013200173,0.004332536,0.025408622,0.73617524,0.0022635616,0.22164431],"study_design_scores_gemma":[0.00038988888,0.0005176949,0.0013341606,0.00010454397,0.0002835177,0.000026633394,0.000048685917,0.5441021,0.00090902677,0.45210904,0.00009510521,0.00007963342],"about_ca_topic_score_codex":0.000053658394,"about_ca_topic_score_gemma":0.000032830183,"teacher_disagreement_score":0.53976953,"about_ca_system_score_codex":0.00004191761,"about_ca_system_score_gemma":0.0002666995,"threshold_uncertainty_score":0.97809505},"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":"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":[0.028986353,0.0010373758,0.9683693,0.000986509,0.00024772107,0.00010850333,0.0001076651,0.00003332702,0.00012322691],"genre_scores_gemma":[0.41714036,0.00024098517,0.58233887,0.00014093352,0.000011723355,0.000004721342,0.000022792063,0.000004357523,0.00009525599],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9978812,0.001024759,0.0005069541,0.00026048406,0.0001597999,0.00016680858],"domain_scores_gemma":[0.9954553,0.0032670803,0.0005708897,0.00030548597,0.00034188214,0.000059320522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032654125,0.00013261137,0.00038049064,0.0003234078,0.0001477071,0.00039906835,0.0008296658,0.000104834595,0.0000042116117],"category_scores_gemma":[0.0014318957,0.00010294908,0.000022822214,0.0003660262,0.0001467327,0.0006122043,0.0002859642,0.00028002128,3.8542606e-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":[0.0002073606,0.00018849605,0.025679478,0.000028993769,0.00040728188,0.000029923824,0.0021538804,0.00007400652,0.011345072,0.51710755,0.0056039765,0.437174],"study_design_scores_gemma":[0.0018804123,0.00055324996,0.6383463,0.00012668656,0.00014435436,0.000029911029,0.0019472595,0.021807967,0.0020145494,0.33187434,0.0009336692,0.00034125702],"about_ca_topic_score_codex":0.0005419821,"about_ca_topic_score_gemma":0.00032187114,"teacher_disagreement_score":0.61266685,"about_ca_system_score_codex":0.000029935327,"about_ca_system_score_gemma":0.0001611205,"threshold_uncertainty_score":0.41981417},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17450152,0.000045678185,0.8242775,0.000050671246,0.00072504877,0.0001443913,0.00020080482,0.000004541259,0.00004981866],"genre_scores_gemma":[0.13710973,0.000046943405,0.8626709,0.0000857491,0.000033654804,0.0000034852023,0.0000076238125,0.000010282618,0.00003162995],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98816544,0.0098734135,0.0012300039,0.00024533115,0.00018723944,0.0002985474],"domain_scores_gemma":[0.9335717,0.064918265,0.0005970866,0.00012810183,0.00067811547,0.00010674227],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.036406383,0.00018144854,0.00085827673,0.00028534196,0.00007998781,0.000042371696,0.00013142443,0.000116628835,0.000044497978],"category_scores_gemma":[0.09429719,0.00014939954,0.000042933774,0.00047290017,0.00012969313,0.000053185002,0.00006186464,0.00051907403,4.2443742e-7],"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":[0.0011538274,0.000532282,0.45851606,0.00024439077,0.00013279931,0.00004404982,0.00032097596,0.000013486966,0.0004861124,0.06290248,0.0024489146,0.4732046],"study_design_scores_gemma":[0.0014073128,0.00036947883,0.46826372,0.00006878095,0.0000441329,0.00005506404,0.00004791757,0.0016500824,0.00028678536,0.5276742,0.000023510174,0.00010900142],"about_ca_topic_score_codex":0.0018312077,"about_ca_topic_score_gemma":0.005167225,"teacher_disagreement_score":0.47309563,"about_ca_system_score_codex":0.00009900922,"about_ca_system_score_gemma":0.0001888078,"threshold_uncertainty_score":0.9922224},"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":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027063245,0.000069219175,0.97209626,0.00019370682,0.00015162147,0.00024815925,0.00010782497,0.000032095893,0.000037849855],"genre_scores_gemma":[0.07729499,0.000058824822,0.9223162,0.0001390999,0.000034203138,0.00001743188,0.00004898284,0.000017018094,0.000073273884],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9962558,0.0024824033,0.0007700726,0.00017711385,0.00015286263,0.00016174001],"domain_scores_gemma":[0.9804232,0.018174509,0.0005669618,0.00019248585,0.0005544342,0.00008840712],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.010689857,0.00015021673,0.0005341887,0.00043063346,0.0001214394,0.000043580047,0.0001223095,0.00011412325,0.000010840223],"category_scores_gemma":[0.008941545,0.000120579934,0.00003686795,0.0003685132,0.000046919642,0.00007046449,0.000028778475,0.0001965749,4.440645e-7],"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":[0.00094498805,0.00022702337,0.24990074,0.000398867,0.00037141138,0.0000064377136,0.0005388454,0.0010441464,0.0010755004,0.29164657,0.004796312,0.44904914],"study_design_scores_gemma":[0.00031143278,0.00022155988,0.5835666,0.000080812526,0.0001122783,0.000024592331,0.000057749196,0.0009998564,0.00032634154,0.41341782,0.00073581346,0.00014510765],"about_ca_topic_score_codex":0.00065958116,"about_ca_topic_score_gemma":0.00042842163,"teacher_disagreement_score":0.44890404,"about_ca_system_score_codex":0.0000368491,"about_ca_system_score_gemma":0.000046595353,"threshold_uncertainty_score":0.9994066},"labels":[],"label_agreement":null}]}