{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":25,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":25,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"478ad34d6f7d","filters":{"venue":"Journal of Survey Statistics and Methodology"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Hyukjun Gweon","is_ca":true},{"name":"Matthias Schonlau","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4858752837440197,"gpt":0.4643715025409455,"spread":0.02150378120307417,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005758173,0.0000604877,0.0002199179,0.0001277735,0.00008284271,0.000086765,0.0003399874,0.00004289773,8.999509e-7],"category_scores_gemma":[0.001906952,0.00004608402,0.00001200248,0.0002084297,0.00003401298,0.0001483375,0.00008416952,0.0000900076,7.339621e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001511731,"about_ca_system_score_gemma":0.0001271321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009544994,"about_ca_topic_score_gemma":0.0001424311,"domain_scores_codex":[0.9985463,0.000786465,0.0003043692,0.0001352718,0.00009661967,0.0001310008],"domain_scores_gemma":[0.9952788,0.003793358,0.0002789434,0.0001402677,0.0004403151,0.00006827304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003361366,0.0001042936,0.01437354,0.00008335959,0.000237161,0.00007285874,0.001278574,0.002523723,0.003472308,0.7300373,0.03569883,0.2117819],"study_design_scores_gemma":[0.0007217293,0.0003719457,0.3934684,0.00001777633,0.00001978638,0.0001147884,0.00004077257,0.5618527,0.00004669099,0.04184914,0.001403324,0.00009299866],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004412487,0.00003078412,0.9939578,0.001046335,0.0003372378,0.0001069125,0.00005317494,0.00003606223,0.00001922265],"genre_scores_gemma":[0.02782387,0.00006616203,0.9718629,0.0001074984,0.00002779667,0.000005253576,0.00001215475,0.000005473625,0.00008894091],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6881881,"threshold_uncertainty_score":0.2282937,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Malte Schierholz","is_ca":false},{"name":"Matthias Schonlau","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.400401439441831,"gpt":0.4705134066249507,"spread":0.07011196718311963,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00437858,0.0001005745,0.0006789394,0.00007252662,0.00005671229,0.00001481625,0.00006080258,0.00004023607,0.00002489636],"category_scores_gemma":[0.01571069,0.00008350674,0.00004050105,0.00009597405,0.00004419174,0.00003581122,0.00003291967,0.0002629689,0.000001094302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000162764,"about_ca_system_score_gemma":0.00006769545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000794246,"about_ca_topic_score_gemma":0.00009662518,"domain_scores_codex":[0.9973524,0.001637991,0.0005685051,0.0001419992,0.000166397,0.0001326991],"domain_scores_gemma":[0.9945121,0.004194802,0.0005120019,0.00006726004,0.0005013901,0.0002124103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003388833,0.0001722636,0.9656792,0.0001074182,0.0002093405,0.00004906419,0.0006244579,0.00008654936,0.0004411006,0.0001199181,0.005460706,0.02366115],"study_design_scores_gemma":[0.003222549,0.004317896,0.9726246,0.00001393406,0.0002205503,0.00004138786,0.0002994243,0.01079891,0.00004062576,0.0001533997,0.008177914,0.0000888016],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1170077,0.0004261326,0.8810257,0.0004091716,0.000208128,0.0002746254,0.0006267659,0.0000099749,0.00001177293],"genre_scores_gemma":[0.7581279,0.0001279828,0.2410116,0.0003649242,0.0001271412,0.000002003016,0.0002054664,0.0000149441,0.00001799972],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6411203,"threshold_uncertainty_score":0.9925804,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"David Pettinicchio","is_ca":true},{"name":"Michelle Maroto","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6228852929621991,"gpt":0.5393534200347042,"spread":0.08353187292749487,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0137842,0.0000353803,0.0001990947,0.00002020072,0.00008985787,0.00003691071,0.0001183238,0.000051414,0.0001143793],"category_scores_gemma":[0.02164641,0.00003243978,0.00001080932,0.00008058974,0.0001778318,0.00007388854,0.00004832205,0.0001374759,5.8198e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004947798,"about_ca_system_score_gemma":0.0003461222,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002741456,"about_ca_topic_score_gemma":0.0216559,"domain_scores_codex":[0.9971143,0.002161544,0.000310372,0.0000870012,0.0001829973,0.00014381],"domain_scores_gemma":[0.9931061,0.006268523,0.0001241912,0.00008599737,0.0003321318,0.00008309395],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002322554,0.00002447902,0.9521439,0.00003656177,0.00001150524,0.00002906955,0.000343724,0.000005382939,0.000001084558,0.02877768,0.003945085,0.0146583],"study_design_scores_gemma":[0.0001377132,0.000006416162,0.9453973,0.00001043127,0.000003973291,0.000006166325,0.0002115501,0.00002594558,8.18609e-7,0.007698175,0.04646931,0.00003218056],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6606619,0.009429136,0.2760573,0.02373319,0.01036849,0.0003282664,0.009072082,0.00001797188,0.01033168],"genre_scores_gemma":[0.4315114,0.0111932,0.5509263,0.003392981,0.001010675,0.000001369049,0.0002187312,0.00002392524,0.001721474],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.274869,"threshold_uncertainty_score":0.9961963,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Emily Berg","is_ca":false},{"name":"Wayne A. Fuller","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3842642301409165,"gpt":0.4131436403482028,"spread":0.02887941020728629,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01169722,0.0001125173,0.0004212695,0.0001436408,0.0001574609,0.00002762473,0.0001699743,0.00007676102,0.00006801052],"category_scores_gemma":[0.02319718,0.0000687193,0.00002178274,0.0002589914,0.0001609076,0.00002282569,0.00002281765,0.0002307063,6.884301e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003141021,"about_ca_system_score_gemma":0.0002812027,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02089122,"about_ca_topic_score_gemma":0.4091819,"domain_scores_codex":[0.9961252,0.002767398,0.0005978635,0.0001324058,0.0001732557,0.0002039282],"domain_scores_gemma":[0.9773777,0.02044133,0.0005085972,0.0001997179,0.001220647,0.0002519984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0002322577,0.00009927613,0.08611111,0.0001472487,0.0001859105,0.00000643101,0.0004194328,0.0000283829,0.0001315648,0.8194305,0.01038859,0.08281936],"study_design_scores_gemma":[0.0002020811,0.0005371742,0.6848664,0.00002909213,0.00006958405,0.00006678584,0.0000420575,0.0002290735,0.0000321527,0.3101812,0.003666296,0.00007808497],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0028646,0.00001474537,0.9894046,0.0002836708,0.0001012533,0.0002432547,0.006984589,0.000003269467,0.0001000814],"genre_scores_gemma":[0.04225738,0.00002010881,0.9573674,0.0001405811,0.00005512959,0.00001690251,0.00004604315,0.00001358381,0.00008292876],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5987554,"threshold_uncertainty_score":0.9856287,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Steven K. Thompson","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6918727978663437,"gpt":0.5395960375672009,"spread":0.1522767602991428,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004403905,0.00007231625,0.0003660964,0.0002498884,0.00005474437,0.000008800292,0.00002283816,0.00005424361,0.000005269499],"category_scores_gemma":[0.00737996,0.00005048554,0.00002050001,0.000110188,0.00008478666,0.00005082906,0.0000356877,0.0001135138,9.040902e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001774716,"about_ca_system_score_gemma":0.00003333075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005616627,"about_ca_topic_score_gemma":0.0007290594,"domain_scores_codex":[0.998763,0.0005146709,0.0003983463,0.0001006893,0.00005453822,0.0001687216],"domain_scores_gemma":[0.9915729,0.007835566,0.0002334245,0.00004607207,0.0002119934,0.0001001135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007552806,0.00005698059,0.5920383,0.0001535508,0.0001219722,0.0000214042,0.002152626,0.000049912,0.0005918825,0.02359161,0.0003605855,0.3801059],"study_design_scores_gemma":[0.001501676,0.0008040223,0.9555449,0.0004541148,0.0001015557,0.0001246756,0.0009710615,0.0006581207,0.000008042996,0.03956946,0.0001850051,0.00007730879],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1670178,0.0006719516,0.8316286,0.0002812118,0.0001382717,0.0001042235,0.0001503853,0.000001717843,0.000005798164],"genre_scores_gemma":[0.4251676,0.0006011048,0.5740307,0.00005048231,0.00007635034,0.000002411296,0.000005903719,0.000007370639,0.0000580737],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3800285,"threshold_uncertainty_score":0.8835034,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Kyle Vincent","is_ca":true},{"name":"Steve Thompson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5549742675041466,"gpt":0.474974966433552,"spread":0.07999930107059461,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005004114,0.000163995,0.000644176,0.00003918966,0.0001115225,0.00003647056,0.00009735829,0.0001364627,0.000006281246],"category_scores_gemma":[0.01361417,0.0001088845,0.00003963186,0.00009253312,0.0001267859,0.00003410179,0.0001180148,0.0004837913,4.100344e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002298947,"about_ca_system_score_gemma":0.00008219371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002363677,"about_ca_topic_score_gemma":0.000250735,"domain_scores_codex":[0.9972056,0.001428699,0.0008975845,0.0001470271,0.0001985647,0.0001225405],"domain_scores_gemma":[0.9847422,0.01254387,0.001911472,0.0001356716,0.0005900256,0.00007682662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002232655,0.0002744214,0.4043017,0.004063246,0.001558309,0.00004409431,0.006247371,0.1655704,0.000291851,0.2988825,0.007685775,0.1088476],"study_design_scores_gemma":[0.0003210817,0.0001363702,0.5807247,0.0001789923,0.0003053357,0.00007888116,0.00003493851,0.05421696,0.000002989647,0.3638379,0.00004998291,0.000111875],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1593477,0.0001787591,0.838865,0.0004796982,0.0003511659,0.0001500773,0.0006191503,0.000004504617,0.000004016667],"genre_scores_gemma":[0.3385229,0.00005488702,0.6611394,0.00002365512,0.0001102763,0.000001316081,0.0001324576,0.00001202633,0.000003157373],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1791752,"threshold_uncertainty_score":0.9946946,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Jean‐François Beaumont","is_ca":true},{"name":"Audrey Béliveau","is_ca":false},{"name":"David Haziza","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6371680919234616,"gpt":0.5436168220745937,"spread":0.09355126984886786,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0211136,0.0001142407,0.000585699,0.0002911866,0.00002763473,0.00001862478,0.0001058318,0.00008676919,0.000004760572],"category_scores_gemma":[0.0348777,0.0001034649,0.00002801615,0.0001682978,0.00007747099,0.0001460036,0.00003115375,0.0002907587,3.111988e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004454356,"about_ca_system_score_gemma":0.0001460801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003239981,"about_ca_topic_score_gemma":0.000152184,"domain_scores_codex":[0.9966576,0.001927043,0.0009312939,0.0001145018,0.0002093521,0.0001602547],"domain_scores_gemma":[0.9859497,0.01235748,0.0008967757,0.0001212171,0.0005705126,0.0001043329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002252904,0.001189502,0.03576418,0.00077947,0.0003236513,0.000158579,0.006797888,0.006716482,0.00490302,0.720599,0.003810026,0.2167053],"study_design_scores_gemma":[0.001831879,0.0003761094,0.01369633,0.0001122151,0.00003877782,0.0001085127,0.0001053248,0.008176624,0.001016187,0.9743791,0.00003895656,0.0001199859],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1063945,0.0002192805,0.8928836,0.00004984732,0.0002652155,0.00007147303,0.00007063094,0.00001003525,0.00003543777],"genre_scores_gemma":[0.2709687,0.00005587776,0.7288914,0.0000280552,0.00003059364,0.000001082003,0.00000911081,0.00001125499,0.000003972549],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2537801,"threshold_uncertainty_score":0.9732519,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Pablo Cabrera‐Álvarez","is_ca":false},{"name":"Peter Lynn","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6092991703284136,"gpt":0.5016061607140164,"spread":0.1076930096143972,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2363634,0.0001739768,0.0005301369,0.000453136,0.0003088574,0.0001027158,0.000276599,0.0001774761,0.0001034861],"category_scores_gemma":[0.04271167,0.0001272733,0.00007637816,0.0006799028,0.0003666063,0.0001313564,0.00004699951,0.0004642414,0.00001089417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009208997,"about_ca_system_score_gemma":0.0004206005,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.008352245,"about_ca_topic_score_gemma":0.1713968,"domain_scores_codex":[0.855783,0.1421856,0.0007788069,0.0003429266,0.0003923914,0.0005171614],"domain_scores_gemma":[0.901554,0.09766591,0.0001152332,0.0001141873,0.0003107667,0.0002398534],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.02804997,0.0004994975,0.1528035,0.0003642225,0.001428005,0.002849636,0.3152901,0.007113351,0.01410601,0.02745405,0.09123014,0.3588116],"study_design_scores_gemma":[0.0003806948,0.000536886,0.9753307,0.00006551856,0.00006901724,0.00006617371,0.002412513,0.0001320762,0.0001502462,0.007370254,0.01325785,0.0002281147],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3181452,0.0004622512,0.6750247,0.004117782,0.001583522,0.0001731929,0.0004431748,0.00000894491,0.00004120616],"genre_scores_gemma":[0.8504634,0.0008134718,0.1475209,0.000430992,0.0002665936,0.00001244712,0.00001331241,0.00002241554,0.0004563651],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8225272,"threshold_uncertainty_score":0.9982512,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Zhoushanyue He","is_ca":true},{"name":"Matthias Schonlau","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.7870611956524755,"gpt":0.5441244124235828,"spread":0.2429367832288927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05333626,0.0001081331,0.0007419871,0.0002874966,0.0001096491,0.0001161651,0.0004235581,0.00008699611,0.00002047213],"category_scores_gemma":[0.04390118,0.00008432916,0.00006985809,0.000393866,0.0001094628,0.0001661999,0.0001709918,0.0002289664,1.308047e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005217147,"about_ca_system_score_gemma":0.0002605016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008526182,"about_ca_topic_score_gemma":0.0004676698,"domain_scores_codex":[0.9933288,0.004125554,0.001484425,0.0002742765,0.0005778907,0.0002090708],"domain_scores_gemma":[0.9816191,0.0158072,0.0009172976,0.0001841605,0.001378087,0.00009420297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003986306,0.002708041,0.3685445,0.0007042751,0.00070526,0.0001646069,0.007477638,0.1011885,0.1110697,0.211837,0.02697876,0.1646354],"study_design_scores_gemma":[0.003970564,0.0006481734,0.5165039,0.0002061922,0.000138965,0.0001586504,0.004695265,0.1904042,0.002221254,0.2801836,0.0005090113,0.0003602097],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07135586,0.0001406674,0.9273774,0.0002445166,0.0002861363,0.0001649582,0.0002880419,0.000001053166,0.0001413317],"genre_scores_gemma":[0.337338,0.0001228901,0.6623521,0.00005782419,0.00001475736,0.00000358836,0.00001034115,0.000004355226,0.00009619544],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2659821,"threshold_uncertainty_score":0.9747896,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Mark Trappmann","is_ca":false},{"name":"Georg‐Christoph Haas","is_ca":false},{"name":"Sonja Malich","is_ca":false},{"name":"Florian Keusch","is_ca":false},{"name":"Sebastian Bähr","is_ca":false},{"name":"Frauke Kreuter","is_ca":false},{"name":"Štefan Schwarz","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.7842892671678372,"gpt":0.5220393702231063,"spread":0.2622498969447309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2161835,0.0001611518,0.0005763823,0.0001739262,0.000765006,0.0001214908,0.00122177,0.00008879008,0.0002797614],"category_scores_gemma":[0.07258289,0.000132001,0.0000257257,0.0004734215,0.0003287744,0.0004167717,0.0008424136,0.0005068162,0.000001877895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004520635,"about_ca_system_score_gemma":0.0004982465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004620215,"about_ca_topic_score_gemma":0.01290819,"domain_scores_codex":[0.9028974,0.09438401,0.0008080965,0.0006312118,0.0007399848,0.0005393071],"domain_scores_gemma":[0.9188347,0.07929695,0.000586382,0.0006163409,0.0004330208,0.0002325447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01588724,0.0002488262,0.8569925,0.00002265454,0.0006421813,0.0003106112,0.01147749,0.00004473302,0.00007172907,0.0005844488,0.04814747,0.06557007],"study_design_scores_gemma":[0.0005803332,0.0005546418,0.965002,0.000009550703,0.00008156303,0.0001100096,0.004842167,0.00005584328,0.00000454632,0.001295412,0.02726976,0.0001941587],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.4304503,0.001027845,0.5455537,0.001121383,0.001114019,0.0002204322,0.02038064,0.00001148676,0.0001202516],"genre_scores_gemma":[0.4330455,0.0009488852,0.5601956,0.001088514,0.0003779306,0.000007725896,0.001728264,0.0000664245,0.002541155],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1436006,"threshold_uncertainty_score":0.9352291,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Marius Stefan","is_ca":false},{"name":"M. Hidiroglou","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.7039901809482423,"gpt":0.5070651107249131,"spread":0.1969250702233292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04224303,0.0002020138,0.0008599104,0.0004866901,0.0002046649,0.00003624533,0.0002295684,0.0001036551,0.0001148929],"category_scores_gemma":[0.05093431,0.000174364,0.00005531933,0.0004322806,0.00008011036,0.00006781577,0.0001537863,0.0006297296,5.219978e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009300444,"about_ca_system_score_gemma":0.0001595053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001697876,"about_ca_topic_score_gemma":0.0008895681,"domain_scores_codex":[0.9851378,0.01269595,0.001254419,0.0002311765,0.0003836172,0.0002970953],"domain_scores_gemma":[0.962586,0.03547962,0.00109595,0.0001977356,0.0005177664,0.0001229625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003881621,0.0007523485,0.8235862,0.000256228,0.0002737019,0.0002488575,0.00206686,0.001702635,0.002903766,0.009872948,0.0764718,0.07798307],"study_design_scores_gemma":[0.00177059,0.0005977122,0.8491873,0.00008847909,0.00005213867,0.0004922578,0.0001994583,0.00466001,0.0004150173,0.1412898,0.0008527058,0.0003944776],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3924406,0.0002170364,0.6060608,0.0000534662,0.0006192185,0.0001010831,0.0004766104,0.00002186258,0.000009289046],"genre_scores_gemma":[0.08660334,0.0001939758,0.9127808,0.0001047557,0.00004174195,0.0000100578,0.0001554784,0.00003779434,0.00007210438],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.30672,"threshold_uncertainty_score":0.9862124,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Henning Silber","is_ca":false},{"name":"Endre Tvinnereim","is_ca":false},{"name":"Tobias Stark","is_ca":false},{"name":"Annelies G. Blom","is_ca":false},{"name":"Jon A. Krosnick","is_ca":false},{"name":"Michael Bošnjak","is_ca":false},{"name":"Sanne Lund Clement","is_ca":false},{"name":"Anne Cornilleau","is_ca":false},{"name":"Anne-Sophie Cousteaux","is_ca":false},{"name":"Melvin John","is_ca":false},{"name":"Guðbjörg Andrea Jónsdóttir","is_ca":false},{"name":"Karen Lawson","is_ca":true},{"name":"Peter Lynn","is_ca":false},{"name":"Johan Martinsson","is_ca":false},{"name":"Ditte Shamshiri-Petersen","is_ca":false},{"name":"Su‐Hao Tu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5870137882448033,"gpt":0.5534318512773253,"spread":0.03358193696747802,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004763285,0.0001065689,0.0004618422,0.00006688416,0.00005518939,0.00002461691,0.00007416805,0.00009808612,0.0001974767],"category_scores_gemma":[0.005908405,0.00006839511,0.00004907878,0.0001645446,0.00007887673,0.00006696081,0.00002702007,0.0001338566,0.000001127411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001694201,"about_ca_system_score_gemma":0.00003427541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00031646,"about_ca_topic_score_gemma":0.0001770595,"domain_scores_codex":[0.9938478,0.005155104,0.0005647797,0.0001808893,0.0001221615,0.0001292273],"domain_scores_gemma":[0.9949663,0.003526299,0.0005853669,0.0001486088,0.0007078051,0.00006557873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003113527,0.0002802057,0.6224492,0.0003103943,0.0008745232,0.000191299,0.008279519,0.0001156179,0.05742922,0.06550685,0.03885655,0.2025932],"study_design_scores_gemma":[0.0008784845,0.0008589526,0.9874936,0.00006394814,0.0001265006,0.0004541752,0.0007425883,0.0001763608,0.002391993,0.006087219,0.0006036262,0.0001225677],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.753745,0.0009469129,0.2442267,0.0001598443,0.0007103629,0.00006314268,0.00009403485,0.000004309302,0.0000496586],"genre_scores_gemma":[0.7053883,0.001861009,0.2901036,0.000241387,0.0003220926,0.000006401423,0.0002041283,0.00001999587,0.00185303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3650444,"threshold_uncertainty_score":0.7073339,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Sixia Chen","is_ca":false},{"name":"David Haziza","is_ca":true},{"name":"Zeinab Mashreghi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6810327651611238,"gpt":0.4918226381347552,"spread":0.1892101270263686,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02214099,0.0001491065,0.0006822618,0.00007512864,0.00004402508,0.00003938386,0.0006143966,0.00009771305,0.00001853457],"category_scores_gemma":[0.1407918,0.0001032685,0.00002341896,0.0003295919,0.0002152077,0.0001269487,0.0001297448,0.0004117736,3.16829e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009444954,"about_ca_system_score_gemma":0.0001299428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005280459,"about_ca_topic_score_gemma":0.0004256068,"domain_scores_codex":[0.9882589,0.009842767,0.001120799,0.0002414181,0.0003183841,0.0002177157],"domain_scores_gemma":[0.9208776,0.07740146,0.0008593114,0.0003017364,0.0004561981,0.0001037351],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003863472,0.001016075,0.2158112,0.001705246,0.0005908215,0.000528961,0.01011542,0.001251715,0.002463566,0.2806349,0.03042552,0.4515932],"study_design_scores_gemma":[0.0008138103,0.0005425329,0.6745058,0.00007211738,0.0000802963,0.00008235272,0.0001538664,0.1035425,0.00005048432,0.2199556,0.00004464167,0.0001560953],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005156936,0.000110354,0.9921327,0.0003543539,0.0001789081,0.0001473444,0.001903139,0.000003251326,0.00001306002],"genre_scores_gemma":[0.08469648,0.0001131911,0.9149357,0.0001591726,0.0000386937,9.165747e-7,0.00004317058,0.00001121271,0.000001481152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4586946,"threshold_uncertainty_score":0.8664456,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Sarah K Heimel","is_ca":false},{"name":"Rebecca L. Medway","is_ca":false},{"name":"Rachel Horwitz","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6823083142602526,"gpt":0.5520341180469343,"spread":0.1302741962133184,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1332019,0.0002136453,0.001074066,0.0004841894,0.0001244473,0.00005183531,0.0001752661,0.0003281266,0.000101816],"category_scores_gemma":[0.08465511,0.0001585056,0.0000621344,0.0004848222,0.0007050006,0.0001501179,0.00006130203,0.0004276845,8.490309e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007987614,"about_ca_system_score_gemma":0.0006589158,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004751195,"about_ca_topic_score_gemma":0.06303002,"domain_scores_codex":[0.8538941,0.1439375,0.001087837,0.0003132479,0.0003489454,0.000418372],"domain_scores_gemma":[0.8017805,0.1974081,0.0003146537,0.0001043714,0.0002214515,0.0001710079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.1307867,0.0008217083,0.6855081,0.0001760643,0.0007780528,0.0006180459,0.02740076,0.00004408632,0.01696466,0.001261262,0.007660812,0.1279798],"study_design_scores_gemma":[0.001119774,0.001263407,0.988532,0.00009659907,0.0001020892,0.00005397244,0.001589457,0.0002191463,0.0003167824,0.002701849,0.003825003,0.0001799133],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9466007,0.005876516,0.04471819,0.0006257477,0.001114344,0.0001503298,0.0008848496,0.000008808836,0.00002046784],"genre_scores_gemma":[0.8870919,0.004297117,0.1077661,0.0001166882,0.00006776403,0.000004152514,0.00001568463,0.00002739072,0.0006132791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3030239,"threshold_uncertainty_score":0.9540672,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"David Haziza","is_ca":true},{"name":"Sixia Chen","is_ca":false},{"name":"Yimeng Gao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6424708043159415,"gpt":0.4784392389837912,"spread":0.1640315653321503,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02710179,0.0001905343,0.0006064836,0.00007622451,0.0001947127,0.00004768306,0.0001741632,0.0001032833,0.000140017],"category_scores_gemma":[0.05877388,0.0001208921,0.00005089139,0.0001802816,0.0001380931,0.00004967824,0.00008248664,0.0002321379,0.000002840079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004833603,"about_ca_system_score_gemma":0.0001264397,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009247941,"about_ca_topic_score_gemma":0.0006350459,"domain_scores_codex":[0.9863091,0.01224164,0.0008115711,0.0001774957,0.0002202853,0.0002398821],"domain_scores_gemma":[0.9308766,0.06755416,0.0007257411,0.0001510146,0.0005318898,0.0001605897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01855287,0.0008536064,0.6355239,0.0007406538,0.002571687,0.0004887176,0.02274453,0.002017629,0.01127258,0.0279978,0.2177164,0.05951963],"study_design_scores_gemma":[0.0047396,0.005849046,0.8549815,0.0001126552,0.0007165655,0.0003904116,0.001671104,0.008896274,0.00614697,0.06704681,0.04821904,0.001230053],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1539377,0.0003050246,0.8437322,0.0003834176,0.0001913357,0.0001212205,0.001287523,0.00002053947,0.00002108161],"genre_scores_gemma":[0.04150026,0.0009785846,0.9563224,0.0004319779,0.0001176605,0.000004404514,0.0001147827,0.00004189856,0.0004880692],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2194576,"threshold_uncertainty_score":0.9491544,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Susana Rubin-Bleuer","is_ca":false},{"name":"Leon Jang","is_ca":false},{"name":"Serge Godbout","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1877846169135838,"gpt":0.3363112003694582,"spread":0.1485265834558744,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00904877,0.00008961403,0.0003843917,0.0001361806,0.0001888334,0.00004587727,0.0001760531,0.00005081183,0.000009354675],"category_scores_gemma":[0.002024361,0.00004535946,0.00002170446,0.0001463932,0.0001113349,0.00006008872,0.00001861509,0.00006387853,0.000001174355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002782842,"about_ca_system_score_gemma":0.0000781353,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1698624,"about_ca_topic_score_gemma":0.6759162,"domain_scores_codex":[0.9986579,0.0004738194,0.0005017489,0.0001532546,0.00003947312,0.0001737992],"domain_scores_gemma":[0.9941335,0.004632482,0.0005838288,0.0001837078,0.0002924362,0.0001739879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008113524,0.00002733198,0.9148454,0.00001062775,0.0003029962,0.000002205834,0.0002471709,0.0000373807,0.00003993148,0.01788739,0.002242425,0.06354576],"study_design_scores_gemma":[0.0004740926,0.0005850858,0.9816481,0.000006174896,0.00002980247,0.00001086363,0.00001719833,0.0009314426,0.00001685154,0.01218371,0.00400934,0.00008735142],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1278453,0.0002728384,0.86344,0.001084726,0.0001112426,0.0001679112,0.007068757,9.756568e-7,0.000008234193],"genre_scores_gemma":[0.8928152,0.000814209,0.1058503,0.0002961536,0.00005582909,0.00001415267,0.00007610457,0.00001742973,0.0000606464],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7649699,"threshold_uncertainty_score":0.8356655,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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)","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.4880688058564743,"gpt":0.5424089670887016,"spread":0.05434016123222729,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01068986,0.0001502167,0.0005341887,0.0004306335,0.0001214394,0.00004358005,0.0001223095,0.0001141232,0.00001084022],"category_scores_gemma":[0.008941545,0.0001205799,0.00003686795,0.0003685132,0.00004691964,0.00007046449,0.00002877848,0.0001965749,4.440645e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000368491,"about_ca_system_score_gemma":0.00004659535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006595812,"about_ca_topic_score_gemma":0.0004284216,"domain_scores_codex":[0.9962558,0.002482403,0.0007700726,0.0001771138,0.0001528626,0.00016174],"domain_scores_gemma":[0.9804232,0.01817451,0.0005669618,0.0001924859,0.0005544342,0.00008840712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000944988,0.0002270234,0.2499007,0.000398867,0.0003714114,0.000006437714,0.0005388454,0.001044146,0.0010755,0.2916466,0.004796312,0.4490491],"study_design_scores_gemma":[0.0003114328,0.0002215599,0.5835666,0.00008081253,0.0001122783,0.00002459233,0.0000577492,0.0009998564,0.0003263415,0.4134178,0.0007358135,0.0001451077],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02706324,0.00006921918,0.9720963,0.0001937068,0.0001516215,0.0002481593,0.000107825,0.00003209589,0.00003784986],"genre_scores_gemma":[0.07729499,0.00005882482,0.9223162,0.0001390999,0.00003420314,0.00001743188,0.00004898284,0.00001701809,0.00007327388],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.448904,"threshold_uncertainty_score":0.9994066,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Statistics Canada","funders":"","keywords":"Estimation; Statistics; Econometrics; Computer science; Population; Mathematics; Medicine; Environmental health; Economics","authors":[{"name":"Marius Stefan","is_ca":false},{"name":"M. Hidiroglou","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.554927493029936,"gpt":0.5121732745467844,"spread":0.04275421848315164,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01212969,0.0001032293,0.0004045262,0.0002985045,0.00004115673,0.00003256501,0.00005124239,0.0001007405,0.00001763672],"category_scores_gemma":[0.01255833,0.00008717179,0.00005347531,0.0001677663,0.00005495895,0.0001067313,0.00002181564,0.0001621213,3.061666e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003856993,"about_ca_system_score_gemma":0.00007510136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004111711,"about_ca_topic_score_gemma":0.00005045414,"domain_scores_codex":[0.9969249,0.001969396,0.0007075295,0.00010336,0.0001839488,0.0001108507],"domain_scores_gemma":[0.9826627,0.01649608,0.0004072044,0.00008978248,0.0002912617,0.00005290901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004928447,0.0004253655,0.02430021,0.003067897,0.001555297,0.000162155,0.00586331,0.01978946,0.02090747,0.2766131,0.01193564,0.6304516],"study_design_scores_gemma":[0.0005556077,0.000448306,0.1383558,0.0003297581,0.0002562523,0.0006426764,0.0001260535,0.157405,0.001327835,0.7003096,0.00003043249,0.000212599],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3895317,0.0001459275,0.6097448,0.00002554102,0.000406195,0.00004033327,0.00009074026,0.00001200319,0.000002730077],"genre_scores_gemma":[0.4339816,0.00002770234,0.5659048,0.000008928844,0.00002428816,4.244595e-7,0.00001455574,0.00001173585,0.00002593899],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.630239,"threshold_uncertainty_score":0.9957593,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Mamadou Yauck","is_ca":true},{"name":"Erica E. M. Moodie","is_ca":false},{"name":"Herak Apelian","is_ca":false},{"name":"Alain Fourmigue","is_ca":false},{"name":"Daniel Grace","is_ca":false},{"name":"Trevor Hart","is_ca":false},{"name":"Gilles Lambert","is_ca":false},{"name":"Joseph Cox","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5731953672614928,"gpt":0.5175135239374811,"spread":0.05568184332401171,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005017424,0.0001297852,0.0006921137,0.0001531049,0.00006407671,0.00002264811,0.00007171977,0.0001260689,0.0000566132],"category_scores_gemma":[0.01810412,0.0001114221,0.00007244357,0.0001336681,0.0000811062,0.00004287639,0.00003861075,0.0003265195,0.00000131686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003271729,"about_ca_system_score_gemma":0.0003342241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002331309,"about_ca_topic_score_gemma":0.00011984,"domain_scores_codex":[0.9973767,0.00134092,0.0006430505,0.0001822443,0.0002027739,0.0002542748],"domain_scores_gemma":[0.9867529,0.0113817,0.0003791846,0.0001508328,0.001095076,0.0002402629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01168984,0.0008810004,0.3317231,0.0009446365,0.00232976,0.002580905,0.007077232,0.0002048132,0.169485,0.01981834,0.0505839,0.4026815],"study_design_scores_gemma":[0.009084417,0.004119762,0.9004757,0.0001809846,0.00102333,0.005930626,0.005365436,0.0008977995,0.00419963,0.03412668,0.03414278,0.0004528762],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07749325,0.0008948554,0.9193943,0.0007871751,0.0006554489,0.0001163933,0.000568011,0.000005144572,0.00008537882],"genre_scores_gemma":[0.06700159,0.0008803217,0.9303576,0.0007662867,0.0003341219,0.000002192643,0.00008389315,0.00003264863,0.0005413912],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5687526,"threshold_uncertainty_score":0.9901668,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Jean‐François Beaumont","is_ca":true},{"name":"Cynthia Bocci","is_ca":true},{"name":"Michel St-Louis","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.7007546710550773,"gpt":0.5016242371275665,"spread":0.1991304339275107,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01540012,0.00009880014,0.0005209672,0.00007904705,0.00005189856,0.00001869187,0.0001184228,0.00007185709,0.00002995738],"category_scores_gemma":[0.08259728,0.00007246347,0.00005099109,0.0001688183,0.0001923298,0.00005166233,0.00004026341,0.0001934769,8.305851e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002200773,"about_ca_system_score_gemma":0.0001846444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007594063,"about_ca_topic_score_gemma":0.0003352012,"domain_scores_codex":[0.9925869,0.006075961,0.0008524394,0.0001167673,0.000215846,0.0001520756],"domain_scores_gemma":[0.9556696,0.04252521,0.0006484034,0.0001114096,0.0009900456,0.00005532802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000203892,0.0002380238,0.117598,0.0006747896,0.0001632822,0.00003899301,0.0004182312,0.0006035738,0.005981202,0.7820944,0.001284178,0.09070151],"study_design_scores_gemma":[0.0003363123,0.00006008156,0.5072963,0.00003826424,0.00002356402,0.00005371018,0.00002508746,0.001239713,0.0006860149,0.4901814,0.00001568678,0.00004378453],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0755771,0.00004869667,0.9231042,0.0001159904,0.0001428394,0.00009305398,0.0009039383,0.000001347873,0.00001283276],"genre_scores_gemma":[0.2447756,0.00002608586,0.7551068,0.00004781011,0.00001556867,0.000002026337,0.0000136436,0.000006746243,0.000005668485],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3896984,"threshold_uncertainty_score":0.9251304,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Victoire Michal","is_ca":true},{"name":"Jonathan Wakefield","is_ca":false},{"name":"Alexandra M. Schmidt","is_ca":true},{"name":"Alicia Cavanaugh","is_ca":true},{"name":"Brian E. Robinson","is_ca":true},{"name":"Jill Baumgartner","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.7662515417175665,"gpt":0.5679552565310851,"spread":0.1982962851864813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01878579,0.0001696679,0.0009468654,0.0002343127,0.00006342043,0.00003648306,0.0001204191,0.0001575047,0.00001427381],"category_scores_gemma":[0.03007506,0.0001344837,0.00009987164,0.0001671851,0.0001585454,0.00003835428,0.0000309096,0.000289467,7.157116e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004191761,"about_ca_system_score_gemma":0.0002666995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005365839,"about_ca_topic_score_gemma":0.00003283018,"domain_scores_codex":[0.9946792,0.003521758,0.001217251,0.0001917353,0.0001666095,0.0002235074],"domain_scores_gemma":[0.9344904,0.06395698,0.0005909906,0.0001232969,0.0007210186,0.0001173318],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001297552,0.0003109982,0.004245936,0.002265309,0.0007107019,0.0000251963,0.001320017,0.004332536,0.02540862,0.7361752,0.002263562,0.2216443],"study_design_scores_gemma":[0.0003898889,0.0005176949,0.001334161,0.000104544,0.0002835177,0.00002663339,0.00004868592,0.5441021,0.0009090268,0.452109,0.00009510521,0.00007963342],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01093803,0.0004036471,0.98595,0.00004282044,0.0007677338,0.000183624,0.00169079,0.00001022519,0.00001312083],"genre_scores_gemma":[0.01971555,0.00004419593,0.9800703,0.00003671712,0.00007939246,0.000004126418,0.000009128588,0.00002900153,0.00001157067],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5397695,"threshold_uncertainty_score":0.9780951,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","authors":[{"name":"Mehdi Dagdoug","is_ca":false},{"name":"Camélia Goga","is_ca":false},{"name":"David Haziza","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5742043220523099,"gpt":0.5636730961020205,"spread":0.01053122595028932,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0479086,0.0003986489,0.002165283,0.0007009712,0.00009850579,0.0002021955,0.0002036394,0.0005100399,0.00002688904],"category_scores_gemma":[0.1171794,0.0003488885,0.00007070966,0.0004250402,0.0002281131,0.000103603,0.000353991,0.002087099,6.589477e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008679569,"about_ca_system_score_gemma":0.0004633757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001264755,"about_ca_topic_score_gemma":0.001526939,"domain_scores_codex":[0.9461686,0.05052046,0.001997486,0.000558166,0.0003584255,0.0003968604],"domain_scores_gemma":[0.9384155,0.05849574,0.001740362,0.000191342,0.0008896432,0.0002674529],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000326029,0.0004874617,0.4992903,0.001804049,0.0003194602,0.0002523015,0.003078422,0.0008487657,0.000504414,0.003587944,0.00007635503,0.4894245],"study_design_scores_gemma":[0.0006599432,0.0005555781,0.4660023,0.0002594986,0.0002565804,0.0003377649,0.0004345798,0.1301763,0.0000866156,0.4008265,0.00000884672,0.0003955605],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.160035,0.001674911,0.837434,0.0000330233,0.0004343269,0.0001730224,0.0002038841,0.000007830613,0.000003945742],"genre_scores_gemma":[0.05015587,0.0008400839,0.9487761,0.0000426537,0.00007825676,0.000003276771,0.00005561064,0.00004476936,0.000003329933],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4890289,"threshold_uncertainty_score":0.9998963,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Ruben L. Bach","is_ca":false},{"name":"Matthias Schonlau","is_ca":true},{"name":"Katharina Meitinger","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1819431608627828,"gpt":0.3925421491784883,"spread":0.2105989883157055,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003265413,0.0001326114,0.0003804906,0.0003234078,0.0001477071,0.0003990683,0.0008296658,0.0001048346,0.000004211612],"category_scores_gemma":[0.001431896,0.0001029491,0.00002282221,0.0003660262,0.0001467327,0.0006122043,0.0002859642,0.0002800213,3.854261e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002993533,"about_ca_system_score_gemma":0.0001611205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005419821,"about_ca_topic_score_gemma":0.0003218711,"domain_scores_codex":[0.9978812,0.001024759,0.0005069541,0.0002604841,0.0001597999,0.0001668086],"domain_scores_gemma":[0.9954553,0.00326708,0.0005708897,0.000305486,0.0003418821,0.00005932052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0002073606,0.0001884961,0.02567948,0.00002899377,0.0004072819,0.00002992382,0.00215388,0.00007400652,0.01134507,0.5171075,0.005603977,0.437174],"study_design_scores_gemma":[0.001880412,0.00055325,0.6383463,0.0001266866,0.0001443544,0.00002991103,0.00194726,0.02180797,0.002014549,0.3318743,0.0009336692,0.000341257],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02898635,0.001037376,0.9683693,0.000986509,0.0002477211,0.0001085033,0.0001076651,0.00003332702,0.0001232269],"genre_scores_gemma":[0.4171404,0.0002409852,0.5823389,0.0001409335,0.00001172335,0.000004721342,0.00002279206,0.000004357523,0.00009525599],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6126668,"threshold_uncertainty_score":0.4198142,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bank of Canada","funders":"","keywords":"Selection (genetic algorithm); Selection bias; Variance (accounting); Calibration; Payment; Estimation","authors":[{"name":"Heng Chen","is_ca":true},{"name":"John Tsang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4738508169731649,"gpt":0.5186313866550564,"spread":0.04478056968189142,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03640638,0.0001814485,0.0008582767,0.000285342,0.00007998781,0.0000423717,0.0001314244,0.0001166288,0.00004449798],"category_scores_gemma":[0.09429719,0.0001493995,0.00004293377,0.0004729002,0.0001296931,0.000053185,0.00006186464,0.000519074,4.244374e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009900922,"about_ca_system_score_gemma":0.0001888078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001831208,"about_ca_topic_score_gemma":0.005167225,"domain_scores_codex":[0.9881654,0.009873413,0.001230004,0.0002453311,0.0001872394,0.0002985474],"domain_scores_gemma":[0.9335717,0.06491826,0.0005970866,0.0001281018,0.0006781155,0.0001067423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001153827,0.000532282,0.4585161,0.0002443908,0.0001327993,0.00004404982,0.000320976,0.00001348697,0.0004861124,0.06290248,0.002448915,0.4732046],"study_design_scores_gemma":[0.001407313,0.0003694788,0.4682637,0.00006878095,0.0000441329,0.00005506404,0.00004791757,0.001650082,0.0002867854,0.5276742,0.00002351017,0.0001090014],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1745015,0.00004567819,0.8242775,0.00005067125,0.0007250488,0.0001443913,0.0002008048,0.000004541259,0.00004981866],"genre_scores_gemma":[0.1371097,0.00004694341,0.8626709,0.0000857491,0.0000336548,0.000003485202,0.000007623813,0.00001028262,0.00003162995],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4730956,"threshold_uncertainty_score":0.9922224,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","authors":[{"name":"Zeinab Mashreghi","is_ca":true},{"name":"Huiqi Deng","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8566941241856907,"gpt":0.5528146051570141,"spread":0.3038795190286766,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0386884,0.000147903,0.0006803843,0.0001232621,0.00009672348,0.00006096794,0.0002879429,0.000148309,0.000010006],"category_scores_gemma":[0.07947464,0.0001294559,0.00004478391,0.0001798727,0.00008208538,0.00008987665,0.0001360906,0.0002622608,1.295063e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001820081,"about_ca_system_score_gemma":0.0002080744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002332542,"about_ca_topic_score_gemma":0.000295347,"domain_scores_codex":[0.9937106,0.004710618,0.0008839938,0.0002690974,0.0001911683,0.0002344963],"domain_scores_gemma":[0.957451,0.04001293,0.0006227634,0.0003996467,0.001396856,0.0001168432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004075237,0.001797477,0.1649456,0.002490441,0.002757223,0.0002342544,0.002034963,0.000316169,0.004159464,0.05395327,0.4863623,0.2768737],"study_design_scores_gemma":[0.003327013,0.0008571694,0.4228768,0.0001504755,0.0004821772,0.001384709,0.0004345082,0.04209785,0.002606212,0.521983,0.002933248,0.0008668618],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007225521,0.0003520289,0.9886755,0.00004848055,0.0003032497,0.0001108101,0.003244573,0.00001814914,0.00002172418],"genre_scores_gemma":[0.009531194,0.0002272137,0.9889873,0.00007851456,0.00009723519,0.00000258549,0.0009941226,0.00002766134,0.00005420522],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.483429,"threshold_uncertainty_score":0.9898726,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}