{"meta":{"query_hash":"f050aeaf760a","filters":{"topic":"Survey Sampling and Estimation Techniques"},"cohort_total":191,"direct_labels_cover":0,"predictions_cover":191,"exported":191,"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/f050aeaf760a","api":"https://metacan.xera.ac/api/v1/cohort?topic=Survey+Sampling+and+Estimation+Techniques"},"results":[{"id":"W1497865302","doi":"10.6092/issn.1973-2201/1004","title":"Random non-response on study variable versus on study as well as auxiliary variables","year":2013,"lang":"en","type":"article","venue":"Università degli Studi di Bologna","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Estimator; Statistics; Mathematics; Simple random sample; Random variable; Variable (mathematics); Population mean; Population; Medicine","score_opus":0.05283423966777031,"score_gpt":0.32116866888827256,"score_spread":0.26833442922050227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1497865302","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":[0.897724,0.000010360761,0.0017546326,0.00012331025,0.00039545854,0.002826065,0.000014365559,0.0006600049,0.096491836],"genre_scores_gemma":[0.98358274,0.000007846002,0.0023796826,0.00014376135,0.000067300054,0.000108144704,0.000009390103,0.000059624013,0.013641504],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.99647665,0.0011577758,0.0004502519,0.0007459563,0.00062938133,0.0005400088],"domain_scores_gemma":[0.9913504,0.006927477,0.00024434517,0.0009747805,0.00031999964,0.00018296983],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0021990181,0.0004924827,0.00071305135,0.00044383193,0.00065178063,0.000102231585,0.0006078235,0.00019837494,0.001383302],"category_scores_gemma":[0.002394979,0.00044780757,0.00012792894,0.0005349391,0.00009931035,0.00025134214,0.00031855653,0.00044217028,0.0026087558],"study_design_candidate":"qualitative","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":[0.19971319,0.11285523,0.14958192,0.00037129864,0.011905321,0.0026235026,0.049086306,0.005538059,0.0021119476,0.071390525,0.3886877,0.006134982],"study_design_scores_gemma":[0.18785156,0.1401516,0.15745114,0.0010461373,0.0044427295,0.00005571885,0.39574972,0.00404767,0.0052899593,0.06529512,0.031128712,0.0074899374],"about_ca_topic_score_codex":0.0013056885,"about_ca_topic_score_gemma":0.000030290019,"teacher_disagreement_score":0.357559,"about_ca_system_score_codex":0.00030527537,"about_ca_system_score_gemma":0.00015781444,"threshold_uncertainty_score":0.99979734},"labels":[],"label_agreement":null},{"id":"W1511896087","doi":"10.1002/0470867205.ch7","title":"Analysis of Categorical Response Data from Complex Surveys: An Appraisal and Update","year":2003,"lang":"en","type":"other","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Categorical variable; Logistic regression; Statistics; Binary data; Computer science; Sample (material); Log-linear model; Domain (mathematical analysis); Regression analysis; Data mining; Linear model; Mathematics; Econometrics; Binary number","score_opus":0.3042676196341385,"score_gpt":0.4512353789808296,"score_spread":0.1469677593466911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1511896087","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":[0.0034488202,0.00019634007,0.93306684,0.00006112619,0.00012841294,0.00029824363,0.0062118876,0.0009694746,0.055618823],"genre_scores_gemma":[0.026197882,0.00023262331,0.8256921,0.0001404575,0.00013562724,0.000021378892,0.031478427,0.0008297189,0.115271755],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99694353,0.0017194296,0.00042513266,0.00051416556,0.00025131376,0.00014643636],"domain_scores_gemma":[0.9953337,0.0024410211,0.00032215568,0.001757793,0.000054180997,0.00009116745],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036476916,0.00024158998,0.00082773925,0.00057347794,0.000025861726,0.000038660863,0.00047138822,0.0002857143,0.0061286483],"category_scores_gemma":[0.0016284536,0.00020714942,0.00006059607,0.00046612037,0.000100078716,0.00005743153,0.00014650171,0.00012482822,0.000015599051],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008708152,0.00025305848,0.0040767575,0.00005610418,0.00195438,0.0000041191265,0.00007922547,0.0000015115941,0.00004121811,0.0026261518,0.9892182,0.0016022254],"study_design_scores_gemma":[0.0020997769,0.00039924355,0.11175539,0.00022485266,0.012912255,0.000013949139,0.00048075122,0.07895484,0.00031179702,0.04254623,0.7464365,0.0038644567],"about_ca_topic_score_codex":0.004773768,"about_ca_topic_score_gemma":0.002776591,"teacher_disagreement_score":0.24278171,"about_ca_system_score_codex":0.000011062812,"about_ca_system_score_gemma":0.000043093485,"threshold_uncertainty_score":0.9947799},"labels":[],"label_agreement":null},{"id":"W1535801153","doi":"10.6092/issn.1973-2201/1118","title":"Regression type estimators for random non-response in survey sampling","year":2013,"lang":"en","type":"article","venue":"Università degli Studi di Bologna","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Estimator; Statistics; Mathematics; Mean squared error; Population mean; Estimation; Simple random sample; Sampling (signal processing); Regression analysis; Population; Computer science","score_opus":0.12407015578754574,"score_gpt":0.36484730166306667,"score_spread":0.24077714587552093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1535801153","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":[0.9005959,0.00004326953,0.097726405,0.00010006685,0.00019117862,0.0007993807,0.000020942109,0.00022307163,0.00029976413],"genre_scores_gemma":[0.9534552,0.000016537657,0.04575325,0.000035469122,0.000020111162,0.00003094709,0.000035966383,0.000031229883,0.0006212703],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985459,0.0003491196,0.00030222058,0.0003120205,0.00015471359,0.0003360627],"domain_scores_gemma":[0.99344546,0.005673715,0.00015961094,0.0003024182,0.0003388246,0.00007998137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019655202,0.00021306281,0.00041213408,0.00029035425,0.00021147882,0.000034327106,0.00024246667,0.00016491537,0.000057459274],"category_scores_gemma":[0.0046601915,0.00018813662,0.0000789045,0.00037983785,0.00007407035,0.00018617578,0.000116297444,0.00015751844,0.000040016832],"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":[0.021724483,0.0014378272,0.8484682,0.00048026026,0.00048003238,0.000057211426,0.008161875,0.0012859683,0.0060175834,0.0059914435,0.090416215,0.015478888],"study_design_scores_gemma":[0.013034932,0.0013414216,0.91124415,0.00089026283,0.00015641209,0.000013952102,0.0028120335,0.019773293,0.0038256606,0.043551125,0.0017946262,0.0015621193],"about_ca_topic_score_codex":0.00038934316,"about_ca_topic_score_gemma":0.00007686207,"teacher_disagreement_score":0.088621594,"about_ca_system_score_codex":0.00012540675,"about_ca_system_score_gemma":0.000071657545,"threshold_uncertainty_score":0.76719886},"labels":[],"label_agreement":null},{"id":"W1581498141","doi":"10.1023/a:1022427530788","title":"Estimation of the Size and Mean Value of a Stigmatized Characteristic of a Hidden Gang in a Finite Population: A Unified Approach","year":2002,"lang":"en","type":"article","venue":"Annals of the Institute of Statistical Mathematics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Mathematics; Statistics; Population; Econometrics; Demography; Sociology","score_opus":0.1366706589260064,"score_gpt":0.34971027216190037,"score_spread":0.21303961323589396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1581498141","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":[0.85131955,0.00004422861,0.14689825,0.00016695428,0.000056451427,0.0006899306,0.0002926278,0.00002112366,0.0005108625],"genre_scores_gemma":[0.724784,0.00001794453,0.27513662,0.000009881734,0.0000043052387,0.000010936671,0.0000055580817,0.000012610547,0.000018113864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975774,0.0001741861,0.0014628075,0.00014211136,0.00050189416,0.00014154775],"domain_scores_gemma":[0.99498135,0.0027978658,0.0013966842,0.0005436939,0.0002431177,0.00003726473],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0011055627,0.00017624555,0.0007771895,0.000113773385,0.000041394986,0.000007659078,0.00034191782,0.00010340416,0.000020078902],"category_scores_gemma":[0.0108114425,0.000117899646,0.000113038055,0.00041821814,0.00049352646,0.00010668493,0.000122032165,0.00013046837,2.7089635e-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":[0.00010747804,0.0016268486,0.0012768384,0.012176671,0.00017593369,9.678732e-7,0.008590016,0.0019221681,0.0018994627,0.96717954,0.00017800761,0.0048660883],"study_design_scores_gemma":[0.000642168,0.00011422746,0.02021926,0.002669793,0.00016586424,0.000008914272,0.00020302655,0.2367143,0.010467241,0.72861594,0.00000200815,0.00017723057],"about_ca_topic_score_codex":0.00017274168,"about_ca_topic_score_gemma":0.000012003342,"teacher_disagreement_score":0.23856355,"about_ca_system_score_codex":0.00001191644,"about_ca_system_score_gemma":0.00003538175,"threshold_uncertainty_score":0.9975209},"labels":[],"label_agreement":null},{"id":"W1599092457","doi":"10.1016/j.csda.2013.07.034","title":"Inclusion probabilities in partially rank ordered set sampling","year":2013,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Rank (graph theory); Variance (accounting); Estimator; Simple random sample; Mathematics; Population; Statistics; Unit (ring theory); Sampling (signal processing); Set (abstract data type); Sampling design; Selection (genetic algorithm); Sample (material); Combinatorics; Computer science; Economics; Artificial intelligence; Demography","score_opus":0.2080757221148221,"score_gpt":0.4147827400347145,"score_spread":0.2067070179198924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599092457","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":[0.033388056,0.000028801442,0.9638286,0.00022161976,0.00003147653,0.000286655,0.0020237346,0.00014034078,0.000050718027],"genre_scores_gemma":[0.35633278,0.0000096739905,0.6337929,0.000059690352,0.000021705146,0.00003714854,0.009700014,0.000014182826,0.000031930736],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978446,0.00022210089,0.0007396733,0.0004474573,0.00050906563,0.00023709773],"domain_scores_gemma":[0.9956606,0.0029769726,0.00022939374,0.00063907396,0.00041739683,0.000076580516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012736253,0.0001801314,0.0004065798,0.0003988018,0.0002710825,0.00015355111,0.00046698676,0.00006908914,0.00058470585],"category_scores_gemma":[0.002584561,0.00017678153,0.00005369907,0.0009254773,0.000077487166,0.00031154754,0.0007706068,0.0001416054,0.000044129454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007935851,0.0009282434,0.13499828,0.000604984,0.0021499554,0.000016920398,0.0054136654,0.4973783,0.000042683736,0.23149168,0.06498962,0.061906334],"study_design_scores_gemma":[0.00012680494,0.000009403718,0.024520528,0.000016104812,0.00015504606,6.069159e-7,0.000028882088,0.47275296,0.0000026468654,0.50211453,0.00014305419,0.00012945075],"about_ca_topic_score_codex":0.0022195086,"about_ca_topic_score_gemma":0.0020151709,"teacher_disagreement_score":0.33003572,"about_ca_system_score_codex":0.000078858204,"about_ca_system_score_gemma":0.00010457436,"threshold_uncertainty_score":0.72089416},"labels":[],"label_agreement":null},{"id":"W1638540087","doi":"","title":"An Optimal Calibration Distance Leading to the Optimal Regresion Estimator","year":2005,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Estimator; Statistics; Mathematics; Calibration; Population; Optimal design; Best linear unbiased prediction; Population mean; Sampling (signal processing); Mean squared error; Computer science; Artificial intelligence; Medicine","score_opus":0.41918027327533336,"score_gpt":0.491450805124762,"score_spread":0.07227053184942867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1638540087","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17895456,0.00004657427,0.81903994,0.0009213587,0.00021478209,0.00027903638,0.000041020907,0.00037462995,0.00012812563],"genre_scores_gemma":[0.28185463,0.0000037562345,0.71736777,0.000222344,0.00017376032,0.000051298863,0.00006346089,0.000037057078,0.00022591522],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99234873,0.006076774,0.0005039181,0.0004415197,0.00023907493,0.00038998554],"domain_scores_gemma":[0.9900575,0.008728982,0.00018647156,0.0007124611,0.0001751587,0.00013941168],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017714733,0.00022278517,0.00039517556,0.00012888697,0.00030719937,0.00007902084,0.00045644448,0.00018179805,0.00011564887],"category_scores_gemma":[0.013150932,0.00016716975,0.00006509746,0.00034382244,0.000087985754,0.0002708258,0.00007385889,0.00025804434,0.000057827605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0050262557,0.0012365459,0.031957522,0.00028710294,0.00030598746,0.000030415062,0.016649876,0.26217192,0.031002866,0.11660794,0.15951927,0.37520427],"study_design_scores_gemma":[0.0016460385,0.001944367,0.09091369,0.0002852721,0.00018558718,0.00021978072,0.0010567972,0.5962316,0.23040624,0.04052959,0.033639006,0.0029420792],"about_ca_topic_score_codex":0.00017766484,"about_ca_topic_score_gemma":0.0005922868,"teacher_disagreement_score":0.3722622,"about_ca_system_score_codex":0.000073033676,"about_ca_system_score_gemma":0.000057449386,"threshold_uncertainty_score":0.9951617},"labels":[],"label_agreement":null},{"id":"W1675559613","doi":"10.1017/cbo9781139022422.023","title":"Incorporating predicted species distribution in adaptive and conventional sampling designs","year":2012,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","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":"Simon Fraser University","funders":"","keywords":"Sampling (signal processing); Sampling design; Stratified sampling; Adaptive sampling; Statistics; Computer science; Population; Habitat; Abundance (ecology); Ecology; Data mining; Econometrics; Mathematics; Monte Carlo method; Biology","score_opus":0.18436936347693184,"score_gpt":0.2790485905156273,"score_spread":0.09467922703869547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1675559613","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021013317,0.00013419711,0.31536075,0.0000080521695,0.00012623396,0.000738763,0.0023498794,0.00043346765,0.6787473],"genre_scores_gemma":[0.0750447,0.00009963924,0.026049735,0.000013412999,0.00023143015,0.0000059077565,0.0016144067,0.000088650384,0.89685214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989377,0.00007459555,0.00027667196,0.00029551098,0.00021372589,0.00020175829],"domain_scores_gemma":[0.9986942,0.00047710337,0.00034981564,0.00020649377,0.00017409098,0.00009834066],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042316798,0.00026802655,0.0003528782,0.00015483389,0.00015676302,0.00003351832,0.00014410348,0.00032268447,0.000005545437],"category_scores_gemma":[0.00010747714,0.00032511543,0.00008199829,0.000012528901,0.0002176662,0.00012437651,0.00017635297,0.0003903933,0.000001650054],"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":[0.00006827208,0.0000144952355,0.00011561924,0.00009852686,0.00005006854,0.000013032229,0.00005287604,0.0000017666518,0.000031635147,0.9964821,0.0025262963,0.0005453257],"study_design_scores_gemma":[0.010012398,0.00094913936,0.021207666,0.014761737,0.0029404415,0.00029475402,0.0015235894,0.0095431,0.0060876478,0.069106355,0.8546639,0.008909268],"about_ca_topic_score_codex":0.000067593566,"about_ca_topic_score_gemma":0.0000052373002,"teacher_disagreement_score":0.92737573,"about_ca_system_score_codex":0.00026134093,"about_ca_system_score_gemma":0.000066553854,"threshold_uncertainty_score":0.99992007},"labels":[],"label_agreement":null},{"id":"W1827082642","doi":"10.1080/00028487.2014.901252","title":"Cluster Sampling: A Pervasive, Yet Little Recognized Survey Design in Fisheries Research","year":2014,"lang":"en","type":"article","venue":"Transactions of the American Fisheries Society","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"U.S. Fish and Wildlife Service; Memorial University of Newfoundland; Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"Cluster sampling; Estimator; Sampling (signal processing); Sampling design; Simple random sample; Cluster (spacecraft); Independence (probability theory); Statistics; Fishery; Sample (material); Population; Sample size determination; Population dynamics of fisheries; Fisheries management; Fish <Actinopterygii>; Computer science; Econometrics; Biology; Mathematics; Fishing; Demography","score_opus":0.32967382582193083,"score_gpt":0.39895957429587403,"score_spread":0.0692857484739432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1827082642","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":[0.42433995,0.0000136438475,0.5727534,0.0016143796,0.00013593698,0.0005031716,0.000057579397,0.00018867243,0.0003932597],"genre_scores_gemma":[0.7539457,0.00012847462,0.24487455,0.00018805322,0.000022440961,0.0001400789,0.000008395493,0.000054236567,0.0006380456],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9964866,0.0019229769,0.000492643,0.00030095634,0.00041541312,0.0003813978],"domain_scores_gemma":[0.9905169,0.008073438,0.00025243542,0.00071567687,0.00038376526,0.000057782152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054372055,0.00019066951,0.00047705526,0.000075719996,0.00035519362,0.00006325275,0.0005048321,0.00009816602,0.00010889237],"category_scores_gemma":[0.0027176565,0.00015537858,0.00027576392,0.0012069675,0.0011907867,0.00017541902,0.000038413436,0.00052555744,0.000004160435],"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":[0.004051141,0.0037439398,0.3526989,0.0019010865,0.001535162,0.0000011518582,0.09952853,0.003361326,0.004982221,0.0009181043,0.37954542,0.14773305],"study_design_scores_gemma":[0.004850218,0.0026441116,0.65051097,0.0010647167,0.00034795495,0.000036939695,0.027467031,0.02513953,0.03443434,0.23306498,0.01763046,0.0028087546],"about_ca_topic_score_codex":0.004348124,"about_ca_topic_score_gemma":0.001093264,"teacher_disagreement_score":0.36191496,"about_ca_system_score_codex":0.00011240216,"about_ca_system_score_gemma":0.00011980722,"threshold_uncertainty_score":0.6573092},"labels":[],"label_agreement":null},{"id":"W1861472101","doi":"10.3968/j.pam.1925252820110201.z55","title":"Two-stage Sampling on Additive Model for Quantitative Sensitive Question Survey and Its Application","year":2011,"lang":"en","type":"article","venue":"Progress in applied mathematics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Beijing; Sampling (signal processing); Statistics; Simple random sample; Variance (accounting); Survey sampling; Stage (stratigraphy); Randomized response; Population; Multistage sampling; Mathematics; Computer science; Medicine; Geography; Environmental health","score_opus":0.27617654986747353,"score_gpt":0.42632973050525363,"score_spread":0.1501531806377801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1861472101","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":[0.07144914,0.00003852047,0.9239042,0.000012521507,0.000025965064,0.0022854703,0.00027972087,0.00033355047,0.0016709405],"genre_scores_gemma":[0.48891497,0.000012579923,0.5099503,0.000016212309,0.00001005002,0.0009581184,0.00007115639,0.000044429486,0.000022233717],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837446,0.00008027969,0.0005670204,0.0004365533,0.00023385015,0.00030785406],"domain_scores_gemma":[0.9965209,0.0024308274,0.00042748754,0.0002901998,0.00025923128,0.000071390496],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025870942,0.00029499203,0.00044067312,0.00020635527,0.00012554665,0.000034981498,0.00014243265,0.0001511687,0.0000037562559],"category_scores_gemma":[0.0008986698,0.00028536073,0.000043596425,0.00020613526,0.00010456191,0.00008876081,0.00005847201,0.00020106607,0.000009391204],"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":[0.00022802966,0.00045325636,0.00016992523,0.00039692022,0.000032224787,5.642785e-7,0.006507219,0.000111866764,0.00012554698,0.98459387,0.00002104244,0.007359553],"study_design_scores_gemma":[0.0005588489,0.00009324883,0.00035212014,0.00019772681,0.000025633715,0.0000016601817,0.0006038599,0.55919725,0.010482036,0.42815682,0.0000036203194,0.00032715077],"about_ca_topic_score_codex":0.000011388675,"about_ca_topic_score_gemma":0.00006899269,"teacher_disagreement_score":0.55908537,"about_ca_system_score_codex":0.00007938309,"about_ca_system_score_gemma":0.000033708446,"threshold_uncertainty_score":0.9999598},"labels":[],"label_agreement":null},{"id":"W1916909999","doi":"10.1002/cjs.11187","title":"A new replicate variance estimator for unequal probability sampling without replacement","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Replicate; Estimator; Population variance; Statistics; Variance (accounting); Mathematics; Sampling (signal processing); Consistency (knowledge bases); Sampling design; Efficient estimator; Bias of an estimator; Consistent estimator; Minimum-variance unbiased estimator; Population; Econometrics; Computer science","score_opus":0.1631710627063437,"score_gpt":0.3555048550044894,"score_spread":0.1923337922981457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1916909999","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":[0.0062858225,0.000035912024,0.99203193,0.00049544696,0.00022860756,0.00055023795,0.0002142252,0.000033394106,0.00012439441],"genre_scores_gemma":[0.06159472,0.0000026727846,0.9378567,0.00008419472,0.000119601194,0.000029381683,0.000012078526,0.000030949694,0.00026970933],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985171,0.000053007174,0.0007590274,0.00017071262,0.0001766737,0.00032348093],"domain_scores_gemma":[0.99674684,0.00090620376,0.00055165985,0.0003260915,0.0008167437,0.00065247004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012136829,0.00015062459,0.00032558618,0.00012773408,0.00016865505,0.00013375674,0.00022160163,0.00007471222,0.000213898],"category_scores_gemma":[0.006165455,0.00013984981,0.00005944701,0.00010412333,0.000054777982,0.00013935902,0.000008947209,0.00017575378,0.00001031751],"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":[0.00013638286,0.000082250306,0.013415088,0.00069372304,0.00021605393,0.00001601071,0.0015776032,0.00063190487,0.00017265217,0.42428616,0.48736703,0.07140511],"study_design_scores_gemma":[0.00052346615,0.00029353602,0.001801403,0.00019706455,0.000065987544,0.00005068988,0.00006118036,0.004618149,0.00020751344,0.9857472,0.0062066335,0.00022713316],"about_ca_topic_score_codex":0.0040236237,"about_ca_topic_score_gemma":0.0025014007,"teacher_disagreement_score":0.5614611,"about_ca_system_score_codex":0.00024008095,"about_ca_system_score_gemma":0.0016034775,"threshold_uncertainty_score":0.73810714},"labels":[],"label_agreement":null},{"id":"W1926189568","doi":"10.1111/j.1467-9574.2012.00524.x","title":"A true simulation study of three estimators at equal protection of respondents in randomized response sampling","year":2012,"lang":"en","type":"article","venue":"Statistica Neerlandica","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Stephen's University","funders":"","keywords":"Estimator; Randomized response; Statistics; Mathematics; Sampling (signal processing); Econometrics; Computer science","score_opus":0.20507386404562242,"score_gpt":0.42678618539677166,"score_spread":0.22171232135114924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1926189568","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":[0.55364805,0.000011569221,0.44529662,0.0000051410484,0.00004667889,0.00089103606,0.00003078453,0.000052147487,0.000017948116],"genre_scores_gemma":[0.947091,0.00000103754,0.05268116,0.0000018946225,0.000015241471,0.00015066443,0.000011882062,0.00002604955,0.000021093292],"study_design_codex":"randomized_trial","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970082,0.0011075252,0.0010037352,0.00017672572,0.0004633798,0.00024043849],"domain_scores_gemma":[0.98891366,0.010072633,0.0005368903,0.00029391615,0.00011315135,0.00006973173],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.006354621,0.0001629938,0.0007092667,0.00044523634,0.000066299246,0.0000095481555,0.00010453093,0.00009853977,0.00007832158],"category_scores_gemma":[0.017173313,0.00014251446,0.00006550127,0.00032773145,0.000077910234,0.0001045063,0.00005321619,0.00013487264,0.000004681786],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7430341,0.007446895,0.14000013,0.0014108805,0.0005754548,0.000013413548,0.04866882,0.014767508,0.0077918577,0.021262702,0.00015052079,0.0148777],"study_design_scores_gemma":[0.1743326,0.0026679141,0.27991378,0.0010523855,0.0006194005,0.000015284902,0.001529712,0.29765856,0.00556825,0.2355046,0.000040660576,0.0010968467],"about_ca_topic_score_codex":0.00027246692,"about_ca_topic_score_gemma":0.00009985892,"teacher_disagreement_score":0.5687015,"about_ca_system_score_codex":0.00010113258,"about_ca_system_score_gemma":0.000040338713,"threshold_uncertainty_score":0.99110544},"labels":[],"label_agreement":null},{"id":"W1964757745","doi":"10.1111/j.0006-341x.2001.00287.x","title":"Catch Estimation in the Presence of Declining Catch Rate Due to Gear Saturation","year":2001,"lang":"en","type":"article","venue":"Biometrics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Fishing; Statistics; Bycatch; Econometrics; Fishery; Mathematics; Computer science; Biology","score_opus":0.164411733545063,"score_gpt":0.3998633404193596,"score_spread":0.23545160687429662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964757745","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":[0.6304937,0.000039154773,0.3683584,0.00040421393,0.00008376312,0.00028338833,0.0000051329084,0.00007100037,0.00026122824],"genre_scores_gemma":[0.8711765,0.000024363997,0.12860775,0.00006933177,0.000022095983,0.000028796423,0.0000142034605,0.000009849446,0.000047104444],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99882644,0.00017820453,0.00039998596,0.00015128987,0.00029356527,0.00015049533],"domain_scores_gemma":[0.99666786,0.0026475084,0.0001702917,0.00030909118,0.00017294456,0.000032296586],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003043872,0.00009164851,0.00016449542,0.0008960014,0.000056938945,0.000046704452,0.00023270115,0.00008334239,0.0000074426107],"category_scores_gemma":[0.010494836,0.00007098918,0.000031026277,0.0048845666,0.000022889255,0.00012124972,0.00003111572,0.00009683,0.000016968332],"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":[0.00042403804,0.0021726564,0.14917198,0.0010679862,0.00010679349,0.00009569335,0.044628132,0.006272997,0.016224412,0.040744144,0.039969623,0.69912153],"study_design_scores_gemma":[0.0016215907,0.00091367995,0.55164266,0.0007392374,0.00011828382,0.0001381361,0.0027098039,0.1697179,0.05493688,0.2103206,0.0057913507,0.0013498494],"about_ca_topic_score_codex":0.00033600643,"about_ca_topic_score_gemma":0.00004618899,"teacher_disagreement_score":0.6977717,"about_ca_system_score_codex":0.000046563862,"about_ca_system_score_gemma":0.00003231236,"threshold_uncertainty_score":0.99784017},"labels":[],"label_agreement":null},{"id":"W1973354056","doi":"10.1093/biomet/asp041","title":"A unified approach to linearization variance estimation from survey data after imputation for item nonresponse","year":2009,"lang":"en","type":"article","venue":"Biometrika","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Imputation (statistics); Categorical variable; Missing data; Statistics; Mathematics; Estimator; Econometrics; Computer science","score_opus":0.24244065568586481,"score_gpt":0.4131986451287096,"score_spread":0.17075798944284476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973354056","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":[0.058266696,0.000035001696,0.939199,0.0001282788,0.000106043284,0.0007786096,0.0010916893,0.00032920763,0.0000655293],"genre_scores_gemma":[0.4660248,0.0000021057076,0.5298397,0.00011545721,0.00005714012,0.000052390205,0.0038182072,0.000017429817,0.00007277972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837774,0.00024874276,0.0004355748,0.00047091633,0.00026641224,0.00020063408],"domain_scores_gemma":[0.99624896,0.0024189476,0.0001789591,0.00076791085,0.00029592417,0.000089313],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0030750104,0.0001703602,0.00023654729,0.00064482196,0.00008690816,0.00015280787,0.00034597283,0.00015145483,0.000009794518],"category_scores_gemma":[0.015913457,0.0001688399,0.000035583555,0.0018435479,0.000013873793,0.00030889368,0.000054683926,0.000064435386,0.000020028681],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0091827195,0.004493954,0.009976326,0.00053305784,0.0003928946,0.000005763821,0.0051797605,0.0035404128,0.010517162,0.009267675,0.064914346,0.8819959],"study_design_scores_gemma":[0.0009257192,0.0002949385,0.26679567,0.00007878217,0.000061321065,0.000002171941,0.000028248276,0.68566626,0.00298009,0.041832425,0.0007927615,0.0005416005],"about_ca_topic_score_codex":0.00013085316,"about_ca_topic_score_gemma":0.000012598464,"teacher_disagreement_score":0.88145435,"about_ca_system_score_codex":0.00006523801,"about_ca_system_score_gemma":0.00005954139,"threshold_uncertainty_score":0.9923759},"labels":[],"label_agreement":null},{"id":"W1975134946","doi":"10.1016/j.csda.2014.02.019","title":"Sample size determination for estimating prevalence and a difference between two prevalences of sensitive attributes using the non-randomized triangular design","year":2014,"lang":"en","type":"article","venue":"Computational Statistics & Data Analysis","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Robarts Clinical Trials; Western University","funders":"Natural Science Foundation of Chongqing","keywords":"Statistics; Sample size determination; Mathematics; Estimation; Contrast (vision); Sample (material); Randomized response; Small area estimation; Computer science; Artificial intelligence; Engineering","score_opus":0.1919506222280558,"score_gpt":0.42107482674447133,"score_spread":0.22912420451641552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975134946","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":[0.02038845,0.00002125431,0.9739013,0.00003325871,0.000020686217,0.0006567572,0.0049435175,0.0000339728,8.53272e-7],"genre_scores_gemma":[0.3757926,0.0000054097354,0.62347513,0.000008182603,0.00003315603,0.000022175385,0.0006518749,0.000008126764,0.0000033423203],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976202,0.0007986289,0.0007004925,0.00035959858,0.00036941824,0.00015165597],"domain_scores_gemma":[0.8946125,0.10373705,0.0006958537,0.0003590111,0.00055359956,0.000041966898],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005085258,0.00017064821,0.00068699155,0.00013249773,0.0002770813,0.00009120212,0.00029397273,0.000042210497,0.0000076378],"category_scores_gemma":[0.038712185,0.00013103863,0.000084361986,0.0003577713,0.00030031003,0.00012719308,0.00012700708,0.000070011956,1.8287805e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004157528,0.000500889,0.06541961,0.005773541,0.009694454,0.0000031557229,0.007642036,0.5907087,0.00029552192,0.076447465,0.000852583,0.23850451],"study_design_scores_gemma":[0.001954697,0.000025539086,0.005235961,0.00006809394,0.002458474,7.2657576e-7,0.000012481004,0.7129993,0.0000661146,0.2770756,3.1738116e-7,0.00010271925],"about_ca_topic_score_codex":0.0002538193,"about_ca_topic_score_gemma":0.000014745522,"teacher_disagreement_score":0.35540414,"about_ca_system_score_codex":0.000022774128,"about_ca_system_score_gemma":0.000051228402,"threshold_uncertainty_score":0.96938515},"labels":[],"label_agreement":null},{"id":"W1976410238","doi":"10.1037/a0029314","title":"Asking sensitive questions: A statistical power analysis of randomized response models.","year":2012,"lang":"en","type":"article","venue":"Psychological Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"World Anti-Doping Agency","keywords":"Randomized response; Statistical power; Statistics; Statistical model; Sample size determination; Wald test; Goodness of fit; Statistical hypothesis testing; Power (physics); Item response theory; Sample (material); Econometrics; Computer science; Statistical analysis; Mathematics; Psychology; Psychometrics","score_opus":0.2830794992700697,"score_gpt":0.5610199716537944,"score_spread":0.27794047238372466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976410238","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":[0.05282803,0.000086228894,0.94409263,0.0001264345,0.0001164802,0.0002723632,0.000043314278,0.00023270099,0.0022018391],"genre_scores_gemma":[0.43644235,0.000008866628,0.56336564,0.00008824457,0.000010782266,0.000043783664,0.000006551431,0.000008405446,0.00002539527],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9886039,0.009971418,0.00065153086,0.00025230984,0.00023786213,0.00028300233],"domain_scores_gemma":[0.9624132,0.036602624,0.00028085613,0.00037957996,0.00019799623,0.00012576257],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027639676,0.0001685913,0.0011387313,0.00037615505,0.000058660473,0.00001660254,0.00011582134,0.0001874217,0.00026839395],"category_scores_gemma":[0.038702965,0.00012022997,0.0003038017,0.00075516995,0.00025650303,0.00008071489,0.000041437193,0.00021574268,0.000004522795],"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":[0.07299909,0.0018053869,0.00044198736,0.000037099115,0.0027995573,0.000007961973,0.0038929696,0.00029438062,0.0043854057,0.8743543,0.0010581181,0.03792374],"study_design_scores_gemma":[0.009072223,0.00019497452,0.009526278,0.000059189282,0.0023666895,0.000018103596,0.00018799152,0.03295132,0.0021910246,0.94290966,0.00011617439,0.00040636488],"about_ca_topic_score_codex":0.00001398473,"about_ca_topic_score_gemma":4.90843e-7,"teacher_disagreement_score":0.3836143,"about_ca_system_score_codex":0.00003082035,"about_ca_system_score_gemma":0.0000074174877,"threshold_uncertainty_score":0.96939445},"labels":[],"label_agreement":null},{"id":"W1978525014","doi":"10.1007/s10651-013-0258-z","title":"Bootstrap confidence intervals for adaptive cluster sampling design based on Horvitz–Thompson type estimators","year":2013,"lang":"en","type":"article","venue":"Environmental and Ecological Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Statistics; Estimator; Confidence interval; Mathematics; Cluster sampling; Sampling (signal processing); CDF-based nonparametric confidence interval; Bootstrap aggregating; Population; Econometrics; Computer science; Demography","score_opus":0.2125262186680697,"score_gpt":0.3547315071271521,"score_spread":0.14220528845908242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978525014","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":[0.04543427,0.000011157122,0.95332795,0.000095981675,0.000074942276,0.0007300441,0.00015017745,0.00008501979,0.0000904397],"genre_scores_gemma":[0.5348746,0.0000070482315,0.46463817,0.00025315935,0.000014817306,0.000098712764,0.000030241014,0.000012185001,0.00007106838],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99898726,0.00010224523,0.00027384819,0.00026385704,0.00013558785,0.0002371818],"domain_scores_gemma":[0.9959457,0.003705128,0.00010988895,0.00011987697,0.000015479873,0.0001039384],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00040011527,0.00018122798,0.00023091822,0.000031946096,0.00015642763,0.00005513271,0.00009013503,0.00011439924,0.0009471199],"category_scores_gemma":[0.0005849259,0.00014225575,0.00003304702,0.000024748602,0.00014047539,0.000059512902,0.000041336378,0.000119785,0.00008121283],"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":[0.005411891,0.011023387,0.04543823,0.0015121907,0.0006881704,0.00007891252,0.0029364398,0.033758577,0.0145255085,0.25076926,0.21456489,0.41929257],"study_design_scores_gemma":[0.00089326804,0.0035632611,0.053790133,0.00008666572,0.00006582744,0.0000073409765,0.00017767624,0.44653547,0.0017157354,0.49226168,0.00032509782,0.00057785684],"about_ca_topic_score_codex":0.000008019721,"about_ca_topic_score_gemma":0.0000011486721,"teacher_disagreement_score":0.48944032,"about_ca_system_score_codex":0.000067454865,"about_ca_system_score_gemma":0.000008067252,"threshold_uncertainty_score":0.99996614},"labels":[],"label_agreement":null},{"id":"W1989279378","doi":"10.1111/j.1751-5823.2006.00002.x","title":"On the Construction of Imputation Classes in Surveys","year":2007,"lang":"en","type":"article","venue":"International Statistical Review","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Estimator; Statistics; Mathematics; Conditional expectation; Homogeneous; Econometrics; Population; Computer science; Missing data; Medicine","score_opus":0.11883605838586077,"score_gpt":0.44963791492650895,"score_spread":0.3308018565406482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989279378","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":[0.007495061,0.00025700944,0.9858387,0.00090751995,0.00015050244,0.00023272853,0.000051829655,0.00003477602,0.005031857],"genre_scores_gemma":[0.8740861,0.0017445758,0.12351685,0.00046790845,0.000035640314,0.000026996939,0.00006757084,0.000013393208,0.000040956253],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988203,0.00022664569,0.00047963898,0.0000977925,0.0002938005,0.000081788385],"domain_scores_gemma":[0.99178725,0.0077736853,0.00015786245,0.000096188596,0.00016434964,0.00002068357],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004249643,0.00006582683,0.000151706,0.00006258357,0.000017505405,0.000008931787,0.00011386025,0.000028235463,0.0004015425],"category_scores_gemma":[0.01203212,0.00004491701,0.00003085667,0.00013371902,0.00006704356,0.000035074572,0.000013877777,0.000102492995,0.00001681789],"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":[0.0000071273466,0.00004434106,0.00083119294,0.00015437207,0.000008641142,0.0000017208649,0.000009841471,0.0000013303655,0.000007812171,0.896796,0.0019549676,0.10018269],"study_design_scores_gemma":[0.00010234451,0.00004199491,0.02616556,0.001633546,0.0000114032855,0.000008792817,0.000013570311,0.00041761494,0.000360113,0.9699813,0.0011855841,0.00007816041],"about_ca_topic_score_codex":0.000046735993,"about_ca_topic_score_gemma":0.000036210695,"teacher_disagreement_score":0.86659104,"about_ca_system_score_codex":0.00005258906,"about_ca_system_score_gemma":0.000019271201,"threshold_uncertainty_score":0.99628997},"labels":[],"label_agreement":null},{"id":"W1989344163","doi":"10.2307/3315914","title":"Variance estimation for two-phase stratified sampling","year":2000,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Statistics Canada","funders":"","keywords":"Estimator; Mathematics; Statistics; Context (archaeology); Stratified sampling; Estimation; Geography; Economics","score_opus":0.12692284442278554,"score_gpt":0.387710841119841,"score_spread":0.26078799669705544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989344163","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":[0.01616809,0.000036975784,0.98233604,0.000107774555,0.00017137386,0.00015838903,0.00065390527,0.000021253936,0.00034618657],"genre_scores_gemma":[0.23447423,0.0000046598575,0.765106,0.000060636885,0.00010335747,0.0000050274434,0.000036088084,0.00002024573,0.00018972794],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99899757,0.00004001329,0.00053846615,0.00007379159,0.0001290766,0.00022109],"domain_scores_gemma":[0.99806386,0.00086731685,0.00026202598,0.00013388442,0.00037292176,0.00030000374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007620185,0.00010811717,0.0002157723,0.00014193488,0.00017415779,0.000099498735,0.00014289969,0.000052990363,0.00045316166],"category_scores_gemma":[0.0016439229,0.00010944818,0.00004582545,0.00010077064,0.000049051465,0.00012841505,0.000001280483,0.0001319517,0.0000068919408],"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":[0.00012157034,0.00009353311,0.000092201204,0.00019360404,0.00009578536,0.000050020437,0.0015941939,0.0054491255,0.00014358318,0.25384372,0.051621296,0.68670136],"study_design_scores_gemma":[0.0017776964,0.00038633207,0.00018496897,0.00022586837,0.00011081498,0.00013547964,0.000107094245,0.045084327,0.00058067025,0.9439661,0.00715934,0.00028131422],"about_ca_topic_score_codex":0.0005310923,"about_ca_topic_score_gemma":0.0021404545,"teacher_disagreement_score":0.69012237,"about_ca_system_score_codex":0.000099149474,"about_ca_system_score_gemma":0.00066838914,"threshold_uncertainty_score":0.49618024},"labels":[],"label_agreement":null},{"id":"W1994123841","doi":"10.1071/wr11105","title":"Assessment of bias in US waterfowl harvest estimates","year":2012,"lang":"en","type":"article","venue":"Wildlife Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Waterfowl; Anas; Goose; Branta; Geography; Context (archaeology); Anatidae; Fishery; Biology; Ecology; Habitat; Archaeology","score_opus":0.4965470248049577,"score_gpt":0.5373102824956577,"score_spread":0.040763257690699994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994123841","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":[0.98969835,0.00007340335,0.004332013,0.00023988912,0.000057062636,0.00030662812,0.0000089913665,0.000115820054,0.005167819],"genre_scores_gemma":[0.92117876,0.00003170419,0.07838404,0.000019384619,0.000059310456,0.00006994104,0.000010458952,0.000024666875,0.00022171189],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976752,0.00048020936,0.00041192418,0.0001603456,0.0007113149,0.0005610304],"domain_scores_gemma":[0.9963273,0.0028466114,0.00007445231,0.00040372004,0.00022469547,0.00012324528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009859075,0.00011121624,0.00027003765,0.00043030301,0.00007662933,0.00003974892,0.00024259932,0.000099211175,0.000114914605],"category_scores_gemma":[0.003447335,0.000091709175,0.000046296886,0.00046164013,0.00013669189,0.00021801048,0.00013688677,0.00036859539,0.000038635655],"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":[0.0000075159924,0.00037036085,0.9782779,0.00021014328,0.0000123600485,0.0000015866389,0.00030666866,0.00001530496,0.00038951717,0.015300201,0.0040395544,0.0010688949],"study_design_scores_gemma":[0.00035837106,0.0001322351,0.9495958,0.00038188387,0.000007482669,0.000007760479,0.00017452071,0.0037694655,0.007220076,0.03637221,0.0017695208,0.00021067864],"about_ca_topic_score_codex":0.0005466916,"about_ca_topic_score_gemma":0.00003296821,"teacher_disagreement_score":0.07405203,"about_ca_system_score_codex":0.00010603772,"about_ca_system_score_gemma":0.00009779554,"threshold_uncertainty_score":0.4127031},"labels":[],"label_agreement":null},{"id":"W1995436618","doi":"10.1007/bf02926010","title":"Imputation by power transformation","year":2003,"lang":"en","type":"article","venue":"Statistical Papers","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":110,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Imputation (statistics); Estimator; Mean squared error; Statistics; Population mean; Mathematics; Econometrics; Missing data","score_opus":0.0340552416612756,"score_gpt":0.3409253376143045,"score_spread":0.3068700959530289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995436618","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":[0.005987993,0.0000112554835,0.90769154,0.00010837481,0.00007253298,0.00014563774,0.00008466328,0.00023981003,0.08565822],"genre_scores_gemma":[0.8523476,0.0000039110355,0.1472603,0.00011405375,0.0000039738325,0.00001723122,0.00006814477,0.000014789181,0.00017001297],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99922854,0.00010046639,0.0002242607,0.00011697278,0.00017722322,0.00015252423],"domain_scores_gemma":[0.9990957,0.00066309184,0.000040354887,0.000093305134,0.0000411926,0.000066382396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040468818,0.00008982679,0.00010637711,0.000030662475,0.00008404861,0.000026373851,0.000039140636,0.000057486937,0.00078798813],"category_scores_gemma":[0.0012514091,0.00008125253,0.0000250443,0.00007940989,0.000042083677,0.00007557609,0.000002017466,0.00008086848,0.00005031871],"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":[0.000009844766,0.00005417182,0.00005534008,0.000031691732,0.000011470944,8.906965e-7,0.00047235153,0.000003932321,0.0009930589,0.9669734,0.022479808,0.0089140115],"study_design_scores_gemma":[0.00045253822,0.00013371572,0.000572064,0.000021369859,0.000027764921,0.000009055773,0.00033925852,0.00048006896,0.0036747644,0.9702014,0.023788104,0.00029989806],"about_ca_topic_score_codex":0.000007902128,"about_ca_topic_score_gemma":0.0000020593293,"teacher_disagreement_score":0.8463596,"about_ca_system_score_codex":0.00003263979,"about_ca_system_score_gemma":0.000018305565,"threshold_uncertainty_score":0.8627917},"labels":[],"label_agreement":null},{"id":"W1997629460","doi":"10.1002/cjs.11134","title":"Doubly robust point and variance estimation in the presence of imputed survey data","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Statistics Canada; Université de Montréal","funders":"","keywords":"Jackknife resampling; Estimator; Statistics; Imputation (statistics); Econometrics; Mathematics; Variance (accounting); Point estimation; Efficiency; Missing data; Computer science","score_opus":0.25911969109213123,"score_gpt":0.35130106348637796,"score_spread":0.09218137239424673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997629460","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":[0.027411701,0.00018748066,0.9710797,0.0001193131,0.00013832298,0.00010426813,0.0008939107,0.0000038800617,0.000061445],"genre_scores_gemma":[0.6582188,0.0000120357345,0.34167728,0.00002204953,0.000020475452,5.970577e-7,0.00003801384,0.000006017831,0.000004714913],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989234,0.00027017223,0.0004250268,0.000059985538,0.00015468776,0.0001667111],"domain_scores_gemma":[0.996645,0.0023597898,0.00033507848,0.00028078354,0.00023081504,0.00014856854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048612123,0.00007017631,0.00016567453,0.00012938943,0.000048758015,0.000040020266,0.00033248772,0.0000450326,0.000015663965],"category_scores_gemma":[0.008019581,0.000054177082,0.0000083047025,0.00016674929,0.000080919155,0.00027317656,0.00001805176,0.00017177442,5.4311795e-7],"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":[0.0001237892,0.0003064706,0.46263188,0.0007913244,0.00018360231,0.000120207456,0.024002338,0.0038952935,0.000042489162,0.15300912,0.3022107,0.05268282],"study_design_scores_gemma":[0.00064008834,0.00015845927,0.8045525,0.0004228107,0.00008764185,0.00036107094,0.00053668406,0.07431707,0.00008068082,0.11814643,0.00041171885,0.00028483698],"about_ca_topic_score_codex":0.0074628526,"about_ca_topic_score_gemma":0.018081293,"teacher_disagreement_score":0.6308071,"about_ca_system_score_codex":0.000034260986,"about_ca_system_score_gemma":0.00031074206,"threshold_uncertainty_score":0.99983615},"labels":[],"label_agreement":null},{"id":"W1997934667","doi":"10.1111/j.0006-341x.2005.030833.x","title":"Bias‐Corrected Maximum Likelihood Estimator of the Negative Binomial Dispersion Parameter","year":2005,"lang":"en","type":"article","venue":"Biometrics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Statistics; Estimator; Negative binomial distribution; Restricted maximum likelihood; Quasi-likelihood; Bias of an estimator; Maximum likelihood; Minimum-variance unbiased estimator; Poisson distribution","score_opus":0.11036399242108111,"score_gpt":0.3339578366602562,"score_spread":0.22359384423917508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997934667","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":[0.92467093,0.000091007874,0.07303534,0.0003806346,0.0004957547,0.00039762547,0.00006892129,0.0003014606,0.0005583411],"genre_scores_gemma":[0.78262544,0.000015377695,0.21706896,0.000056637542,0.000076183205,0.000013369067,0.000008232404,0.000024715291,0.00011112283],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986742,0.000121370824,0.00041069795,0.00019543705,0.00037661553,0.00022165499],"domain_scores_gemma":[0.99670094,0.0022780837,0.00030795403,0.00043478797,0.00021100366,0.00006720794],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006798297,0.00015876838,0.00024538054,0.0006928359,0.0001092206,0.000034945748,0.0003123102,0.0001417139,0.000059301896],"category_scores_gemma":[0.009915211,0.00010706461,0.00014725346,0.0032498112,0.00009935313,0.000099063334,0.00011345044,0.00014119822,0.000026506737],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021652879,0.0019762125,0.052873794,0.00038715242,0.00023646397,0.0000028646134,0.0025128622,0.000049275422,0.0095803635,0.0037536698,0.08264417,0.84576666],"study_design_scores_gemma":[0.0032143898,0.000717809,0.07941839,0.0006005928,0.0003865924,0.000042471165,0.0005374598,0.045791257,0.6816632,0.17122734,0.01476064,0.0016398552],"about_ca_topic_score_codex":0.00006420394,"about_ca_topic_score_gemma":0.000008140232,"teacher_disagreement_score":0.84412676,"about_ca_system_score_codex":0.00009735299,"about_ca_system_score_gemma":0.00005420262,"threshold_uncertainty_score":0.9984247},"labels":[],"label_agreement":null},{"id":"W1999057766","doi":"10.1016/s0378-3758(99)00092-0","title":"Some alternative strategies to Moors’ model in randomized response sampling","year":2000,"lang":"en","type":"article","venue":"Journal of Statistical Planning and Inference","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Randomized response; Moors; Mathematics; Efficiency; Statistics; Econometrics; Sampling (signal processing); Mathematical economics; Geography; Computer science; Archaeology","score_opus":0.1514197559372908,"score_gpt":0.4420925287823689,"score_spread":0.2906727728450781,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999057766","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":[0.42474696,0.000057754816,0.5748519,0.000091800066,0.000019269846,0.0000640171,0.000013981322,0.000015440488,0.0001388648],"genre_scores_gemma":[0.72765857,0.000046268477,0.2721678,0.000057695448,0.000028491611,0.0000041973803,9.4496124e-7,0.000006595727,0.000029424751],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99859005,0.00028262063,0.0006408191,0.000109478344,0.00021636277,0.0001606622],"domain_scores_gemma":[0.9914947,0.008049512,0.00016360405,0.00007111318,0.00010712771,0.000113904556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028892157,0.000116477815,0.0005183451,0.00019471784,0.000048013255,0.00009693664,0.000103478844,0.000051156043,0.000039645372],"category_scores_gemma":[0.006274376,0.00008954072,0.000035026904,0.00007926658,0.000069310125,0.00026988384,0.00001544534,0.00027046635,0.0000026699136],"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":[0.1449924,0.0003233948,0.0008316622,0.00018547851,0.00015169103,0.00020731676,0.022918638,0.29530054,0.00082629116,0.5010056,0.0014023833,0.03185464],"study_design_scores_gemma":[0.0058184643,0.00016717317,0.0010294383,0.0004933984,0.00001816951,0.00002241377,0.00023404803,0.13455315,0.0000828563,0.85743815,0.0000146951015,0.00012804756],"about_ca_topic_score_codex":0.000031050324,"about_ca_topic_score_gemma":0.0000012914421,"teacher_disagreement_score":0.35643256,"about_ca_system_score_codex":0.000029358449,"about_ca_system_score_gemma":0.00009796278,"threshold_uncertainty_score":0.75114673},"labels":[],"label_agreement":null},{"id":"W1999320738","doi":"10.1007/s10852-013-9238-4","title":"Optimum Allocation in Multivariate Stratified Random Sampling: A Modified Prékopa’s Approach","year":2013,"lang":"en","type":"article","venue":"Journal of Mathematical Modelling and Algorithms in Operations Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Consejo Nacional de Ciencia y Tecnología; Centre de Recherches Mathématiques","keywords":"Stratified sampling; Multivariate statistics; Sampling (signal processing); Statistics; Multivariate t-distribution; Multivariate analysis; Mathematics; Optimal allocation; Multivariate normal distribution; Computer science; Mathematical optimization","score_opus":0.3513715485652514,"score_gpt":0.447891761590875,"score_spread":0.09652021302562364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999320738","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":[0.2027489,0.00007697639,0.7956191,0.0003640846,0.000025137875,0.0006482259,0.0000018252041,0.000022916549,0.00049285346],"genre_scores_gemma":[0.5027459,0.00007625561,0.49691248,0.00000554936,0.0000445201,0.00010072752,0.00000289627,0.000017030294,0.00009460547],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966866,0.0006405175,0.0013311276,0.00025357882,0.0007069626,0.0003812286],"domain_scores_gemma":[0.9961805,0.0024959752,0.00011548905,0.0002566452,0.0008043809,0.0001470596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008892364,0.00017965058,0.0005431064,0.0007849045,0.00017195467,0.0003209664,0.00026471866,0.00018033719,0.000034563574],"category_scores_gemma":[0.0025538455,0.00014033732,0.00007033759,0.00049694383,0.00012721986,0.0004813712,0.000058030935,0.0009525118,0.0000069171333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000111206005,0.0016457572,0.00003535028,0.000387739,0.0000469411,0.0000075323205,0.005772479,0.9164924,0.00080638536,0.067945756,0.00009911577,0.0066493405],"study_design_scores_gemma":[0.0009636699,0.00006961687,0.000028147517,0.00028194403,0.000005718335,0.00002599928,0.0006616297,0.73581475,0.00020482262,0.26183584,0.0000017091273,0.0001061668],"about_ca_topic_score_codex":0.00022636227,"about_ca_topic_score_gemma":0.0000098517585,"teacher_disagreement_score":0.29999703,"about_ca_system_score_codex":0.00010992018,"about_ca_system_score_gemma":0.00015291857,"threshold_uncertainty_score":0.572279},"labels":[],"label_agreement":null},{"id":"W1999617781","doi":"10.1577/m06-293.1","title":"Evaluation of Sampling Designs for Red Sea Urchins Strongylocentrotus franciscanus in British Columbia","year":2008,"lang":"en","type":"article","venue":"North American Journal of Fisheries Management","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Quadrat; Transect; Sampling (signal processing); Environmental science; Distance sampling; Statistics; Cluster sampling; Sampling design; Oceanography; Ecology; Mathematics; Biology; Geology; Computer science; Population; Telecommunications","score_opus":0.14488375461961756,"score_gpt":0.3330629434748082,"score_spread":0.18817918885519064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999617781","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":[0.8339805,0.0000355731,0.16507442,0.000046117915,0.00008572164,0.0005261628,0.000023935349,0.0000249212,0.00020262756],"genre_scores_gemma":[0.8128556,0.00007642994,0.18689837,0.00002131396,0.000039264585,0.000045982302,0.000008948962,0.00002053785,0.000033579083],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99780005,0.00021134083,0.00082169246,0.00014969331,0.00078199717,0.00023520981],"domain_scores_gemma":[0.9978481,0.0002550136,0.00093242107,0.00019365229,0.0007010612,0.00006975717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002341484,0.00010317282,0.00045178176,0.0001385176,0.000104506384,0.000054706037,0.0002108854,0.00002267158,0.00005080721],"category_scores_gemma":[0.00072062813,0.00014698345,0.00012661668,0.00032771658,0.00014920489,0.00015808312,0.000029022829,0.00012708886,1.8560604e-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":[0.00010961687,0.00028410164,0.547258,0.00014798931,0.00022258746,0.000017687287,0.00063489086,0.002186805,0.0000047055314,0.00001397247,0.0059484364,0.44317117],"study_design_scores_gemma":[0.0016049836,0.00076277036,0.98655653,0.00020879964,0.000254592,0.0000553874,0.00091374695,0.0025244148,0.0000345132,0.006140744,0.0007162789,0.00022723251],"about_ca_topic_score_codex":0.0016438942,"about_ca_topic_score_gemma":0.011950909,"teacher_disagreement_score":0.44294393,"about_ca_system_score_codex":0.00018827413,"about_ca_system_score_gemma":0.000109602945,"threshold_uncertainty_score":0.6668888},"labels":[],"label_agreement":null},{"id":"W2001784416","doi":"10.1139/f07-138","title":"Estimating abundance of spatially aggregated populations: comparing adaptive sampling with other survey designs","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Fisheries and Aquatic Sciences","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"National Marine Fisheries Service","keywords":"Estimator; Cluster sampling; Sampling (signal processing); Simple random sample; Survey research; Stratified sampling; Statistics; Population; Survey methodology; Pollock; Survey data collection; Cluster (spacecraft); Sampling design; Systematic sampling; Abundance (ecology); Computer science; Mathematics; Ecology; Fishery; Biology","score_opus":0.376136716516481,"score_gpt":0.34714386438096334,"score_spread":0.028992852135517666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001784416","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":[0.7165608,0.00013065986,0.2829663,0.000057656554,0.00006410406,0.00006110912,0.0000041568132,0.00000833246,0.00014689757],"genre_scores_gemma":[0.6330124,0.0000027819085,0.36694032,0.000014079221,0.000014694043,8.2241945e-7,5.3932376e-7,0.0000055950522,0.000008785847],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99894154,0.00010964477,0.0004423546,0.0001051065,0.00022210891,0.00017921944],"domain_scores_gemma":[0.99835825,0.00067960535,0.0005543304,0.00008113007,0.00017276207,0.00015390378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014881013,0.0001020772,0.00029017287,0.00018185146,0.00044249772,0.00007108012,0.00017121783,0.000031511827,0.00001863584],"category_scores_gemma":[0.0016434204,0.00007736771,0.000026334894,0.000349534,0.00063090463,0.00027908382,0.0000061400274,0.00008894697,2.0575413e-7],"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":[0.000027461867,0.000014918798,0.9893712,0.00003009035,0.000030529558,0.000008018254,0.0034969312,0.0024923387,0.000029276587,0.0011906801,0.00016457935,0.0031439709],"study_design_scores_gemma":[0.0010610638,0.0019849767,0.6637278,0.0036386251,0.00010450019,0.00079036097,0.0023103198,0.22667983,0.0011038319,0.09763332,0.000103513084,0.00086185505],"about_ca_topic_score_codex":0.024737792,"about_ca_topic_score_gemma":0.05883915,"teacher_disagreement_score":0.3256434,"about_ca_system_score_codex":0.000029541954,"about_ca_system_score_gemma":0.0006544754,"threshold_uncertainty_score":0.98175657},"labels":[],"label_agreement":null},{"id":"W2006314746","doi":"10.1017/s0950268801005222","title":"Comparison of methods to analyse imprecise faecal coliform count data from environmental samples","year":2001,"lang":"en","type":"article","venue":"Epidemiology and Infection","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre Integre de Sante et de Services Sociaux de Laval; Armand Frappier Museum; McGill University; Institut National de la Recherche Scientifique; Montreal General Hospital","funders":"","keywords":"Imputation (statistics); Statistics; Confidence interval; Count data; Interval data; Missing data; Regression; Regression analysis; Mathematics; Computer science","score_opus":0.455501061543638,"score_gpt":0.5373909895660133,"score_spread":0.08188992802237527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006314746","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":[0.50758606,0.00010983041,0.4918898,0.00006263066,0.00007187657,0.000081997925,0.00006736785,0.00004764274,0.00008279125],"genre_scores_gemma":[0.7054642,0.00023076129,0.29384232,0.000109084154,0.000054213848,0.000012422967,0.00026813196,0.0000070485034,0.0000118609105],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99834573,0.0006558864,0.000555458,0.00025834367,0.00004302093,0.00014155585],"domain_scores_gemma":[0.99432343,0.0049661393,0.00023568587,0.00039191605,0.000016104745,0.00006672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003801262,0.00010656943,0.00048079176,0.00008574025,0.00008968378,0.000004262742,0.00009892645,0.00015629127,0.00018763689],"category_scores_gemma":[0.004797999,0.0000931255,0.000037629365,0.0000810798,0.000084417945,0.00010871816,0.00011381983,0.00013045329,0.000011576748],"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":[0.000060008322,0.000109938075,0.9508654,0.000009963804,0.0000513908,1.0449801e-7,0.00017002365,0.000052256684,0.0012622216,0.00048489938,0.0054737506,0.041460063],"study_design_scores_gemma":[0.00023038438,0.00023753001,0.86358017,0.00003404728,0.00012579364,0.000009693302,0.00010720849,0.031047681,0.00462297,0.08675387,0.013055396,0.00019524999],"about_ca_topic_score_codex":0.0015127677,"about_ca_topic_score_gemma":0.00021658362,"teacher_disagreement_score":0.1980475,"about_ca_system_score_codex":0.000036209793,"about_ca_system_score_gemma":0.000007794999,"threshold_uncertainty_score":0.57439995},"labels":[],"label_agreement":null},{"id":"W2019293164","doi":"10.1198/016214501750333054","title":"A Model-Calibration Approach to Using Complete Auxiliary Information From Survey Data","year":2001,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":336,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Estimator; Calibration; Mathematics; Population; Applied mathematics; Statistics; Function (biology); Linear model; Linear regression","score_opus":0.3089299026417691,"score_gpt":0.40148143882740894,"score_spread":0.09255153618563983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2019293164","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":[0.1515126,0.0000021868777,0.8468643,0.00027687213,0.00009050858,0.00012562843,0.0009861162,0.000028427487,0.0001133628],"genre_scores_gemma":[0.5034769,0.0000051353904,0.49580017,0.00039957417,0.00007737453,0.0000016065515,0.00021549119,0.000010973275,0.000012748945],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976723,0.00061955664,0.0007398689,0.00011197351,0.0006878681,0.0001684382],"domain_scores_gemma":[0.9953274,0.0021752787,0.0016493783,0.0003621212,0.0003976223,0.000088158464],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0028246206,0.0001130429,0.00034490306,0.00009679256,0.00012398152,0.00012099573,0.00046601516,0.000045376262,0.000008002173],"category_scores_gemma":[0.01071689,0.000084510946,0.000048599475,0.0004255622,0.000036577425,0.00067068235,0.00013372302,0.00022631895,0.000004276264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021036563,0.0016733039,0.48658213,0.000114448245,0.0012598366,0.0000052469923,0.0052321167,0.08409233,0.0023840687,0.016104195,0.31866652,0.081782155],"study_design_scores_gemma":[0.00017713083,0.000043879183,0.085709184,0.000026723132,0.0000793587,0.000006839372,0.00008444121,0.87082064,0.000017453469,0.042746373,0.00016999478,0.00011797904],"about_ca_topic_score_codex":0.00094075146,"about_ca_topic_score_gemma":0.00004882612,"teacher_disagreement_score":0.7867283,"about_ca_system_score_codex":0.00036031232,"about_ca_system_score_gemma":0.00012063363,"threshold_uncertainty_score":0.9976163},"labels":[],"label_agreement":null},{"id":"W2022391270","doi":"10.1111/j.1467-842x.2005.00402.x","title":"MODEL-ASSISTED HIGHER-ORDER CALIBRATION OF ESTIMATORS OF VARIANCE","year":2005,"lang":"en","type":"article","venue":"Australian & New Zealand Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Estimator; Mathematics; Variance (accounting); Population variance; Statistics; Variable (mathematics); Calibration; Inference; Population; Extremum estimator; Set (abstract data type); Econometrics; M-estimator; Computer science; Artificial intelligence","score_opus":0.11294393876240591,"score_gpt":0.36076452407601867,"score_spread":0.24782058531361276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2022391270","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":[0.031739343,0.000020629333,0.96675515,0.0009416619,0.00013330308,0.000096310156,0.00019509632,0.000029008623,0.00008950279],"genre_scores_gemma":[0.34513202,0.000023081622,0.6520427,0.000016602333,0.00007505194,5.334594e-7,0.000010957454,0.0000164954,0.0026825487],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99825346,0.000064004525,0.0010701164,0.00008978751,0.00036558666,0.0001570674],"domain_scores_gemma":[0.997617,0.00040397054,0.0011992399,0.00017705011,0.00047554867,0.00012716904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000499557,0.00014257425,0.00044118654,0.00013723095,0.000028884566,0.00001976161,0.00016652461,0.0001048061,0.00013538206],"category_scores_gemma":[0.00041446483,0.00012379515,0.00006465478,0.00018663802,0.00006760234,0.00019400047,0.000012847353,0.0001781559,0.0000010545117],"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":[0.00041441462,0.0010103781,0.010236313,0.0006102505,0.0004071241,0.00002698079,0.0019544463,0.038515877,0.00469039,0.10218685,0.8044478,0.035499178],"study_design_scores_gemma":[0.0051254304,0.0017129965,0.029075768,0.001655038,0.00092184875,0.00027536837,0.00012573953,0.12414835,0.03826176,0.7895849,0.008145046,0.0009677994],"about_ca_topic_score_codex":0.00007451464,"about_ca_topic_score_gemma":0.000018255136,"teacher_disagreement_score":0.79630274,"about_ca_system_score_codex":0.00003534779,"about_ca_system_score_gemma":0.00021405068,"threshold_uncertainty_score":0.50482196},"labels":[],"label_agreement":null},{"id":"W2024395005","doi":"10.1007/s00338-004-0377-y","title":"Has random sampling been neglected in coral reef faunal surveys?","year":2004,"lang":"en","type":"article","venue":"Coral Reefs","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Coral reef; Coral; Reef; Oceanography; Sampling (signal processing); Fishery; Cnidaria; Geography; Ecology; Geology; Environmental science; Biology; Computer science","score_opus":0.2515569302831572,"score_gpt":0.3873813148324256,"score_spread":0.13582438454926843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024395005","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":[0.58532685,0.000082832325,0.4126037,0.00024819266,0.00020205951,0.0003673942,0.000022289894,0.00057214696,0.00057449646],"genre_scores_gemma":[0.9311887,0.0000134731,0.06829223,0.00007353226,0.00009026637,0.000037365877,0.00007828718,0.00004635198,0.00017979514],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99796283,0.00034170173,0.0005925952,0.00034597024,0.00032289786,0.00043402295],"domain_scores_gemma":[0.99822176,0.00089037995,0.00018097862,0.00041972726,0.00017193584,0.00011522744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001569249,0.0002443347,0.00046921612,0.0002285547,0.00017025217,0.000120080214,0.00028189755,0.00018986191,0.00007385925],"category_scores_gemma":[0.0030895618,0.0002356823,0.0001140598,0.00053574017,0.00011404553,0.00017843522,0.00007313021,0.00036528733,0.00006764211],"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":[0.0055334936,0.005563734,0.4948469,0.0016991085,0.0005963754,0.0006420636,0.013780792,0.006603271,0.03788955,0.12020438,0.029913949,0.28272638],"study_design_scores_gemma":[0.010627562,0.000471819,0.26503325,0.0010176607,0.00006258931,0.000061413615,0.00016528279,0.002617066,0.008713504,0.70880306,0.0011939814,0.0012328569],"about_ca_topic_score_codex":0.000979238,"about_ca_topic_score_gemma":0.0006475254,"teacher_disagreement_score":0.58859867,"about_ca_system_score_codex":0.00018904453,"about_ca_system_score_gemma":0.00013596014,"threshold_uncertainty_score":0.96108454},"labels":[],"label_agreement":null},{"id":"W2026967907","doi":"10.5539/ijsp.v1n2p269","title":"On Bias Correction in a Class of Inflated Beta Regression Models","year":2012,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Estimator; Mathematics; Statistics; Mean squared error; Regression analysis; Maximum likelihood; Regression; BETA (programming language); Restricted maximum likelihood; Econometrics; Computer science","score_opus":0.13612407447614275,"score_gpt":0.3824119095513791,"score_spread":0.24628783507523636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026967907","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":[0.8163602,0.000037422367,0.18251717,0.00009901422,0.00052698294,0.000081556944,0.000051886054,0.000009035292,0.00031677238],"genre_scores_gemma":[0.93102366,0.000042504897,0.06885964,0.000013802349,0.000036021207,0.0000015772104,0.0000055096057,0.0000050534445,0.000012264383],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99890435,0.00011548576,0.000544348,0.00005837868,0.00030341785,0.00007403786],"domain_scores_gemma":[0.997672,0.0012199681,0.00047031802,0.000069715315,0.00052376674,0.00004420727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016253726,0.00006948322,0.00017149592,0.00014572797,0.00001495584,0.0000140657,0.00008596976,0.00005302195,0.000019837875],"category_scores_gemma":[0.0018282088,0.000052982516,0.000028872833,0.000057653506,0.00004255,0.00015773959,0.000022026832,0.00015804915,3.3644568e-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":[0.0015725977,0.00194953,0.16478835,0.00025322541,0.00019338478,0.000011395877,0.0038653433,0.0034895805,0.00041873,0.6774799,0.007522734,0.13845523],"study_design_scores_gemma":[0.00039260442,0.00015703628,0.022543924,0.00035598403,0.00001308331,0.0000272922,0.00002934206,0.017069008,0.0014207849,0.95785254,0.00006815148,0.000070275266],"about_ca_topic_score_codex":0.000041499123,"about_ca_topic_score_gemma":0.000012290247,"teacher_disagreement_score":0.28037262,"about_ca_system_score_codex":0.000071272305,"about_ca_system_score_gemma":0.000033988705,"threshold_uncertainty_score":0.21886688},"labels":[],"label_agreement":null},{"id":"W2027764114","doi":"10.1198/016214502760047069","title":"Efficient Estimation of Quadratic Finite Population Functions in the Presence of Auxiliary Information","year":2002,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Estimator; Mathematics; Population; Covariance; Quadratic equation; Applied mathematics; Correctness; Linear model; Variance (accounting); Mathematical optimization; Statistics; Algorithm","score_opus":0.0370660623633208,"score_gpt":0.3227786959343425,"score_spread":0.2857126335710217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027764114","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":[0.59398854,0.000007716496,0.40493193,0.00061199616,0.00010534714,0.0001752467,0.00004798564,0.000009860402,0.00012134587],"genre_scores_gemma":[0.97421443,0.00000494835,0.025684768,0.00004572996,0.000018395234,0.0000050672625,0.000006865932,0.000004310383,0.000015462738],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976603,0.000541033,0.0009539846,0.0000463917,0.0006956128,0.00010268599],"domain_scores_gemma":[0.99166864,0.0051509514,0.0026879336,0.00015776975,0.0003149657,0.00001972527],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021199253,0.000075436394,0.00026739461,0.00015063141,0.00006219118,0.00002095134,0.0001764516,0.00003561394,0.000019879926],"category_scores_gemma":[0.016032476,0.000047362893,0.000080148384,0.0005612082,0.000066187065,0.00015712646,0.000017021925,0.00019480706,0.0000028113543],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036847574,0.0022740266,0.24193141,0.0006308251,0.0002885135,0.0000023983198,0.018706704,0.5115259,0.00035070174,0.050738387,0.029256396,0.14392626],"study_design_scores_gemma":[0.0002979961,0.00023431316,0.43127984,0.00015496157,0.00010564246,0.0000065506097,0.0006660962,0.53228456,0.00010370116,0.03475854,0.000022941058,0.000084856976],"about_ca_topic_score_codex":0.00016799146,"about_ca_topic_score_gemma":0.000012404022,"teacher_disagreement_score":0.3802259,"about_ca_system_score_codex":0.00017092393,"about_ca_system_score_gemma":0.000024182928,"threshold_uncertainty_score":0.9922559},"labels":[],"label_agreement":null},{"id":"W2028182691","doi":"10.1007/s11336-005-1495-y","title":"Item Randomized-Response Models for Measuring Noncompliance: Risk-Return Perceptions, Social Influences, and Self-Protective Responses","year":2007,"lang":"en","type":"article","venue":"Psychometrika","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":101,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Respondent; Psychology; Econometrics; CLARITY; Univariate; Multivariate statistics; Sample (material); Statistics; Multivariate analysis; Randomized response; Covariate; Social psychology; Actuarial science; Mathematics; Economics","score_opus":0.14517262607149914,"score_gpt":0.40033502116672676,"score_spread":0.25516239509522765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028182691","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":[0.53198946,0.00026791808,0.46583614,0.00009843422,0.00010312448,0.0010068892,0.00005481592,0.00046994386,0.00017325222],"genre_scores_gemma":[0.80836314,0.00012500865,0.1908294,0.000051424664,0.0001468977,0.00032362607,0.0000035440967,0.000045104785,0.00011187552],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99724007,0.0008285922,0.00067996833,0.00043534074,0.00040466627,0.00041135403],"domain_scores_gemma":[0.9771682,0.021634152,0.0004122327,0.00027849097,0.000388178,0.000118752665],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.017485868,0.00027437994,0.0006368996,0.00088761986,0.0006162119,0.00011112718,0.00020648935,0.00022690956,0.000020166324],"category_scores_gemma":[0.018842658,0.00024883126,0.00023126333,0.00080230995,0.0001721009,0.00026021813,0.000038280148,0.00030398183,0.0000061314454],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.7221716,0.0021465113,0.027207937,0.0013093642,0.0017586491,0.000010084015,0.049568024,0.000102645005,0.004860946,0.014751992,0.008653676,0.1674586],"study_design_scores_gemma":[0.089605205,0.0005754211,0.11833717,0.00043919726,0.00051528076,0.000053969376,0.0025605923,0.014440068,0.0039444366,0.76643777,0.0014086452,0.0016822435],"about_ca_topic_score_codex":0.000056042896,"about_ca_topic_score_gemma":0.0000151474105,"teacher_disagreement_score":0.7516858,"about_ca_system_score_codex":0.00015664169,"about_ca_system_score_gemma":0.000051169114,"threshold_uncertainty_score":0.99999636},"labels":[],"label_agreement":null},{"id":"W2029555586","doi":"10.1198/016214506000000195","title":"Estimation in Multiple-Frame Surveys","year":2006,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Social Sciences and Humanities Research Council","funders":"","keywords":"Estimator; Frame (networking); Sampling (signal processing); Variance (accounting); Sampling frame; Statistics; Mathematics; Population; Maximum likelihood; M-estimator; Computer science; Econometrics","score_opus":0.03637944048334951,"score_gpt":0.34047377115739413,"score_spread":0.3040943306740446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029555586","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":[0.44609222,0.0000047255107,0.55299085,0.00055286306,0.00011018734,0.00007417675,0.000024662057,0.000024026824,0.00012631527],"genre_scores_gemma":[0.87585145,0.0000027096369,0.123927146,0.000050199862,0.000060468392,0.0000027261965,0.0000045526713,0.000011111963,0.000089634595],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9976638,0.0009319886,0.0006662408,0.00007709691,0.0004950229,0.00016583744],"domain_scores_gemma":[0.9926225,0.005438537,0.0015764481,0.000115819465,0.00021664033,0.000030067375],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0039516534,0.00009004686,0.00030756052,0.00010478958,0.000059855138,0.00004044904,0.00015524005,0.000042074404,0.000011580361],"category_scores_gemma":[0.01442054,0.000064748034,0.000076297445,0.00036195086,0.0000568738,0.00010694275,0.000021195352,0.00026272677,0.00000514343],"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":[0.00006794787,0.00046715874,0.9052087,0.000030278625,0.00005819692,0.0000063016428,0.00016631583,0.0022945942,0.00060579664,0.015405479,0.025387194,0.050302032],"study_design_scores_gemma":[0.0002629557,0.000060582297,0.7566481,0.00003740126,0.000024512146,0.000006132951,0.000025793628,0.013191354,0.00031824288,0.22928551,0.000061155944,0.00007821687],"about_ca_topic_score_codex":0.00062767864,"about_ca_topic_score_gemma":0.00018859516,"teacher_disagreement_score":0.42975923,"about_ca_system_score_codex":0.0005018514,"about_ca_system_score_gemma":0.000053965756,"threshold_uncertainty_score":0.9938814},"labels":[],"label_agreement":null},{"id":"W2032036069","doi":"10.1007/s10651-008-0105-9","title":"Empirical likelihood confidence intervals for adaptive cluster sampling","year":2008,"lang":"en","type":"article","venue":"Environmental and Ecological Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Confidence interval; Statistics; Mathematics; Estimator; Confidence distribution; Robust confidence intervals; CDF-based nonparametric confidence interval; Coverage probability; Percentile; Cluster sampling; Sampling (signal processing); Population; Computer science; Medicine","score_opus":0.20008354560464617,"score_gpt":0.366483344531908,"score_spread":0.16639979892726184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032036069","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":[0.30276063,0.000027562057,0.6963626,0.00007688296,0.000046651858,0.00026530464,0.00029501558,0.00006822791,0.000097089614],"genre_scores_gemma":[0.6276999,0.00007169681,0.37168205,0.0002904012,0.000031405623,0.00005657729,0.000035952322,0.0000100707475,0.00012195593],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99904567,0.00006232668,0.0002885301,0.00024357796,0.000122066056,0.0002378476],"domain_scores_gemma":[0.9974298,0.0022737854,0.00008883434,0.000093799674,0.000009750048,0.00010406239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031224778,0.00014325144,0.00022944712,0.000020756204,0.00024361968,0.00001603659,0.0000786616,0.00010423188,0.00029388937],"category_scores_gemma":[0.0004652912,0.00011446503,0.00004131962,0.00001829448,0.00022874975,0.000049480765,0.00008962864,0.0001159084,0.000028995511],"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":[0.0025274314,0.009091905,0.41072375,0.0007483812,0.000713295,0.00024362358,0.0125011,0.00021126954,0.0040669553,0.14857885,0.2634319,0.14716153],"study_design_scores_gemma":[0.0008972303,0.001410765,0.20669076,0.000028147508,0.000052494357,0.00009854332,0.00025582427,0.007152492,0.00054772344,0.779986,0.002402259,0.00047774197],"about_ca_topic_score_codex":0.0000040945024,"about_ca_topic_score_gemma":0.0000047347717,"teacher_disagreement_score":0.63140714,"about_ca_system_score_codex":0.000055391494,"about_ca_system_score_gemma":0.0000075675957,"threshold_uncertainty_score":0.46677485},"labels":[],"label_agreement":null},{"id":"W203707744","doi":"","title":"A new face on two-phase sampling with calibration estimators","year":2010,"lang":"en","type":"article","venue":"Quality Engineering","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Rogers Communications (Canada)","funders":"","keywords":"Estimator; Categorical variable; Sampling (signal processing); Calibration; Mathematics; Phase (matter); Statistics; Population; Sample (material); Sample size determination; Sampling design; Range (aeronautics); Context (archaeology); Computer science; Engineering","score_opus":0.11759523154337344,"score_gpt":0.42095476869326554,"score_spread":0.3033595371498921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W203707744","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":[0.31971622,0.0000017014636,0.6791626,0.000072638024,0.00010261074,0.000108867105,0.000004880081,0.00072702055,0.000103419305],"genre_scores_gemma":[0.521391,1.7187371e-7,0.47844172,0.000019704745,0.00005969543,0.000010994486,0.000010239659,0.000026834818,0.000039698305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910146,0.000024257191,0.0002758606,0.00019261325,0.00021903269,0.0001867485],"domain_scores_gemma":[0.99876827,0.0006590521,0.00008408524,0.00033542444,0.000034894438,0.00011825248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006793206,0.00016481942,0.00019173387,0.0000929158,0.000060094782,0.00007033989,0.00010793871,0.00007453211,0.000041128907],"category_scores_gemma":[0.0009922498,0.00014662158,0.000037910497,0.00015428111,0.000010794041,0.00013869526,0.000014474008,0.00029644047,0.000008427904],"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":[0.0001792271,0.00036981943,0.0009348442,0.0004957771,0.00011023383,0.000008440475,0.0030648212,0.07688813,0.06561243,0.82024336,0.001338845,0.03075405],"study_design_scores_gemma":[0.005292869,0.00066472427,0.0024729772,0.0007948553,0.000101624915,0.00006532452,0.00030497837,0.677452,0.20251578,0.10572113,0.0022452148,0.0023684767],"about_ca_topic_score_codex":0.00012078022,"about_ca_topic_score_gemma":0.000027931243,"teacher_disagreement_score":0.71452224,"about_ca_system_score_codex":0.000024287567,"about_ca_system_score_gemma":0.000038816586,"threshold_uncertainty_score":0.59790546},"labels":[],"label_agreement":null},{"id":"W2039009716","doi":"10.1071/am09037","title":"Estimating western ringtail possum (Pseudocheirus occidentalis) density using distance sampling","year":2010,"lang":"en","type":"article","venue":"Australian Mammalogy","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kingswood University","funders":"","keywords":"Distance sampling; Abundance (ecology); Sampling (signal processing); Biology; Population density; Population; Range (aeronautics); Habitat; Ecology; Zoology; Geography; Demography; Computer science","score_opus":0.15260192408790124,"score_gpt":0.40258353935841706,"score_spread":0.24998161527051582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039009716","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":[0.8031604,0.0000033926783,0.19515495,0.00012232002,0.00072537485,0.00018372315,0.000015741158,0.000489878,0.00014421543],"genre_scores_gemma":[0.6513515,4.6923515e-7,0.3479398,0.000048748934,0.00023004881,0.0000089022515,0.000016111579,0.000042833773,0.00036157164],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99799156,0.00009591862,0.0006022499,0.00046952002,0.0002628649,0.00057789404],"domain_scores_gemma":[0.998266,0.00044855344,0.0003256549,0.0006349063,0.000149366,0.00017555486],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007537812,0.00031504102,0.00041640396,0.0001344088,0.0003111561,0.00014106021,0.00036931105,0.00027285318,0.00016289632],"category_scores_gemma":[0.0009097792,0.00033487123,0.00011906838,0.00019738515,0.00017105533,0.00028727113,0.00011678984,0.00060415,0.00006936911],"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":[0.000088581524,0.00027646706,0.8412358,0.0004936452,0.00014827446,0.00014731215,0.0015061023,0.0005343756,0.11505957,0.03326482,0.0014845808,0.0057604485],"study_design_scores_gemma":[0.0024753641,0.00028426392,0.26884896,0.0010848374,0.0005543255,0.0031726544,0.00058864756,0.022068841,0.16722694,0.5256169,0.003683274,0.0043949797],"about_ca_topic_score_codex":0.0006214141,"about_ca_topic_score_gemma":0.0007580467,"teacher_disagreement_score":0.57238686,"about_ca_system_score_codex":0.00007093709,"about_ca_system_score_gemma":0.000049013557,"threshold_uncertainty_score":0.99991035},"labels":[],"label_agreement":null},{"id":"W2041354798","doi":"10.1080/15598608.2010.10411970","title":"Kernel Regression Estimators for Nonparametric Model Calibration in Survey Sampling","year":2010,"lang":"en","type":"article","venue":"Journal of Statistical Theory and Practice","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Fisheries and Oceans Canada","funders":"Fisheries and Oceans Canada; Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Mathematics; Nonparametric regression; Smoothing; Context (archaeology); Statistics; Kernel regression; Kernel smoother; Nonparametric statistics; Sampling (signal processing); Kernel (algebra); Variance (accounting); Kernel method; Econometrics; Applied mathematics; Computer science","score_opus":0.1695077544001508,"score_gpt":0.46870056226444257,"score_spread":0.29919280786429175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2041354798","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":[0.074145965,0.000033619843,0.92521966,0.00012046396,0.00013484994,0.000120653975,0.000050360974,0.00001627672,0.00015817623],"genre_scores_gemma":[0.4233309,0.000024591403,0.5765189,0.00005370359,0.00003192601,0.0000034514399,0.0000055716155,0.000011186758,0.000019746083],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99821454,0.0007751279,0.0005617282,0.00011629762,0.00019808332,0.00013419658],"domain_scores_gemma":[0.9239605,0.07508309,0.00048094834,0.00010226199,0.00028016817,0.000093017625],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017414246,0.000106292566,0.00026128106,0.00017942052,0.00008473748,0.00007585137,0.00008882324,0.00011744489,0.000023207987],"category_scores_gemma":[0.16315553,0.00008074582,0.00003096975,0.00016477161,0.00006838273,0.0005022696,0.000018604758,0.00047278855,7.295959e-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":[0.0038015503,0.0003189943,0.0011178311,0.0001298444,0.00003500091,0.000010498231,0.00039038938,0.00056178315,0.0008427865,0.97315985,0.001274543,0.018356958],"study_design_scores_gemma":[0.00040831743,0.00012801588,0.0017122416,0.0000718803,0.000050423234,0.00012807547,0.00008710908,0.085202746,0.00027130748,0.9117324,0.0000996012,0.00010793235],"about_ca_topic_score_codex":0.000012309692,"about_ca_topic_score_gemma":0.000006742971,"teacher_disagreement_score":0.34918493,"about_ca_system_score_codex":0.000016102038,"about_ca_system_score_gemma":0.00008151024,"threshold_uncertainty_score":0.8438936},"labels":[],"label_agreement":null},{"id":"W2042186389","doi":"10.1191/1471082x06st121oa","title":"Modelling repeated ordinal reports from multiple informants","year":2006,"lang":"en","type":"article","venue":"Statistical Modelling","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"Economic and Social Research Council","keywords":"Multivariate statistics; Psychology; Multilevel model; Random effects model; Aggression; Continuation; Ordinal regression; Multivariate analysis; Mathematics; Longitudinal data; Demography; Repeated measures design; Generalized linear model; Statistics; Developmental psychology; Econometrics; Medicine; Computer science; Meta-analysis","score_opus":0.11255771401037017,"score_gpt":0.32497840660770777,"score_spread":0.2124206925973376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042186389","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":[0.1196241,0.00002570236,0.8775758,0.000013388018,0.0001108145,0.00016816848,0.000117630756,0.0005831733,0.0017812223],"genre_scores_gemma":[0.52480876,0.0000036840759,0.47475922,0.000010447166,0.00007250979,0.000013085547,0.00021941033,0.000025970252,0.00008688525],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979057,0.000059098864,0.00088677456,0.00038291133,0.00038913844,0.00037638217],"domain_scores_gemma":[0.9975485,0.0015447848,0.00022773138,0.0003993228,0.00017725134,0.00010238254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006002291,0.00022588483,0.00033442545,0.00009378857,0.0001879756,0.00009110993,0.000104786464,0.00013814261,0.00010225801],"category_scores_gemma":[0.0004179021,0.00021718099,0.000062251405,0.0001330756,0.000059735015,0.00017875084,0.000042343403,0.00024852404,0.000027526188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059369482,0.00010852336,0.0012588119,0.00005008452,0.000025455367,0.000093212715,0.00014805318,0.952279,0.000057538957,0.042625647,0.00196006,0.0013342928],"study_design_scores_gemma":[0.00010068685,0.000012021377,0.000024013943,0.00004976186,0.000020076255,0.00000827669,0.000010602176,0.573535,0.0003481487,0.42559916,0.00013679467,0.00015545178],"about_ca_topic_score_codex":0.0043296088,"about_ca_topic_score_gemma":0.00002975733,"teacher_disagreement_score":0.4051847,"about_ca_system_score_codex":0.000057229885,"about_ca_system_score_gemma":0.000039269577,"threshold_uncertainty_score":0.88563836},"labels":[],"label_agreement":null},{"id":"W2043586387","doi":"10.1139/f06-063","title":"Improving the precision of design-based scallop drag surveys using adaptive allocation methods","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Fisheries and Aquatic Sciences","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Stratified sampling; Scallop; Sampling design; Sampling (signal processing); Stratum; Population; Fishery; Boom; Variance (accounting); Sample size determination; Environmental science; Statistics; Computer science; Engineering; Mathematics; Biology; Environmental engineering; Filter (signal processing)","score_opus":0.16937649444474545,"score_gpt":0.35422471965436797,"score_spread":0.18484822520962252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043586387","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":[0.19146511,0.00017942965,0.807884,0.00021507709,0.00008392694,0.000083348874,0.0000013173207,0.000004379646,0.00008340707],"genre_scores_gemma":[0.553485,0.0000014083138,0.44646937,0.0000141029595,0.000017946428,7.7398784e-7,1.7399184e-7,0.000003305394,0.00000795448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99849004,0.0006652974,0.00040941077,0.00008824878,0.00020238962,0.00014459254],"domain_scores_gemma":[0.99680114,0.0024163374,0.0004582639,0.000088742,0.00015400544,0.000081486156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010000943,0.00007883534,0.00017765682,0.00016567313,0.00033505177,0.0001275547,0.00020160373,0.00003913066,0.000014010228],"category_scores_gemma":[0.0023514337,0.00005050176,0.000041062332,0.00031839358,0.00047515714,0.00020106173,0.0000064054793,0.00007262675,7.213972e-8],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007865322,0.00011501434,0.07113938,0.0002122707,0.00009435541,0.000015878168,0.0055053523,0.013151748,0.015177135,0.011889957,0.0029459964,0.87967426],"study_design_scores_gemma":[0.00035954107,0.00076300954,0.017948156,0.0005524703,0.000104237944,0.000058715825,0.0023228317,0.71341485,0.03332409,0.23072045,0.00011228044,0.000319399],"about_ca_topic_score_codex":0.017380754,"about_ca_topic_score_gemma":0.004954776,"teacher_disagreement_score":0.87935483,"about_ca_system_score_codex":0.000041532297,"about_ca_system_score_gemma":0.00089579885,"threshold_uncertainty_score":0.98916256},"labels":[],"label_agreement":null},{"id":"W2048495621","doi":"10.1081/sta-200026577","title":"Estimating Function Jackknife Variance Estimators Under Stratified Multistage Sampling","year":2004,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Carleton University","funders":"","keywords":"Jackknife resampling; Estimator; Mathematics; Statistics; Resampling; Consistency (knowledge bases); Population; Variance (accounting); Sampling (signal processing); Computer science","score_opus":0.16511029963787274,"score_gpt":0.48696503093815735,"score_spread":0.32185473130028464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048495621","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":[0.007887201,0.000293571,0.99045736,0.00007512327,0.00017534792,0.00030113285,0.000035759364,0.00026385154,0.0005106789],"genre_scores_gemma":[0.20956726,0.000040684958,0.7900683,0.000094504554,0.00001914671,0.00007146263,0.000048970956,0.0000299766,0.00005966877],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967474,0.0019166528,0.00066670496,0.00029192504,0.00014464237,0.00023268753],"domain_scores_gemma":[0.99025047,0.008463891,0.000320002,0.00074623676,0.00013747552,0.00008191166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008594423,0.00021681533,0.00032328913,0.00015253137,0.00037105204,0.00011115562,0.0002606578,0.0001525901,0.00004663933],"category_scores_gemma":[0.0062924353,0.00022483764,0.00003083121,0.00023835167,0.00022995946,0.00021487958,0.00010761495,0.00041628597,0.0000048349502],"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":[0.0000645418,0.00008027142,0.00011815857,0.00011651937,0.000019429312,6.794542e-7,0.0010837248,0.003505096,0.00041686354,0.9408812,0.000028538658,0.05368496],"study_design_scores_gemma":[0.0005322266,0.000039300823,0.0028378537,0.00029593738,0.000038708575,0.000008814364,0.00042155513,0.011276582,0.0005691118,0.9836768,0.00006639734,0.00023670642],"about_ca_topic_score_codex":0.000084866144,"about_ca_topic_score_gemma":0.00003730641,"teacher_disagreement_score":0.20168005,"about_ca_system_score_codex":0.000097988064,"about_ca_system_score_gemma":0.000072124356,"threshold_uncertainty_score":0.9168613},"labels":[],"label_agreement":null},{"id":"W2048788123","doi":"10.1002/jae.1052","title":"Do randomized‐response designs eliminate response biases? An empirical study of non‐compliance behavior","year":2009,"lang":"en","type":"article","venue":"Journal of Applied Econometrics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Ministerie van Sociale Zaken en Werkgelegenheid","keywords":"Econometrics; Toolbox; Response bias; Computer science; Multivariate statistics; Randomized response; Statistics; Contrast (vision); Mathematics; Artificial intelligence","score_opus":0.36306465952520045,"score_gpt":0.45225861928823247,"score_spread":0.08919395976303202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2048788123","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":[0.9638949,0.000046088568,0.034884077,0.00007593746,0.00009758069,0.00078149984,0.000009715164,0.00005359593,0.00015660014],"genre_scores_gemma":[0.934663,0.000025422001,0.06510547,0.000071370036,0.000052230887,0.000029415069,0.0000011055774,0.000028798446,0.000023190816],"study_design_codex":"randomized_trial","study_design_gemma":"observational","domain_scores_codex":[0.9965349,0.00068342296,0.0018221504,0.0002606379,0.00042950234,0.00026940627],"domain_scores_gemma":[0.9869756,0.010168184,0.0017300415,0.0005120203,0.00039800548,0.00021612702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01776595,0.00025502493,0.0012659612,0.0020318981,0.000098451164,0.000091380345,0.0004959191,0.00014915125,0.00006620734],"category_scores_gemma":[0.0073280227,0.00021825921,0.00025059894,0.0012444764,0.00007811992,0.00023510553,0.000036157544,0.0003649264,0.000007822817],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.8802097,0.019681606,0.006219082,0.00009953098,0.00041171428,0.00018003983,0.012310347,0.0022780634,0.005244079,0.0006508272,0.0024184668,0.07029654],"study_design_scores_gemma":[0.29793167,0.036324125,0.49144065,0.0006697566,0.0026985386,0.0005540734,0.013535163,0.008724275,0.038483445,0.10633671,0.00035105235,0.0029505466],"about_ca_topic_score_codex":0.0000024211597,"about_ca_topic_score_gemma":6.31165e-7,"teacher_disagreement_score":0.582278,"about_ca_system_score_codex":0.00015193461,"about_ca_system_score_gemma":0.00013332728,"threshold_uncertainty_score":0.8900353},"labels":[],"label_agreement":null},{"id":"W2052097769","doi":"10.1093/biomet/87.4.929","title":"Empirical likelihood inference under stratified random sampling using auxiliary population information","year":2000,"lang":"en","type":"article","venue":"Biometrika","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Mathematics; Stratified sampling; Inference; Population; Statistics; Library science; Sampling (signal processing); Demography; Computer science; Artificial intelligence; Sociology; Telecommunications","score_opus":0.22994452866867715,"score_gpt":0.4337713915434576,"score_spread":0.20382686287478047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052097769","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":[0.6201614,0.000029493747,0.3785087,0.00005563779,0.00008735928,0.00022443796,0.000017159626,0.00038441192,0.0005314275],"genre_scores_gemma":[0.88159585,0.000016988679,0.11800345,0.00012005613,0.00006369535,0.000011749686,0.00013867406,0.000015091806,0.000034419365],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985105,0.000108675405,0.0006019009,0.0001687434,0.00035644427,0.00025377612],"domain_scores_gemma":[0.9984671,0.000866935,0.00017065136,0.00028064533,0.00012710794,0.000087576824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009920598,0.00017238622,0.0002514217,0.00066002685,0.00018287869,0.00016241166,0.00013658746,0.00018307359,0.00042079197],"category_scores_gemma":[0.0010690705,0.00016045067,0.00010156476,0.0013126519,0.000029569172,0.0006856583,0.00002188377,0.00013880241,0.00007213051],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006655673,0.00064538704,0.049306296,0.0004819865,0.00023778182,0.000002379437,0.0021100915,0.0031482645,0.0025242227,0.0055062026,0.0026712876,0.9327005],"study_design_scores_gemma":[0.0067462763,0.00038870607,0.2662083,0.0006721167,0.00031416526,0.000054519893,0.00055502175,0.10578292,0.0076785116,0.6034858,0.0058095283,0.0023040867],"about_ca_topic_score_codex":0.0002753092,"about_ca_topic_score_gemma":0.000010178317,"teacher_disagreement_score":0.93039644,"about_ca_system_score_codex":0.00011426836,"about_ca_system_score_gemma":0.00006268917,"threshold_uncertainty_score":0.65429884},"labels":[],"label_agreement":null},{"id":"W2054434336","doi":"10.1080/15598608.2010.10412021","title":"Variance Estimation in Two-Stage Cluster Sampling under Imputation for Missing Data","year":2010,"lang":"en","type":"article","venue":"Journal of Statistical Theory and Practice","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Variance (accounting); Imputation (statistics); Statistics; Mathematics; Cluster sampling; Missing data; Econometrics; Sampling (signal processing); Computer science; Population","score_opus":0.18683189298929878,"score_gpt":0.5013992226714341,"score_spread":0.3145673296821353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2054434336","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":[0.00535645,0.000027513814,0.9931027,0.00085106597,0.00017361043,0.00013659774,0.0000630297,0.00001664492,0.00027238543],"genre_scores_gemma":[0.22788575,0.000009503608,0.77177864,0.00020450847,0.00006919079,0.0000020610703,0.000017695314,0.000011368157,0.000021269643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998527,0.0005438693,0.000517403,0.0001331478,0.00015845099,0.00012011902],"domain_scores_gemma":[0.9474401,0.051635824,0.0004892187,0.00017066913,0.00020112097,0.00006305084],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014603616,0.000088203145,0.00018797016,0.00008408029,0.0000970572,0.00012152048,0.0001291443,0.000056973415,0.000040714676],"category_scores_gemma":[0.06699608,0.000075321725,0.000016561136,0.00007169022,0.00006109582,0.0009700288,0.000036003978,0.00037912017,0.0000013146478],"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":[0.0012416088,0.00011208666,0.000021196829,0.00011429811,0.000030853298,0.000006057159,0.0003263798,0.0006056735,0.000724069,0.9400946,0.0002775727,0.056445595],"study_design_scores_gemma":[0.00062322966,0.0000636996,0.00026418729,0.00007707151,0.00008192004,0.00019819895,0.00025640117,0.06294804,0.00008887184,0.9344402,0.0008677346,0.0000904548],"about_ca_topic_score_codex":0.000007903291,"about_ca_topic_score_gemma":0.000005718857,"teacher_disagreement_score":0.2225293,"about_ca_system_score_codex":0.000016878152,"about_ca_system_score_gemma":0.00006878284,"threshold_uncertainty_score":0.940863},"labels":[],"label_agreement":null},{"id":"W2055071270","doi":"10.5539/mas.v8n5p70","title":"Ratio Estimators Using Coefficient of Variation and Coefficient of Correlation","year":2014,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Faculty of Science, Silpakorn University; Silpakorn University","keywords":"Estimator; Statistics; Mathematics; Simple random sample; Ratio estimator; Stratified sampling; Mean squared error; Sample size determination; Coefficient of variation; Population mean; Correlation coefficient; Sampling (signal processing); Population; Efficient estimator; Minimum-variance unbiased estimator; Computer science","score_opus":0.05820248393307978,"score_gpt":0.32207637783953613,"score_spread":0.2638738939064563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055071270","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":[0.36135486,0.0000032713876,0.63807786,0.000003937647,0.000037247664,0.00013819324,0.0000017744168,0.00004036387,0.00034251512],"genre_scores_gemma":[0.8607864,4.7858464e-7,0.13918273,0.0000074339823,0.000005449823,0.000004750333,0.0000014671313,0.000006813396,0.000004468923],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883914,0.000029557566,0.00034395413,0.00022290989,0.00043176158,0.00013265539],"domain_scores_gemma":[0.99890494,0.00031362224,0.00031547184,0.00023853943,0.00018304348,0.000044381333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021064312,0.00008652997,0.00017854657,0.0001749174,0.0001452257,0.000025968382,0.00013652486,0.00004451667,0.0000036809058],"category_scores_gemma":[0.0005777245,0.00008053604,0.000016905458,0.00038498585,0.0003212613,0.00007951222,0.000054790693,0.00005016136,7.754504e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024051602,0.00014137416,0.0008523747,0.00013419162,0.00000506302,4.7412083e-8,0.0055409796,0.19180425,0.613359,0.1806831,0.000013225672,0.007442381],"study_design_scores_gemma":[0.00012170544,0.00002478544,0.0015391966,0.000032451888,0.0000114051945,0.000001148835,0.000025966938,0.9087694,0.054582767,0.03481797,0.000001431128,0.00007172673],"about_ca_topic_score_codex":0.00003058378,"about_ca_topic_score_gemma":0.000001099437,"teacher_disagreement_score":0.7169652,"about_ca_system_score_codex":0.00005263104,"about_ca_system_score_gemma":0.00008450185,"threshold_uncertainty_score":0.32841644},"labels":[],"label_agreement":null},{"id":"W2059158409","doi":"10.1111/1467-842x.00153","title":"Median Estimation Using Double Sampling","year":2001,"lang":"en","type":"article","venue":"Australian & New Zealand Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; University of Saskatchewan","funders":"","keywords":"Mathematics; Estimator; Statistics; Minimum-variance unbiased estimator; Sampling (signal processing); Stratified sampling","score_opus":0.23842227075481248,"score_gpt":0.4195964561187449,"score_spread":0.18117418536393243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059158409","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":[0.10658074,0.000013729176,0.892115,0.0006783838,0.00034939736,0.0001033676,0.000033913584,0.000056084526,0.00006938529],"genre_scores_gemma":[0.111694165,0.000059208087,0.88582736,0.000030361061,0.00033259182,5.967438e-7,0.000018114106,0.000030562875,0.00200701],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99840945,0.0000489309,0.0007840516,0.00010932189,0.00038403974,0.0002641938],"domain_scores_gemma":[0.9981418,0.00048616136,0.0006743363,0.00016201986,0.00029214902,0.00024350091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007992019,0.00016547399,0.0003290574,0.00020329666,0.000098920296,0.000101492515,0.00017104924,0.000101188256,0.00018434269],"category_scores_gemma":[0.0005030899,0.0001470608,0.000065858294,0.00020015273,0.000041104366,0.00023746952,0.00001485889,0.00026674772,0.000009534154],"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":[0.0010572769,0.00071134715,0.05109418,0.0003717548,0.00054152636,0.00059747853,0.0050924798,0.014709003,0.002448402,0.03464984,0.69913006,0.18959665],"study_design_scores_gemma":[0.0037905336,0.0006215969,0.0061701178,0.0008423992,0.00044964172,0.0023465247,0.00031224889,0.009938086,0.0024500813,0.9518733,0.020503977,0.00070149614],"about_ca_topic_score_codex":0.0003300371,"about_ca_topic_score_gemma":0.00005285188,"teacher_disagreement_score":0.91722345,"about_ca_system_score_codex":0.00008396827,"about_ca_system_score_gemma":0.00016754038,"threshold_uncertainty_score":0.5996965},"labels":[],"label_agreement":null},{"id":"W2061337431","doi":"10.1080/01621459.2000.10474281","title":"Jackknife Variance Estimation under Imputation for Estimators Using Poststratification Information","year":2000,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Statistics Canada","funders":"","keywords":"Jackknife resampling; Estimator; Statistics; Imputation (statistics); Mathematics; Weighting; Econometrics; Missing data","score_opus":0.03967785128842156,"score_gpt":0.3694318726392187,"score_spread":0.3297540213507971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061337431","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":[0.1995094,0.000003120371,0.79912263,0.0007901847,0.00014594711,0.00025423555,0.00007430896,0.00004163563,0.000058536483],"genre_scores_gemma":[0.5180125,0.000004159617,0.481631,0.0001924664,0.00007081398,0.000008675926,0.000024776555,0.000012794531,0.00004279703],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99798304,0.00025320158,0.00092146633,0.000095241914,0.00055500347,0.00019203631],"domain_scores_gemma":[0.9946814,0.0020666162,0.002356651,0.00015396776,0.00067909324,0.00006225061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017209615,0.0001351117,0.000304561,0.00010542021,0.00021428481,0.00013249014,0.00017405408,0.00006763786,0.000040943018],"category_scores_gemma":[0.0049481844,0.00010587519,0.00011627231,0.00036278486,0.00006184535,0.0007034547,0.000009324329,0.00017834659,0.000009303857],"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":[0.0010783989,0.00058551267,0.008501122,0.00028548954,0.0005369393,0.0000012723382,0.0019784493,0.13248333,0.0018790896,0.16083245,0.027499191,0.66433877],"study_design_scores_gemma":[0.000647723,0.00027063987,0.05774311,0.00010527419,0.00026998596,0.00003504593,0.00016659556,0.38463825,0.000796358,0.55472475,0.00035373427,0.00024851414],"about_ca_topic_score_codex":0.000055764798,"about_ca_topic_score_gemma":0.0000030558022,"teacher_disagreement_score":0.6640902,"about_ca_system_score_codex":0.00062594813,"about_ca_system_score_gemma":0.00015900348,"threshold_uncertainty_score":0.5923796},"labels":[],"label_agreement":null},{"id":"W2072591790","doi":"10.1007/s11336-013-9390-9","title":"Modeling Motivated Misreports to Sensitive Survey Questions","year":2013,"lang":"en","type":"article","venue":"Psychometrika","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Response bias; Psychology; Scale (ratio); Item response theory; Computer science; Process (computing); Data science; Econometrics; Social psychology; Cognitive psychology; Psychometrics; Mathematics; Developmental psychology","score_opus":0.17963799569682887,"score_gpt":0.3932901266850871,"score_spread":0.21365213098825825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072591790","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":[0.59364134,0.000013303211,0.40403667,0.00019054532,0.000181538,0.00038815485,0.000018548648,0.0005365712,0.0009933314],"genre_scores_gemma":[0.90269643,0.000007492201,0.09651274,0.00016525736,0.00004670583,0.000080995356,0.000036404814,0.00003842801,0.00041557272],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9984263,0.00019550702,0.00046159912,0.0003388341,0.00028222773,0.0002955289],"domain_scores_gemma":[0.99715155,0.0013818318,0.00009044173,0.0004818855,0.0006947075,0.00019960677],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0015566597,0.0001809692,0.00027034944,0.00062264607,0.00011741089,0.00009492541,0.00013163335,0.00010565908,0.00018150466],"category_scores_gemma":[0.011279854,0.00017145523,0.00006435902,0.0015502997,0.000018431865,0.00014750693,0.000035575744,0.00015644605,0.00036391255],"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":[0.0003163958,0.004201014,0.26978064,0.00044063843,0.001112842,0.00004413164,0.009615591,0.014647999,0.015062584,0.01289583,0.48995492,0.18192741],"study_design_scores_gemma":[0.0012658046,0.00046124213,0.58797497,0.0007385868,0.00009693243,0.000095912525,0.0006377325,0.14308028,0.01448403,0.24737875,0.0011157981,0.0026700045],"about_ca_topic_score_codex":0.00227919,"about_ca_topic_score_gemma":0.00007093402,"teacher_disagreement_score":0.48883912,"about_ca_system_score_codex":0.000060618935,"about_ca_system_score_gemma":0.000024368863,"threshold_uncertainty_score":0.99704856},"labels":[],"label_agreement":null},{"id":"W2075601854","doi":"10.1002/cjs.5550350403","title":"Nonresponse weighting adjustment using estimated response probability","year":2007,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Statistics; Estimator; Weighting; Inverse probability weighting; Non-response bias; Mathematics; Variance (accounting); Respondent; Probability sampling; Inverse probability; Econometrics; Bayesian probability; Posterior probability","score_opus":0.2125820364407258,"score_gpt":0.3825614725344622,"score_spread":0.16997943609373642,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2075601854","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":[0.4581069,0.00006832055,0.541267,0.000047919995,0.00022789247,0.00009928373,0.00010753678,0.000021304726,0.00005389646],"genre_scores_gemma":[0.38814083,0.0000019452232,0.61169875,0.00003979185,0.000059580118,5.146592e-7,0.0000029312775,0.000020274067,0.000035390665],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99811786,0.00030501996,0.00081919745,0.000113532515,0.00025655678,0.00038781404],"domain_scores_gemma":[0.994634,0.0033274528,0.0005000515,0.0002089987,0.00074696034,0.0005825747],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007946387,0.0001485319,0.00027311823,0.00042206515,0.00018940831,0.000052705986,0.00017767865,0.000093922965,0.00011294659],"category_scores_gemma":[0.014374636,0.00014146722,0.000054079006,0.00024227273,0.000120896475,0.0000989394,0.000009784739,0.00025968262,0.0000041065605],"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":[0.021882595,0.0015598199,0.14926736,0.0022786683,0.0014518836,0.014439976,0.034473076,0.0064094113,0.03056439,0.26814547,0.15281291,0.31671444],"study_design_scores_gemma":[0.002444642,0.0016066615,0.19741678,0.0018527714,0.0004991298,0.0030425892,0.0012811485,0.021875873,0.015157236,0.7474858,0.0058424813,0.0014948618],"about_ca_topic_score_codex":0.0011928804,"about_ca_topic_score_gemma":0.0040146345,"teacher_disagreement_score":0.47934034,"about_ca_system_score_codex":0.00061157503,"about_ca_system_score_gemma":0.0016962549,"threshold_uncertainty_score":0.9939277},"labels":[],"label_agreement":null},{"id":"W2076056045","doi":"10.1007/s10651-009-0129-9","title":"A new design for sampling with adaptive sample plots","year":2009,"lang":"en","type":"article","venue":"Environmental and Ecological Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"Deutsche Forschungsgemeinschaft","keywords":"Plot (graphics); Sampling (signal processing); Estimator; Sample size determination; Adaptive sampling; Statistics; Mathematics; Sample (material); Sampling design; Scatter plot; Tree (set theory); Cluster sampling; Computer science; Population; Monte Carlo method","score_opus":0.14950292604653148,"score_gpt":0.3203638840833363,"score_spread":0.17086095803680484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076056045","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":[0.025191544,0.000019619654,0.9739896,0.000059941318,0.000013911352,0.0003733309,0.00022862165,0.00008838881,0.00003500775],"genre_scores_gemma":[0.26579294,0.000019490028,0.73391885,0.00011086235,0.000023947347,0.000019763398,0.000034128454,0.000008048562,0.000071978386],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999301,0.0000329072,0.00016512659,0.00019988496,0.00010119681,0.0001998624],"domain_scores_gemma":[0.997635,0.0021065713,0.00006964601,0.00007658407,0.000005031592,0.000107166234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019951073,0.00013394193,0.00017971,0.000017922359,0.00015502614,0.000026606544,0.000055805605,0.000066288245,0.00017851028],"category_scores_gemma":[0.00024572402,0.00009743834,0.000017984341,0.000021486143,0.000051844476,0.000040866624,0.00001769947,0.000072585644,0.000005943954],"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":[0.0021931503,0.0020143397,0.0064097745,0.00008067137,0.00019100787,0.00003209332,0.0015556274,0.0012881256,0.0015063062,0.36538243,0.031861205,0.58748525],"study_design_scores_gemma":[0.00056881533,0.0026622147,0.0362889,0.000013087631,0.000041487096,0.000009926431,0.000092010574,0.0034268,0.00035130675,0.95572346,0.00058115047,0.00024081989],"about_ca_topic_score_codex":0.0000076200827,"about_ca_topic_score_gemma":0.00000414001,"teacher_disagreement_score":0.5903411,"about_ca_system_score_codex":0.00004578918,"about_ca_system_score_gemma":0.000009663735,"threshold_uncertainty_score":0.397342},"labels":[],"label_agreement":null},{"id":"W2079857135","doi":"10.1016/j.zool.2005.10.002","title":"Filter-feeding dabbling ducks (Anas spp.) can actively select particles by size","year":2006,"lang":"en","type":"article","venue":"Zoology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Biology; Predation; Interspecific competition; Anas; Botany; Ecology","score_opus":0.05375368357893183,"score_gpt":0.31504229631134933,"score_spread":0.2612886127324175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2079857135","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":[0.9598435,0.000058610694,0.035423916,0.0007316671,0.00012692495,0.00013953402,0.000022049599,0.0005971676,0.0030566081],"genre_scores_gemma":[0.9655035,0.000005111005,0.033419818,0.00012924439,0.0001222979,0.000029235687,0.000018058476,0.000030460638,0.00074226677],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988494,0.00011867367,0.0002996803,0.00025168378,0.00012033083,0.00036022623],"domain_scores_gemma":[0.9980723,0.001455778,0.00014343591,0.00020013818,0.000078940924,0.000049383547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005033197,0.00015326902,0.00025196784,0.00006503386,0.00013991458,0.0000395607,0.00014686454,0.0001375026,0.0001712705],"category_scores_gemma":[0.0010767743,0.00014786955,0.000053666445,0.00016726922,0.00007238854,0.00007718357,0.00003906041,0.00016637985,0.000029348057],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020398485,0.00095426646,0.13711269,0.0002704336,0.00021919506,0.00005702246,0.0021461218,0.00016083953,0.36772457,0.05412556,0.41571972,0.021305578],"study_design_scores_gemma":[0.00091126765,0.00026705684,0.023111302,0.00008385023,0.00009985221,0.00009148751,0.00030501912,0.0020735317,0.47754374,0.48929965,0.0054243333,0.0007888923],"about_ca_topic_score_codex":0.0007336822,"about_ca_topic_score_gemma":0.00029595607,"teacher_disagreement_score":0.4351741,"about_ca_system_score_codex":0.000060978207,"about_ca_system_score_gemma":0.000033498363,"threshold_uncertainty_score":0.6029945},"labels":[],"label_agreement":null},{"id":"W2082120092","doi":"10.1007/s003620100067","title":"Estimation of mean and variance of stigmatized quantitative variable using distinct units in randomized response sampling","year":2001,"lang":"en","type":"article","venue":"Statistical Papers","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Randomized response; Statistics; Variance (accounting); Estimation; Econometrics; Mathematics; Estimator; Economics","score_opus":0.13691295140119766,"score_gpt":0.40082266029477076,"score_spread":0.2639097088935731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082120092","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":[0.31258667,0.00002598128,0.68666553,0.00001302286,0.000020912707,0.00026633794,0.00007506611,0.000033731416,0.0003127641],"genre_scores_gemma":[0.5422368,0.000007698317,0.45771182,0.0000036631473,0.0000018474303,0.00000884001,0.000011536497,0.000009850409,0.000007905186],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770445,0.0009512446,0.0007702995,0.00018707065,0.00021957055,0.00016735056],"domain_scores_gemma":[0.9765627,0.02275331,0.0003147851,0.00015615251,0.00015915098,0.000053903186],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0042781257,0.00013993403,0.0007154565,0.00015887956,0.000051443236,0.000013736531,0.000070038914,0.00007733663,0.00006728538],"category_scores_gemma":[0.041386507,0.00012551149,0.000027811857,0.00040943484,0.00026293762,0.00007640243,0.000026898559,0.00011701052,4.774669e-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":[0.084599525,0.0002648484,0.00079947326,0.0009833588,0.00015308996,0.000011612489,0.005087715,0.0096594095,0.013212303,0.87514806,0.000023377686,0.010057224],"study_design_scores_gemma":[0.019238217,0.00012179676,0.002843972,0.00081041927,0.00012517702,0.000009854592,0.0005065925,0.5705558,0.0006099406,0.4049296,0.0000067099613,0.00024190573],"about_ca_topic_score_codex":0.0005248385,"about_ca_topic_score_gemma":0.000047714628,"teacher_disagreement_score":0.5608964,"about_ca_system_score_codex":0.000041565916,"about_ca_system_score_gemma":0.000094445124,"threshold_uncertainty_score":0.9666883},"labels":[],"label_agreement":null},{"id":"W2085472393","doi":"10.1007/s13171-014-0062-3","title":"Nonparametric Confidence Intervals for Quantiles with Randomized Nomination Sampling","year":2014,"lang":"en","type":"article","venue":"Sankhya A","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Quantile; Confidence interval; CDF-based nonparametric confidence interval; Statistics; Nonparametric statistics; Sampling design; Robust confidence intervals; Coverage probability; Sampling (signal processing); Range (aeronautics); Mathematics; Population; Computer science; Medicine; Engineering","score_opus":0.12439986094424264,"score_gpt":0.3942032311730128,"score_spread":0.26980337022877016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085472393","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":[0.07544885,0.000035921803,0.9223731,0.00014122139,0.00007807927,0.000731139,0.000006056886,0.00028876547,0.0008968776],"genre_scores_gemma":[0.6577645,0.0000058723826,0.3418095,0.000062644365,0.00004008382,0.00020635943,0.000010264039,0.000019278394,0.00008149405],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99891865,0.0001695037,0.00036505738,0.00020989763,0.00016405157,0.000172832],"domain_scores_gemma":[0.99008346,0.009145136,0.00024776705,0.00024829406,0.00023590786,0.000039440696],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031915857,0.0001392923,0.0004650876,0.0001919118,0.00009061987,0.00007107566,0.00014033014,0.0000686736,0.000028003053],"category_scores_gemma":[0.009612816,0.0001033568,0.000113927126,0.00019165082,0.00008170882,0.000103631784,0.000016963526,0.00007218932,0.000011219589],"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":[0.019164668,0.00032919456,0.001040288,0.0011076544,0.0002888007,7.770645e-7,0.002263487,0.00024138181,0.0011646324,0.8912376,0.004244342,0.07891718],"study_design_scores_gemma":[0.0388681,0.00030712038,0.0004058266,0.0006121322,0.00019609615,0.000012536583,0.00012825182,0.077077486,0.014388385,0.8665137,0.0009851714,0.0005051799],"about_ca_topic_score_codex":0.000031072464,"about_ca_topic_score_gemma":0.000009716254,"teacher_disagreement_score":0.5823156,"about_ca_system_score_codex":0.000023786235,"about_ca_system_score_gemma":0.000020960266,"threshold_uncertainty_score":0.99872965},"labels":[],"label_agreement":null},{"id":"W2090064355","doi":"10.1111/j.1541-0420.2008.01082_12.x","title":"Advanced Distance Sampling: Estimating Abundance of Biological Populations by BUCKLAND, S. T., ANDERSON, D. R., BURNHAM, K. P., LAAKE, J. L., BORCHERS, C. L., and THOMAS, L.","year":2008,"lang":"en","type":"article","venue":"Biometrics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Citation; Sampling (signal processing); Mathematics; Combinatorics; Statistics; Library science; Computer science","score_opus":0.30857341672865873,"score_gpt":0.3971899444011155,"score_spread":0.08861652767245676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090064355","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":[0.3295765,0.0026475703,0.6666461,0.000083349696,0.00013476636,0.00023357809,0.00014207927,0.00029490492,0.00024110163],"genre_scores_gemma":[0.5167061,0.00033739718,0.48268762,0.000020295718,0.000027112606,0.00001574133,0.00006544107,0.000019957282,0.000120308556],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99839455,0.00008005848,0.00057774823,0.00034799287,0.00031051296,0.0002891188],"domain_scores_gemma":[0.9977729,0.0012013781,0.00039480816,0.00032083524,0.00019517314,0.000114922455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069973397,0.00022186956,0.00042143985,0.00043346937,0.00026979254,0.000029905033,0.00018732103,0.00018261088,0.0000124333765],"category_scores_gemma":[0.004428923,0.00019504581,0.00006862849,0.001927775,0.00023780318,0.00014775332,0.00006200892,0.00015271915,0.0000018580531],"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":[0.00038905733,0.0023546438,0.6650801,0.0017780546,0.00026934256,0.0000340853,0.0037184455,0.00033943012,0.024586849,0.059570964,0.08980732,0.15207174],"study_design_scores_gemma":[0.011554844,0.0032195724,0.28370228,0.0022224819,0.000389041,0.0007122683,0.0016242355,0.06829923,0.048761893,0.46369255,0.10824927,0.00757235],"about_ca_topic_score_codex":0.000048576603,"about_ca_topic_score_gemma":0.0000037300636,"teacher_disagreement_score":0.40412158,"about_ca_system_score_codex":0.000054020158,"about_ca_system_score_gemma":0.000028646626,"threshold_uncertainty_score":0.79537374},"labels":[],"label_agreement":null},{"id":"W2090079919","doi":"10.1081/sta-100002142","title":"ESTIMATION PROCEDURES FOR CATEGORICAL SURVEY DATA WITH NONIGNORABLE NONRESPONSE","year":2001,"lang":"en","type":"article","venue":"Communication in Statistics- Theory and Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Categorical variable; Covariate; Weighting; Imputation (statistics); Econometrics; Statistics; Computer science; Non-response bias; Missing data; Logistic regression; Mathematics","score_opus":0.2777480386831461,"score_gpt":0.5313532696232803,"score_spread":0.2536052309401342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090079919","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":[0.004252577,0.00029566986,0.99434733,0.00006617776,0.00002378045,0.00048177733,0.00020030315,0.00010366771,0.00022868597],"genre_scores_gemma":[0.17437385,0.00024045211,0.8243547,0.000040984298,0.000006562494,0.00015346389,0.0006018427,0.00002404432,0.00020406139],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9946512,0.0043982514,0.0003992879,0.00026774494,0.00010445932,0.00017906078],"domain_scores_gemma":[0.96588916,0.032501705,0.00019045781,0.0011576206,0.000204904,0.00005615173],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02174532,0.00014571508,0.0002643842,0.00012016995,0.0002270006,0.00007366401,0.0004765528,0.00008559632,0.00001888586],"category_scores_gemma":[0.028073141,0.00012587223,0.00001010821,0.0002470477,0.00016904679,0.00020029212,0.00014501277,0.00016620063,0.000001191144],"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":[0.0026638932,0.00028493148,0.0038791173,0.0002851604,0.000043531145,0.0000018435336,0.0016574517,0.00014916957,0.00005712197,0.7832436,0.0023597232,0.20537445],"study_design_scores_gemma":[0.00050806,0.000091137066,0.006732284,0.000094102536,0.00003800952,0.000024017254,0.00020378083,0.050274856,0.0002006573,0.94103634,0.0005942356,0.00020254248],"about_ca_topic_score_codex":0.00012277988,"about_ca_topic_score_gemma":0.00041761014,"teacher_disagreement_score":0.2051719,"about_ca_system_score_codex":0.000033166223,"about_ca_system_score_gemma":0.00011379249,"threshold_uncertainty_score":0.9801138},"labels":[],"label_agreement":null},{"id":"W2093139043","doi":"10.1186/1471-2288-14-2","title":"Assessing outcomes of large-scale public health interventions in the absence of baseline data using a mixture of Cox and binomial regressions","year":2014,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; FHI 360; Indian Council of Medical Research; University of Manitoba; Bill and Melinda Gates Foundation","keywords":"Condom; Psychological intervention; Scale (ratio); Negative binomial distribution; Statistics; Inference; Baseline (sea); Population; Econometrics; Medicine; Computer science; Mathematics; Environmental health; Human immunodeficiency virus (HIV); Poisson distribution; Family medicine; Geography; Artificial intelligence","score_opus":0.8928951245828125,"score_gpt":0.6854779576295542,"score_spread":0.2074171669532583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2093139043","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":[0.22238837,0.00018249129,0.7753323,0.0018233872,0.000038859765,0.0001646105,0.000034334735,0.000010590791,0.000025107833],"genre_scores_gemma":[0.37160903,0.000063452244,0.6282189,0.00004632611,0.000021234888,0.0000074294653,0.000020312813,0.000006764698,0.0000065239956],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9541291,0.042178873,0.0014905565,0.00038124822,0.0013106446,0.0005095677],"domain_scores_gemma":[0.87169194,0.12638906,0.00046914266,0.000930056,0.00035861807,0.00016120584],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.16713138,0.00007712846,0.0006274399,0.00036779093,0.00009094915,0.000012978687,0.00070536294,0.00016024105,0.00006942501],"category_scores_gemma":[0.35632715,0.000048313927,0.00006391819,0.0004588909,0.0006404305,0.00009976712,0.0005027605,0.000512456,1.6363722e-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":[0.0003329427,0.005369903,0.4965933,0.019689541,0.00022531538,0.000010896595,0.017027883,0.000021636526,0.0056563006,0.13932696,0.011504464,0.30424085],"study_design_scores_gemma":[0.004746203,0.0012867603,0.24374044,0.012850413,0.00008006871,0.00012742977,0.022658007,0.4323807,0.002827864,0.27741438,0.0013620378,0.00052569323],"about_ca_topic_score_codex":0.000630944,"about_ca_topic_score_gemma":0.0015436113,"teacher_disagreement_score":0.43235907,"about_ca_system_score_codex":0.000017972417,"about_ca_system_score_gemma":0.0006976502,"threshold_uncertainty_score":0.8576135},"labels":[],"label_agreement":null},{"id":"W2096274285","doi":"10.2307/3315854","title":"On quasi‐likelihood inference in generalized linear mixed models with two components of dispersion","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Mathematics; Statistics; Estimator; Quasi-maximum likelihood; Generalized linear model; Dispersion (optics); Variance components; Generalized linear mixed model; Maximum likelihood; Mixed model; Applied mathematics; Likelihood function; Physics","score_opus":0.10384777765582501,"score_gpt":0.3234960585517568,"score_spread":0.21964828089593177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096274285","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":[0.41000646,0.000024495484,0.58953565,0.000020075071,0.000067230074,0.00006697058,0.00012586027,0.000004535434,0.00014870861],"genre_scores_gemma":[0.68181115,0.000011205798,0.3181182,0.000021670663,0.0000065707236,8.2854507e-7,0.000008761873,0.000012023901,0.000009569264],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989085,0.00014629531,0.00046649098,0.000077309545,0.00021140405,0.00019000308],"domain_scores_gemma":[0.99829525,0.00068066205,0.0003213249,0.00013539632,0.00032106318,0.00024631323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058246276,0.00011066988,0.0002900997,0.00028994065,0.00004321147,0.000015502173,0.00011823298,0.00004478297,0.000037348458],"category_scores_gemma":[0.0012995627,0.00009265215,0.000026404996,0.00014734252,0.000059348917,0.0000680174,0.0000029057583,0.00018460669,0.0000013325468],"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":[0.00021791786,0.00037221727,0.018341133,0.00021955003,0.00010467537,0.00026825696,0.0024730428,0.026679305,0.00027910317,0.94264156,0.003958654,0.0044446136],"study_design_scores_gemma":[0.0026919981,0.0008416085,0.0020376372,0.0010076094,0.00006189179,0.000050500323,0.00024175676,0.051984817,0.0018702593,0.93872863,0.00014747179,0.0003358207],"about_ca_topic_score_codex":0.0033715484,"about_ca_topic_score_gemma":0.014603367,"teacher_disagreement_score":0.2718047,"about_ca_system_score_codex":0.00011174178,"about_ca_system_score_gemma":0.00049301056,"threshold_uncertainty_score":0.8149022},"labels":[],"label_agreement":null},{"id":"W2116330103","doi":"10.1007/s13571-011-0009-9","title":"Improved prediction in finite population sampling using convex combination of parametric and non-parametric models","year":2010,"lang":"en","type":"article","venue":"Sankhya B","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Parametric statistics; Parametric model; Sample size determination; Sampling (signal processing); Population; Computer science; Mathematics; Inference; Mathematical optimization; Applied mathematics; Algorithm; Statistics; Artificial intelligence","score_opus":0.11664878038783764,"score_gpt":0.35694771972489026,"score_spread":0.2402989393370526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116330103","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":[0.73069584,0.000020973814,0.26873377,0.0000061788855,0.00012445185,0.00025920794,0.000011772005,0.0000772769,0.00007052519],"genre_scores_gemma":[0.8804258,0.000009305279,0.11947099,0.000005897945,0.000018377466,0.000013719697,0.000032291944,0.000017100696,0.000006491611],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989653,0.000051189196,0.00047203535,0.00019567511,0.0001715943,0.000144199],"domain_scores_gemma":[0.9983959,0.0009487986,0.00027027845,0.00020827694,0.00013897209,0.0000377598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010471521,0.00011710632,0.00024532044,0.0008105624,0.00005907332,0.000030624273,0.00006770383,0.00017514573,0.000010507597],"category_scores_gemma":[0.0018768861,0.00012248706,0.000041717216,0.0008931682,0.000034258712,0.00027471213,0.000028382441,0.00022724185,5.5533826e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031394293,0.0018290915,0.73521423,0.001992892,0.00016519346,0.0000025931502,0.0032529444,0.037278704,0.06888474,0.046574045,0.00011721459,0.10437441],"study_design_scores_gemma":[0.00040725537,0.00004921203,0.052794654,0.0000592787,0.000021298869,0.0000023561665,0.000028239527,0.80051535,0.0022400075,0.1437789,0.0000011826968,0.00010226702],"about_ca_topic_score_codex":0.000631305,"about_ca_topic_score_gemma":0.000037130038,"teacher_disagreement_score":0.76323664,"about_ca_system_score_codex":0.000040737585,"about_ca_system_score_gemma":0.000021424996,"threshold_uncertainty_score":0.49948776},"labels":[],"label_agreement":null},{"id":"W2121049202","doi":"10.1007/s10342-005-0074-6","title":"Adaptive cluster sampling for estimation of deforestation rates","year":2005,"lang":"en","type":"article","venue":"European Journal of Forest Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"Government of Canada","keywords":"Statistics; Sample size determination; Sampling (signal processing); Estimator; Mean squared error; Cluster sampling; Efficiency; Population; Deforestation (computer science); Mathematics; Population size; Sample (material); Simple random sample; Sampling design; Econometrics; Computer science; Demography; Physics","score_opus":0.346117542520027,"score_gpt":0.4815740246007563,"score_spread":0.1354564820807293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121049202","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":[0.3442555,0.000055683267,0.6544144,0.00023086621,0.000037859874,0.00022206758,0.0000062242652,0.000019666291,0.0007576913],"genre_scores_gemma":[0.62507427,0.000011586761,0.3746681,0.0000075598596,0.00013935391,0.000003370973,0.000004364361,0.000023435383,0.00006797009],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977204,0.0006715347,0.0007476643,0.0001055347,0.0005261349,0.0002287339],"domain_scores_gemma":[0.99523187,0.0026193175,0.00046629016,0.00016648044,0.0014378829,0.00007814725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011683103,0.000094275856,0.00020783386,0.00042866773,0.00012863213,0.000050417566,0.0002596176,0.000028679931,0.000016156868],"category_scores_gemma":[0.0051407325,0.000076306154,0.0001083051,0.00021981889,0.000102044425,0.00028814518,0.000042662166,0.00027537893,0.000011314369],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003478808,0.0010698141,0.0075257765,0.0009886593,0.0003346063,0.000022648679,0.009672112,0.16467728,0.002033195,0.08356556,0.036801346,0.6898302],"study_design_scores_gemma":[0.005856703,0.006661463,0.06240076,0.0028386083,0.00013608641,0.00022656379,0.0016627269,0.31862077,0.037877962,0.5575467,0.0054711117,0.00070056407],"about_ca_topic_score_codex":0.000004763007,"about_ca_topic_score_gemma":0.000011877694,"teacher_disagreement_score":0.68912965,"about_ca_system_score_codex":0.00007483159,"about_ca_system_score_gemma":0.00008477996,"threshold_uncertainty_score":0.61543083},"labels":[],"label_agreement":null},{"id":"W2125837536","doi":"10.1002/cjs.10030","title":"Designing sampling plans to capture rare objects","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rare events; Hypergeometric distribution; Sampling (signal processing); Computer science; Monte Carlo method; Statistics; Sample (material); Population; Sample size determination; Sampling design; Data mining; Mathematics; Demography; Physics","score_opus":0.11116036013211086,"score_gpt":0.32922199897459936,"score_spread":0.2180616388424885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125837536","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":[0.007191222,0.00006389861,0.99120796,0.0003114397,0.00020236221,0.00008999233,0.00028258155,0.000027643175,0.00062289956],"genre_scores_gemma":[0.40478992,0.0000027191145,0.5946569,0.00038170375,0.000083978695,5.252054e-7,0.0000068827494,0.00001278975,0.00006460893],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990211,0.000048256257,0.00039771915,0.000085675536,0.00017213915,0.00027511685],"domain_scores_gemma":[0.9982041,0.00050404476,0.00019870543,0.00013023498,0.00036321284,0.0005996882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056975737,0.00011966238,0.00023127095,0.00030458154,0.00014374308,0.00008869197,0.00018669025,0.00007281701,0.000059286544],"category_scores_gemma":[0.0027787143,0.00011563471,0.000037048718,0.00016327275,0.000020121293,0.00007059589,0.0000031890543,0.00023935329,0.0000075394723],"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":[0.00011330359,0.000095663374,0.00691754,0.00025357387,0.00019000354,0.0021329958,0.032414448,0.0037920612,0.0020540203,0.13525948,0.7082516,0.10852533],"study_design_scores_gemma":[0.00088326575,0.001127321,0.013634651,0.0015931712,0.00020309427,0.0011718912,0.0033968338,0.00060714985,0.0047426815,0.95842713,0.013107906,0.0011048773],"about_ca_topic_score_codex":0.00057180884,"about_ca_topic_score_gemma":0.0058143586,"teacher_disagreement_score":0.8231677,"about_ca_system_score_codex":0.00014154003,"about_ca_system_score_gemma":0.0006278858,"threshold_uncertainty_score":0.47154468},"labels":[],"label_agreement":null},{"id":"W2132467996","doi":"10.1111/j.1541-0420.2006.00576.x","title":"Adaptive Web Sampling","year":2006,"lang":"en","type":"article","venue":"Biometrics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Los Alamos National Laboratory; National Science Foundation","keywords":"Resampling; Computer science; Inference; Sampling (signal processing); Markov chain; Sampling design; Sample (material); Statistic; Population; Markov chain Monte Carlo; Adaptive sampling; Data mining; Statistics; Machine learning; Artificial intelligence; Mathematics; Monte Carlo method","score_opus":0.24144060586953597,"score_gpt":0.38212463865982765,"score_spread":0.14068403279029168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132467996","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":[0.114717126,0.0002860928,0.8688769,0.0000704332,0.00025376384,0.00018148805,0.000043722976,0.0010802178,0.014490285],"genre_scores_gemma":[0.6407796,0.0000088861025,0.35862184,0.000019946798,0.00010721088,0.0000091391385,0.000012332539,0.000018110808,0.0004229357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991734,0.00003015034,0.00023386853,0.00015294876,0.00023036993,0.00017926551],"domain_scores_gemma":[0.9986134,0.00092242856,0.0000993924,0.00020422487,0.00012556057,0.00003495357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062170136,0.00010083513,0.00013900214,0.0009010043,0.000079866186,0.000041850537,0.000121940415,0.000087434295,0.00004056284],"category_scores_gemma":[0.0010525212,0.00009386849,0.000055486893,0.0023942592,0.00002929503,0.00005964688,0.000032558477,0.000073191055,0.00005502031],"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":[0.00006669637,0.0012109304,0.025362918,0.0002458992,0.00010229287,0.000018216379,0.00020581548,0.00008625613,0.009529148,0.5895335,0.21951537,0.15412296],"study_design_scores_gemma":[0.0007426996,0.0002170045,0.01654248,0.00009244306,0.000060909424,0.000020692229,0.000106029824,0.007093769,0.014918758,0.9007625,0.05857314,0.00086954853],"about_ca_topic_score_codex":0.000080450816,"about_ca_topic_score_gemma":0.0000056682084,"teacher_disagreement_score":0.5260625,"about_ca_system_score_codex":0.00006145189,"about_ca_system_score_gemma":0.000025771804,"threshold_uncertainty_score":0.3827846},"labels":[],"label_agreement":null},{"id":"W2134587091","doi":"10.2307/3316078","title":"Variance estimation for the finite population distribution function with complete auxiliary information","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Waterloo","funders":"","keywords":"Jackknife resampling; Estimator; Consistency (knowledge bases); Statistics; Variance (accounting); Mathematics; Population; Population variance; Sample (material); Econometrics; Applied mathematics; Computer science; Discrete mathematics; Demography","score_opus":0.06617314236239594,"score_gpt":0.2869820243308996,"score_spread":0.22080888196850365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134587091","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":[0.0025449474,0.000024073854,0.9957545,0.00034009232,0.00024989757,0.00024486837,0.0007853165,0.00002081654,0.000035495694],"genre_scores_gemma":[0.7457036,0.0000129991995,0.25318754,0.000117397736,0.000093510505,0.000014426634,0.000826121,0.000012497972,0.000031952877],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912846,0.000042705444,0.00044356764,0.00005089693,0.0001769592,0.00015740973],"domain_scores_gemma":[0.99745387,0.0011227387,0.0005039949,0.00012393069,0.00067615416,0.00011930719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007415807,0.00009567239,0.0001352703,0.00011021746,0.0003286607,0.000115276525,0.00009893586,0.0000525678,0.00002819781],"category_scores_gemma":[0.0019197589,0.00007024293,0.00003017502,0.00017701644,0.000044003085,0.0004567385,0.0000025012398,0.00012533936,0.0000035541216],"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":[0.0007296446,0.000052450498,0.01689719,0.00035359076,0.000253195,0.000019506964,0.0013673975,0.083193205,0.000007936567,0.4616289,0.09558755,0.3399094],"study_design_scores_gemma":[0.0011410229,0.00065751857,0.10611962,0.0002748418,0.00034568584,0.00021637733,0.00025420863,0.44638506,0.000016174732,0.39947578,0.044781543,0.00033216935],"about_ca_topic_score_codex":0.0013135558,"about_ca_topic_score_gemma":0.0034137068,"teacher_disagreement_score":0.74315864,"about_ca_system_score_codex":0.00016979323,"about_ca_system_score_gemma":0.00025180826,"threshold_uncertainty_score":0.28644234},"labels":[],"label_agreement":null},{"id":"W2135885901","doi":"","title":"On sample allocation for efficient domain estimation","year":2013,"lang":"en","type":"article","venue":"Quality Engineering","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Statistics; Sample (material); Estimator; Sample size determination; Population; Econometrics; Context (archaeology); Simple random sample; Stratified sampling; Stratum; Mathematics; Reliability (semiconductor); Estimation; Sampling design; Survey sampling; Aggregate (composite); Computer science; Geography; Economics; Engineering; Demography","score_opus":0.08950316587032563,"score_gpt":0.3695666906709428,"score_spread":0.28006352480061714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135885901","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":[0.2808356,0.0000026951964,0.7181526,0.00012883852,0.00007180384,0.00034766752,0.000008606806,0.00039935805,0.00005288193],"genre_scores_gemma":[0.54448706,1.9530377e-7,0.45519444,0.000023570512,0.000022300072,0.0002117273,0.00003020745,0.00001538312,0.000015096879],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992729,0.000029354254,0.00027470253,0.00013483796,0.0001404031,0.00014779909],"domain_scores_gemma":[0.9972758,0.002318313,0.00006933497,0.0002132244,0.00008293116,0.00004034579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092720793,0.00010025327,0.0001290013,0.00007481929,0.000055191616,0.000041229887,0.00006959661,0.000055361943,0.000031208772],"category_scores_gemma":[0.0033583052,0.000098476274,0.000047657184,0.00008263099,0.000006789488,0.000054931268,0.000009020659,0.000056846173,0.000025734525],"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":[0.000012063084,0.00013368289,0.00003925019,0.00045016457,0.000023085422,5.244466e-8,0.00080208137,0.1580592,0.0032147968,0.8231781,0.002211433,0.0118761035],"study_design_scores_gemma":[0.0001983781,0.00004296486,0.00095033983,0.00006997654,0.000005271735,4.311441e-7,0.000039796574,0.6913927,0.005836907,0.3011352,0.00014546845,0.00018253896],"about_ca_topic_score_codex":0.000101277656,"about_ca_topic_score_gemma":0.0000014838972,"teacher_disagreement_score":0.53333354,"about_ca_system_score_codex":0.00006844961,"about_ca_system_score_gemma":0.000007892781,"threshold_uncertainty_score":0.40204477},"labels":[],"label_agreement":null},{"id":"W2135933669","doi":"10.1111/j.1467-842x.2008.00532.x","title":"VARIANCE ESTIMATION IN TWO‐PHASE SAMPLING","year":2009,"lang":"en","type":"article","venue":"Australian & New Zealand Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":6,"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; Carleton University; Statistics Canada","funders":"","keywords":"Mathematics; Statistics; Estimator; Sampling (signal processing); Poisson sampling; Sampling design; Sample size determination; Population; Population variance; Variance (accounting); Sample (material); Slice sampling; Monte Carlo method; Importance sampling","score_opus":0.11149051485329006,"score_gpt":0.42611062503086006,"score_spread":0.31462011017756997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135933669","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":[0.056698218,0.000015998106,0.94167954,0.0011693627,0.00016738765,0.000111904985,0.00005012344,0.000043518296,0.000063965104],"genre_scores_gemma":[0.32464132,0.000025736108,0.6743755,0.000059191047,0.00010745718,4.8359254e-7,0.000013548559,0.000011597094,0.0007651914],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984599,0.00007147302,0.0008422609,0.00010992643,0.00028361776,0.00023282829],"domain_scores_gemma":[0.99842566,0.0005373041,0.00056362443,0.0001490634,0.00016858085,0.00015577936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000919668,0.00014982486,0.00033340888,0.00020910443,0.00004404069,0.000073808966,0.00015974995,0.000058520945,0.000070477356],"category_scores_gemma":[0.0010260395,0.00013719381,0.000046458776,0.00020472017,0.000022223378,0.0002114273,0.000006429839,0.00030542884,0.000006383275],"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":[0.00064756384,0.0015875167,0.0063852374,0.0001363136,0.00011035484,0.00041532223,0.003798223,0.008850805,0.001619509,0.09253301,0.4082823,0.47563386],"study_design_scores_gemma":[0.0033500018,0.0007325503,0.010692656,0.00044024902,0.00006987658,0.00023338257,0.000056639277,0.0032236322,0.00065777375,0.9780693,0.002212107,0.0002618301],"about_ca_topic_score_codex":0.000105212835,"about_ca_topic_score_gemma":0.000035522888,"teacher_disagreement_score":0.8855363,"about_ca_system_score_codex":0.00007021335,"about_ca_system_score_gemma":0.00012197853,"threshold_uncertainty_score":0.5594601},"labels":[],"label_agreement":null},{"id":"W2136816468","doi":"10.5539/ijsp.v4n4p20","title":"A SAS Macro for Adaptive Spatial Sampling","year":2015,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Contiguity; Macro; Sampling (signal processing); Computer science; Grid; Adaptive sampling; Data mining; Spatial analysis; Algorithm; Mathematical optimization; Mathematics; Statistics; Monte Carlo method; Computer vision","score_opus":0.22145649468582748,"score_gpt":0.4132125461777905,"score_spread":0.19175605149196304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136816468","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":[0.03517129,0.000034171433,0.9635066,0.00024633546,0.0004324407,0.00014096643,0.00034640476,0.000015628455,0.00010617135],"genre_scores_gemma":[0.3843551,0.000007687639,0.6154274,0.000027003685,0.0001504062,0.000004936439,0.000007845736,0.000006375171,0.000013279713],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990104,0.00005144306,0.000448978,0.00009254701,0.00031235415,0.00008429154],"domain_scores_gemma":[0.99642503,0.0012012642,0.00034630488,0.00006596877,0.0018699197,0.00009152185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016802335,0.00007987782,0.00017234693,0.00006264244,0.00003187958,0.000057120596,0.00013911679,0.000040504445,0.000012912892],"category_scores_gemma":[0.00441384,0.00006722823,0.00004230069,0.0000242662,0.00005935481,0.00008539046,0.0000330591,0.00009877937,5.3303853e-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":[0.0027333274,0.0006299995,0.012104857,0.0001868016,0.00049931597,0.000022848719,0.0033241438,0.0003086586,0.00013021904,0.63699865,0.019742496,0.3233187],"study_design_scores_gemma":[0.00057260966,0.00027355773,0.0013542234,0.000048363367,0.000023422657,0.00004554747,0.000057660105,0.0035115862,0.00019132825,0.99223363,0.0016119693,0.000076083525],"about_ca_topic_score_codex":0.000058266367,"about_ca_topic_score_gemma":0.00003523763,"teacher_disagreement_score":0.355235,"about_ca_system_score_codex":0.0000846381,"about_ca_system_score_gemma":0.00012571122,"threshold_uncertainty_score":0.5284098},"labels":[],"label_agreement":null},{"id":"W2142707184","doi":"10.1002/cjs.11200","title":"Replication variance estimation in unequal probability sampling without replacement: One‐stage and two‐stage","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Simon Fraser University; Acadia University; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster sampling; Jackknife resampling; Replication (statistics); Statistics; Sampling (signal processing); Sampling design; Stratified sampling; Variance (accounting); Poisson sampling; Sample (material); Stage (stratigraphy); Multistage sampling; Mathematics; Sample size determination; Fraction (chemistry); Population; Econometrics; Importance sampling; Slice sampling; Computer science; Estimator; Monte Carlo method; Biology; Demography","score_opus":0.13133059440766823,"score_gpt":0.3534591225779179,"score_spread":0.22212852817024967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142707184","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":[0.23487921,0.000030968928,0.76423424,0.00017343415,0.000062911524,0.00033694712,0.00012562583,0.00001978065,0.00013689284],"genre_scores_gemma":[0.47960177,0.0000068145832,0.5202036,0.000034442503,0.000017179073,0.000012258788,0.000016005257,0.000013543745,0.000094379364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984978,0.00012880229,0.0007556188,0.00019808918,0.00018642051,0.00023330124],"domain_scores_gemma":[0.9978044,0.00058097014,0.0005493878,0.0003585208,0.00042813586,0.0002785663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019587413,0.00012771809,0.0002637467,0.00022782243,0.000110551824,0.0001311611,0.0001322534,0.00006752964,0.00013388593],"category_scores_gemma":[0.0053563975,0.0001328229,0.00001932337,0.00016234374,0.000087479115,0.00027918635,0.00001085712,0.00024396999,0.0000046492937],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000189442,0.00029708515,0.22998041,0.0017963692,0.00015672961,0.000047034802,0.009209141,0.010820189,0.0008469826,0.6325619,0.006298752,0.10779595],"study_design_scores_gemma":[0.0012942831,0.0003073241,0.08110127,0.00063758326,0.00005845431,0.000044606742,0.0003639417,0.10476318,0.00044157566,0.8096651,0.0008499029,0.0004727739],"about_ca_topic_score_codex":0.0077176793,"about_ca_topic_score_gemma":0.010902279,"teacher_disagreement_score":0.24472257,"about_ca_system_score_codex":0.0002745224,"about_ca_system_score_gemma":0.0004572799,"threshold_uncertainty_score":0.99889004},"labels":[],"label_agreement":null},{"id":"W2144914506","doi":"10.1111/j.1541-0420.2008.01018.x","title":"Estimating the Encounter Rate Variance in Distance Sampling","year":2008,"lang":"en","type":"article","venue":"Biometrics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":162,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Raincoast Conservation Foundation; Leverhulme Trust","keywords":"Statistics; Distance sampling; Variance (accounting); Sampling (signal processing); Mathematics; Econometrics; Computer science; Biology; Economics","score_opus":0.20028066032329941,"score_gpt":0.3769286227303718,"score_spread":0.1766479624070724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144914506","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":[0.1852697,0.00015306755,0.8133558,0.00011803809,0.0002395588,0.00014255906,0.000008921882,0.00018227467,0.0005300757],"genre_scores_gemma":[0.67739886,0.000025214507,0.32225734,0.000083014565,0.0000670521,0.000023909552,0.000003745774,0.00001651086,0.00012436011],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99892056,0.000089200206,0.0003496928,0.00019302641,0.00022062685,0.00022686712],"domain_scores_gemma":[0.9971696,0.0022182434,0.00015194922,0.00033639633,0.00009187405,0.000031916086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017850886,0.0001200856,0.00016928792,0.0004471248,0.00019202942,0.000043318323,0.00025750446,0.00006713731,0.000016871034],"category_scores_gemma":[0.0054334435,0.000088402645,0.0000413565,0.0030158458,0.00007506601,0.00011170198,0.00004576402,0.000158635,0.000019817146],"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":[0.00031936026,0.0027563714,0.5086824,0.002016729,0.0002800346,0.00032824793,0.023708027,0.008896714,0.011006562,0.1706892,0.062014922,0.2093014],"study_design_scores_gemma":[0.0020836694,0.00022035564,0.21466272,0.0009807297,0.000060041042,0.00021777117,0.00033748156,0.26654083,0.007853024,0.48018932,0.02474275,0.0021113066],"about_ca_topic_score_codex":0.00005463718,"about_ca_topic_score_gemma":0.000008179956,"teacher_disagreement_score":0.49212918,"about_ca_system_score_codex":0.00008394072,"about_ca_system_score_gemma":0.000033524095,"threshold_uncertainty_score":0.6504732},"labels":[],"label_agreement":null},{"id":"W2156627773","doi":"10.1002/cjs.11153","title":"Blending domain estimates from two victimization surveys with possible bias","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Statistics; Domain (mathematical analysis); Context (archaeology); Small area estimation; Survey data collection; Measure (data warehouse); Econometrics; Survey methodology; Estimation; Survey research; Geography; Computer science; Mathematics; Psychology; Data mining; Engineering; Applied psychology; Archaeology","score_opus":0.10849927180080875,"score_gpt":0.32130927353019983,"score_spread":0.21281000172939107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156627773","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":[0.09902028,0.00014149441,0.89966106,0.000055966288,0.00027066152,0.000068857924,0.00041897438,0.000028449633,0.0003342643],"genre_scores_gemma":[0.43426293,0.000006802623,0.5654947,0.000020348614,0.00012347939,9.51077e-7,0.0000425093,0.000025145457,0.000023105662],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998752,0.00019201271,0.00043035386,0.00007830775,0.00021370006,0.0003336167],"domain_scores_gemma":[0.9972028,0.0013322743,0.0004295467,0.0001485203,0.00036368828,0.0005231632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018720184,0.00014484777,0.0002592368,0.00027641584,0.00017583978,0.00010992308,0.00014290346,0.000055315497,0.00026519925],"category_scores_gemma":[0.0015624738,0.0001227874,0.000029920244,0.00019978554,0.00007126369,0.0002761457,0.0000060137336,0.00018224819,0.000009194315],"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":[0.000034489913,0.00006864562,0.9038656,0.00009611601,0.00027497864,0.00014527109,0.005011321,0.0013829373,0.000076402284,0.051853307,0.018436175,0.018754762],"study_design_scores_gemma":[0.0024894013,0.0005391321,0.22382013,0.0012801031,0.000535707,0.0006535589,0.0017727014,0.0073262784,0.0039721685,0.7529779,0.003343332,0.0012895692],"about_ca_topic_score_codex":0.0053933905,"about_ca_topic_score_gemma":0.010962263,"teacher_disagreement_score":0.7011246,"about_ca_system_score_codex":0.00017005953,"about_ca_system_score_gemma":0.00048732755,"threshold_uncertainty_score":0.81532294},"labels":[],"label_agreement":null},{"id":"W2157208850","doi":"10.2307/3316077","title":"Consistency of semiparametric maximum likelihood estimators for two‐phase sampling","year":2001,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Mathematics; Consistency (knowledge bases); Covariate; Statistics; M-estimator; Extremum estimator; Restricted maximum likelihood; Maximum likelihood; Maximization; Econometrics; Mathematical optimization","score_opus":0.12727959841211947,"score_gpt":0.37912430213776743,"score_spread":0.25184470372564793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157208850","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":[0.06045024,0.00023493679,0.9378357,0.000065702414,0.0002927768,0.0001753677,0.0007362033,0.000017507447,0.00019155117],"genre_scores_gemma":[0.35675693,0.000019266561,0.6430672,0.000035916706,0.000058356658,0.0000034353318,0.000014152825,0.000026301288,0.000018473373],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99844825,0.000046375117,0.0008799313,0.00010369858,0.00019450956,0.00032722089],"domain_scores_gemma":[0.9955551,0.0021073772,0.0006925305,0.00018793781,0.0009838775,0.00047318073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010689743,0.00014656907,0.00042346292,0.00062270387,0.00012833672,0.00004540126,0.0002056289,0.00007591999,0.00008399505],"category_scores_gemma":[0.0074628023,0.00014548659,0.00009936134,0.00036397012,0.000111375004,0.000082215716,0.00000617025,0.00017106363,0.0000020588056],"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":[0.00047437998,0.00075275777,0.05253293,0.0019163302,0.00082120614,0.00071925,0.004214186,0.0010924403,0.000777284,0.2717165,0.21046324,0.45451948],"study_design_scores_gemma":[0.0024724724,0.0008132973,0.0006258151,0.00044268125,0.00030169694,0.0005415484,0.0003639911,0.004568675,0.0010988258,0.98324054,0.0051486096,0.0003818488],"about_ca_topic_score_codex":0.00090526766,"about_ca_topic_score_gemma":0.0020076905,"teacher_disagreement_score":0.711524,"about_ca_system_score_codex":0.00012807119,"about_ca_system_score_gemma":0.0011266809,"threshold_uncertainty_score":0.89342105},"labels":[],"label_agreement":null},{"id":"W2159217576","doi":"10.5705/ss.2011.024a","title":"On variance estimation under auxiliary value imputation in sample surveys","year":2011,"lang":"en","type":"article","venue":"Statistica Sinica","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Statistics; Imputation (statistics); Variance (accounting); Estimation; Value (mathematics); Econometrics; Sample (material); Mathematics; Missing data; Economics; Accounting","score_opus":0.15025223259561843,"score_gpt":0.3878844082013983,"score_spread":0.23763217560577987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159217576","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":[0.010330493,0.000005136188,0.98469424,0.00007412928,0.00014738114,0.00027431056,0.00016565528,0.0002938898,0.0040147672],"genre_scores_gemma":[0.5342607,0.0000033503893,0.46549267,0.00007476491,0.000009857053,0.00003012281,0.000076402546,0.000022041722,0.000030100036],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979504,0.00066356536,0.00054957246,0.00032404647,0.0002560024,0.00025643155],"domain_scores_gemma":[0.9923103,0.006961266,0.00018938437,0.0003712036,0.00009666755,0.00007119167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025268572,0.00017766781,0.00025776474,0.00015902822,0.00008571764,0.000031512503,0.00015434262,0.00011361826,0.00039625092],"category_scores_gemma":[0.007776434,0.00017743482,0.000038107704,0.00026243908,0.00007737227,0.00013590684,0.000028901597,0.00019427498,0.000084430125],"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":[0.00006217029,0.00036646548,0.000736568,0.00006730012,0.00002018537,0.000007021419,0.0008267007,0.0006252352,0.0000149379875,0.96286243,0.0021100254,0.03230096],"study_design_scores_gemma":[0.00029635482,0.00014009236,0.069351375,0.00008229098,0.00001434429,0.0000022536785,0.000029648383,0.036571447,0.00018065768,0.89313686,0.000010337215,0.0001843338],"about_ca_topic_score_codex":0.00076023093,"about_ca_topic_score_gemma":0.00009886297,"teacher_disagreement_score":0.5239302,"about_ca_system_score_codex":0.00009502571,"about_ca_system_score_gemma":0.00009014354,"threshold_uncertainty_score":0.930968},"labels":[],"label_agreement":null},{"id":"W2159263306","doi":"10.1177/0049124107301944","title":"Log-Linear Randomized-Response Models Taking Self-Protective Response Behavior Into Account","year":2007,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Randomized response; Respondent; Log-linear model; Response bias; Item response theory; Statistics; Outcome (game theory); Psychology; Social psychology; Econometrics; Response time; Linear model; Mathematics; Computer science; Psychometrics","score_opus":0.5305748280486128,"score_gpt":0.619559010240721,"score_spread":0.08898418219210824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159263306","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":[0.44412878,0.00013100813,0.5529666,0.00032780741,0.000072622126,0.0014527602,0.0000048144134,0.00063748925,0.000278107],"genre_scores_gemma":[0.3979232,0.000018928997,0.60100013,0.000060902104,0.00010689738,0.0007197568,0.0000024525116,0.000040384584,0.00012733144],"study_design_codex":"randomized_trial","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94390076,0.05170805,0.0011148083,0.0008693488,0.0011672155,0.0012398069],"domain_scores_gemma":[0.8583457,0.13918649,0.00031994662,0.0007348845,0.0011490223,0.0002639683],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.30283156,0.00035906892,0.0010762353,0.000582255,0.0008272186,0.00009351878,0.000728001,0.00089832715,0.0001681802],"category_scores_gemma":[0.13761303,0.0002607276,0.00042268334,0.0007843976,0.0013055659,0.00018998029,0.00048161106,0.002170064,0.000054739132],"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":[0.6701828,0.001991803,0.0005465531,0.00022564616,0.0004231035,0.00027472107,0.032056935,0.000092940834,0.09996552,0.071395285,0.000568355,0.1222763],"study_design_scores_gemma":[0.008625555,0.00052526116,0.0016411825,0.000064349246,0.00005292947,0.000018024966,0.0018618583,0.0042007156,0.018165974,0.9642385,0.00019715355,0.00040848163],"about_ca_topic_score_codex":0.0002346718,"about_ca_topic_score_gemma":0.000004556497,"teacher_disagreement_score":0.89284325,"about_ca_system_score_codex":0.0005444169,"about_ca_system_score_gemma":0.00025393334,"threshold_uncertainty_score":0.9999845},"labels":[],"label_agreement":null},{"id":"W2164246043","doi":"10.1002/cjs.11230","title":"Doubly robust imputation procedures for finite population means in the presence of a large number of zeros","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Statistics Canada; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Mathematics; Jackknife resampling; Statistics; Estimator; Econometrics; Missing data; Population; Demography; Sociology","score_opus":0.07166732454922295,"score_gpt":0.34149687148203484,"score_spread":0.2698295469328119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164246043","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":[0.08555338,0.000010257722,0.9137092,0.000082431274,0.00005871647,0.0001779006,0.00034706964,0.0000032608075,0.000057740184],"genre_scores_gemma":[0.7690589,0.0000020039338,0.23084907,0.000023629065,0.000024316352,0.0000040534164,0.000019956331,0.000008000803,0.000010086578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905556,0.00009371421,0.00051627075,0.00004980858,0.00015916789,0.0001254551],"domain_scores_gemma":[0.9971382,0.0017149576,0.0005245014,0.00009445467,0.00046647465,0.00006141332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014495904,0.00006353857,0.0001800198,0.00013017346,0.00004559637,0.000017786388,0.0001384384,0.0000461843,0.000012482518],"category_scores_gemma":[0.007309214,0.00005018911,0.000033431395,0.00012477112,0.000034168308,0.000073746996,0.000002745749,0.00008598817,2.4407626e-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":[0.00017666313,0.00023475979,0.2071185,0.0027751902,0.000101970705,0.000011661203,0.021837326,0.030492615,0.000104459985,0.67923045,0.046011552,0.011904879],"study_design_scores_gemma":[0.0010601892,0.0002895741,0.06572643,0.000655842,0.00009430822,0.00004311409,0.0007121268,0.06910448,0.0004511413,0.8613054,0.00037163042,0.0001857407],"about_ca_topic_score_codex":0.0015771982,"about_ca_topic_score_gemma":0.0145195965,"teacher_disagreement_score":0.6835055,"about_ca_system_score_codex":0.000033086137,"about_ca_system_score_gemma":0.00024814974,"threshold_uncertainty_score":0.875034},"labels":[],"label_agreement":null},{"id":"W2165564908","doi":"10.1016/j.jmva.2007.08.005","title":"Confidence intervals for marginal parameters under fractional linear regression imputation for missing data","year":2007,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Health Information; Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Mathematics; Statistics; Confidence interval; Missing data; Imputation (statistics); Estimator; Quantile; Linear regression; Sample size determination; Asymptotic distribution; Empirical likelihood","score_opus":0.27899504807781234,"score_gpt":0.49122350565029355,"score_spread":0.2122284575724812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165564908","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":[0.025466109,0.000038616028,0.97360307,0.0005061772,0.0001413746,0.00016195224,0.000045285953,0.0000275335,0.000009894011],"genre_scores_gemma":[0.3652187,0.000007138767,0.6344638,0.000058154455,0.000120616125,0.000002562692,0.0000764911,0.000012830737,0.000039736507],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829084,0.00009650558,0.0009166892,0.00019622523,0.0003203429,0.00017937721],"domain_scores_gemma":[0.9922902,0.0051818327,0.001331083,0.0002850838,0.00082479184,0.00008700295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063062757,0.00013286667,0.0004325719,0.0005056121,0.00014272728,0.00006650383,0.00028841026,0.000105536856,0.000021121892],"category_scores_gemma":[0.004678964,0.000102748694,0.0003394573,0.00032625312,0.000028212213,0.00041769983,0.0000353135,0.00015077963,5.9478793e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025494022,0.005678051,0.016310433,0.0027115268,0.055892117,0.00013536969,0.008865993,0.19564457,0.08626926,0.06735052,0.05087956,0.48476857],"study_design_scores_gemma":[0.001546945,0.00024907957,0.0041684215,0.0003760666,0.0034764549,0.00004192742,0.00045114075,0.74990696,0.009831808,0.22900538,0.0006491371,0.00029670584],"about_ca_topic_score_codex":0.00005544761,"about_ca_topic_score_gemma":0.000018522924,"teacher_disagreement_score":0.55426234,"about_ca_system_score_codex":0.00008711018,"about_ca_system_score_gemma":0.000069960515,"threshold_uncertainty_score":0.5601495},"labels":[],"label_agreement":null},{"id":"W2170140228","doi":"10.5539/mas.v6n11p20","title":"Murthy’s Estimator in Unequal Probability Inverse Adaptive Cluster Sampling","year":2012,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Faculty of Science, Silpakorn University; Silpakorn University","keywords":"Statistics; Cluster sampling; Mathematics; Estimator; Sampling (signal processing); Probability sampling; Inverse; Bias of an estimator; Poisson sampling; Minimum-variance unbiased estimator; Population; Cluster (spacecraft); Importance sampling; Slice sampling; Monte Carlo method; Computer science","score_opus":0.21962709087410662,"score_gpt":0.3729644768379233,"score_spread":0.15333738596381666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170140228","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":[0.36486953,0.0000065746403,0.63192296,0.000033524822,0.00007621506,0.0003889599,0.0000035972637,0.00022828997,0.002470359],"genre_scores_gemma":[0.65473527,3.5939323e-7,0.34507465,0.000060714763,0.000024264122,0.00007900456,0.0000011474178,0.0000119067,0.000012682726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99809957,0.000050746374,0.00036268425,0.0004031756,0.0004882686,0.0005955454],"domain_scores_gemma":[0.9986982,0.00046210858,0.00012359011,0.0004574029,0.00008387793,0.00017487149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043672533,0.00017639855,0.00022830372,0.00019418371,0.00022331014,0.000060649374,0.00037416798,0.000084645166,0.000019579791],"category_scores_gemma":[0.00081234175,0.00016071588,0.000034022865,0.00056078663,0.00040506347,0.00042301364,0.0001842687,0.00021903009,0.000045422206],"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":[0.0006915128,0.0029117113,0.045531496,0.0005376388,0.000034091852,0.0000031336494,0.06450278,0.014229186,0.12193239,0.66859615,0.0013733379,0.079656556],"study_design_scores_gemma":[0.00040208775,0.000027525666,0.0062772785,0.00005633636,0.000009202677,0.0000034325474,0.0003384947,0.41818705,0.008151622,0.566077,0.00004825077,0.00042174628],"about_ca_topic_score_codex":0.000045050732,"about_ca_topic_score_gemma":0.000044186036,"teacher_disagreement_score":0.40395784,"about_ca_system_score_codex":0.00024511374,"about_ca_system_score_gemma":0.00013414209,"threshold_uncertainty_score":0.6553803},"labels":[],"label_agreement":null},{"id":"W2187434310","doi":"10.1002/cjs.11266","title":"Edgeworth expansions for two‐stage sampling with applications to stratified and cluster sampling","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"Vetenskapsrådet","keywords":"Cluster sampling; Stratified sampling; Statistics; Studentized range; Sampling (signal processing); Sampling design; Multistage sampling; Mathematics; Term (time); Sample (material); Confidence interval; Population; Cluster (spacecraft); Sample size determination; Econometrics; Demography; Standard error; Computer science; Sociology","score_opus":0.22635430402938014,"score_gpt":0.38693827107591844,"score_spread":0.1605839670465383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187434310","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":[0.011487861,0.000045474735,0.9869421,0.0002439126,0.000078655125,0.00041398924,0.0006492534,0.000019445768,0.0001192997],"genre_scores_gemma":[0.13348037,0.000002206389,0.8660475,0.00015358024,0.00011130987,0.000033675864,0.000023065077,0.000028887884,0.00011940708],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990546,0.000030351302,0.0004113718,0.00012196054,0.00014677284,0.00023495927],"domain_scores_gemma":[0.99701566,0.00094946724,0.00022614919,0.00016698493,0.00079785334,0.0008439113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080473605,0.00012349861,0.00022936304,0.00024537687,0.0001889111,0.000121563105,0.00012614134,0.000045822795,0.000009907369],"category_scores_gemma":[0.0013191517,0.000108803215,0.000021990803,0.00012509206,0.00005875521,0.00008530769,0.000008354188,0.00014418257,0.0000015048961],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042315677,0.00016494624,0.011218383,0.0008004539,0.00039885554,0.00006194511,0.017784774,0.016593581,0.00031505988,0.7565573,0.089333184,0.10634839],"study_design_scores_gemma":[0.0047266823,0.001989455,0.0030898782,0.0010777039,0.00053216855,0.0005057293,0.007542347,0.0069822003,0.0007253412,0.8503376,0.120938115,0.0015527263],"about_ca_topic_score_codex":0.0005873951,"about_ca_topic_score_gemma":0.019795584,"teacher_disagreement_score":0.12199251,"about_ca_system_score_codex":0.000100106896,"about_ca_system_score_gemma":0.00095400587,"threshold_uncertainty_score":0.99809057},"labels":[],"label_agreement":null},{"id":"W2188992153","doi":"","title":"Simulation-based randomized systematic PPS sampling under substitution of units","year":2008,"lang":"en","type":"article","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Substitution (logic); Computer science; Sampling (signal processing); Econometrics; Statistics; Mathematics; Filter (signal processing)","score_opus":0.2725552137362245,"score_gpt":0.3808668996483965,"score_spread":0.108311685912172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188992153","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":[0.11395414,0.000047553465,0.8843165,0.000019233494,0.000054209253,0.00071810884,0.0000029930534,0.0003820731,0.000505179],"genre_scores_gemma":[0.9075334,0.0000033347283,0.09220254,0.000035521854,0.000012886945,0.000049256534,0.000015774502,0.000015296615,0.0001319964],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837685,0.0003278929,0.00075860496,0.0001298827,0.00028382707,0.00012295808],"domain_scores_gemma":[0.9832842,0.015568024,0.00033192104,0.0002932581,0.00048347298,0.000039124574],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0017813955,0.00013332558,0.0006601536,0.00017007391,0.00012133916,0.000011240027,0.000097302654,0.00008763445,0.00006827101],"category_scores_gemma":[0.01134331,0.000101463804,0.000112763715,0.00033685096,0.00012132124,0.0000808661,0.000009992449,0.000066036606,0.000011420074],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023614715,0.00022928644,0.0003798417,0.012374971,0.0001718008,0.0000018095545,0.0007186987,0.7636365,0.00025935506,0.21975018,0.00008399626,0.00003203979],"study_design_scores_gemma":[0.022261674,0.000025212606,0.00006091055,0.002491748,0.00016078433,0.0000038509797,0.00010045706,0.89039963,0.0065592094,0.07766095,0.0000035048656,0.00027205326],"about_ca_topic_score_codex":0.000045592038,"about_ca_topic_score_gemma":0.000004347838,"teacher_disagreement_score":0.7935793,"about_ca_system_score_codex":0.000039489423,"about_ca_system_score_gemma":0.00009661162,"threshold_uncertainty_score":0.99698454},"labels":[],"label_agreement":null},{"id":"W2189585271","doi":"","title":"Conservative variance estimation for sampling designs with zero pairwise inclusion probabilities","year":2012,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Pairwise comparison; Statistics; Mathematics; Variance (accounting); Standard error; Zero (linguistics); Population variance; Sampling (signal processing); Bias of an estimator; Econometrics; Minimum-variance unbiased estimator; Computer science","score_opus":0.6908408875368,"score_gpt":0.4942956986946006,"score_spread":0.19654518884219935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189585271","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12349749,0.00006596881,0.8748333,0.00011089952,0.00019921082,0.0008279035,0.000073346855,0.00032086912,0.00007101246],"genre_scores_gemma":[0.25415978,0.0000025219433,0.7451828,0.00009450139,0.000041532112,0.00027960463,0.00010456654,0.000036979447,0.000097714095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935906,0.0050026556,0.00046610885,0.00029754397,0.00018171786,0.00046137537],"domain_scores_gemma":[0.9486688,0.050080232,0.00031984158,0.00035611822,0.0004830523,0.00009200418],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.028883988,0.00023425663,0.00049990223,0.00012123385,0.0004151572,0.000021600288,0.00017936615,0.00019887002,0.000026612233],"category_scores_gemma":[0.03830421,0.0001919331,0.000059067053,0.0002515528,0.00017177925,0.00026896005,0.00014320127,0.00015950129,0.000004162281],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007405387,0.0017326772,0.20982057,0.0030218826,0.00074979255,0.0000025089835,0.05325132,0.0036552567,0.0055784583,0.6061436,0.009609051,0.09902951],"study_design_scores_gemma":[0.0007101329,0.00044210514,0.042364556,0.00012940285,0.00007319721,0.000021774107,0.00017673688,0.0044486783,0.010109881,0.9406498,0.00038556926,0.00048814696],"about_ca_topic_score_codex":0.00041542493,"about_ca_topic_score_gemma":0.00016500309,"teacher_disagreement_score":0.33450624,"about_ca_system_score_codex":0.0000904491,"about_ca_system_score_gemma":0.00010741819,"threshold_uncertainty_score":0.9999683},"labels":[],"label_agreement":null},{"id":"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":"W2199713456","doi":"10.22099/ijsts.2010.2185","title":"TWO-PHASE SAMPLE SIZE ESTIMATION WITH PRE-ASSIGNED VARIANCE UNDER NORMALITY ASSUMPTION","year":2010,"lang":"en","type":"article","venue":"Qatar University QSpace (Qatar University)","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":"Carleton University","funders":"","keywords":"Mathematics; Statistics; Estimator; Population mean; Bias of an estimator; Minimum-variance unbiased estimator; Sample size determination; Variance (accounting); Sample (material); Population; Normality; U-statistic; Poisson sampling; Simple random sample; Population variance; Importance sampling; Slice sampling; Monte Carlo method","score_opus":0.0325923328480465,"score_gpt":0.29394903796419425,"score_spread":0.2613567051161477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2199713456","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":[0.3858321,0.0000018034639,0.6096488,0.0005492276,0.00012398005,0.0003988037,0.00024841807,0.0007560327,0.0024407706],"genre_scores_gemma":[0.6021553,0.000013733147,0.39378783,0.00004290786,0.000042693202,4.1861375e-7,0.0001479817,0.000033520566,0.0037755887],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808764,0.00027285222,0.00018748848,0.0005974376,0.00042141715,0.0004331425],"domain_scores_gemma":[0.9966336,0.0015754647,0.00033979147,0.00085238146,0.0003381108,0.00026065466],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061490154,0.0003449201,0.00036877676,0.00039490877,0.00068772264,0.00007620033,0.000601323,0.00024934125,0.00042953162],"category_scores_gemma":[0.00062549976,0.00039470682,0.0001180663,0.00088130817,0.00027059834,0.0013255969,0.0001843716,0.0005495574,0.000037973092],"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":[0.009088155,0.0050495802,0.028344233,0.00089918496,0.001344571,0.00084429473,0.006365648,0.009390045,0.014961939,0.89170915,0.015238346,0.01676484],"study_design_scores_gemma":[0.09145472,0.005813841,0.12430485,0.001737814,0.0065602097,0.00036865886,0.030365052,0.18326065,0.039891314,0.223269,0.27769157,0.015282296],"about_ca_topic_score_codex":0.0034503962,"about_ca_topic_score_gemma":0.00476575,"teacher_disagreement_score":0.66844016,"about_ca_system_score_codex":0.00034974885,"about_ca_system_score_gemma":0.00023389015,"threshold_uncertainty_score":0.9998505},"labels":[],"label_agreement":null},{"id":"W2204079748","doi":"10.1111/sjos.12198","title":"Doubly Robust Inference for the Distribution Function in the Presence of Missing Survey Data","year":2015,"lang":"en","type":"article","venue":"Scandinavian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":10,"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":"Agence Nationale de la Recherche","keywords":"Imputation (statistics); Missing data; Estimator; Mathematics; Statistics; Inference; Robustness (evolution); Econometrics; Computer science; Artificial intelligence","score_opus":0.42826035656898226,"score_gpt":0.42774654250774347,"score_spread":0.0005138140612387931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2204079748","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":[0.005293817,0.00011164217,0.99267685,0.00015566776,0.00021334623,0.00017386708,0.0013522338,0.000006116177,0.000016455162],"genre_scores_gemma":[0.90114516,0.000018815248,0.09853517,0.000011478075,0.000059341426,0.0000032414457,0.0002090872,0.0000075382686,0.000010181993],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99863315,0.00031059267,0.000517771,0.0000801646,0.00033940715,0.00011892969],"domain_scores_gemma":[0.99161255,0.0067326683,0.0005789707,0.00034354714,0.00068922434,0.00004302519],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0075692195,0.0000790267,0.00018252987,0.000043812895,0.00008027454,0.00006495386,0.00051785546,0.00003883272,0.000004038138],"category_scores_gemma":[0.015838733,0.0000456657,0.000021163918,0.00019994765,0.00009478812,0.00017556644,0.000038789258,0.00017507364,3.0431087e-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":[0.0029817563,0.000888406,0.22064511,0.0007798672,0.0002800237,0.000032303124,0.008862609,0.00826239,0.0000633805,0.060737066,0.5156837,0.18078335],"study_design_scores_gemma":[0.002037462,0.001145446,0.27095544,0.0009932156,0.0003116051,0.00012855558,0.002344039,0.10270718,0.000198038,0.6177441,0.0011179743,0.0003169488],"about_ca_topic_score_codex":0.00018695282,"about_ca_topic_score_gemma":0.00013380559,"teacher_disagreement_score":0.8958513,"about_ca_system_score_codex":0.000042756044,"about_ca_system_score_gemma":0.00014659896,"threshold_uncertainty_score":0.99245125},"labels":[],"label_agreement":null},{"id":"W2212232216","doi":"10.1002/jwmg.1013","title":"Survival of female mallards along the Vermont–Quebec border region","year":2015,"lang":"en","type":"article","venue":"Journal of Wildlife Management","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":1,"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":"Waterfowl; Hunting season; Geography; Anas; Seasonal breeder; Hatching; Demography; Biology; Animal science; Ecology; Habitat; Population","score_opus":0.13748769695055185,"score_gpt":0.3654250821871739,"score_spread":0.22793738523662205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2212232216","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":[0.581611,0.00044196745,0.38960326,0.009261963,0.0013718056,0.0006291904,0.0000039861584,0.00012946343,0.0169474],"genre_scores_gemma":[0.965485,0.00015699044,0.03080269,0.00046989307,0.00026213485,0.0000071508193,0.0000017152973,0.00003268312,0.002781759],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830407,0.00017885854,0.00064338726,0.00008687713,0.00064285955,0.00014394126],"domain_scores_gemma":[0.99832773,0.00023567867,0.0006713862,0.0003287216,0.00036047795,0.00007599276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00300614,0.000117860065,0.0002832563,0.00013873387,0.000049251543,0.000038536884,0.00034197,0.000047054662,0.000016401842],"category_scores_gemma":[0.00043261168,0.000077961166,0.00013197483,0.00017483853,0.000053389536,0.00013370812,0.00010077504,0.00014579944,0.000003680936],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00055051857,0.0008762387,0.051654898,0.00073502545,0.0011705137,0.00025679442,0.0046385354,0.0012750175,0.000014873658,0.07268797,0.80695575,0.05918387],"study_design_scores_gemma":[0.007845669,0.0016917292,0.16247733,0.0026765876,0.0016450272,0.00044864853,0.01766775,0.0016863608,0.0011704158,0.24665034,0.5546438,0.0013963326],"about_ca_topic_score_codex":0.00025347027,"about_ca_topic_score_gemma":0.00012130895,"teacher_disagreement_score":0.383874,"about_ca_system_score_codex":0.00009199758,"about_ca_system_score_gemma":0.000056586578,"threshold_uncertainty_score":0.31791642},"labels":[],"label_agreement":null},{"id":"W2228863754","doi":"10.1080/02664763.2015.1094454","title":"Exact confidence intervals for randomized response strategies","year":2015,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":9,"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":"University of Saskatchewan","keywords":"Exact statistics; Confidence interval; Statistics; Randomized response; Test statistic; Coverage probability; Statistical hypothesis testing; Confidence distribution; Mathematics; CDF-based nonparametric confidence interval; Likelihood-ratio test; p-value; Statistic; Test (biology); Inference; Computer science; Artificial intelligence","score_opus":0.14001051688027102,"score_gpt":0.41346491575438765,"score_spread":0.2734543988741166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2228863754","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":[0.008464328,0.000033060634,0.9897316,0.00008777877,0.00018641393,0.00037568336,0.00006578889,0.00004534248,0.001010005],"genre_scores_gemma":[0.32590693,0.000012841733,0.6738443,0.000043994005,0.00007230019,0.000022767008,0.0000035441103,0.000018437298,0.00007493151],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99837095,0.00020847301,0.000869785,0.00008347651,0.00032395552,0.00014337264],"domain_scores_gemma":[0.9878076,0.010278399,0.0008575267,0.00014638768,0.0007929803,0.00011711346],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008893905,0.00012818379,0.0006261105,0.00012623791,0.00004061293,0.00010419505,0.00018066469,0.00006612363,0.000020216594],"category_scores_gemma":[0.009905287,0.0000985028,0.00009413867,0.00006447177,0.00010844158,0.00010012079,0.000017323278,0.00015201756,0.000004089178],"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":[0.142824,0.000093751376,0.0000022732468,0.00012192213,0.00013665411,0.000011936991,0.003184122,0.00019745427,0.00049735914,0.777411,0.073131055,0.0023885],"study_design_scores_gemma":[0.022250174,0.00022370226,0.000006956566,0.00006910215,0.00009597602,0.000026334565,0.0012440704,0.0014910139,0.0017410957,0.9719862,0.000750377,0.00011499839],"about_ca_topic_score_codex":0.000004163296,"about_ca_topic_score_gemma":0.0000021037301,"teacher_disagreement_score":0.3174426,"about_ca_system_score_codex":0.000058094058,"about_ca_system_score_gemma":0.00034050582,"threshold_uncertainty_score":0.9984347},"labels":[],"label_agreement":null},{"id":"W2276203798","doi":"","title":"Design effects for the weighted mean and total estimators under complex survey sampling","year":2006,"lang":"en","type":"article","venue":"Quality Engineering","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Estimator; Statistics; Sampling (signal processing); Weighted arithmetic mean; Mathematics; Survey research; Sampling design; Econometrics; Computer science; Psychology; Demography; Telecommunications; Sociology; Applied psychology","score_opus":0.24238952622116794,"score_gpt":0.39020836300012235,"score_spread":0.1478188367789544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2276203798","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":[0.1738979,0.00007234204,0.82508093,0.000046848316,0.00008519588,0.00038299404,0.000013848073,0.0004123769,0.0000075641897],"genre_scores_gemma":[0.6470011,0.0000014628173,0.352812,0.000015452772,0.000044785087,0.000053265634,0.000024953177,0.00003012282,0.000016866665],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989974,0.00014397145,0.0003139619,0.00017801978,0.00014244334,0.00022424114],"domain_scores_gemma":[0.9861484,0.013442877,0.00007701176,0.00022379462,0.00006931799,0.000038608126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028526732,0.00016651781,0.00024117355,0.000054533957,0.00015139455,0.00007523859,0.00009369233,0.000070536924,0.0000037136276],"category_scores_gemma":[0.0009995472,0.00013218274,0.000047336973,0.000119894336,0.000028255741,0.000058768535,0.00002712729,0.00009754262,0.0000011331756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031152897,0.00051466486,0.009325238,0.005140475,0.0007475454,0.0000036563601,0.002491577,0.5050279,0.027309788,0.4220442,0.009339706,0.017743772],"study_design_scores_gemma":[0.00060403143,0.000057006087,0.14721563,0.00012017465,0.000059421644,0.000009761214,0.00003573785,0.79298264,0.006530828,0.05178824,0.00008673141,0.00050979],"about_ca_topic_score_codex":0.00036427917,"about_ca_topic_score_gemma":0.000030921445,"teacher_disagreement_score":0.4731032,"about_ca_system_score_codex":0.000037790564,"about_ca_system_score_gemma":0.000011805902,"threshold_uncertainty_score":0.53902555},"labels":[],"label_agreement":null},{"id":"W2295376133","doi":"10.2501/jar-2015-006","title":"Accounting for Social-Desirability Bias in Survey Sampling","year":2015,"lang":"en","type":"article","venue":"Journal of Advertising Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Advantage Forensics (Canada)","funders":"","keywords":"Social desirability; Accounting; Sampling (signal processing); Social desirability bias; Survey research; Business; Reporting bias; Marketing; Psychology; Social psychology; Political science; MEDLINE; Computer science; Business administration; Telecommunications","score_opus":0.8263005776308638,"score_gpt":0.5848368616876762,"score_spread":0.2414637159431876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295376133","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":[0.9236098,0.000083666746,0.075443864,0.0003118742,0.00013083025,0.00021706632,0.000006071795,0.000030923067,0.00016593558],"genre_scores_gemma":[0.9137856,0.0000065433296,0.08594173,0.000011671622,0.00017929178,0.000005380376,0.0000024295596,0.000025183008,0.000042208885],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99629915,0.000973399,0.0012763246,0.00014964824,0.0009004004,0.00040110925],"domain_scores_gemma":[0.98653173,0.009466498,0.0007211439,0.00016758959,0.0030019388,0.00011111178],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.0784379,0.00009893085,0.00040623118,0.0005257816,0.00017983433,0.00013271437,0.0003024221,0.00012147195,0.0000054096004],"category_scores_gemma":[0.12703834,0.00008618097,0.00010846561,0.0006119648,0.00008633058,0.00030036067,0.0000683528,0.00060083246,0.0000021228848],"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":[0.0016232828,0.0008486798,0.883852,0.0007376543,0.00009239181,0.000019897794,0.008312438,0.00035931848,0.0022205077,0.0022072063,0.028333269,0.07139338],"study_design_scores_gemma":[0.0019828528,0.00042845323,0.41481057,0.0008253676,0.000014731339,0.000041163188,0.0016941904,0.0022469522,0.004230944,0.57266927,0.0007457055,0.00030981298],"about_ca_topic_score_codex":0.00029523516,"about_ca_topic_score_gemma":0.0001518639,"teacher_disagreement_score":0.57046205,"about_ca_system_score_codex":0.00044160502,"about_ca_system_score_gemma":0.0004476677,"threshold_uncertainty_score":0.9489421},"labels":[],"label_agreement":null},{"id":"W2297613290","doi":"10.71781/15242","title":"Inférence doublement robuste en présence de données imputées dans les enquêtes","year":2010,"lang":"fr","type":"dissertation","venue":"Open MIND","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","keywords":"Geography; Humanities; Art","score_opus":0.10833521118519138,"score_gpt":0.38957479041219906,"score_spread":0.2812395792270077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2297613290","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":[0.91998506,0.00022117364,0.058808856,0.00029099846,0.001297168,0.001966433,0.00020645512,0.000042353764,0.017181491],"genre_scores_gemma":[0.2055649,0.00028183512,0.7745474,0.000021332382,0.00024663063,0.00040148816,0.00097487215,0.00009839574,0.017863149],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99700403,0.0003255342,0.00095755426,0.0007067731,0.00043557354,0.0005705374],"domain_scores_gemma":[0.9963564,0.0015260176,0.0007998504,0.00075994665,0.00037148746,0.00018626732],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002404057,0.00058173545,0.0006467343,0.00017431512,0.00051702134,0.00085351476,0.0016171136,0.0008398827,0.003682772],"category_scores_gemma":[0.0013642516,0.0005761416,0.00015291599,0.00023488034,0.00016076528,0.0004447935,0.00030931685,0.0008929796,0.00033483293],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029242306,0.0012144203,0.028645717,0.0021437057,0.00042668873,0.000056723384,0.17892638,0.0012287778,0.059289373,0.0051337103,0.0035422903,0.7190998],"study_design_scores_gemma":[0.001097364,0.00046674017,0.011966843,0.0068672956,0.0007049536,0.00009133619,0.023777282,0.014233234,0.8748873,0.014088986,0.049409483,0.0024092179],"about_ca_topic_score_codex":0.0046389825,"about_ca_topic_score_gemma":0.013455655,"teacher_disagreement_score":0.8155979,"about_ca_system_score_codex":0.00017132045,"about_ca_system_score_gemma":0.00062305125,"threshold_uncertainty_score":0.999669},"labels":[],"label_agreement":null},{"id":"W2342002759","doi":"10.5539/ijsp.v5n3p55","title":"Use of Auxiliary Variables and Asymptotically Optimum Estimators in Double Sampling","year":2016,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Mathematics; Efficiency; Mean squared error; Extremum estimator; Statistics; Variable (mathematics); Population; Sampling (signal processing); Applied mathematics; Sample size determination; Efficient estimator; Asymptotically optimal algorithm; M-estimator; Mathematical optimization; Minimum-variance unbiased estimator; Computer science; Mathematical analysis","score_opus":0.12438493973769305,"score_gpt":0.36809434378673567,"score_spread":0.24370940404904262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342002759","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":[0.46314353,0.000017890628,0.536307,0.00023435455,0.00009570046,0.00006603361,0.00010330447,0.0000074185514,0.000024792862],"genre_scores_gemma":[0.4848367,0.00006249199,0.5150609,0.000009044547,0.000015260719,0.0000012574272,0.0000012810809,0.000004830528,0.0000082353345],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988583,0.000059033217,0.0006366557,0.00010608758,0.00025440138,0.00008556081],"domain_scores_gemma":[0.9961126,0.0028107623,0.0003221948,0.00008226112,0.00061386335,0.00005832279],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013351021,0.00008394254,0.00021839842,0.00011637383,0.000018110146,0.000043946602,0.00010512379,0.000052009018,0.000024289939],"category_scores_gemma":[0.0031531313,0.000057781348,0.00002316554,0.00004092671,0.00013432666,0.00020625514,0.000055127166,0.00008976917,1.7432352e-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":[0.00078781944,0.00042710625,0.26098856,0.00025233784,0.00016711644,0.000020620353,0.00042382334,0.00029185222,0.0012011471,0.668139,0.00038853558,0.06691211],"study_design_scores_gemma":[0.00072053797,0.00011144567,0.04264498,0.00042797418,0.000020388337,0.00004455686,0.000008625645,0.0017553639,0.00067160866,0.9533675,0.00013133649,0.00009572554],"about_ca_topic_score_codex":0.000056592224,"about_ca_topic_score_gemma":0.000016693628,"teacher_disagreement_score":0.2852285,"about_ca_system_score_codex":0.000046460867,"about_ca_system_score_gemma":0.00007066441,"threshold_uncertainty_score":0.37748206},"labels":[],"label_agreement":null},{"id":"W2380336261","doi":"10.1111/sjos.12226","title":"Robust Inference in Two‐phase Sampling Designs with Application to Unit Nonresponse","year":2016,"lang":"en","type":"article","venue":"Scandinavian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","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":"Statistics Canada; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Mathematics; Statistics; Sampling (signal processing); Constant (computer programming); Inference; Sample (material); Econometrics; Robust statistics; Calibration; Set (abstract data type); Computer science; Artificial intelligence","score_opus":0.23253206881293637,"score_gpt":0.4396689738413207,"score_spread":0.20713690502838433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2380336261","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":[0.13504125,0.0000070871347,0.8644659,0.00012621292,0.000035094916,0.00016595829,0.00010117453,0.000025846703,0.000031470514],"genre_scores_gemma":[0.5465122,0.000008614648,0.4533775,0.000018681378,0.000026502632,0.0000075212984,0.0000023041268,0.000014974717,0.00003175089],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986512,0.0001551172,0.0005638568,0.0001321185,0.00028296828,0.00021473602],"domain_scores_gemma":[0.9957009,0.0030716523,0.00040802243,0.00020455383,0.0004424912,0.00017240981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014840108,0.00014154511,0.00027424467,0.00035182032,0.000060193255,0.000041335472,0.00020095079,0.000035927507,0.000042515905],"category_scores_gemma":[0.00289795,0.000094507865,0.000022833,0.00033094903,0.000057756097,0.00013839161,0.000019415462,0.0001477644,0.000010218107],"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":[0.0091933785,0.001783782,0.17155747,0.00038275032,0.0002080002,0.00042702223,0.0064696786,0.008110163,0.023207929,0.14094268,0.0039442987,0.63377285],"study_design_scores_gemma":[0.018792318,0.0074981963,0.06038034,0.009811903,0.00032797284,0.000663305,0.0013515053,0.00648004,0.017243646,0.87411165,0.0012990981,0.0020400127],"about_ca_topic_score_codex":0.000027108881,"about_ca_topic_score_gemma":0.00010192732,"teacher_disagreement_score":0.73316896,"about_ca_system_score_codex":0.00012330597,"about_ca_system_score_gemma":0.00013685136,"threshold_uncertainty_score":0.3853919},"labels":[],"label_agreement":null},{"id":"W2496536496","doi":"10.1093/forestscience/48.3.569","title":"Polya Posterior Frequency Distributions for Stratified Double Sampling of Categorical Data","year":2002,"lang":"en","type":"article","venue":"Forest Science","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Mathematics; Categorical distribution; Statistics; Categorical variable; Dirichlet distribution; Multinomial distribution; Resampling; Sampling (signal processing); Sampling distribution; Posterior probability; Bayesian probability; Bayesian inference; Bayesian linear regression; Mathematical analysis; Computer science","score_opus":0.41288726790521013,"score_gpt":0.4316226193668395,"score_spread":0.018735351461629357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2496536496","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":[0.18879905,0.000028162134,0.8096767,0.00019213991,0.00013067745,0.0003165386,0.00033469306,0.00013837268,0.00038364652],"genre_scores_gemma":[0.83354145,0.000002116201,0.1662843,0.000006820644,0.000026348893,0.000022788632,0.000065577166,0.0000066169573,0.000043992834],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886113,0.000011082373,0.00031533794,0.00029357607,0.0002629932,0.00025586842],"domain_scores_gemma":[0.99846566,0.00037755258,0.00013551764,0.00074566435,0.00019905088,0.000076542456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009848335,0.00008841495,0.00014713,0.00008651862,0.00027865966,0.00007244382,0.0007939629,0.000043330332,0.00003937339],"category_scores_gemma":[0.0013997088,0.0000768461,0.000031960608,0.0004447005,0.0003014705,0.00039549405,0.00012621177,0.000063599946,0.0000065428526],"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":[0.000016921158,0.00022862526,0.0030247816,0.000093005685,0.000008140089,6.7895974e-7,0.00031944434,0.000053627085,0.008859458,0.9832759,0.0021123658,0.002007091],"study_design_scores_gemma":[0.0005328918,0.00019795196,0.0037794348,0.000078973724,0.00003663314,0.000024477245,0.00008110083,0.054833904,0.012108537,0.9278102,0.00019174514,0.00032416085],"about_ca_topic_score_codex":0.00014296974,"about_ca_topic_score_gemma":0.00006278519,"teacher_disagreement_score":0.64474237,"about_ca_system_score_codex":0.000039562612,"about_ca_system_score_gemma":0.000074001015,"threshold_uncertainty_score":0.31336933},"labels":[],"label_agreement":null},{"id":"W2578167321","doi":"10.1177/0008068316634977","title":"Revisiting Basu's Circus Example: Another Look at the Horvitz-Thompson Estimator","year":2016,"lang":"en","type":"article","venue":"Calcutta Statistical Association Bulletin","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":"Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Estimator; Minimum-variance unbiased estimator; Stein's unbiased risk estimate; Bias of an estimator; Mathematics; James–Stein estimator; Consistent estimator; Efficient estimator; Statistics; Invariant estimator; Econometrics","score_opus":0.061519331116248285,"score_gpt":0.3214329783579497,"score_spread":0.2599136472417014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2578167321","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":[0.0053349836,0.000074289586,0.963575,0.023737399,0.00023761812,0.00047393542,0.00048568324,0.0006494777,0.005431634],"genre_scores_gemma":[0.5658337,0.0000952503,0.33369815,0.0047239903,0.001694726,0.0005784664,0.00026248535,0.00041820723,0.09269501],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99704266,0.00062191795,0.0006685413,0.0004512777,0.00067960675,0.0005360222],"domain_scores_gemma":[0.98419243,0.0144323725,0.00049317087,0.00046765,0.00029356527,0.00012078594],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003043794,0.0002646349,0.00039451823,0.00005656703,0.00043544002,0.00011441764,0.00025216647,0.00021567444,0.008859017],"category_scores_gemma":[0.018319706,0.00016426561,0.00010456529,0.00015546636,0.000114423965,0.00005310077,0.00011984085,0.00020878128,0.0016286831],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046670964,0.00009261382,0.009664381,0.00008991445,0.00009791422,0.000011803154,0.00018825528,0.0000016828125,0.0011175165,0.11481788,0.81882435,0.055046994],"study_design_scores_gemma":[0.002095589,0.0001536747,0.02923936,0.0006729613,0.00029272604,0.000039005154,0.00013464542,0.0008771526,0.0057346066,0.14707473,0.81230634,0.0013791816],"about_ca_topic_score_codex":0.00006857194,"about_ca_topic_score_gemma":0.000008630942,"teacher_disagreement_score":0.6298768,"about_ca_system_score_codex":0.00080392364,"about_ca_system_score_gemma":0.000050258797,"threshold_uncertainty_score":0.99914867},"labels":[],"label_agreement":null},{"id":"W2607179242","doi":"10.1017/pan.2017.8","title":"The Statistical Analysis of Misreporting on Sensitive Survey Questions","year":2017,"lang":"en","type":"article","venue":"Political Analysis","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Context (archaeology); Variety (cybernetics); Prejudice (legal term); Computer science; Survey data collection; Ideology; Multivariate statistics; Scale (ratio); Social psychology; Psychology; Econometrics; Statistics; Political science; Artificial intelligence; Mathematics; Law; Machine learning","score_opus":0.17872944379696518,"score_gpt":0.4678313315530983,"score_spread":0.2891018877561331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607179242","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":[0.4838129,0.0000061455294,0.50644433,0.0010555203,0.000050954404,0.00012021111,0.0007325468,0.00013612366,0.007641261],"genre_scores_gemma":[0.9918908,0.0000026081873,0.0077417195,0.00004043418,0.0000224359,0.00000831799,0.000092242764,0.000009176497,0.00019228888],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9979013,0.0004700862,0.0006508237,0.00024839383,0.00038225265,0.00034710564],"domain_scores_gemma":[0.98729426,0.010634142,0.00045314935,0.0010055688,0.0004582285,0.0001546522],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031535397,0.00013080135,0.0005907174,0.00032454083,0.00069068256,0.00013816307,0.0002423328,0.0000699776,0.0000536216],"category_scores_gemma":[0.037367377,0.00008923789,0.00038728464,0.0006443645,0.00038450095,0.000041790914,0.00006422396,0.00014508925,0.000007598313],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020910127,0.000109369445,0.20531425,0.000007857054,0.0061967713,0.0000057289126,0.000050302,0.00009806174,0.000007810782,0.7871761,0.00016151748,0.00085136766],"study_design_scores_gemma":[0.00004017401,0.00002353017,0.8759353,0.000009388193,0.007186271,5.1589507e-7,0.000054441436,0.033526078,0.00045630132,0.08264272,0.0000119666975,0.00011327518],"about_ca_topic_score_codex":0.006992076,"about_ca_topic_score_gemma":0.0033429812,"teacher_disagreement_score":0.70453334,"about_ca_system_score_codex":0.000051312447,"about_ca_system_score_gemma":0.00003644843,"threshold_uncertainty_score":0.99962044},"labels":[],"label_agreement":null},{"id":"W2612643943","doi":"","title":"Some contributions to jackknifing two-phase sampling estimators","year":2010,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Statistics; Mathematics; Sampling (signal processing); Econometrics; Computer science","score_opus":0.4680701557935121,"score_gpt":0.5642361375453836,"score_spread":0.09616598175187152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2612643943","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38789624,0.00001545979,0.60984015,0.00022532606,0.0009712826,0.0002509817,0.0002409244,0.0004823824,0.00007725915],"genre_scores_gemma":[0.2453654,0.000002042299,0.75384897,0.00022333204,0.00026262956,0.00007245092,0.00010769626,0.00004520011,0.000072291754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949763,0.0031288043,0.0006529075,0.0004701948,0.0002001463,0.0005716886],"domain_scores_gemma":[0.9706113,0.027713457,0.00020760324,0.00068762933,0.0005150047,0.00026500452],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02572515,0.00026110167,0.0006176886,0.00032993636,0.00028631667,0.000058491674,0.00036022632,0.0002621946,0.00015646828],"category_scores_gemma":[0.11266426,0.00025704736,0.00011243788,0.00044144876,0.00012602775,0.0001361381,0.00012875856,0.0006190824,0.00012107818],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005485725,0.0007492684,0.013308451,0.000110944624,0.00022731572,0.000019777834,0.0014848529,0.00026587004,0.2624787,0.66481906,0.009480405,0.046506763],"study_design_scores_gemma":[0.0016876397,0.00023056929,0.015013118,0.000044470467,0.000066109475,0.00007874656,0.000061292834,0.0009950942,0.07592414,0.9025037,0.0026099398,0.00078512594],"about_ca_topic_score_codex":0.0010254333,"about_ca_topic_score_gemma":0.0007695263,"teacher_disagreement_score":0.23768467,"about_ca_system_score_codex":0.0000500245,"about_ca_system_score_gemma":0.00012490869,"threshold_uncertainty_score":0.9999882},"labels":[],"label_agreement":null},{"id":"W2742915952","doi":"10.5539/ijsp.v6n5p101","title":"Improving Estimation Accuracy in Nonrandomized Response Questioning Methods by Multiple Answers","year":2017,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Randomized response; Respondent; Estimation; Computer science; Sample (material); Statistics; Econometrics; Mathematics; Estimator; Economics","score_opus":0.06701143131268104,"score_gpt":0.4387301240009815,"score_spread":0.37171869268830043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2742915952","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":[0.25950408,0.00003529598,0.73957396,0.0004073146,0.00023870326,0.00013134071,0.00007651443,0.000012958436,0.00001985136],"genre_scores_gemma":[0.4626991,0.000022100208,0.53722334,0.000011729249,0.000019375953,0.000004944135,0.000005355014,0.0000057935995,0.000008289653],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99823403,0.0005152272,0.00072627026,0.00013705624,0.00028153823,0.000105846586],"domain_scores_gemma":[0.99048746,0.0075419587,0.0010792761,0.00018578059,0.0006448391,0.000060717957],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008467669,0.00010886951,0.0002733066,0.000116046125,0.00014005044,0.00027207946,0.00029782634,0.000063468215,0.000015757605],"category_scores_gemma":[0.08685902,0.00009638217,0.000045001685,0.000024527833,0.00011368468,0.00040743363,0.000064952495,0.00021342679,3.7216083e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01243912,0.00060931296,0.046460796,0.00020091953,0.00019191862,0.00004462462,0.0018871729,0.00048102657,0.008947935,0.01316449,0.0016438458,0.91392887],"study_design_scores_gemma":[0.006106481,0.00020917381,0.04164143,0.00034965732,0.000044831486,0.00006842714,0.0000649269,0.14538652,0.0046858722,0.800909,0.00027559727,0.00025812312],"about_ca_topic_score_codex":0.0002748057,"about_ca_topic_score_gemma":0.000040335603,"teacher_disagreement_score":0.9136707,"about_ca_system_score_codex":0.000121468736,"about_ca_system_score_gemma":0.000096163276,"threshold_uncertainty_score":0.92083275},"labels":[],"label_agreement":null},{"id":"W2759870632","doi":"10.1093/biomet/asx007","title":"OUP accepted manuscript","year":2017,"lang":"en","type":"article","venue":"Biometrika","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Jackknife resampling; Imputation (statistics); Robustness (evolution); Estimator; Mathematics; Covariate; Missing data; Statistics; Simple random sample; Econometrics; Population; Medicine","score_opus":0.358109777955419,"score_gpt":0.45048046587162255,"score_spread":0.09237068791620356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759870632","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":[0.6911315,0.00028673478,0.164702,0.0017756134,0.002123744,0.00071118976,0.00008286113,0.0027402048,0.13644618],"genre_scores_gemma":[0.92179775,0.0000145826,0.07524982,0.000049821494,0.000104076375,0.000015741212,0.000007692578,0.000020566322,0.002739936],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99927807,0.00002571664,0.00018007965,0.00016071288,0.00018507763,0.00017036482],"domain_scores_gemma":[0.99866873,0.00019959224,0.00017901979,0.0008096413,0.00008189676,0.000061115294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006713538,0.000098881086,0.00015440083,0.00036378927,0.00032505416,0.00021053586,0.0004471335,0.000086960856,0.00039381848],"category_scores_gemma":[0.003613899,0.00008706934,0.0000624182,0.00021273743,0.00006509606,0.00015713769,0.00009834506,0.00006911591,0.00017694516],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005028961,0.00041522182,0.02442503,0.00019834563,0.00013223017,0.000022422382,0.00033042228,1.6154506e-7,0.008576501,0.0373375,0.36496466,0.5635472],"study_design_scores_gemma":[0.0016289793,0.00026276257,0.2514065,0.00020590976,0.00009086757,0.00002825008,0.00011939746,0.0005350619,0.20355777,0.3492999,0.19168144,0.0011831583],"about_ca_topic_score_codex":0.00007008482,"about_ca_topic_score_gemma":0.0000033625217,"teacher_disagreement_score":0.56236404,"about_ca_system_score_codex":0.000027440752,"about_ca_system_score_gemma":0.000012846715,"threshold_uncertainty_score":0.43264356},"labels":[],"label_agreement":null},{"id":"W2760577312","doi":"10.1002/cjs.11339","title":"Statistical inference using generalized linear mixed models under informative cluster sampling","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"National Science Foundation","keywords":"Cluster sampling; Statistics; Estimator; Statistical inference; Mathematics; Inference; Sampling distribution; Sampling (signal processing); Generalized linear mixed model; Population; Sample size determination; Generalized linear model; Computer science; Artificial intelligence","score_opus":0.35343284176033385,"score_gpt":0.4198353914725869,"score_spread":0.06640254971225307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760577312","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":[0.045553353,0.000020348021,0.95287097,0.000091642956,0.00035858268,0.00010014687,0.0007241627,0.0000150147325,0.0002657567],"genre_scores_gemma":[0.40117806,0.000009480646,0.59858954,0.00008654093,0.00007603866,9.680115e-7,0.000014319693,0.000019572153,0.000025491861],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984293,0.000098131124,0.0007586068,0.000101745834,0.0002692968,0.00034290043],"domain_scores_gemma":[0.9963899,0.001062894,0.0008682037,0.00033561734,0.0008295856,0.0005137737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009611218,0.00017932133,0.00038207852,0.00023145574,0.0005981665,0.00031414238,0.00039343926,0.00011298248,0.00009321925],"category_scores_gemma":[0.0044829478,0.00016656383,0.000050604398,0.000048100053,0.00023615749,0.00049751456,0.000033300486,0.00033945832,0.0000054761],"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":[0.00008539449,0.000044887707,0.0028486608,0.00024288791,0.00025593623,0.00013112785,0.0035464868,0.041262742,0.00004138166,0.9259695,0.014448795,0.011122223],"study_design_scores_gemma":[0.0005962309,0.000074255804,0.002005911,0.00022676714,0.000088809116,0.00008470144,0.00022971003,0.23258537,0.00010616788,0.7634416,0.00028793598,0.0002725299],"about_ca_topic_score_codex":0.0036352444,"about_ca_topic_score_gemma":0.00597576,"teacher_disagreement_score":0.3556247,"about_ca_system_score_codex":0.00021145043,"about_ca_system_score_gemma":0.0013041265,"threshold_uncertainty_score":0.67922753},"labels":[],"label_agreement":null},{"id":"W2792032639","doi":"10.1177/0049124117747302","title":"Optimizing Count Responses in Surveys: A Machine-learning Approach","year":2018,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; Social Science Research Institute, Duke University; University of British Columbia; University of Victoria","keywords":"Censoring (clinical trials); Count data; Poisson distribution; Computer science; Bayesian probability; Multinomial distribution; Machine learning; Statistics; Artificial intelligence; Mathematics","score_opus":0.6338353326777821,"score_gpt":0.602291176727981,"score_spread":0.03154415594980109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792032639","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":[0.19575998,0.0003434719,0.79350626,0.00023082449,0.0000624135,0.0004630191,0.000006438911,0.00048409708,0.00914351],"genre_scores_gemma":[0.29747367,0.000060406735,0.7017583,0.000028371454,0.00010914597,0.00013041636,0.000007948908,0.000024339937,0.00040737068],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.955602,0.042007882,0.0004989511,0.0005541374,0.0005520859,0.0007849384],"domain_scores_gemma":[0.9716456,0.027256982,0.00009520695,0.00038746858,0.00049443875,0.00012028948],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.12610207,0.00019043575,0.00046569746,0.00037454374,0.0005024675,0.000088796594,0.00048569744,0.00041304764,0.00020646631],"category_scores_gemma":[0.05589541,0.00014306883,0.00009891347,0.0008085016,0.00096951704,0.00008159902,0.00033174438,0.0017724081,0.000040223058],"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":[0.0023551988,0.003171595,0.1410369,0.00089714397,0.00031042125,0.00011024253,0.05720783,0.00020737234,0.031108595,0.20610315,0.004343772,0.5531478],"study_design_scores_gemma":[0.00076911156,0.0013090593,0.018691719,0.00014791159,0.000011174621,0.000020388588,0.003937999,0.043733716,0.0060923067,0.92147225,0.003159029,0.00065532705],"about_ca_topic_score_codex":0.00028107114,"about_ca_topic_score_gemma":0.000011587739,"teacher_disagreement_score":0.7153691,"about_ca_system_score_codex":0.00019163101,"about_ca_system_score_gemma":0.00009760294,"threshold_uncertainty_score":0.9520572},"labels":[],"label_agreement":null},{"id":"W2793196379","doi":"10.1177/0032885517753163","title":"Underreporting in HIV-Related High-Risk Behaviors: Comparing the Results of Multiple Data Collection Methods in a Behavioral Survey of Prisoners in Iran","year":2018,"lang":"en","type":"article","venue":"The Prison Journal","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Institute on Drug Abuse; National Institute of Mental Health","keywords":"Prison; Respondent; Proxy (statistics); Psychology; Data collection; Human immunodeficiency virus (HIV); Sexual behavior; Social psychology; Criminology; Statistics; Medicine; Mathematics; Family medicine; Political science","score_opus":0.39027020770892396,"score_gpt":0.4862011414550483,"score_spread":0.09593093374612433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793196379","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":[0.9572285,0.00003689741,0.04212325,0.00007249216,0.00013605587,0.0003142012,0.00002105757,0.00002759861,0.000039985258],"genre_scores_gemma":[0.9052153,0.00002180392,0.09468679,0.0000018651074,0.00001398104,0.000006370716,0.000023495055,0.000018430837,0.000011935916],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9944609,0.0028932553,0.0019159856,0.00020269853,0.00028768965,0.00023951266],"domain_scores_gemma":[0.994719,0.002623148,0.0018098861,0.0006532497,0.00016181561,0.00003286541],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.030606318,0.00013868733,0.00045074898,0.00033753962,0.00013808566,0.000033435943,0.00060061633,0.000114477756,0.000007760714],"category_scores_gemma":[0.0077747763,0.00009337728,0.00004361559,0.0010041464,0.00016826593,0.00016233398,0.0001831114,0.00081591384,5.360898e-7],"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":[0.0003196196,0.00034311434,0.9835234,0.000012167036,0.000016965061,0.0000025012819,0.009028842,0.00041935616,0.00069479167,0.000015947086,0.00022793762,0.0053953184],"study_design_scores_gemma":[0.001668494,0.00013163494,0.9317766,0.00034828298,0.00004428276,0.000031291453,0.0015118521,0.056511987,0.004250107,0.0036030465,0.0000035468954,0.00011887539],"about_ca_topic_score_codex":0.027254144,"about_ca_topic_score_gemma":0.025878457,"teacher_disagreement_score":0.05609263,"about_ca_system_score_codex":0.00012650562,"about_ca_system_score_gemma":0.00008959254,"threshold_uncertainty_score":0.9981948},"labels":[],"label_agreement":null},{"id":"W2811261010","doi":"10.5539/ijsp.v7n4p104","title":"On Comparison of Local Polynomial Regression Estimators for P=0 and P=1 in a Model Based Framework","year":2018,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Polynomial regression; Estimator; Mathematics; Minimum-variance unbiased estimator; Polynomial; Regression analysis; Applied mathematics; Population; Statistics; Linear regression; Regression; Mathematical analysis","score_opus":0.09162686261805891,"score_gpt":0.4286441812531887,"score_spread":0.3370173186351298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2811261010","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":[0.32243222,0.000010520543,0.67718726,0.000108810455,0.000081244616,0.000072294206,0.00009256505,0.0000036945899,0.000011396921],"genre_scores_gemma":[0.55215114,0.0000019548133,0.44780266,0.00001643981,0.000019825895,0.0000017771308,0.0000019742718,0.000003331878,8.9985156e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990949,0.00004317125,0.00049488834,0.000089080844,0.00021474116,0.00006322958],"domain_scores_gemma":[0.9970556,0.001964589,0.00035296858,0.00006494724,0.0005213916,0.000040516745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008594552,0.000072870076,0.00021288145,0.000102713835,0.000026272479,0.000019137946,0.00008905944,0.00006217683,0.0000072784483],"category_scores_gemma":[0.002400547,0.000057297748,0.000024524865,0.000029878283,0.00016843101,0.000041110212,0.000018905917,0.000118346434,7.216026e-8],"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":[0.0109875,0.0024421723,0.09863022,0.00088710926,0.00018008727,0.000008155017,0.0034066688,0.0091807,0.0003669727,0.6110381,0.010840869,0.25203148],"study_design_scores_gemma":[0.0003595072,0.0002821669,0.0020932737,0.00028328365,0.00000798929,0.0000023693808,0.000014737189,0.34542987,0.0011493361,0.650325,0.000010261388,0.00004219789],"about_ca_topic_score_codex":0.000011271528,"about_ca_topic_score_gemma":0.000017335227,"teacher_disagreement_score":0.33624917,"about_ca_system_score_codex":0.000043175653,"about_ca_system_score_gemma":0.000067743335,"threshold_uncertainty_score":0.28738526},"labels":[],"label_agreement":null},{"id":"W2900988085","doi":"10.1080/03610918.2018.1516290","title":"Calibration using power transformation","year":2018,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":9,"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":"Texas A and M University","keywords":"Estimator; Statistics; Calibration; Mathematics; Nonparametric statistics; Population; Computer science; Econometrics; Demography; Sociology","score_opus":0.3697412499577581,"score_gpt":0.5172665598279156,"score_spread":0.1475253098701575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900988085","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":[0.079198055,0.000027453996,0.91940933,0.00011055847,0.00006502215,0.00028643516,0.000040509898,0.00014698271,0.0007156739],"genre_scores_gemma":[0.65845543,0.000011014156,0.34130168,0.00004359295,0.000013368394,0.000009899938,0.00014608429,0.000012218061,0.000006693218],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987768,0.00024400088,0.0005363276,0.00015454926,0.00016475719,0.00012359538],"domain_scores_gemma":[0.9979355,0.0011706862,0.0001862032,0.00035229322,0.00031503345,0.00004032697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061496015,0.00011921696,0.00014561968,0.000252343,0.0003116902,0.0000898656,0.00013999137,0.00008426261,0.000026441247],"category_scores_gemma":[0.00042665884,0.0001340792,0.000016761034,0.00034495763,0.00016990471,0.00035004123,0.00004944437,0.0001195706,0.000004344783],"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":[0.00009694603,0.00041293236,0.0049320953,0.0001260013,0.00003806454,8.1753205e-7,0.016202554,0.083378226,0.00032564253,0.7971498,0.00053152133,0.096805416],"study_design_scores_gemma":[0.00025393371,0.0000400159,0.0024560278,0.000037555743,0.00001098334,0.0000019900226,0.00016929007,0.7877175,0.00005574338,0.20899531,0.00014744094,0.00011417583],"about_ca_topic_score_codex":0.00005730986,"about_ca_topic_score_gemma":0.00010152799,"teacher_disagreement_score":0.7043393,"about_ca_system_score_codex":0.00007518462,"about_ca_system_score_gemma":0.000038731174,"threshold_uncertainty_score":0.5467591},"labels":[],"label_agreement":null},{"id":"W2906823368","doi":"10.48550/arxiv.1812.10694","title":"Combining Non-probability and Probability Survey Samples Through Mass Imputation","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":10,"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 Waterloo","funders":"","keywords":"Imputation (statistics); Estimator; Statistics; Mathematics; Probability mass function; Probability sampling; Consistency (knowledge bases); Econometrics; Probability distribution; Missing data; Discrete mathematics; Population","score_opus":0.31925953690946884,"score_gpt":0.2879491935998081,"score_spread":0.03131034330966076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906823368","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":[0.5567784,0.0000073626857,0.44167578,0.00001371374,0.00014751064,0.00050122314,0.000102121965,0.00033672297,0.0004371615],"genre_scores_gemma":[0.9032117,0.00003909154,0.096376896,0.00001826808,0.000042704294,0.000004985263,0.0001833364,0.00003712009,0.000085878615],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971894,0.00073407526,0.00045416493,0.0011563048,0.00012496566,0.0003410953],"domain_scores_gemma":[0.9959133,0.0018141085,0.0004986053,0.0010611626,0.0005964824,0.000116341835],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0030494416,0.00041413907,0.0006042121,0.00011534856,0.00026053202,0.000110423054,0.00044433985,0.00049416756,0.000045171266],"category_scores_gemma":[0.0020781201,0.00046087336,0.00014603228,0.00032624908,0.00041822455,0.000256859,0.0006410042,0.0005242296,0.000014230165],"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":[0.00061297114,0.00086790556,0.80283374,0.003983095,0.0005372959,0.00003054272,0.0035473583,0.015277976,0.00008306365,0.16865066,0.0024857281,0.0010896856],"study_design_scores_gemma":[0.00031018243,0.00007559057,0.046877287,0.0001742835,0.00008473111,0.0000014647587,0.00005563618,0.027849494,0.0002874501,0.92383194,0.000014823554,0.00043713237],"about_ca_topic_score_codex":0.0019250527,"about_ca_topic_score_gemma":0.00045051618,"teacher_disagreement_score":0.7559564,"about_ca_system_score_codex":0.00026344793,"about_ca_system_score_gemma":0.00017512735,"threshold_uncertainty_score":0.9997843},"labels":[],"label_agreement":null},{"id":"W2907415047","doi":"10.4236/jmf.2019.91001","title":"Bayesian Item Response Analysis of Method-of-Payment Habits in Banking Surveys","year":2018,"lang":"en","type":"article","venue":"Journal of Mathematical Finance","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 Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Payment; Computer science; Payment card; Variety (cybernetics); Bayesian probability; Econometrics; Bayesian inference; Data science; Actuarial science; Artificial intelligence; Economics","score_opus":0.09204852193230298,"score_gpt":0.40615240952986087,"score_spread":0.3141038875975579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907415047","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":[0.39770812,0.000029638377,0.6017955,0.00010439331,0.000031344945,0.00007089508,0.0000055412106,0.000009736073,0.0002448312],"genre_scores_gemma":[0.5742412,0.000009023701,0.4256596,0.00000829413,0.00001713398,0.0000021134178,2.906828e-7,0.000010625462,0.000051692816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99625915,0.0012005583,0.0017074966,0.00013703325,0.0005021831,0.00019360014],"domain_scores_gemma":[0.98977,0.007998317,0.001303485,0.00035849484,0.0005212341,0.00004844941],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019327337,0.00014717836,0.0010275651,0.00073543715,0.000029820363,0.000012223898,0.00030551763,0.00010954579,0.000086323045],"category_scores_gemma":[0.010814068,0.000117030664,0.00029301216,0.0012241132,0.000115914714,0.000116905256,0.000048045466,0.00019561978,0.0000025228103],"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":[0.0071607083,0.011361085,0.13662103,0.0062356694,0.0067167105,0.00026048796,0.04481838,0.003452753,0.038308635,0.5635795,0.006029468,0.17545559],"study_design_scores_gemma":[0.0010097416,0.0010679268,0.1337744,0.0030377759,0.00085948844,0.000076894765,0.00022390645,0.070665136,0.0764327,0.7122915,0.00014381914,0.00041671703],"about_ca_topic_score_codex":0.000009044433,"about_ca_topic_score_gemma":0.000009542337,"teacher_disagreement_score":0.1765331,"about_ca_system_score_codex":0.00006453097,"about_ca_system_score_gemma":0.000082669576,"threshold_uncertainty_score":0.99751824},"labels":[],"label_agreement":null},{"id":"W2922443277","doi":"10.1093/forsci/fxy070","title":"A Jackknife Estimator of Variance for a Random Tessellated Stratified Sampling Design","year":2019,"lang":"en","type":"article","venue":"Forest Science","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada; Canadian Forest Service","funders":"","keywords":"Jackknife resampling; Estimator; Statistics; Stratified sampling; Simple random sample; Sampling design; Variance (accounting); Mathematics; Sampling (signal processing); Population variance; Poisson sampling; Population; Bias of an estimator; Econometrics; Minimum-variance unbiased estimator; Computer science; Importance sampling; Monte Carlo method; Slice sampling; Accounting","score_opus":0.15622286776024136,"score_gpt":0.3853165975245371,"score_spread":0.22909372976429576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922443277","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":[0.16240013,0.0000108233435,0.8362434,0.000029032637,0.00011831771,0.0008015506,0.0000105908075,0.00014981737,0.00023632475],"genre_scores_gemma":[0.5713018,8.185533e-7,0.4285636,0.000010148294,0.00000905748,0.00003613909,0.0000018038364,0.000009464709,0.00006713743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987007,0.00003515233,0.00036877304,0.00029599754,0.00031996524,0.00027941298],"domain_scores_gemma":[0.99673223,0.0022333115,0.00023753002,0.00038534877,0.00034373451,0.00006783411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029568018,0.00012182514,0.00026708102,0.00013570682,0.00015290044,0.00006764697,0.00040290915,0.000057786765,0.00003094211],"category_scores_gemma":[0.0034255327,0.00010398622,0.000055294367,0.00052434823,0.00019618683,0.0002360539,0.000033908593,0.00006507311,0.000015360836],"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":[0.0007281222,0.00032523414,0.0038320734,0.000772102,0.000041764873,0.000001125716,0.0012778887,0.07177999,0.14351,0.7742259,0.0014989759,0.0020068192],"study_design_scores_gemma":[0.0009495452,0.00017904676,0.0005199523,0.00022634909,0.000015265794,0.0000034964203,0.000038125472,0.34313554,0.040788483,0.613929,0.000025314257,0.00018992774],"about_ca_topic_score_codex":0.000020464502,"about_ca_topic_score_gemma":0.0000028537195,"teacher_disagreement_score":0.4089017,"about_ca_system_score_codex":0.000029446155,"about_ca_system_score_gemma":0.00026159594,"threshold_uncertainty_score":0.4240435},"labels":[],"label_agreement":null},{"id":"W2941226102","doi":"10.5539/ijsp.v8n3p83","title":"A Boundary Corrected Non-Parametric Regression Estimator for Finite Population Total","year":2019,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Mathematics; Nonparametric statistics; Population; Statistics; Invariant estimator; Nonparametric regression; Consistent estimator; Robustness (evolution); Applied mathematics; Minimum-variance unbiased estimator","score_opus":0.04436863559320481,"score_gpt":0.3628509801065114,"score_spread":0.3184823445133066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941226102","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":[0.519751,0.000021041806,0.4790352,0.00008455987,0.0006444293,0.00021815444,0.00019330814,0.000016416296,0.000035890935],"genre_scores_gemma":[0.6184523,0.000008927202,0.3813605,0.0000146697785,0.000056249217,0.0000051092147,0.000042288502,0.000008281357,0.000051682346],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998828,0.000051603525,0.00055750454,0.00012771424,0.00034065865,0.000094515715],"domain_scores_gemma":[0.99603045,0.0022494714,0.00053705805,0.00010259675,0.0010222633,0.000058182446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010233021,0.00010388139,0.00023314937,0.00016337633,0.000054386106,0.00009280689,0.00012362277,0.00006384029,0.000050183797],"category_scores_gemma":[0.004484905,0.00008325423,0.00005926103,0.00008195119,0.000033227076,0.00014949217,0.0000329631,0.00013222924,0.0000018654853],"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":[0.00452113,0.0017296075,0.45516896,0.0017713144,0.00077109615,0.00003394957,0.0016862839,0.002542266,0.0011165695,0.1259359,0.021999769,0.38272315],"study_design_scores_gemma":[0.0009743645,0.00039073147,0.10924387,0.00027271343,0.000038624934,0.000079930345,0.00002363642,0.07118235,0.00023042792,0.81710947,0.0002939177,0.00015997115],"about_ca_topic_score_codex":0.000028460063,"about_ca_topic_score_gemma":0.000003596757,"teacher_disagreement_score":0.69117355,"about_ca_system_score_codex":0.00008635447,"about_ca_system_score_gemma":0.00007158104,"threshold_uncertainty_score":0.5369174},"labels":[],"label_agreement":null},{"id":"W2941668132","doi":"","title":"Old Techniques in Differentially Private Linear Regression.","year":2019,"lang":"en","type":"article","venue":"Algorithmic Learning Theory","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Linear regression; Computer science; Statistics; Mathematics","score_opus":0.029171362033690015,"score_gpt":0.3203901574777243,"score_spread":0.2912187954440343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941668132","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":[0.8303974,0.0000650436,0.16159315,0.000095597985,0.0002284336,0.00056715147,0.0000025612578,0.0018639725,0.005186648],"genre_scores_gemma":[0.75386363,0.00008247158,0.23286404,0.00010191553,0.00015728254,0.000077202814,0.000026074698,0.0001081511,0.012719245],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99812824,0.0006010485,0.00039402622,0.00033131248,0.00023955185,0.00030583655],"domain_scores_gemma":[0.9980303,0.0012317057,0.00020109939,0.00042476924,0.000060636576,0.000051469466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024361424,0.00021852013,0.000338155,0.00024223719,0.0000792551,0.00003326262,0.00028663594,0.000186488,0.00033163585],"category_scores_gemma":[0.0011919212,0.00018003632,0.000086525826,0.00021562968,0.00005049894,0.00012725702,0.0001244281,0.0006318568,0.00015137994],"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":[0.000428797,0.00071597093,0.056481067,0.00065815577,0.00016522125,0.000059101865,0.0055077,0.00016297722,0.017830323,0.4248807,0.0014233807,0.49168658],"study_design_scores_gemma":[0.0009414415,0.0003097004,0.0047497423,0.0014321477,0.00003378985,0.000029029605,0.0003023038,0.0104023125,0.04290889,0.9285349,0.009489298,0.0008664074],"about_ca_topic_score_codex":0.000026972499,"about_ca_topic_score_gemma":0.0000014852266,"teacher_disagreement_score":0.50365424,"about_ca_system_score_codex":0.000072570685,"about_ca_system_score_gemma":0.00002852172,"threshold_uncertainty_score":0.7341668},"labels":[],"label_agreement":null},{"id":"W2969546447","doi":"10.5539/ijsp.v8n5p66","title":"Bayesian Analysis of Sparse Counts Obtained From the Unrelated Question Design","year":2019,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Simons Foundation","keywords":"Mathematics; Bayesian probability; Statistics; Inference; Population; Sample size determination; Sample (material); Cheating; Bayesian inference; Binary data; Computer science; Binary number; Artificial intelligence; Psychology","score_opus":0.0608767721284798,"score_gpt":0.3461086499499526,"score_spread":0.2852318778214728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969546447","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":[0.09497597,0.000033387973,0.9042337,0.00013573123,0.00016571225,0.000076083496,0.00021137662,0.0000073898327,0.00016067622],"genre_scores_gemma":[0.8172343,0.0000307471,0.18265009,0.000019586694,0.000019215771,5.3572575e-7,0.000019322835,0.000003143417,0.000023070414],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991882,0.0001317967,0.00034645767,0.00005790131,0.00023890224,0.000036770292],"domain_scores_gemma":[0.99732107,0.0016585722,0.00033536766,0.00008721088,0.00057798903,0.000019762763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012214063,0.00004784766,0.00015040873,0.000064186126,0.00001384519,0.000022344655,0.00011705359,0.000032623786,0.00023872926],"category_scores_gemma":[0.0010569615,0.000032486496,0.000039623475,0.00008586026,0.000037528916,0.000040072133,0.0000136114195,0.000081491075,0.0000018657151],"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":[0.000907079,0.0006120641,0.4585262,0.00009890735,0.0062622363,0.000016314101,0.0022996424,0.006115359,0.00050217164,0.45297924,0.011831817,0.059849],"study_design_scores_gemma":[0.0002052058,0.00006736734,0.06939841,0.00006302173,0.00029758742,0.0000035895214,0.00002077959,0.0473485,0.0001401958,0.88218915,0.00020810284,0.000058087197],"about_ca_topic_score_codex":0.00007072023,"about_ca_topic_score_gemma":0.000010259202,"teacher_disagreement_score":0.7222583,"about_ca_system_score_codex":0.00003107415,"about_ca_system_score_gemma":0.000040703675,"threshold_uncertainty_score":0.26139182},"labels":[],"label_agreement":null},{"id":"W2971444553","doi":"10.1080/03610918.2019.1659364","title":"Formulation of logarithmic type estimators to estimate population mean in successive sampling in presence of random non response and measurement errors","year":2019,"lang":"en","type":"article","venue":"Communications in Statistics - Simulation and Computation","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":5,"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":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Logarithm; Statistics; Mean squared error; Mathematics; Population mean; Sample size determination; Imputation (statistics); Observational error; Simple random sample; Population; Survey sampling; Mean square; Econometrics; Missing data","score_opus":0.2410489768739878,"score_gpt":0.4972057453040018,"score_spread":0.256156768430014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971444553","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":[0.60324675,0.000028062275,0.39607024,0.000029327173,0.000022493014,0.00055985386,0.000011723669,0.000021311533,0.000010213593],"genre_scores_gemma":[0.78202903,0.000010469199,0.21784559,0.000004656827,0.0000012939735,0.000018609066,0.0000744535,0.000014367826,0.0000015237209],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99817383,0.00038605326,0.00087187404,0.00019333069,0.00025986056,0.00011504719],"domain_scores_gemma":[0.99495703,0.0039107064,0.0003808989,0.00033413482,0.00038410243,0.000033149845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021732787,0.00012492057,0.00032037732,0.0006443108,0.00004134614,0.000021855076,0.0001325832,0.00007952686,0.0000021934152],"category_scores_gemma":[0.002641209,0.00014166409,0.000013440035,0.00057062,0.000043758297,0.00019131103,0.000091265785,0.0001260018,4.694037e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005989206,0.00012606474,0.16648042,0.00021015671,0.0000066750886,2.2137957e-7,0.00432667,0.8102592,0.0005316431,0.006719101,0.000001806721,0.01073912],"study_design_scores_gemma":[0.0007874134,0.000066246816,0.3400657,0.00034203648,0.0000067557016,3.0820593e-7,0.00012516521,0.6333057,0.000052878826,0.025165856,9.2833534e-7,0.00008097624],"about_ca_topic_score_codex":0.0005875686,"about_ca_topic_score_gemma":0.0012957826,"teacher_disagreement_score":0.17878227,"about_ca_system_score_codex":0.00012957395,"about_ca_system_score_gemma":0.000048528993,"threshold_uncertainty_score":0.5776894},"labels":[],"label_agreement":null},{"id":"W2971819817","doi":"10.1039/c9em00215d","title":"Theory and modelling approaches to passive sampling","year":2019,"lang":"en","type":"review","venue":"Environmental Science Processes & Impacts","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Regional Municipality of Waterloo; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Sampling (signal processing); Interpretation (philosophy); Sampling theory; Computer science; Environmental science; Mathematics; Statistics; Telecommunications; Sample size determination","score_opus":0.433973485328245,"score_gpt":0.3977896918861622,"score_spread":0.03618379344208278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971819817","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018143713,0.9219408,0.07442214,0.000015762524,0.00007932642,0.0012479842,0.00006235677,0.00016753665,0.00024971773],"genre_scores_gemma":[0.0060376087,0.94210553,0.051416744,0.00003654398,0.000055658402,0.0001245519,0.000022218846,0.000071052855,0.00013008462],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99757236,0.000102142025,0.0004535348,0.00076905795,0.00055385154,0.00054902164],"domain_scores_gemma":[0.99754035,0.0013492475,0.0003532114,0.00043153288,0.000011258229,0.00031442492],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022100708,0.0004504509,0.0008570347,0.00029565825,0.00031969495,0.00025522464,0.0005689677,0.00016165838,0.000028903643],"category_scores_gemma":[0.0011520792,0.00034297383,0.00009060755,0.0005594781,0.00035999255,0.00047391915,0.0003581982,0.00027284666,0.00008319712],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012580133,0.00012171253,0.000013195606,0.01848856,0.000040109502,0.0000015412702,0.0016713276,0.000286933,0.000014359584,0.0024229672,0.000036775607,0.97688997],"study_design_scores_gemma":[0.0008039524,0.0015130888,0.000051637744,0.10280769,0.003241778,0.0007199002,0.0037623986,0.0043520303,0.0028772953,0.30269018,0.5673148,0.00986524],"about_ca_topic_score_codex":0.0000047878107,"about_ca_topic_score_gemma":5.880129e-7,"teacher_disagreement_score":0.9670247,"about_ca_system_score_codex":0.00029987982,"about_ca_system_score_gemma":0.00032238776,"threshold_uncertainty_score":0.99990225},"labels":[],"label_agreement":null},{"id":"W2977170828","doi":"10.21083/surg.v1i2.407","title":"A comparison of variance estimators with known and unknown population means","year":2008,"lang":"en","type":"article","venue":"SURG Journal","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":true,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; University of Guelph","keywords":"Estimator; Statistics; Variance (accounting); Population mean; Mathematics; Population variance; Population; Sample mean and sample covariance; Exponential function; Distribution (mathematics); Standard error; Demography","score_opus":0.12657328339163362,"score_gpt":0.38569454935667374,"score_spread":0.25912126596504015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977170828","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":[0.8109132,0.0001302216,0.18824592,0.00004673522,0.00006772187,0.00006256494,0.0000020396733,0.000068097535,0.00046349393],"genre_scores_gemma":[0.8468011,0.00003159265,0.15305999,0.0000047928847,0.000041223557,0.0000016147201,0.0000021116177,0.000011947593,0.000045642748],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99915206,0.000080281214,0.00034529716,0.000084228144,0.00022224785,0.00011588173],"domain_scores_gemma":[0.9990943,0.00029299877,0.00030117875,0.000109927496,0.0001361967,0.00006540099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005830223,0.0000913296,0.00025978297,0.00009607859,0.00017228867,0.000018791055,0.000060032933,0.00005196914,0.000025054464],"category_scores_gemma":[0.00024017926,0.000069684254,0.00003084638,0.00012640785,0.00006143584,0.00012827876,0.000010951919,0.00017481428,9.2882635e-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":[0.00009535198,0.00019720287,0.9748057,0.00008899734,0.000060723818,0.000016538963,0.001682563,0.00038340152,0.000092284485,0.008073077,0.0030820598,0.011422074],"study_design_scores_gemma":[0.0037729286,0.0014172704,0.6849684,0.0022246474,0.00030147698,0.006080686,0.00049216626,0.050848298,0.011278351,0.23131797,0.0058901208,0.0014076874],"about_ca_topic_score_codex":0.00003684186,"about_ca_topic_score_gemma":0.000014605696,"teacher_disagreement_score":0.28983733,"about_ca_system_score_codex":0.000021668699,"about_ca_system_score_gemma":0.00003938727,"threshold_uncertainty_score":0.28416413},"labels":[],"label_agreement":null},{"id":"W2993287308","doi":"","title":"Multi-objective optimisation for optimum allocation in multivariate stratified sampling","year":2008,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Stratified sampling; Multivariate statistics; Statistics; Sampling (signal processing); Mathematics; Computer science","score_opus":0.6825131120236855,"score_gpt":0.5037334109630854,"score_spread":0.17877970106060004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993287308","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2215482,0.000017793438,0.7772363,0.000039902265,0.00022212451,0.00065913977,0.000042789557,0.00019192265,0.000041849304],"genre_scores_gemma":[0.29404625,0.000010096444,0.7053984,0.000029125038,0.000032208067,0.00019325974,0.00017336945,0.000030089166,0.00008722288],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9945441,0.0039062616,0.0006463013,0.00044123278,0.00012781002,0.00033432618],"domain_scores_gemma":[0.97723526,0.0217331,0.00027658642,0.0003134114,0.00038886335,0.000052761603],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014826429,0.0002081149,0.00048180993,0.00027812607,0.000162774,0.000014578123,0.0001701209,0.00027796807,0.000019170218],"category_scores_gemma":[0.03186441,0.00021368719,0.00007927205,0.00030420453,0.00008716888,0.00014105963,0.000032249736,0.00021060981,0.0000049870932],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0116788875,0.0063180993,0.25786784,0.0016307599,0.0013287419,0.000041591917,0.08525735,0.0973061,0.35559565,0.06803167,0.0037118462,0.11123145],"study_design_scores_gemma":[0.0033911483,0.0003101794,0.7806591,0.00007418545,0.000037353715,0.000034240336,0.00046600244,0.08433104,0.035170108,0.09467565,0.000053093805,0.0007979132],"about_ca_topic_score_codex":0.0022186516,"about_ca_topic_score_gemma":0.001305849,"teacher_disagreement_score":0.52279127,"about_ca_system_score_codex":0.000109512286,"about_ca_system_score_gemma":0.00011626337,"threshold_uncertainty_score":0.9762906},"labels":[],"label_agreement":null},{"id":"W3011442131","doi":"10.2991/jsta.d.200303.001","title":"Sample Design and Estimation of Parameters of Half Logistic Distribution Using Generalized Ranked-Set Sampling","year":2020,"lang":"en","type":"article","venue":"Journal of Statistical Theory and Applications","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":"University of Lethbridge","funders":"","keywords":"Mathematics; Statistics; Sample (material); Logistic distribution; Sampling design; Estimation; Sampling (signal processing); Logistic regression; Computer science; Engineering","score_opus":0.2709871524496742,"score_gpt":0.42015899527755346,"score_spread":0.14917184282787926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011442131","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":[0.045894165,0.00009413668,0.95341116,0.00006283152,0.00000832616,0.00020725606,0.00030484283,0.000014335733,0.0000029214293],"genre_scores_gemma":[0.49979436,0.00003163802,0.5001208,0.000011132341,0.000011343863,0.0000049660252,0.000020568466,0.0000049576493,2.0811773e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987853,0.00026029162,0.0006249775,0.00009858058,0.00013831712,0.00009251796],"domain_scores_gemma":[0.9922306,0.0068987114,0.0005144416,0.000083931736,0.00016682869,0.000105464445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015999951,0.00008947475,0.00031624935,0.00004160692,0.00007747693,0.00001807589,0.00006865588,0.000050821276,0.000012437561],"category_scores_gemma":[0.0043621166,0.00007697683,0.000036037192,0.00012407146,0.00022185608,0.00007071016,0.000019662519,0.00010188161,1.662532e-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":[0.00027340368,0.0000680217,0.00007976402,0.0002593613,0.00006163175,4.588679e-7,0.00023516869,0.0048511233,0.002496225,0.9783596,0.000041494284,0.013273762],"study_design_scores_gemma":[0.0003180153,0.00014757598,0.00015000683,0.0000734573,0.00018164757,0.000018514233,0.0000885383,0.09061851,0.0043668183,0.9039232,0.00003387208,0.00007980701],"about_ca_topic_score_codex":0.000022539714,"about_ca_topic_score_gemma":1.8655679e-7,"teacher_disagreement_score":0.4539002,"about_ca_system_score_codex":0.000015959999,"about_ca_system_score_gemma":0.000038459984,"threshold_uncertainty_score":0.52221763},"labels":[],"label_agreement":null},{"id":"W3012530420","doi":"10.2478/jos-2020-0009","title":"A Procedure for Estimating the Variance of the Population Mean in Rejective Sampling","year":2020,"lang":"en","type":"article","venue":"Journal of Official Statistics","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":"Statistics Canada","funders":"","keywords":"Mathematics; Estimator; Statistics; Sample size determination; Sampling (signal processing); Sample (material); Variance (accounting); Unit cube; Monte Carlo method; Population; Population variance; Simple random sample; Computer science; Combinatorics","score_opus":0.142898274363777,"score_gpt":0.386249078736028,"score_spread":0.24335080437225098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012530420","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":[0.05363287,0.000014033855,0.94528615,0.00054678,0.00015494446,0.00027429286,0.000065534194,0.000010975418,0.00001441601],"genre_scores_gemma":[0.5187643,9.729066e-7,0.48101985,0.000053391395,0.00014630979,0.0000025728762,0.0000014611463,0.0000093710505,0.0000017355184],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886405,0.00009323836,0.00063865137,0.00006691705,0.00024198675,0.0000951447],"domain_scores_gemma":[0.9969205,0.0017025134,0.0009296646,0.00008013322,0.00034218596,0.000024960655],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0010109214,0.00007749071,0.00022606377,0.000032898948,0.00009876844,0.000021382713,0.00018731238,0.000044089047,0.0000027933932],"category_scores_gemma":[0.012707185,0.000047674657,0.00005970047,0.00020737191,0.000030193938,0.000052961637,0.000021886244,0.0002052521,1.18438614e-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":[0.0024589235,0.0009544339,0.0457549,0.003837104,0.0004321382,0.000013320917,0.06727215,0.24956402,0.0024728498,0.506872,0.017439693,0.10292848],"study_design_scores_gemma":[0.000668518,0.00035878274,0.03533741,0.0006642583,0.00012857563,0.000020238487,0.0006562237,0.32452297,0.00084210804,0.63655865,0.00007070699,0.00017156523],"about_ca_topic_score_codex":0.000036895708,"about_ca_topic_score_gemma":0.00008261892,"teacher_disagreement_score":0.46513146,"about_ca_system_score_codex":0.000048044218,"about_ca_system_score_gemma":0.000111398105,"threshold_uncertainty_score":0.9956092},"labels":[],"label_agreement":null},{"id":"W3021782267","doi":"10.1111/rssb.12368","title":"Inference for Two-Stage Sampling Designs","year":2020,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":12,"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 Laval","funders":"","keywords":"Estimator; Statistics; Sampling (signal processing); Mathematics; Sampling design; Consistency (knowledge bases); Poisson sampling; Confidence interval; Variance (accounting); Econometrics; Asymptotic distribution; Importance sampling; Slice sampling; Computer science; Monte Carlo method","score_opus":0.4918263075505696,"score_gpt":0.4826409255602239,"score_spread":0.009185381990345687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021782267","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":[0.0012571473,0.00003883369,0.99431634,0.0028391008,0.00037929154,0.0003509205,0.0006419623,0.00008931586,0.00008710602],"genre_scores_gemma":[0.02695792,0.000009546631,0.9713447,0.0011619303,0.00033242148,0.000020415877,0.00000993781,0.000044889708,0.00011823818],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963729,0.0012218109,0.0011612116,0.00029317677,0.00047466205,0.00047627048],"domain_scores_gemma":[0.95974255,0.038531255,0.0006620705,0.00022899169,0.00048679873,0.000348345],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0040721665,0.0002922776,0.00085413235,0.000021789925,0.00035107954,0.00009432714,0.0005756614,0.0001973334,0.0003504864],"category_scores_gemma":[0.08253012,0.00019894235,0.00037028553,0.00020004823,0.0005735145,0.00011058657,0.00016695152,0.0007716414,0.0000050261724],"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":[0.00092795625,0.00013544713,0.00047032553,0.00057419395,0.0003348925,0.000012472415,0.0014174933,0.0012729549,0.0009308939,0.9420089,0.03912492,0.012789556],"study_design_scores_gemma":[0.0011171642,0.0011096959,0.0012699866,0.00009503404,0.00040187498,0.000029677913,0.0005721329,0.027652735,0.0021717432,0.958665,0.006500584,0.00041435705],"about_ca_topic_score_codex":0.000022013683,"about_ca_topic_score_gemma":0.0000042878337,"teacher_disagreement_score":0.07845795,"about_ca_system_score_codex":0.00009413244,"about_ca_system_score_gemma":0.00019487344,"threshold_uncertainty_score":0.92519814},"labels":[],"label_agreement":null},{"id":"W3024066691","doi":"10.1007/978-3-030-44246-0_4","title":"General Theory and Methods of Unequal Probability Sampling","year":2020,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sampling (signal processing); Sampling theory; Sampling design; Probability sampling; Computer science; Importance sampling; Mathematics; Statistics; Sample size determination; Monte Carlo method","score_opus":0.16256893914108192,"score_gpt":0.4231218197370672,"score_spread":0.26055288059598525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024066691","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":[0.000051803592,0.00054023665,0.9564741,0.000032441585,0.00014511899,0.00047363754,0.0013489552,0.00016291528,0.040770784],"genre_scores_gemma":[0.00008244881,0.00049081864,0.9787491,0.00006886166,0.00006599418,0.000020963338,0.00012057255,0.00008743304,0.020313809],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979608,0.00029215886,0.0009352543,0.00038707315,0.0002397132,0.00018496638],"domain_scores_gemma":[0.99454564,0.0042577814,0.0004959484,0.00041814148,0.00020444508,0.00007807444],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022972906,0.00035486123,0.0008164807,0.00011283348,0.000055417124,0.000029478553,0.00017673007,0.0003251517,0.0001896944],"category_scores_gemma":[0.0036185903,0.0003642378,0.000061573635,0.00003521896,0.00046004786,0.000104848456,0.00017637516,0.00045718843,0.000002020633],"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":[0.0001032142,0.000015035983,0.000021828779,0.00095415005,0.00004669103,0.000006113072,0.00062516687,0.000011565483,0.000028494442,0.9829813,0.00064960297,0.014556786],"study_design_scores_gemma":[0.000116676965,0.00012430067,0.000022678762,0.0002469236,0.00007275445,0.000005559379,0.00002725569,0.00022116386,0.00032945003,0.9789091,0.019605236,0.00031892437],"about_ca_topic_score_codex":0.000014787768,"about_ca_topic_score_gemma":0.000030794305,"teacher_disagreement_score":0.022274993,"about_ca_system_score_codex":0.000074970725,"about_ca_system_score_gemma":0.00012341858,"threshold_uncertainty_score":0.99988097},"labels":[],"label_agreement":null},{"id":"W3024834316","doi":"10.1007/978-3-030-44246-0_15","title":"Adaptive and Network Surveys","year":2020,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sampling frame; Sampling (signal processing); Frame (networking); Population; Computer science; Geography; Statistics; Demography; Mathematics; Telecommunications; Sociology","score_opus":0.10126418826503661,"score_gpt":0.32381259306761506,"score_spread":0.22254840480257845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024834316","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":[0.0000021491046,0.0012625755,0.63983834,0.00011333358,0.00035733744,0.00058619113,0.0023094804,0.00042943424,0.35510114],"genre_scores_gemma":[0.00030187803,0.0031933694,0.75209695,0.0003262523,0.00038092778,0.00003882693,0.0004452283,0.00024825401,0.24296832],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982982,0.00014243186,0.00062829757,0.0003967825,0.00027589788,0.0002583897],"domain_scores_gemma":[0.9972198,0.0018290823,0.00034811237,0.00033464152,0.0001596379,0.000108709355],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009156952,0.0004145328,0.00071622594,0.000082592356,0.000092609866,0.00005953576,0.00016592165,0.00035353252,0.00028115764],"category_scores_gemma":[0.00068982184,0.00045350776,0.00004342856,0.000039608985,0.00028390874,0.00013311084,0.0001611755,0.0005659445,0.00002771696],"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":[0.00003209709,0.00000669186,0.00004668222,0.00017026364,0.00004882509,0.00006695707,0.00021732197,0.000010391026,1.6526845e-7,0.93513167,0.058123328,0.006145614],"study_design_scores_gemma":[0.00012212207,0.00015579445,0.00007807559,0.00032469523,0.000047662925,0.00001287136,0.000017338161,0.00035333878,0.000004626849,0.88997906,0.10847571,0.0004286795],"about_ca_topic_score_codex":0.000028615808,"about_ca_topic_score_gemma":0.00031424867,"teacher_disagreement_score":0.112258576,"about_ca_system_score_codex":0.00008061834,"about_ca_system_score_gemma":0.00009660292,"threshold_uncertainty_score":0.9997917},"labels":[],"label_agreement":null},{"id":"W3025268994","doi":"10.1007/978-3-030-44246-0_17","title":"Non-probability Survey Samples","year":2020,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Survey research; Probability and statistics; Survey data collection; Focus (optics); Survey methodology; Probability sampling; Survey sampling; Computer science; Data science; Statistics; Inference; Psychology; Mathematics; Artificial intelligence; Applied psychology; Sociology; Physics; Demography","score_opus":0.1889367811007782,"score_gpt":0.35488867641780786,"score_spread":0.16595189531702967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025268994","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":[0.00006716192,0.00047006132,0.563514,0.00022308061,0.00096304534,0.0019284026,0.024819978,0.0011361724,0.4068781],"genre_scores_gemma":[0.0007444477,0.0011434861,0.80426157,0.00037962815,0.00022999,0.00008098418,0.0031373396,0.00035942384,0.18966313],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99735314,0.00011021685,0.0011143094,0.0006197161,0.00047264353,0.00032995155],"domain_scores_gemma":[0.9952208,0.0029262125,0.00050931063,0.00081625965,0.0003852644,0.00014215818],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012550972,0.00057949766,0.0010048987,0.00014177008,0.000103166545,0.00008726616,0.0004137927,0.0004970141,0.00086870417],"category_scores_gemma":[0.0037043607,0.00062934816,0.000096897595,0.00006423168,0.00037115617,0.00017492965,0.00021487239,0.0007453716,0.00009559215],"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":[0.00010010177,0.000034159268,0.00067337096,0.00072411716,0.000060001443,0.0000434699,0.00032093833,0.0000059376403,0.000001642054,0.9176714,0.07832167,0.0020432041],"study_design_scores_gemma":[0.0001482728,0.000121904064,0.0007878678,0.0002576591,0.000041215993,0.0000065339063,0.000009084542,0.00010519939,0.000048659418,0.8968307,0.10104873,0.0005942126],"about_ca_topic_score_codex":0.00024108317,"about_ca_topic_score_gemma":0.0020761867,"teacher_disagreement_score":0.24074757,"about_ca_system_score_codex":0.00021744419,"about_ca_system_score_gemma":0.00025300498,"threshold_uncertainty_score":0.9996158},"labels":[],"label_agreement":null},{"id":"W3025286918","doi":"10.1007/978-3-030-44246-0_2","title":"Simple Single-Stage Sampling Methods","year":2020,"lang":"en","type":"book-chapter","venue":"ICSA book series in statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sampling (signal processing); Cluster sampling; Stage (stratigraphy); Selection (genetic algorithm); Probability sampling; Statistics; Simple random sample; Sampling design; Sampling frame; Poisson sampling; Population; Single stage; Computer science; Systematic sampling; Mathematics; Importance sampling; Slice sampling; Artificial intelligence; Engineering; Monte Carlo method; Biology","score_opus":0.26629314089212247,"score_gpt":0.43931247144995483,"score_spread":0.17301933055783236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025286918","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":[0.0000016568442,0.00032843702,0.8014127,0.000060289418,0.0002809801,0.0003970446,0.0022309409,0.00053810596,0.19474983],"genre_scores_gemma":[0.000026670175,0.0003891587,0.85053045,0.00029729752,0.00017188588,0.000028099723,0.0005688837,0.00023597767,0.14775155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973241,0.00012820774,0.0011684337,0.0005851306,0.00041110913,0.00038300094],"domain_scores_gemma":[0.99491066,0.003360173,0.00064185075,0.00069736765,0.00023832731,0.00015161218],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009093042,0.0006144521,0.0010141626,0.00022526307,0.00012900507,0.00012412245,0.00038075433,0.00051579764,0.0012376861],"category_scores_gemma":[0.0030010073,0.00069357635,0.00012234805,0.000068349815,0.00025508105,0.00020998232,0.00024010125,0.0008398997,0.00005351453],"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":[0.00004413181,0.000024730914,0.0000085109705,0.00061028247,0.00006003043,0.000063941814,0.00044446051,0.000024036066,0.000044883065,0.9710352,0.015396569,0.012243256],"study_design_scores_gemma":[0.00009722465,0.000097965836,0.0000022294585,0.00018327408,0.000048156475,0.0000065291797,0.00003416901,0.0002756462,0.00029006973,0.57821965,0.42030597,0.0004391152],"about_ca_topic_score_codex":0.000022126755,"about_ca_topic_score_gemma":0.000108658554,"teacher_disagreement_score":0.4049094,"about_ca_system_score_codex":0.00025237817,"about_ca_system_score_gemma":0.00014623589,"threshold_uncertainty_score":0.99967533},"labels":[],"label_agreement":null},{"id":"W3025393907","doi":"10.1017/psrm.2020.18","title":"Placebo statements in list experiments: Evidence from a face-to-face survey in Singapore","year":2020,"lang":"en","type":"article","venue":"Political Science Research and Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Treatment and control groups; Face (sociological concept); Psychology; Placebo; Inflation (cosmology); Interpretation (philosophy); Statement (logic); Survey data collection; Social psychology; Econometrics; Actuarial science; Statistics; Computer science; Economics; Medicine; Sociology; Political science; Alternative medicine; Mathematics; Social science","score_opus":0.7576034810771761,"score_gpt":0.6772032127523472,"score_spread":0.08040026832482894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025393907","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":[0.83496374,0.00007879937,0.16149397,0.0024708037,0.000028623175,0.0004904058,0.000028114413,0.00005268044,0.00039282985],"genre_scores_gemma":[0.7316325,0.0000147852925,0.2681306,0.00011938333,0.000014876171,0.000051811312,0.0000020881334,0.0000075632383,0.00002643237],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.994758,0.0022220267,0.000390425,0.0005750349,0.00085845834,0.0011960163],"domain_scores_gemma":[0.98879385,0.009783581,0.000028786479,0.00024560225,0.00019255899,0.00095559185],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02698747,0.000117528754,0.00025688703,0.00028823956,0.00014026371,0.00020288311,0.00048587756,0.000058112313,0.000049124374],"category_scores_gemma":[0.08303034,0.0001015385,0.000013748775,0.0016354091,0.0006014148,0.0004009557,0.00043995903,0.0003770988,0.0000118462085],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018086192,0.0013794058,0.54600155,0.0005100414,0.000029111172,0.00011242067,0.041644156,0.000044058528,0.19076912,0.13483232,0.0019769073,0.08089229],"study_design_scores_gemma":[0.0010823335,0.0008984194,0.27341846,0.0010166074,0.0000036103934,0.0000024100975,0.005431377,0.02003367,0.2822681,0.415054,0.000174991,0.0006160445],"about_ca_topic_score_codex":0.01154804,"about_ca_topic_score_gemma":0.00029619393,"teacher_disagreement_score":0.28022167,"about_ca_system_score_codex":0.00029569786,"about_ca_system_score_gemma":0.00030079772,"threshold_uncertainty_score":0.99503416},"labels":[],"label_agreement":null},{"id":"W3036162187","doi":"10.1111/apps.12278","title":"Economic Predictors of Differences in Interview Faking Between Countries: Economic Inequality Matters, Not the State of Economy","year":2020,"lang":"en","type":"article","venue":"Applied Psychology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Inequality; Gross domestic product; Unemployment; Per capita; Globe; Psychology; Demographic economics; Economic inequality; Economics; Product (mathematics); Social psychology; Labour economics; Economic growth; Sociology; Demography","score_opus":0.17231852527124167,"score_gpt":0.37715633943769894,"score_spread":0.20483781416645727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036162187","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":[0.9810613,0.000021220167,0.014183279,0.0029232583,0.00009072981,0.00033368083,0.0001289333,0.00006067541,0.0011969615],"genre_scores_gemma":[0.9975832,0.000050642735,0.0010896556,0.001150484,0.000048710866,0.000047716025,0.000011225664,0.000015960282,0.0000024158212],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985146,0.00015429962,0.0008845643,0.00024950568,0.000039154842,0.00015786462],"domain_scores_gemma":[0.9978121,0.0012932197,0.00053550676,0.00031166762,0.000012450686,0.00003506301],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010531549,0.0001408443,0.0005566649,0.00007273144,0.000019782932,0.000010851672,0.00038283592,0.00007473552,0.00012474938],"category_scores_gemma":[0.000032644053,0.00011573143,0.000057942514,0.000045089702,0.00017378511,0.000043884516,0.000067305875,0.00013839408,0.000030004283],"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":[0.0006237147,0.00023433843,0.82876456,0.002839226,0.0009901751,0.0000016626983,0.03594421,0.00025352178,0.00046716264,0.07419549,0.025478065,0.030207893],"study_design_scores_gemma":[0.0038313414,0.00071834546,0.5059539,0.00040814982,0.00019897941,0.000004605517,0.0013264088,0.0010628498,0.019785391,0.45563915,0.009908486,0.0011624183],"about_ca_topic_score_codex":0.00009389241,"about_ca_topic_score_gemma":0.000048262245,"teacher_disagreement_score":0.38144365,"about_ca_system_score_codex":0.000038348084,"about_ca_system_score_gemma":0.00003819295,"threshold_uncertainty_score":0.4719391},"labels":[],"label_agreement":null},{"id":"W3041227018","doi":"","title":"“Optimal” calibration weights under unit nonresponse in survey sampling","year":2019,"lang":"en","type":"article","venue":"Survey methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Statistics; Estimator; Calibration; Sampling (signal processing); Sample (material); Variance (accounting); Population; Survey sampling; Econometrics; Non-response bias; Mathematics; Computer science; Demography; Physics; Economics","score_opus":0.6246140539733327,"score_gpt":0.49634499195555926,"score_spread":0.12826906201777344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041227018","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5688576,0.000026755555,0.4301544,0.000040857194,0.00030539613,0.00025096748,0.00005108533,0.00016124059,0.00015166264],"genre_scores_gemma":[0.53429186,0.000012581954,0.46434993,0.00013472645,0.00003145093,0.000028946986,0.00034667895,0.00006032348,0.00074353616],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96960396,0.0283122,0.0007878898,0.00055164093,0.00024948426,0.0004948271],"domain_scores_gemma":[0.93241453,0.066392176,0.00024717496,0.00062184455,0.0002411807,0.00008308396],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.051632814,0.0002738963,0.00069452095,0.00047053333,0.00007267875,0.00004379086,0.00031283192,0.00038605015,0.00040037357],"category_scores_gemma":[0.023171866,0.00026230354,0.000078523626,0.0007110535,0.00007503028,0.00018085544,0.00009730448,0.00040242018,0.000091477144],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020651296,0.00025493826,0.97451794,0.00010779008,0.00009171698,0.0000058851156,0.0009265218,0.0032261708,0.0031790715,0.013416221,0.0006580393,0.0015505857],"study_design_scores_gemma":[0.00053095905,0.00010523377,0.9351648,0.00003985982,0.0000084723415,0.000009781493,0.00007832022,0.003209205,0.0028618248,0.057530064,0.00011184313,0.00034962417],"about_ca_topic_score_codex":0.0063724057,"about_ca_topic_score_gemma":0.008610399,"teacher_disagreement_score":0.044113845,"about_ca_system_score_codex":0.00007611829,"about_ca_system_score_gemma":0.00015583422,"threshold_uncertainty_score":0.9999829},"labels":[],"label_agreement":null},{"id":"W3089427001","doi":"10.1002/cjs.11802","title":"Efficient multiply robust imputation in the presence of influential units in surveys","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","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":true,"route_about_ca":false,"ca_institutions":"McGill University; University of Ottawa","funders":"Canadian Statistical Sciences Institute; National Institute on Minority Health and Health Disparities; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Imputation (statistics); Estimator; Missing data; Econometrics; Statistics; Computer science; Robust statistics; Population; Mathematics; Medicine","score_opus":0.13107467349651783,"score_gpt":0.32916749712087007,"score_spread":0.19809282362435224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089427001","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":[0.7679769,0.000018168772,0.23139037,0.00007787536,0.00014305007,0.00012628222,0.000218616,0.0000073059236,0.00004146182],"genre_scores_gemma":[0.9742343,0.000005328882,0.025695808,0.000012981505,0.000017044391,0.0000021807637,0.000013654443,0.000008871222,0.000009858431],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9985958,0.0004341245,0.0005267736,0.000055723427,0.00021388714,0.00017371902],"domain_scores_gemma":[0.99709004,0.002090878,0.00025577465,0.00010147104,0.00037897762,0.00008283459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041041416,0.00006609154,0.00015522754,0.0005556559,0.000038525446,0.000026271402,0.00019335351,0.000043971715,0.0000110954325],"category_scores_gemma":[0.0072691576,0.000054563036,0.000016565835,0.0009156349,0.0000638655,0.000032039097,0.0000067291976,0.0001872173,0.0000020714701],"study_design_candidate":"simulation_or_modeling","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":[0.00003804105,0.0001226125,0.14741021,0.0003972435,0.000043807308,0.0006930835,0.0334316,0.7375262,0.00009055097,0.026062265,0.022090912,0.03209347],"study_design_scores_gemma":[0.0009037787,0.00016468989,0.7392208,0.0004986371,0.000025058045,0.000046411027,0.0028872017,0.20030932,0.00017594744,0.055456724,0.00010279305,0.00020865582],"about_ca_topic_score_codex":0.0073010474,"about_ca_topic_score_gemma":0.050735075,"teacher_disagreement_score":0.5918106,"about_ca_system_score_codex":0.000069562564,"about_ca_system_score_gemma":0.0005801963,"threshold_uncertainty_score":0.9993094},"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":"W3125799862","doi":"10.1920/wp.cem.2010.3610","title":"Testing for threshold effects in regression models","year":2010,"lang":"en","type":"preprint","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","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":"Economic and Social Research Council; Social Sciences and Humanities Research Council of Canada","keywords":"Statistics; Regression analysis; Regression; Econometrics; Computer science; Mathematics","score_opus":0.23520808079981403,"score_gpt":0.41044037705655967,"score_spread":0.17523229625674563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3125799862","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":[0.13371526,0.00004941534,0.8537281,0.00008639687,0.00044855496,0.0016240267,0.000011888402,0.0010718919,0.009264455],"genre_scores_gemma":[0.3004596,0.0000017266653,0.6986273,0.00003084321,0.000074185475,0.00047725372,0.000024796218,0.000043241642,0.00026104756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988419,0.00004092531,0.000383453,0.00036436945,0.0001530889,0.00021627468],"domain_scores_gemma":[0.9958041,0.0032455001,0.00020993047,0.0005463097,0.00014984587,0.000044335473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013564266,0.00024008112,0.00039897038,0.00017455062,0.000052536063,0.000058105074,0.0002532918,0.0005806352,0.0000060688058],"category_scores_gemma":[0.0034784656,0.00018897178,0.00009104112,0.00007767782,0.000019985866,0.00005898849,0.00027821524,0.00070377975,0.000002022197],"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":[0.00026627723,0.0015803907,0.012653796,0.031733762,0.00015519986,0.000031559455,0.00312101,0.016055724,0.010819136,0.6461732,0.06513637,0.21227357],"study_design_scores_gemma":[0.00013692082,0.00002071736,0.00010252556,0.0012387945,0.00001035367,0.0000010283594,0.0000038547455,0.23807095,0.004799981,0.7554284,0.000010284869,0.00017620761],"about_ca_topic_score_codex":0.00011755975,"about_ca_topic_score_gemma":0.00004546269,"teacher_disagreement_score":0.22201522,"about_ca_system_score_codex":0.00003994845,"about_ca_system_score_gemma":0.00008013027,"threshold_uncertainty_score":0.77060455},"labels":[],"label_agreement":null},{"id":"W3154947088","doi":"10.1111/rssa.12678","title":"Modified Poisson Regression Analysis of Grouped and Right-Censored Counts","year":2021,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series A (Statistics in Society)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":13,"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 British Columbia","funders":"Research Grants Council, University Grants Committee","keywords":"Poisson regression; Censoring (clinical trials); Estimator; Poisson distribution; Statistics; Logistic regression; Econometrics; Inference; Statistical inference; Mathematics; Sample (material); Computer science; Psychology; Demography; Sociology; Artificial intelligence; Population","score_opus":0.0364367142514604,"score_gpt":0.33326259166066363,"score_spread":0.29682587740920324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3154947088","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":[0.044904295,0.00041054518,0.95241874,0.00040437444,0.0003067832,0.0001261673,0.0008348025,0.000027166569,0.00056713267],"genre_scores_gemma":[0.2243777,0.00043508326,0.7741379,0.000115689974,0.000051657637,0.0000027357842,0.000029558092,0.000023044715,0.0008266238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983609,0.00017355567,0.0006819052,0.00013998135,0.0004686419,0.00017502885],"domain_scores_gemma":[0.9972347,0.0016021054,0.00048835046,0.00019222258,0.00041080735,0.000071789975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081204076,0.0001424336,0.00053043274,0.00002817016,0.000115648196,0.000042059273,0.00015593573,0.00014031192,0.00020965647],"category_scores_gemma":[0.001443097,0.00009868309,0.00029007028,0.0004796905,0.0002601124,0.00004972035,0.000083564744,0.0003427405,4.5427362e-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":[0.00021724831,0.00072583696,0.011424094,0.0009893909,0.0034373244,0.00006819904,0.0061156647,0.0015264144,0.00043496361,0.68263865,0.2856056,0.0068165893],"study_design_scores_gemma":[0.0013844194,0.0002024922,0.044324968,0.00049189484,0.0024974109,0.00003676175,0.0021136387,0.15563391,0.0012021438,0.7889359,0.0026565227,0.0005199168],"about_ca_topic_score_codex":0.000023721888,"about_ca_topic_score_gemma":0.000020617897,"teacher_disagreement_score":0.2829491,"about_ca_system_score_codex":0.00009843222,"about_ca_system_score_gemma":0.00009882275,"threshold_uncertainty_score":0.402418},"labels":[],"label_agreement":null},{"id":"W3174992558","doi":"10.3389/fpsyg.2021.655592","title":"Functionality of the Crosswise Model for Assessing Sensitive or Transgressive Behavior: A Systematic Review and Meta-Analysis","year":2021,"lang":"en","type":"review","venue":"Frontiers in Psychology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"World Anti-Doping Agency","keywords":"Meta-analysis; Psychology; Transgressive; Empirical research; Population; Systematic review; Misconduct; Warrant; Protocol (science); Statistics; Econometrics; Social psychology; Mathematics; MEDLINE; Demography; Medicine","score_opus":0.43276226243122323,"score_gpt":0.5249382097685608,"score_spread":0.09217594733733753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174992558","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.5843616e-7,0.5873677,0.4102134,0.00004405054,0.000093095114,0.0019282496,0.00032254608,0.000017547525,0.000013111245],"genre_scores_gemma":[0.0000057667876,0.8688332,0.12827957,0.0002062074,0.0000068743975,0.0023135208,0.0000765595,0.000037518876,0.00024079754],"study_design_codex":"systematic_review","study_design_gemma":"meta_analysis","domain_scores_codex":[0.9959091,0.001593125,0.001574165,0.0005348298,0.00019552256,0.00019327513],"domain_scores_gemma":[0.99612224,0.0012525722,0.0014236809,0.00088233256,0.00028290262,0.000036297937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025820276,0.00037435707,0.007913406,0.0002777247,0.000081218306,0.000029445577,0.00026471214,0.00037508423,0.000021331289],"category_scores_gemma":[0.0014421213,0.00020996908,0.0023467187,0.0008230887,0.00017613992,0.00005884179,0.00004023269,0.00031410842,1.5787566e-7],"study_design_candidate":"meta_analysis","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":[0.000008160138,0.00018706934,0.000007323434,0.93079513,0.0564204,0.000005377173,0.00017598893,0.0000037127481,3.0029344e-8,0.00023651597,0.005126015,0.0070342952],"study_design_scores_gemma":[0.00012229354,0.000012871356,0.0000022297938,0.031328984,0.9611009,0.00005278751,0.000044606368,0.00038760432,3.3139222e-7,0.0060328105,0.0006391987,0.0002754322],"about_ca_topic_score_codex":0.0000041852995,"about_ca_topic_score_gemma":0.000014502382,"teacher_disagreement_score":0.90468043,"about_ca_system_score_codex":0.000060445655,"about_ca_system_score_gemma":0.00015622836,"threshold_uncertainty_score":0.856229},"labels":[],"label_agreement":null},{"id":"W3215800506","doi":"10.13052/jrss0974-8024.14210","title":"Estimation of Finite Population Variance Under Stratified Sampling Technique","year":2021,"lang":"en","type":"article","venue":"Journal of Reliability and Statistical Studies","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Estimator; Stratified sampling; Statistics; Sampling (signal processing); Population; Mathematics; Population variance; Sampling design; Simple random sample; Variance (accounting); Mean squared error; Sample (material); Sample size determination; Survey sampling; Cluster sampling; Ratio estimator; Econometrics; Bias of an estimator; Minimum-variance unbiased estimator; Computer science; Demography","score_opus":0.15412998701692696,"score_gpt":0.42401339108278235,"score_spread":0.2698834040658554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215800506","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":[0.11178631,0.0002809716,0.88750476,0.00020014598,0.00006696378,0.000086918015,0.00002503601,0.0000187171,0.00003019012],"genre_scores_gemma":[0.54381245,0.00011803754,0.45602834,0.000010233314,0.00001346897,0.0000030432977,0.0000034043383,0.000003707687,0.0000072927646],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998617,0.00019210331,0.00074654864,0.000117578646,0.00023653558,0.000090268935],"domain_scores_gemma":[0.9936609,0.005198207,0.0003757857,0.0001211206,0.00060193316,0.000041998326],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016623139,0.00009455971,0.0004098407,0.000046605357,0.00008852719,0.000020805664,0.000043825672,0.00006745085,0.000014412744],"category_scores_gemma":[0.015181959,0.000075840726,0.000047417743,0.000120521174,0.0001152445,0.00011310579,0.000030808274,0.00016841177,2.0160878e-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":[0.0005537155,0.0009778957,0.009476988,0.004273125,0.00056288997,0.00002640704,0.0019833886,0.03018765,0.002008991,0.8630357,0.0009001928,0.0860131],"study_design_scores_gemma":[0.00017596816,0.00014307752,0.02197649,0.00030112898,0.00007790185,0.00002188483,0.000271474,0.0041827355,0.0017570248,0.9709814,0.000022160233,0.0000887098],"about_ca_topic_score_codex":0.000012193283,"about_ca_topic_score_gemma":0.00000662009,"teacher_disagreement_score":0.43202618,"about_ca_system_score_codex":0.000045211047,"about_ca_system_score_gemma":0.000045591358,"threshold_uncertainty_score":0.9931136},"labels":[],"label_agreement":null},{"id":"W4220761010","doi":"10.1111/rssa.12805","title":"Analysis of Clustered Survey Data Based on Two-Stage Informative Sampling and Associated Two-Level Models","year":2022,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series A (Statistics in Society)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Cluster sampling; Matching (statistics); Statistics; Inference; Sampling (signal processing); Computer science; Bayesian probability; Statistical inference; Cluster (spacecraft); Sampling design; Population; Mathematics; Econometrics; Data mining; Artificial intelligence; Demography","score_opus":0.22993242625856886,"score_gpt":0.3951960580398399,"score_spread":0.16526363178127107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220761010","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":[0.020812908,0.000028497438,0.94908017,0.00010705699,0.00014751655,0.00024508106,0.02947017,0.00002624051,0.00008237613],"genre_scores_gemma":[0.4467822,0.00003006293,0.5521228,0.00030210975,0.00001884093,0.000010081703,0.0005823464,0.000033527103,0.000118041295],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957233,0.0009691777,0.0014751313,0.00027438276,0.0011993428,0.0003586807],"domain_scores_gemma":[0.9866217,0.0106379725,0.0015569121,0.0005612023,0.0005069359,0.00011531746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007517122,0.00027978423,0.0009305729,0.00010012936,0.0004789998,0.000094405324,0.0008330584,0.000101940226,0.0001232493],"category_scores_gemma":[0.00491128,0.00022855775,0.00031737948,0.001129734,0.00037809488,0.00020647429,0.0006713578,0.0009907192,1.5169503e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006724805,0.0009806233,0.035002016,0.00037755334,0.0035258632,0.000009483738,0.009678774,0.8854731,0.000010257805,0.041628726,0.020635264,0.0020058989],"study_design_scores_gemma":[0.0011535758,0.00020141262,0.027001236,0.00006600405,0.00057817204,0.0000017412881,0.0020207998,0.9297038,0.0000068030936,0.038991068,0.000043671425,0.00023171578],"about_ca_topic_score_codex":0.00063665275,"about_ca_topic_score_gemma":0.0005516554,"teacher_disagreement_score":0.4259693,"about_ca_system_score_codex":0.00043486245,"about_ca_system_score_gemma":0.00029059927,"threshold_uncertainty_score":0.93203145},"labels":[],"label_agreement":null},{"id":"W4224235507","doi":"10.31234/osf.io/emabf","title":"Correcting bias in extreme groups design using a missing data approach","year":2022,"lang":"en","type":"preprint","venue":"","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":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Missing data; Computer science; Statistics; Data collection; Variable (mathematics); Power (physics); Data mining; Mathematics","score_opus":0.8907203583539185,"score_gpt":0.4664453053583704,"score_spread":0.4242750529955481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224235507","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":[0.01653856,0.0001269945,0.97860646,0.000026168515,0.00038702122,0.000718807,0.000031773758,0.0008254313,0.0027387873],"genre_scores_gemma":[0.07237057,0.0000067527385,0.92684454,0.00003445302,0.0000870149,0.0000627041,0.00034498834,0.00008689556,0.00016207105],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966351,0.00091142463,0.0008010732,0.0008873293,0.00042324653,0.0003418425],"domain_scores_gemma":[0.9952892,0.002301709,0.00048690828,0.0018020074,0.000059744132,0.000060441453],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.008298529,0.00034781528,0.0005806934,0.0004117364,0.00020273692,0.00021837014,0.001086473,0.0002587149,0.00025709334],"category_scores_gemma":[0.0044253883,0.00035762214,0.000076835466,0.00033714712,0.000032000484,0.00015334568,0.002917654,0.0011265071,0.0000016926141],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065551803,0.006617691,0.040371563,0.015863832,0.0011108653,0.00032547026,0.03806756,0.32838798,0.0014220538,0.013515777,0.053853035,0.49980867],"study_design_scores_gemma":[0.0001518065,0.000010391161,0.00004985187,0.00040610108,0.00004849867,0.000056220488,0.000906443,0.9121426,0.00022353478,0.08548477,0.000044014312,0.00047578153],"about_ca_topic_score_codex":0.0013800906,"about_ca_topic_score_gemma":0.000024593654,"teacher_disagreement_score":0.5837546,"about_ca_system_score_codex":0.00030968565,"about_ca_system_score_gemma":0.0002652658,"threshold_uncertainty_score":0.9998876},"labels":[],"label_agreement":null},{"id":"W4225265622","doi":"10.1007/s13171-022-00281-8","title":"Cluster Correlations and Complexity in Binary Regression Analysis Using Two-stage Cluster Samples","year":2022,"lang":"en","type":"article","venue":"Sankhya A","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Mathematics; Statistics; Cluster sampling; Population; Cluster (spacecraft); Sample (material); Binary number; Regression analysis; Binary data; Correlation; Poisson sampling; Function (biology); Regression; Sample size determination; Sampling (signal processing); Computer science; Importance sampling; Demography; Physics","score_opus":0.27455777256376057,"score_gpt":0.4130207722257053,"score_spread":0.13846299966194475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225265622","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":[0.90810734,0.00008608159,0.09069694,0.00018551854,0.000067473346,0.00024255882,0.00009482041,0.00015119038,0.00036805478],"genre_scores_gemma":[0.90245444,0.000004086707,0.0970393,0.00012992331,0.000017215421,0.000034106906,0.000093747105,0.00001764351,0.00020953483],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860036,0.0004145578,0.00033949644,0.000246921,0.00022225355,0.00017640273],"domain_scores_gemma":[0.99870926,0.0007523744,0.00015941264,0.00029863598,0.000036337227,0.00004395832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010816187,0.00012953003,0.00027940623,0.00047961657,0.0003688243,0.000036017704,0.00010794301,0.00004299393,0.00047686422],"category_scores_gemma":[0.00025457627,0.00012159059,0.000083053244,0.00076921063,0.0000691093,0.00010808783,0.00025294514,0.00023370759,0.0000018361567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004683758,0.0010098853,0.8381396,0.00034042855,0.00058362365,0.00004180476,0.014574566,0.10105779,0.0011246676,0.02885856,0.009242426,0.0045582694],"study_design_scores_gemma":[0.0009865705,0.000064576416,0.054560423,0.00007715821,0.00027953828,0.00001929802,0.0013951838,0.8572008,0.00007894392,0.084274486,0.0006758104,0.00038720676],"about_ca_topic_score_codex":0.0005698464,"about_ca_topic_score_gemma":0.00038099848,"teacher_disagreement_score":0.7835792,"about_ca_system_score_codex":0.000109265646,"about_ca_system_score_gemma":0.000026679796,"threshold_uncertainty_score":0.5221329},"labels":[],"label_agreement":null},{"id":"W4234703289","doi":"10.5539/ijsp.v6n5p100","title":"Improving Estimation Accuracy in Non\\-randomized Response Questioning Methods by Multiple Answers","year":2017,"lang":"en","type":"article","venue":"International Journal of Statistics and Probability","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Randomized response; Respondent; Estimation; Computer science; Sample (material); Maximum likelihood; Statistics; Mathematics; Econometrics; Estimator; Economics","score_opus":0.05680252958917185,"score_gpt":0.4333470648051148,"score_spread":0.37654453521594294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234703289","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":[0.23694229,0.000031270025,0.7620613,0.00042890676,0.00024843548,0.00018201944,0.000065336,0.000012305131,0.0000281124],"genre_scores_gemma":[0.48271763,0.000024870604,0.5171979,0.000012491383,0.000019265399,0.0000072738785,0.000005167178,0.000005955663,0.000009423396],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998004,0.0006124582,0.0008316751,0.00014398654,0.00029778646,0.00011005251],"domain_scores_gemma":[0.9880431,0.009764408,0.0012502606,0.00019193586,0.000687613,0.00006262988],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011524281,0.000118275726,0.00036622683,0.00013317706,0.00013990836,0.00026240878,0.00030949354,0.00006809778,0.000013542575],"category_scores_gemma":[0.101750635,0.00010151647,0.00005952168,0.000026690535,0.00023222234,0.0004151443,0.000070127826,0.00022752401,3.9880564e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.05668008,0.00063695764,0.029605081,0.00032887087,0.00032623662,0.000054728127,0.003920778,0.0007571974,0.0060792356,0.030853007,0.0017884079,0.86896944],"study_design_scores_gemma":[0.014617877,0.000099140336,0.016335813,0.0002894623,0.00004267375,0.000041284133,0.00005659776,0.2130131,0.0022730087,0.7529655,0.000077215314,0.0001882926],"about_ca_topic_score_codex":0.00038559435,"about_ca_topic_score_gemma":0.000032953212,"teacher_disagreement_score":0.86878115,"about_ca_system_score_codex":0.00012169272,"about_ca_system_score_gemma":0.00008842642,"threshold_uncertainty_score":0.9058157},"labels":[],"label_agreement":null},{"id":"W4238602643","doi":"10.1007/978-3-662-53120-4_300648","title":"Sputter Deposition","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Sputtering; Materials science; Deposition (geology); Nanotechnology; Geology; Thin film; Paleontology","score_opus":0.11903210071359917,"score_gpt":0.33276222906310793,"score_spread":0.21373012834950877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238602643","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013916509,0.00001895758,0.118770175,0.00007525917,0.00012747903,0.00018125432,0.000009439616,0.0005153487,0.8802882],"genre_scores_gemma":[0.0004490337,0.000014497232,0.0841153,0.00022912076,0.00009865942,0.000004013539,0.00006127689,0.00006135011,0.91496676],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99932855,0.000007856256,0.00022729055,0.0001794674,0.00016641985,0.000090420486],"domain_scores_gemma":[0.9991934,0.00023995496,0.0001223552,0.00034727884,0.000070788396,0.000026274105],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018769254,0.00017386542,0.00022631697,0.00009028349,0.000025956055,0.00002789765,0.00009015551,0.00028805019,0.0023421887],"category_scores_gemma":[0.000036408634,0.00015173464,0.000103528815,0.000006390949,0.00001593315,0.000038235856,0.000030797124,0.00016989317,0.0014952992],"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":[0.0000033750223,0.0000064908036,0.0000054058182,0.0000966197,0.00002761223,0.0000020706254,0.000016361751,2.0937979e-7,0.000011527891,0.900918,0.093402684,0.005509618],"study_design_scores_gemma":[0.000064148386,0.00003281204,0.000006594692,0.00024608924,0.00004157977,0.000013041129,0.0000011041334,0.00007275314,0.00069893856,0.9442923,0.0542543,0.0002763442],"about_ca_topic_score_codex":0.0000075681905,"about_ca_topic_score_gemma":0.0000059444383,"teacher_disagreement_score":0.043374266,"about_ca_system_score_codex":0.000036359932,"about_ca_system_score_gemma":0.00002395506,"threshold_uncertainty_score":0.9992822},"labels":[],"label_agreement":null},{"id":"W4242275550","doi":"10.1007/978-1-4939-7131-2_100746","title":"Network Sampling","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Sampling (signal processing); Environmental science; Computer science; Computer vision","score_opus":0.2710469549354656,"score_gpt":0.37474260075512217,"score_spread":0.10369564581965657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242275550","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005649564,0.00005932189,0.23076397,0.000027827564,0.00018356855,0.00013784373,0.000007168965,0.0009261461,0.7678885],"genre_scores_gemma":[0.00003849763,0.000020381547,0.33266655,0.00016576074,0.0008820394,0.000005937822,0.00002832228,0.00007901419,0.6661135],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99898154,0.0000103637585,0.00035550745,0.00025384725,0.00019723795,0.00020150167],"domain_scores_gemma":[0.9984857,0.00063601957,0.0001974348,0.00047909858,0.00014632076,0.000055427296],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00063688855,0.00025266985,0.00033951286,0.000066559114,0.000096659795,0.00004183737,0.00017657001,0.0003689565,0.008221856],"category_scores_gemma":[0.0001832158,0.00022456814,0.00011351369,0.000016175656,0.00006099652,0.000029953164,0.000074319956,0.0002197793,0.0008416198],"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":[0.0000032306216,0.0000029954613,0.0000023637074,0.000034153196,0.0000260927,7.188435e-7,0.00001937801,0.0000010686254,3.4309826e-7,0.6677432,0.33012804,0.0020383901],"study_design_scores_gemma":[0.000025121253,0.000021759486,0.0000011362058,0.00021997983,0.000025841106,0.0000038594567,0.0000011986524,0.00002526146,0.00001199994,0.74856967,0.25089198,0.00020219845],"about_ca_topic_score_codex":0.0000047897165,"about_ca_topic_score_gemma":0.000008887428,"teacher_disagreement_score":0.1019026,"about_ca_system_score_codex":0.00003744354,"about_ca_system_score_gemma":0.00003026028,"threshold_uncertainty_score":0.99993634},"labels":[],"label_agreement":null},{"id":"W4247174712","doi":"10.1111/j.1751-5823.2011.00145.x","title":"Discussions","year":2011,"lang":"en","type":"article","venue":"International Statistical Review","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":"University of Waterloo","funders":"Office of Naval Research; National Institutes of Health; National Science Foundation","keywords":"Chatterjee; Statistics; Chen; Library science; Mathematics; Biostatistics; Computer science; Artificial intelligence; Medicine","score_opus":0.37185557481601134,"score_gpt":0.4727230996262103,"score_spread":0.10086752481019895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247174712","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":[0.000051279712,0.0008782201,0.8996395,0.000826,0.00024017852,0.00019230864,0.0001082467,0.00021782448,0.09784644],"genre_scores_gemma":[0.08078705,0.006959518,0.9088242,0.0015946832,0.00009195522,0.00014145854,0.000105932624,0.000031200834,0.0014640129],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99922854,0.00005682294,0.00028636924,0.00012167125,0.0002138225,0.00009279137],"domain_scores_gemma":[0.9991434,0.00048907136,0.000066661785,0.00013990968,0.00009541383,0.00006550039],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00040627172,0.00007454197,0.00014398144,0.000026306727,0.00003136597,0.000009464798,0.00018417728,0.000022108608,0.0072487686],"category_scores_gemma":[0.0039405576,0.000051675615,0.0000441883,0.00005459236,0.000037980397,0.00005295272,0.000039140315,0.00007839771,0.0002682722],"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":[0.0000030922808,0.00006941445,0.00013491312,0.00015432505,0.000015641588,0.000005690763,0.000022877031,6.4742047e-9,0.0000020044515,0.8744994,0.05458755,0.07050508],"study_design_scores_gemma":[0.00006085608,0.000022984132,0.0024410263,0.0013662152,0.00003430092,0.000016324468,0.0000047376047,0.0000834964,0.00006232689,0.92431265,0.07146944,0.00012565154],"about_ca_topic_score_codex":0.000025540461,"about_ca_topic_score_gemma":0.000003196555,"teacher_disagreement_score":0.09638243,"about_ca_system_score_codex":0.000022602037,"about_ca_system_score_gemma":0.00001159141,"threshold_uncertainty_score":0.9936587},"labels":[],"label_agreement":null},{"id":"W4247186967","doi":"10.1007/978-0-387-70782-2","title":"Indirect Sampling","year":2007,"lang":"en","type":"book","venue":"Springer series in statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":60,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Sampling (signal processing); Environmental science; Computer science; Statistics; Psychology; Mathematics; Computer vision","score_opus":0.13620423966175615,"score_gpt":0.3843215157834575,"score_spread":0.24811727612170137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247186967","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":[0.00009147884,0.0002623938,0.6790626,0.000014952474,0.00090810837,0.00044819477,0.0007257178,0.00071513705,0.3177714],"genre_scores_gemma":[0.00008213292,0.00017871101,0.7248927,0.00004147417,0.00022177615,0.000024903655,0.0002330316,0.00014507188,0.27418023],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99783254,0.000054903987,0.0008356698,0.00040254614,0.0004372938,0.00043702152],"domain_scores_gemma":[0.996853,0.0019188353,0.00039568797,0.00057372474,0.00017687451,0.00008187705],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013611972,0.00042008027,0.0006876156,0.0004597708,0.00008669719,0.00007318531,0.00031266743,0.00049594714,0.00023656889],"category_scores_gemma":[0.0018436215,0.00046728697,0.0000694855,0.00014367308,0.00018250247,0.00008810934,0.00014778938,0.0007729352,0.000060356157],"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":[0.000077194905,0.00008029552,0.0005622325,0.0014791864,0.00010454062,0.00015361965,0.0011000903,0.000013724298,0.0000065027393,0.83304834,0.12483006,0.038544185],"study_design_scores_gemma":[0.00012180546,0.00005247591,0.0002905813,0.0006122569,0.000042359654,0.000014820969,0.000025284135,0.000025919167,0.00015860602,0.8480011,0.1501033,0.0005514766],"about_ca_topic_score_codex":0.00002388242,"about_ca_topic_score_gemma":0.000291977,"teacher_disagreement_score":0.045830052,"about_ca_system_score_codex":0.00038566793,"about_ca_system_score_gemma":0.0002636064,"threshold_uncertainty_score":0.9997779},"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":"W4252825074","doi":"10.1007/978-1-4614-6170-8_100306","title":"Network Sampling","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Sampling (signal processing); Computer vision","score_opus":0.22779250425297923,"score_gpt":0.3584170620774445,"score_spread":0.13062455782446528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252825074","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001033496,0.000040106752,0.4382025,0.000031974043,0.00010567797,0.00009324404,0.0000028618886,0.0006807922,0.5608418],"genre_scores_gemma":[0.00014355723,0.000019915022,0.29771912,0.00025098032,0.00059287477,0.0000071177483,0.00003200919,0.00008697413,0.70114744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99898505,0.000014326594,0.00036871035,0.00024172758,0.00019610657,0.00019406216],"domain_scores_gemma":[0.9981463,0.0010148581,0.00020996133,0.00047781286,0.00009368683,0.000057372472],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00076471595,0.00025623292,0.0003960339,0.00006510689,0.00008375023,0.00003888815,0.00016977687,0.0003611313,0.001612795],"category_scores_gemma":[0.00021480332,0.00022859397,0.00012489442,0.00001279545,0.000032837852,0.00001591892,0.000060172064,0.00026978608,0.00037775643],"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":[0.0000019661582,0.000001631913,0.0000027767014,0.000044713295,0.000018617964,4.126035e-7,0.0000057200905,0.000008497026,2.673346e-7,0.8687446,0.12388301,0.007287762],"study_design_scores_gemma":[0.000026766853,0.000013511651,0.0000013291406,0.00019714623,0.000024413064,0.000003115131,3.778529e-7,0.00006271893,0.0000054172447,0.6995131,0.29995558,0.00019656777],"about_ca_topic_score_codex":0.0000058849696,"about_ca_topic_score_gemma":0.0000065509894,"teacher_disagreement_score":0.17607257,"about_ca_system_score_codex":0.00003169018,"about_ca_system_score_gemma":0.000021210157,"threshold_uncertainty_score":0.9992999},"labels":[],"label_agreement":null},{"id":"W4252872151","doi":"10.1007/978-94-007-0753-5_104302","title":"Two-Stage Sampling","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University; University of Northern British Columbia","funders":"","keywords":"Stage (stratigraphy); Sampling (signal processing); Mathematics; Computer science; Geology; Paleontology; Computer vision","score_opus":0.2340493557911223,"score_gpt":0.3910345699989679,"score_spread":0.1569852142078456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4252872151","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000058675278,0.000020359712,0.38648364,0.000026365786,0.00009458814,0.00012030008,0.000014437893,0.0008103381,0.61242414],"genre_scores_gemma":[0.00032674978,0.000016592374,0.23871186,0.00013495315,0.0001858576,0.000007863185,0.0000420137,0.00009498102,0.7604791],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988462,0.000016204598,0.0004162605,0.00029414735,0.0002497903,0.00017741157],"domain_scores_gemma":[0.9980701,0.0009097196,0.00024441667,0.0005914627,0.000113989285,0.0000702992],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00075133843,0.00030100258,0.00042855926,0.00014553922,0.00007603797,0.000051354273,0.00020273893,0.00028270332,0.0031940981],"category_scores_gemma":[0.0003031441,0.00026942987,0.0001609585,0.000012339147,0.000043189655,0.000025298925,0.00007062502,0.00030338232,0.0004998912],"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":[0.000002503153,0.0000035968053,0.0000023879834,0.00009025317,0.000024651794,0.0000010167499,0.000017775128,0.0000024755232,0.0000052876676,0.9838229,0.0101822,0.005844975],"study_design_scores_gemma":[0.000083840096,0.000018221035,7.875516e-7,0.00018361285,0.000028555496,0.0000035778385,0.0000027474132,0.0001295103,0.0001329859,0.6942445,0.30486757,0.0003041014],"about_ca_topic_score_codex":0.000027461836,"about_ca_topic_score_gemma":0.00002647475,"teacher_disagreement_score":0.29468536,"about_ca_system_score_codex":0.00004543302,"about_ca_system_score_gemma":0.000029215042,"threshold_uncertainty_score":0.9999758},"labels":[],"label_agreement":null},{"id":"W4288050399","doi":"10.1002/cjs.11717","title":"Statistical inference from finite population samples: A critical review of frequentist and Bayesian approaches","year":2022,"lang":"en","type":"review","venue":"Canadian Journal of Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Statistics Canada","funders":"","keywords":"Frequentist inference; Statistics; Bayesian probability; Population; Point estimation; Statistical inference; Inference; Sampling (signal processing); Fiducial inference; Context (archaeology); Econometrics; Poisson sampling; Computer science; Population variance; Mathematics; Bayesian statistics; Bayesian inference; Artificial intelligence; Markov chain Monte Carlo; Slice sampling; Geography","score_opus":0.43906916507925553,"score_gpt":0.4184496835917175,"score_spread":0.020619481487538005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288050399","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.3469732e-7,0.5833505,0.40536347,0.000016904714,0.00013373014,0.00017344081,0.0109097855,0.0000069792427,0.000044870943],"genre_scores_gemma":[0.000059281756,0.68920785,0.30962586,0.000030020408,0.00005406571,0.000012175923,0.000965688,0.0000388489,0.0000062050394],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99669075,0.000628333,0.0018023492,0.00022355556,0.00039400783,0.0002610177],"domain_scores_gemma":[0.98433316,0.013454664,0.001198062,0.00029580639,0.00021788102,0.0005004476],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013504843,0.0003129418,0.0018587078,0.0003680476,0.00013965149,0.000073272306,0.00030723755,0.00016478996,0.0013614433],"category_scores_gemma":[0.029916596,0.0002902018,0.00014732599,0.00018522587,0.00023072184,0.000084792635,0.000031979966,0.0006683472,0.0000015172598],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022902514,0.000026772126,0.00012741813,0.08356478,0.00013327443,0.000120916826,0.00012651754,5.567242e-7,4.7468607e-9,0.099058226,0.006505193,0.810334],"study_design_scores_gemma":[0.00015388618,0.00023384651,0.0001743019,0.12036554,0.0029141535,0.00025605675,0.00007125569,0.00018172641,1.3652327e-7,0.37460172,0.50037885,0.00066852814],"about_ca_topic_score_codex":0.004825876,"about_ca_topic_score_gemma":0.0027906636,"teacher_disagreement_score":0.8096655,"about_ca_system_score_codex":0.00024199896,"about_ca_system_score_gemma":0.0017055371,"threshold_uncertainty_score":0.999955},"labels":[],"label_agreement":null},{"id":"W4288758431","doi":"10.1177/00131644221104220","title":"Supervised Classes, Unsupervised Mixing Proportions: Detection of Bots in a Likert-Type Questionnaire","year":2022,"lang":"en","type":"article","venue":"Educational and Psychological Measurement","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mahalanobis distance; Cutoff; Sample (material); Statistics; Likert scale; Computer science; Calibration; Sample size determination; Mixture model; Artificial intelligence; Mathematics","score_opus":0.26873442613628207,"score_gpt":0.39222254678309215,"score_spread":0.12348812064681008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288758431","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":[0.9930046,0.0006488898,0.0027558007,0.002031524,0.00044594333,0.00051220367,0.00002065914,0.000099561265,0.00048082246],"genre_scores_gemma":[0.99281573,0.000021795498,0.0065687075,0.00010686591,0.000046460427,0.00035479298,0.000028165749,0.000008481312,0.000049014696],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984796,0.00028097315,0.0003989543,0.00024624937,0.00046556507,0.00012866585],"domain_scores_gemma":[0.9992567,0.00019596113,0.00011640697,0.00015320841,0.00022780607,0.000049956412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014335747,0.00010382205,0.00015654086,0.00013877903,0.00017205007,0.000012788474,0.00009768427,0.00004895828,0.0008092291],"category_scores_gemma":[0.0011921774,0.00009280968,0.000037781432,0.00036285506,0.0000442143,0.00005229746,0.000029213263,0.0001877497,0.0000024844765],"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":[0.002614918,0.03839879,0.36395493,0.0016836012,0.00035091452,0.000015858035,0.009824151,0.0003757777,0.14080848,0.09760879,0.052325018,0.29203877],"study_design_scores_gemma":[0.0008792763,0.0010020375,0.6636363,0.00026616163,0.000027385382,0.00005106574,0.0006229338,0.0004660399,0.0013644062,0.32880208,0.0025055353,0.00037674588],"about_ca_topic_score_codex":0.000056310077,"about_ca_topic_score_gemma":0.000029421213,"teacher_disagreement_score":0.2996814,"about_ca_system_score_codex":0.00013866684,"about_ca_system_score_gemma":0.000075936856,"threshold_uncertainty_score":0.8860491},"labels":[],"label_agreement":null},{"id":"W4290613457","doi":"10.1177/00491241221113877","title":"The Design and Optimality of Survey Counts: A Unified Framework Via the Fisher Information Maximizer","year":2022,"lang":"en","type":"article","venue":"Sociological Methods & Research","topic":"Survey Sampling and Estimation Techniques","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 British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Hong Kong Polytechnic University","keywords":"Fisher information; Range (aeronautics); Mathematics; Statistics; Generalized linear model; Computer science; Econometrics; Optimal design; Mathematical optimization","score_opus":0.6171696352915063,"score_gpt":0.5685923866874328,"score_spread":0.04857724860407342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4290613457","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":[0.0052647796,0.00014321091,0.9920392,0.0008009196,0.000061339124,0.00041931352,0.000013588661,0.00005664245,0.0012010101],"genre_scores_gemma":[0.10367368,0.000100175064,0.8957006,0.000112676484,0.0000189005,0.00023647318,0.000008276874,0.000007682564,0.00014158296],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9831102,0.015926229,0.00026674007,0.00010183862,0.00039091444,0.00020409036],"domain_scores_gemma":[0.9493376,0.049991872,0.000091597496,0.0002873913,0.00026426464,0.000027299278],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.067398556,0.00006217152,0.00014334076,0.000033043514,0.00078219624,0.00004634321,0.00032662586,0.000105924315,0.00026070984],"category_scores_gemma":[0.019930165,0.00003191103,0.000036829962,0.00027556837,0.00050383684,0.000043123364,0.0002632465,0.00078289607,0.00000515025],"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":[0.0010294187,0.000255829,0.005992867,0.00014446085,0.00020369647,0.0000015187296,0.007119836,0.00022882727,0.0002001848,0.44083023,0.07579109,0.46820202],"study_design_scores_gemma":[0.00005499393,0.000104846884,0.007884416,0.0000041169037,0.0000035875873,0.000001393333,0.0005302235,0.002535113,0.00009247405,0.9843289,0.0044095484,0.000050348823],"about_ca_topic_score_codex":0.000093506715,"about_ca_topic_score_gemma":4.0657048e-7,"teacher_disagreement_score":0.5434987,"about_ca_system_score_codex":0.00004422359,"about_ca_system_score_gemma":0.00004637995,"threshold_uncertainty_score":0.98832536},"labels":[],"label_agreement":null},{"id":"W4297920516","doi":"10.31234/osf.io/nu26z","title":"Model-agnostic unsupervised detection of bots in a Likert-type questionnaire","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Respondent; Computer science; Likert scale; Permutation (music); Calibration; Sensitivity (control systems); Statistical hypothesis testing; Null hypothesis; Type I and type II errors; Relation (database); Outlier; Data mining; Artificial intelligence; Machine learning; Algorithm; Statistics; Mathematics; Engineering","score_opus":0.14190345853495273,"score_gpt":0.37203078547473073,"score_spread":0.230127326939778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297920516","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":[0.5245341,0.00020910552,0.47155255,0.00009206031,0.0004479266,0.000772105,0.000024045828,0.00084762834,0.0015204394],"genre_scores_gemma":[0.9511246,0.00008331781,0.0481962,0.000028019313,0.000020249074,0.00017570505,0.000041295538,0.00004357534,0.00028701892],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99828357,0.000222543,0.00064688973,0.00035812586,0.000319367,0.000169486],"domain_scores_gemma":[0.99847806,0.0004415162,0.00025349567,0.00059204985,0.00019286711,0.00004204542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104737,0.00023181427,0.00043878073,0.00037196674,0.000054478318,0.00002029937,0.00026660867,0.0002848051,0.00017799533],"category_scores_gemma":[0.0021524895,0.00024043731,0.00010954105,0.00028462947,0.000031047242,0.000053203603,0.0003698159,0.0006031062,0.000003914332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089073944,0.003541234,0.026910413,0.013069858,0.00040181942,0.00004201005,0.011157925,0.845674,0.010375463,0.034310818,0.0047824425,0.048843294],"study_design_scores_gemma":[0.00023656333,0.000100327874,0.001978327,0.00068311684,0.000048347752,0.0000036151355,0.00006147748,0.4954806,0.005074184,0.49594933,0.00001752998,0.0003666002],"about_ca_topic_score_codex":0.0010499414,"about_ca_topic_score_gemma":0.00044732576,"teacher_disagreement_score":0.4616385,"about_ca_system_score_codex":0.00019976436,"about_ca_system_score_gemma":0.00018467162,"threshold_uncertainty_score":0.9804749},"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":"W4310935478","doi":"10.1016/b978-0-323-90799-6.00037-9","title":"Sampling Methods and Theory","year":2022,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Sampling (signal processing); Cluster sampling; Probability sampling; Nonprobability sampling; Statistics; Sampling theory; Temptation; Stratified sampling; Poisson sampling; Sampling design; Lot quality assurance sampling; Sample (material); Computer science; Mathematics; Sample size determination; Importance sampling; Slice sampling; Monte Carlo method; Psychology; Sociology","score_opus":0.12984616627775453,"score_gpt":0.40561286259849555,"score_spread":0.275766696320741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310935478","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000009413158,0.0010482678,0.01593726,0.000021464533,0.0002096071,0.00036983128,0.000045899305,0.00046622395,0.98189205],"genre_scores_gemma":[0.00001181696,0.00008976204,0.32441968,0.00011622161,0.000086794564,0.00005660921,0.00002004634,0.00010647674,0.6750926],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99846685,0.00023046239,0.00045935798,0.00040309335,0.00024058028,0.00019965835],"domain_scores_gemma":[0.9965944,0.0024052304,0.00029471293,0.0005630185,0.00006128623,0.00008129521],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0036190134,0.00034796674,0.00054885366,0.00018661832,0.00023250583,0.000049568047,0.0002134226,0.0002390261,0.0013281739],"category_scores_gemma":[0.0004607221,0.00033612235,0.00015897794,0.00001031562,0.00011347169,0.000030178888,0.00026154684,0.00061946595,0.000017374643],"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":[0.0000065162985,0.000002510756,4.95179e-7,0.00009084694,0.000049344126,0.000002173392,0.00020218344,8.798944e-8,0.000009176263,0.32866332,0.00008913724,0.6708842],"study_design_scores_gemma":[0.00004105423,0.000018551265,9.144892e-7,0.00010253465,0.00006776573,0.000015075232,0.000007711768,0.000003838312,0.000038559156,0.5148037,0.48470402,0.00019624928],"about_ca_topic_score_codex":4.058779e-7,"about_ca_topic_score_gemma":0.0000013973297,"teacher_disagreement_score":0.670688,"about_ca_system_score_codex":0.000068205394,"about_ca_system_score_gemma":0.00005232651,"threshold_uncertainty_score":0.9999091},"labels":[],"label_agreement":null},{"id":"W4312447901","doi":"10.2478/stattrans-2022-0010","title":"Variance estimation in stratified adaptive cluster sampling","year":2022,"lang":"en","type":"article","venue":"Statistics in Transition New Series","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"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 Waterloo","funders":"","keywords":"Estimator; Cluster sampling; Stratified sampling; Statistics; Sampling (signal processing); Simple random sample; Sampling design; Variance (accounting); Mathematics; Population variance; Mean squared error; Multistage sampling; Population; Slice sampling; Importance sampling; Computer science; Monte Carlo method","score_opus":0.08296716982804798,"score_gpt":0.34688744362688245,"score_spread":0.2639202737988345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312447901","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":[0.009219102,0.000016171902,0.98900306,0.0004117873,0.00013587091,0.00033041072,0.0004095431,0.00013614251,0.0003379253],"genre_scores_gemma":[0.42544097,0.0000064066435,0.5740736,0.00008528612,0.000014437405,0.000087025364,0.00016832948,0.000017884515,0.000106051084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986008,0.00023149292,0.00048280988,0.00022582893,0.0002664057,0.0001927024],"domain_scores_gemma":[0.99897695,0.00066349143,0.000113133,0.00016156345,0.0000472676,0.000037598333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007600885,0.00013899998,0.00021085345,0.00020219728,0.00014718396,0.000040651383,0.000101407015,0.000048729165,0.00025090217],"category_scores_gemma":[0.00027843117,0.00017027013,0.000021889788,0.00033863637,0.000041167088,0.00023389148,0.00002031455,0.00029456677,0.0000031822362],"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":[0.00066151307,0.00025930788,0.00013415728,0.00018464995,0.000020930247,0.00003181413,0.017862882,0.14694276,0.00028713094,0.8172344,0.0034197427,0.012960707],"study_design_scores_gemma":[0.00061330735,0.00015173673,0.0010352789,0.00006618025,0.000010554333,0.000015124612,0.0012432396,0.05772256,0.00032698375,0.93850017,0.000099654666,0.00021521085],"about_ca_topic_score_codex":0.00028240256,"about_ca_topic_score_gemma":0.0007957708,"teacher_disagreement_score":0.41622186,"about_ca_system_score_codex":0.0001585846,"about_ca_system_score_gemma":0.000119221404,"threshold_uncertainty_score":0.6943414},"labels":[],"label_agreement":null},{"id":"W4322496125","doi":"10.28924/2291-8639-21-2023-14","title":"Estimation of Finite Population Mean by Utilizing the Auxiliary and Square of the Auxiliary Information","year":2023,"lang":"en","type":"article","venue":"International Journal of Analysis and Applications","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Mathematics; Proposition; Estimation; Population mean; Dual (grammatical number); Scheme (mathematics); Population; Variable (mathematics); Mean squared error; Mathematical optimization; Statistics; Applied mathematics; Demography; Sociology; Mathematical analysis; Engineering; Linguistics","score_opus":0.03547363057261326,"score_gpt":0.3478926133780345,"score_spread":0.31241898280542124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322496125","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":[0.7291012,0.00010360943,0.26825505,0.0018220823,0.00006600121,0.00025276683,0.00014370946,0.000034213273,0.00022135008],"genre_scores_gemma":[0.9968939,0.00015012712,0.0027834899,0.000034257508,0.000025183388,0.000012926846,0.00007624001,0.000004297774,0.000019572322],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99875045,0.00006862618,0.0006744963,0.00006255729,0.000389672,0.000054196993],"domain_scores_gemma":[0.9978474,0.0006644028,0.0008862665,0.00015763371,0.00042030952,0.000023981998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097060436,0.00007131078,0.00017853669,0.0003270586,0.00010399998,0.00004117016,0.00022305775,0.000042289714,0.000008548835],"category_scores_gemma":[0.0003827596,0.00004554268,0.00012902425,0.000661992,0.00007027581,0.00027067977,0.000057649002,0.00009414363,6.08691e-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":[0.00015499642,0.00045609032,0.22542869,0.00043995932,0.0043557887,7.7223496e-7,0.008329762,0.047829792,0.0030538854,0.17652728,0.008229085,0.5251939],"study_design_scores_gemma":[0.00070855644,0.00007975713,0.42505124,0.00031578785,0.0016324288,0.000025987052,0.003066887,0.35593572,0.00720067,0.20381385,0.001896274,0.00027284547],"about_ca_topic_score_codex":0.00011117427,"about_ca_topic_score_gemma":0.000019970676,"teacher_disagreement_score":0.52492106,"about_ca_system_score_codex":0.000019818828,"about_ca_system_score_gemma":0.000020309912,"threshold_uncertainty_score":0.18571767},"labels":[],"label_agreement":null},{"id":"W4382751254","doi":"10.5267/j.msl.2023.5.001","title":"A new improved estimator for the population mean using twofold auxiliary information under simple random sampling","year":2023,"lang":"en","type":"article","venue":"Management Science Letters","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Mean squared error; Population mean; Mathematics; Ratio estimator; Simple random sample; Statistics; Efficient estimator; Bias of an estimator; Variable (mathematics); Rank (graph theory); Minimum mean square error; Population; Simple (philosophy); Invariant estimator; Applied mathematics; Minimum-variance unbiased estimator; Combinatorics","score_opus":0.11600474728146389,"score_gpt":0.37414338689413995,"score_spread":0.2581386396126761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382751254","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":[0.10171099,0.0000016955914,0.8942529,0.0023197795,0.000251112,0.00092796964,0.0000039836655,0.0004909206,0.000040637704],"genre_scores_gemma":[0.5732263,0.0000033305314,0.42446455,0.0019706322,0.00008887513,0.0001166121,0.00005011979,0.000022830875,0.000056768426],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866897,0.000023735553,0.00033836663,0.00020897867,0.00040583275,0.0003541137],"domain_scores_gemma":[0.99883676,0.0005438172,0.00017743286,0.00035500174,0.000033251956,0.00005373524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002690026,0.00013044813,0.00012540806,0.0003569235,0.00076050253,0.00033876815,0.00037381577,0.000026770933,0.0000067709484],"category_scores_gemma":[0.0003481399,0.000100902296,0.00006735026,0.0008382799,0.00006773598,0.00088115205,0.00012861047,0.00006281685,0.000010623707],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003781448,0.00008384317,0.014143726,0.0013614461,0.0003350681,0.0000029590176,0.0046725734,0.38647002,0.018851377,0.18946603,0.082328685,0.30190614],"study_design_scores_gemma":[0.00091883756,0.0000146614175,0.0148633905,0.000060222083,0.00008081057,0.0000013479332,0.00078529073,0.9069311,0.00048974814,0.07489146,0.0007079019,0.00025520154],"about_ca_topic_score_codex":0.00039935074,"about_ca_topic_score_gemma":0.000011687573,"teacher_disagreement_score":0.5204611,"about_ca_system_score_codex":0.00012679097,"about_ca_system_score_gemma":0.000014025463,"threshold_uncertainty_score":0.58492476},"labels":[],"label_agreement":null},{"id":"W4386011332","doi":"10.1038/s41598-023-40687-4","title":"Combination of memory type ratio and product estimators under extended EWMA statistic with application to wheat production","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"King Saud University","keywords":"Estimator; Statistic; Statistics; EWMA chart; Mean squared error; Computer science; Population; Mathematics; Control chart","score_opus":0.051829002382278784,"score_gpt":0.341565493740901,"score_spread":0.28973649135862223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386011332","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":[0.8673991,0.000013617674,0.1295454,0.0003895581,0.0010443615,0.0010411296,0.0000021274197,0.0004330517,0.0001316279],"genre_scores_gemma":[0.9677952,0.0000014080678,0.030475745,0.000005532944,0.000018740559,0.00008889438,0.000094115116,0.00001873639,0.0015016411],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985504,0.000049292725,0.0003697162,0.00050032896,0.00039817442,0.0001320772],"domain_scores_gemma":[0.99851274,0.00009275675,0.00026133907,0.00057009724,0.00050855096,0.00005448192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021983802,0.0000993943,0.0001547419,0.00027933082,0.0001734536,0.00007397483,0.00004774714,0.000028716087,0.000007700159],"category_scores_gemma":[0.0013142526,0.000084772866,0.000012371848,0.0010609084,0.000121656456,0.00014846114,0.00002740183,0.000047859507,0.000009479523],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003332729,0.0013994466,0.021295944,0.0032138317,0.00020308276,0.00007435066,0.011913243,0.014416379,0.47576156,0.05220555,0.28735012,0.13183323],"study_design_scores_gemma":[0.00020034677,0.00022588391,0.030679768,0.0002563734,0.0000792408,0.00018963279,0.00044762192,0.007223002,0.3380449,0.62173593,0.0005008329,0.00041644365],"about_ca_topic_score_codex":0.000027968505,"about_ca_topic_score_gemma":0.000022983948,"teacher_disagreement_score":0.5695304,"about_ca_system_score_codex":0.000035912788,"about_ca_system_score_gemma":0.00008833844,"threshold_uncertainty_score":0.34569374},"labels":[],"label_agreement":null},{"id":"W4386833686","doi":"10.1017/xps.2023.24","title":"Assessing the Validity of Prevalence Estimates in Double List Experiments","year":2023,"lang":"en","type":"article","venue":"Journal of Experimental Political Science","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"American Political Science Association","keywords":"Identification (biology); Variance (accounting); Estimator; Econometrics; Computer science; Population; Frontier; Social desirability bias; Psychology; Sensitivity (control systems); Data science; Statistics; Social psychology; Mathematics; Geography; Social desirability; Economics; Sociology; Engineering; Demography","score_opus":0.32898889808531834,"score_gpt":0.5234984095083213,"score_spread":0.19450951142300293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386833686","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":[0.9972208,0.000044979974,0.0008490566,0.00020849585,0.00018371917,0.00009564263,0.0000014375454,0.000032944554,0.0013628971],"genre_scores_gemma":[0.98904365,0.0000032913795,0.010848558,0.000029565022,0.000040108273,0.000005757631,1.9614804e-7,0.000006778663,0.000022074379],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981202,0.00007520371,0.00055529067,0.00012890542,0.0007038928,0.00041652622],"domain_scores_gemma":[0.9983706,0.0009085186,0.0002446042,0.00018561994,0.00014183577,0.00014881657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003648471,0.00009393346,0.00020546354,0.00018595967,0.00013640072,0.00012066597,0.00051639293,0.00003299245,0.00003984105],"category_scores_gemma":[0.001655479,0.00006108593,0.000067991336,0.0006217284,0.00068832305,0.000635689,0.0001394097,0.0001445857,0.0000033650708],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048166334,0.00088137924,0.054155417,0.00013146759,0.000012782238,0.000027671456,0.002741676,0.00003433024,0.6245624,0.31653684,0.0005914433,0.00027642204],"study_design_scores_gemma":[0.0002592798,0.00011806497,0.023077223,0.00021335369,0.0000054101993,0.000030988453,0.0016449242,0.0012099952,0.9305559,0.042803742,0.000004776774,0.00007638336],"about_ca_topic_score_codex":0.000075960656,"about_ca_topic_score_gemma":5.51505e-7,"teacher_disagreement_score":0.30599347,"about_ca_system_score_codex":0.00019344324,"about_ca_system_score_gemma":0.00015554296,"threshold_uncertainty_score":0.2536155},"labels":[],"label_agreement":null},{"id":"W4387660977","doi":"10.1080/10669817.2023.2262336","title":"An international consensus on gaps in mechanisms of forced-based manipulation research: findings from a nominal group technique","year":2023,"lang":"en","type":"article","venue":"Journal of Manual & Manipulative Therapy","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":13,"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 Trois-Rivières; Canadian Memorial Chiropractic College","funders":"National Center for Complementary and Integrative Health","keywords":"Nominal group technique; Medicine; Psychology; Computer science; Artificial intelligence","score_opus":0.35205080525606935,"score_gpt":0.481175468363598,"score_spread":0.12912466310752863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387660977","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":[0.9078985,0.000008152984,0.09092714,0.00029571482,0.00015933908,0.00043658676,0.000029737763,0.00008366202,0.00016116316],"genre_scores_gemma":[0.94026875,0.000022228573,0.05943737,0.00004567477,0.00009148648,0.000029676645,0.00004172886,0.000039446833,0.000023647232],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99704796,0.00067367725,0.0009092005,0.00022845395,0.0008913632,0.0002493157],"domain_scores_gemma":[0.9963732,0.0021932372,0.0005738594,0.000272698,0.00051393494,0.00007307818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005497711,0.00019378951,0.00041651464,0.0013721928,0.000078484736,0.000043520686,0.00042895644,0.0001625372,0.00010829258],"category_scores_gemma":[0.00060640776,0.00016985525,0.0001368856,0.0005128168,0.000088645786,0.00020771712,0.000030766278,0.0004998407,0.000007022097],"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":[0.012988641,0.0029848407,0.019704312,0.00016513903,0.00049111206,0.00035024545,0.0075905477,0.008054284,0.64788127,0.28316855,0.0031559006,0.013465193],"study_design_scores_gemma":[0.001795794,0.0020710619,0.07547045,0.00058909797,0.000011313314,0.000014657791,0.000724331,0.010882629,0.16812886,0.74001664,0.00006853363,0.00022664394],"about_ca_topic_score_codex":0.00016385803,"about_ca_topic_score_gemma":0.000038596572,"teacher_disagreement_score":0.4797524,"about_ca_system_score_codex":0.00020907454,"about_ca_system_score_gemma":0.000058982976,"threshold_uncertainty_score":0.6926496},"labels":[],"label_agreement":null},{"id":"W4388821770","doi":"10.3758/s13428-023-02246-7","title":"Model-agnostic unsupervised detection of bots in a Likert-type questionnaire","year":2023,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Respondent; Computer science; Likert scale; Permutation (music); Calibration; Sensitivity (control systems); Statistical hypothesis testing; Type I and type II errors; Null hypothesis; Outlier; Relation (database); Artificial intelligence; Data mining; Machine learning; Statistics; Algorithm; Mathematics","score_opus":0.6771024707565433,"score_gpt":0.6449932992528221,"score_spread":0.03210917150372117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388821770","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":[0.80802524,0.00006503999,0.19059499,0.00005795108,0.00009636611,0.00060107576,0.0000055872206,0.00044678894,0.00010696634],"genre_scores_gemma":[0.7767241,0.000060250193,0.22260605,0.00000276911,0.000015843449,0.00031169684,0.0000069362077,0.000034508448,0.00023783311],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9961967,0.0020849698,0.00045555772,0.00028642832,0.0005726946,0.0004036649],"domain_scores_gemma":[0.99613565,0.0026975106,0.000066313994,0.00047193322,0.0005367212,0.000091890885],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013750975,0.00012390391,0.0002760208,0.0009540042,0.0001137249,0.00002682461,0.0002465256,0.00017525708,0.000023292461],"category_scores_gemma":[0.014720839,0.00012115338,0.00006504906,0.0021978482,0.00011596441,0.00011282212,0.00012323726,0.000456549,0.000022608228],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002257004,0.0008436152,0.024635455,0.0006968249,0.00002145016,0.000051144132,0.0031904855,0.0011857499,0.48314565,0.0027265109,0.0009191345,0.48235828],"study_design_scores_gemma":[0.0008221921,0.0005605182,0.12079134,0.0008824787,0.000045649005,0.000014898439,0.000411471,0.24546996,0.34924877,0.28118154,0.000084243926,0.00048693453],"about_ca_topic_score_codex":0.00044584772,"about_ca_topic_score_gemma":0.00011931608,"teacher_disagreement_score":0.48187134,"about_ca_system_score_codex":0.000121118755,"about_ca_system_score_gemma":0.00013526356,"threshold_uncertainty_score":0.9935786},"labels":[],"label_agreement":null},{"id":"W4389617452","doi":"10.3390/sym15122187","title":"A New Cosine-Originated Probability Distribution with Symmetrical and Asymmetrical Behaviors: Repetitive Acceptance Sampling with Reliability Application","year":2023,"lang":"en","type":"article","venue":"Symmetry","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":"University of Saskatchewan","funders":"","keywords":"Trigonometric functions; Weibull distribution; Sampling (signal processing); Trigonometry; Algorithm; Computer science; Reliability (semiconductor); Probabilistic logic; Mathematics; Set (abstract data type); Probability density function; Power (physics); Statistics; Mathematical analysis","score_opus":0.050645206793982225,"score_gpt":0.3447342227785338,"score_spread":0.2940890159845516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389617452","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":[0.4559978,0.000025612973,0.54145944,0.000268137,0.000025571455,0.0007931421,0.00006880463,0.0011224449,0.0002390304],"genre_scores_gemma":[0.8528134,0.0000143835805,0.14653355,0.00001782818,0.00005208309,0.00018289872,0.00025403601,0.00003956182,0.00009221584],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99768966,0.00015253035,0.00045455038,0.000764711,0.0005392693,0.00039929166],"domain_scores_gemma":[0.9971223,0.0013566623,0.00024305566,0.0006448771,0.00041655515,0.00021657228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014978045,0.0002888313,0.0004128782,0.00028051285,0.00021084954,0.00009305935,0.00017903057,0.0002040407,0.000012426092],"category_scores_gemma":[0.002973866,0.00022172515,0.000053514967,0.004228639,0.0001693461,0.00023685905,0.000080192716,0.00037721483,0.000016761442],"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":[0.0014106544,0.0012873914,0.5969041,0.0011871201,0.00017631495,0.000028156866,0.0005693005,0.00009224489,0.00037942865,0.13054438,0.0073778355,0.26004305],"study_design_scores_gemma":[0.0025522478,0.0014161677,0.76998377,0.0007193441,0.00033602194,0.0001104647,0.0003837507,0.0049549122,0.009408356,0.20618942,0.0024319764,0.0015135964],"about_ca_topic_score_codex":0.00038530794,"about_ca_topic_score_gemma":0.000028330582,"teacher_disagreement_score":0.39681563,"about_ca_system_score_codex":0.00028687794,"about_ca_system_score_gemma":0.00012883768,"threshold_uncertainty_score":0.9041689},"labels":[],"label_agreement":null},{"id":"W4390607365","doi":"10.1080/26939169.2024.2302179","title":"Investigating Sensitive Issues in Class Through Randomized Response Polling","year":2024,"lang":"en","type":"article","venue":"Journal of Statistics and Data Science Education","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Polling; Randomized response; Randomized controlled trial; Class (philosophy); Psychology; Computer science; Medicine; Artificial intelligence; Mathematics; Statistics; Computer network; Internal medicine","score_opus":0.14624332511523538,"score_gpt":0.47133521061021993,"score_spread":0.3250918854949846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390607365","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":[0.275393,0.00091806555,0.7195253,0.0028111318,0.0008419286,0.00018648854,0.00013200876,0.000030208914,0.00016185512],"genre_scores_gemma":[0.36792225,0.00044149687,0.6314387,0.00005995075,0.00008871863,0.0000012720899,0.000012093409,0.0000058135774,0.000029765319],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987097,0.00022959012,0.00048623045,0.00016250057,0.0003057235,0.00010629884],"domain_scores_gemma":[0.99530756,0.003916142,0.00023531055,0.00018038187,0.00030492496,0.000055695054],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01222083,0.00006932693,0.00021892568,0.00027889144,0.000098493234,0.00028936425,0.00019198778,0.000025138246,0.000004069287],"category_scores_gemma":[0.023307722,0.00005378582,0.000012525468,0.00040853533,0.00034614294,0.001044868,0.000060475817,0.00016080358,9.661062e-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":[0.0017952092,0.00021561817,0.0003281527,0.00030306145,0.000036068934,0.000020923231,0.024090791,0.00003623534,0.0052519036,0.887333,0.029236292,0.05135275],"study_design_scores_gemma":[0.0022503678,0.00008597158,0.00090249325,0.0014473918,0.00004703779,0.00013669053,0.003340863,0.06552233,0.002020745,0.9223756,0.0017013462,0.00016914216],"about_ca_topic_score_codex":0.00009412088,"about_ca_topic_score_gemma":0.000009264306,"teacher_disagreement_score":0.09252923,"about_ca_system_score_codex":0.00006294694,"about_ca_system_score_gemma":0.0012831561,"threshold_uncertainty_score":0.98491937},"labels":[],"label_agreement":null},{"id":"W4391718096","doi":"10.31234/osf.io/4nmxh","title":"Unsupervised [randomly responding] survey bot detection: In search of high classification accuracy","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Variety (cybernetics); Set (abstract data type); Data mining; Sample (material); Machine learning; Data set; Data quality; Artificial intelligence","score_opus":0.26437617079629333,"score_gpt":0.42608481981517105,"score_spread":0.16170864901887771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391718096","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":[0.9036729,0.00011496893,0.09156964,0.00033689605,0.000534091,0.0010192129,0.00015098747,0.0007491627,0.0018521454],"genre_scores_gemma":[0.98225564,0.000087375105,0.016010277,0.000010518103,0.000058407808,0.00016643196,0.00016797762,0.000063353276,0.0011800402],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99660075,0.0010291019,0.001052944,0.0005839329,0.00048895774,0.00024430058],"domain_scores_gemma":[0.9931152,0.0052712304,0.00024404515,0.00088174554,0.00042875388,0.00005906516],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0075205807,0.00029417092,0.00064743275,0.0011903917,0.000046953715,0.000115601295,0.00040715619,0.00052312546,0.00018067154],"category_scores_gemma":[0.0053348886,0.00027047168,0.00015071512,0.0009058692,0.000068500405,0.0000610895,0.00047438103,0.0010282536,0.00004195875],"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":[0.0147483405,0.00503495,0.068867445,0.0502916,0.00233185,0.000109587294,0.020459507,0.0027471762,0.068557836,0.3577925,0.040189587,0.36886963],"study_design_scores_gemma":[0.0014204663,0.00013682281,0.13731492,0.0019300162,0.000095079595,0.000008795139,0.00027002898,0.03556446,0.1061223,0.71614814,0.00011180739,0.00087717903],"about_ca_topic_score_codex":0.004667374,"about_ca_topic_score_gemma":0.001298581,"teacher_disagreement_score":0.36799246,"about_ca_system_score_codex":0.00020305639,"about_ca_system_score_gemma":0.00026452675,"threshold_uncertainty_score":0.9999747},"labels":[],"label_agreement":null},{"id":"W4391754879","doi":"10.1093/jrsssa/qnae009","title":"The one-sayers model for the Extended Crosswise design","year":2024,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series A (Statistics in Society)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":6,"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":"World Anti-Doping Agency","keywords":"Randomized response; Test (biology); Logistic regression; Goodness of fit; Statistics; Response bias; Psychology; Randomization; Mathematics; Econometrics; Social psychology; Randomized controlled trial; Medicine","score_opus":0.11217203106890922,"score_gpt":0.3741153706668705,"score_spread":0.2619433395979613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391754879","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":[0.00011963628,0.0009961526,0.9939474,0.0030738488,0.0006620648,0.00056555786,0.00052720634,0.0000677695,0.000040387793],"genre_scores_gemma":[0.027240064,0.0008951779,0.9688013,0.0003581628,0.0002561838,0.00009222934,0.0000051302445,0.000076114535,0.002275629],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99725246,0.000234882,0.0010259888,0.00022662697,0.0007565097,0.0005035513],"domain_scores_gemma":[0.977486,0.021237368,0.00038367754,0.00036898092,0.0004229275,0.00010102178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004764551,0.0002759746,0.00039904867,0.000014341396,0.0010750713,0.0005705611,0.00077630515,0.00017975824,0.00002579495],"category_scores_gemma":[0.004198635,0.00014187681,0.00060020457,0.00029098912,0.00088676874,0.00012537059,0.00014226133,0.00093236176,0.0000019163078],"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":[0.0001764747,0.00011823121,0.000021255328,0.00034024345,0.0004946763,0.000004561619,0.00464448,0.01651584,0.000022016811,0.44439617,0.52143717,0.011828884],"study_design_scores_gemma":[0.0001926018,0.00007288044,0.00009267557,0.00010206784,0.00015230566,0.0000074342515,0.00072717405,0.513375,0.000041982305,0.48248598,0.0026333465,0.00011653822],"about_ca_topic_score_codex":0.000018915976,"about_ca_topic_score_gemma":0.000031021435,"teacher_disagreement_score":0.51880383,"about_ca_system_score_codex":0.00033470007,"about_ca_system_score_gemma":0.0004400883,"threshold_uncertainty_score":0.82686883},"labels":[],"label_agreement":null},{"id":"W4392002900","doi":"10.1038/s41598-024-53909-0","title":"Design based synthetic imputation methods for domain mean","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hotel Dieu Hospital","funders":"King Saud University","keywords":"Imputation (statistics); Computer science; Data mining; Machine learning; Missing data","score_opus":0.15116022414885102,"score_gpt":0.4454367757931334,"score_spread":0.29427655164428235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392002900","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":[0.0025368694,0.00010051602,0.9920142,0.00013244068,0.0035212173,0.00060955144,0.000001959794,0.00084412977,0.00023907848],"genre_scores_gemma":[0.061926387,2.5686705e-7,0.9369108,0.000011477359,0.00003078118,0.0001717949,0.000027879432,0.000029873856,0.00089076895],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983678,0.00023866337,0.00045027924,0.0005205969,0.0002265603,0.00019611037],"domain_scores_gemma":[0.9970851,0.0020493902,0.00013373548,0.0005106735,0.00016452096,0.000056586607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015504187,0.00011355355,0.00015406494,0.00025268458,0.00021860188,0.00045299035,0.00007799941,0.00006528556,0.00005538138],"category_scores_gemma":[0.0017513162,0.00009592124,0.00011060586,0.0003868942,0.00008248813,0.00011243665,0.00001447727,0.000060688173,0.0000089624755],"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":[0.000059174265,0.0003295943,0.000046667537,0.0022426867,0.00015220344,0.00023942997,0.0055646678,0.0026303239,0.13417146,0.045409363,0.17678024,0.6323742],"study_design_scores_gemma":[0.000026621568,0.000019710496,0.0000013518893,0.00011091969,0.000025859705,0.000045109977,0.00002287417,0.08024929,0.10255957,0.8073245,0.009508226,0.00010594537],"about_ca_topic_score_codex":0.0000039044376,"about_ca_topic_score_gemma":0.0000011254984,"teacher_disagreement_score":0.76191515,"about_ca_system_score_codex":0.00005189819,"about_ca_system_score_gemma":0.00016746484,"threshold_uncertainty_score":0.53734726},"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":"W4393927562","doi":"10.32920/25461076","title":"Examining differential success in recruitment using respondent driven sampling (RDS) in a multi-site study of gay, bisexual and other men who have sex with men","year":2024,"lang":"en","type":"preprint","venue":"","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":true,"ca_institutions":"University of British Columbia; McGill University Health Centre; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; University of Toronto; Toronto Metropolitan University; University of Victoria; Institut National de Santé Publique du Québec; Simon Fraser University; Community Based Research Centre; AIDS Vancouver","funders":"","keywords":"Respondent; Differential (mechanical device); Psychology; Sampling (signal processing); Demography; Political science; Sociology; Physics; Computer science; Law; Telecommunications","score_opus":0.5031523559149481,"score_gpt":0.47344684031306034,"score_spread":0.029705515601887778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393927562","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":[0.95205456,0.000047633628,0.044462346,0.000008555208,0.00003377707,0.002555036,0.00004286438,0.00016797618,0.0006272255],"genre_scores_gemma":[0.94922227,0.000008764213,0.049533024,0.0000055631763,0.000029235787,0.00037020503,0.000013422838,0.00010105453,0.0007164918],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968415,0.00048729827,0.0010139988,0.0008504593,0.00048387624,0.0003228543],"domain_scores_gemma":[0.99822134,0.00066507875,0.0003901051,0.00057333795,0.00007910184,0.000071063136],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016898614,0.00046691913,0.0009663998,0.0009273261,0.000048579488,0.0001698811,0.00025473486,0.00027109875,0.00003624032],"category_scores_gemma":[0.0001466081,0.00038393735,0.000036077217,0.00021156673,0.000058780734,0.0000577141,0.0011284527,0.00068013207,6.3417036e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070106075,0.0025895461,0.8374495,0.0026756527,0.00065938744,0.00007827692,0.1389226,0.00999114,0.002612034,0.00018983491,0.00008569221,0.0040452755],"study_design_scores_gemma":[0.0052589723,0.00096984074,0.09642496,0.008358992,0.000426085,0.000017194656,0.051766843,0.82597286,0.0030881108,0.00614527,0.00000703951,0.0015638123],"about_ca_topic_score_codex":0.009231614,"about_ca_topic_score_gemma":0.006917552,"teacher_disagreement_score":0.81598175,"about_ca_system_score_codex":0.00028112656,"about_ca_system_score_gemma":0.00010392468,"threshold_uncertainty_score":0.99986124},"labels":[],"label_agreement":null},{"id":"W4393952326","doi":"10.32920/25461076.v1","title":"Examining differential success in recruitment using respondent driven sampling (RDS) in a multi-site study of gay, bisexual and other men who have sex with men","year":2024,"lang":"en","type":"preprint","venue":"","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":true,"ca_institutions":"University of British Columbia; McGill University Health Centre; Centre Intégré Universitaire de Santé et de Services Sociaux du Centre-Sud-de-l'Île-de-Montréal; University of Toronto; Toronto Metropolitan University; University of Victoria; Institut National de Santé Publique du Québec; Simon Fraser University; Community Based Research Centre; AIDS Vancouver","funders":"","keywords":"Respondent; Differential (mechanical device); Psychology; Homosexuality; Sex partners; Sampling (signal processing); Gender studies; Demography; Social psychology; Political science; Sociology; Medicine; Human immunodeficiency virus (HIV); Computer science; Telecommunications; Engineering; Family medicine","score_opus":0.5031523559149481,"score_gpt":0.47344684031306034,"score_spread":0.029705515601887778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393952326","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":[0.95205456,0.000047633628,0.044462346,0.000008555208,0.00003377707,0.002555036,0.00004286438,0.00016797618,0.0006272255],"genre_scores_gemma":[0.94922227,0.000008764213,0.049533024,0.0000055631763,0.000029235787,0.00037020503,0.000013422838,0.00010105453,0.0007164918],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968415,0.00048729827,0.0010139988,0.0008504593,0.00048387624,0.0003228543],"domain_scores_gemma":[0.99822134,0.00066507875,0.0003901051,0.00057333795,0.00007910184,0.000071063136],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016898614,0.00046691913,0.0009663998,0.0009273261,0.000048579488,0.0001698811,0.00025473486,0.00027109875,0.00003624032],"category_scores_gemma":[0.0001466081,0.00038393735,0.000036077217,0.00021156673,0.000058780734,0.0000577141,0.0011284527,0.00068013207,6.3417036e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070106075,0.0025895461,0.8374495,0.0026756527,0.00065938744,0.00007827692,0.1389226,0.00999114,0.002612034,0.00018983491,0.00008569221,0.0040452755],"study_design_scores_gemma":[0.0052589723,0.00096984074,0.09642496,0.008358992,0.000426085,0.000017194656,0.051766843,0.82597286,0.0030881108,0.00614527,0.00000703951,0.0015638123],"about_ca_topic_score_codex":0.009231614,"about_ca_topic_score_gemma":0.006917552,"teacher_disagreement_score":0.81598175,"about_ca_system_score_codex":0.00028112656,"about_ca_system_score_gemma":0.00010392468,"threshold_uncertainty_score":0.99986124},"labels":[],"label_agreement":null},{"id":"W4394679458","doi":"10.1093/forestscience/50.6.810","title":"A Pòlya-Urn Resampling Scheme for Estimating Precision and Confidence Intervals Under One-Stage Cluster Sampling: Application to Map Classification Accuracy and Cover-Type Frequencies","year":2004,"lang":"en","type":"article","venue":"Forest Science","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Forest Service","funders":"","keywords":"Resampling; Statistics; Confidence interval; Mathematics; Sampling (signal processing); Cluster sampling; Cover (algebra); Cluster (spacecraft); Computer science; Demography; Population","score_opus":0.23403914503973008,"score_gpt":0.4314568123309775,"score_spread":0.1974176672912474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394679458","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":[0.3046572,0.000026766358,0.6936843,0.0005730009,0.00008173302,0.00079437584,0.000010803574,0.00014594123,0.000025938842],"genre_scores_gemma":[0.50814205,0.0000052916143,0.49156344,0.00012255242,0.00002867398,0.00009296802,0.000007546246,0.000012860135,0.000024627168],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981915,0.000027563286,0.00046715024,0.0005938268,0.0003955695,0.00032441362],"domain_scores_gemma":[0.99699205,0.0016384136,0.0002939943,0.00044270226,0.00047673236,0.00015609471],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0026391575,0.00017980614,0.00021808887,0.00021919986,0.0005396023,0.00037638514,0.00034357974,0.00009016739,0.0000034987725],"category_scores_gemma":[0.008377486,0.00017121481,0.000027650116,0.0004368804,0.0003236093,0.0007120449,0.00017822935,0.00012453059,0.000011339265],"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":[0.00022093323,0.00018441684,0.0036174506,0.00080689683,0.000021028593,3.869844e-7,0.004274664,0.042812515,0.14639479,0.7869666,0.00021973024,0.014480533],"study_design_scores_gemma":[0.00041105406,0.00020214514,0.0047496473,0.0007296148,0.000017247898,0.00000839821,0.00032660912,0.2587358,0.007106258,0.727183,0.00019680065,0.0003334081],"about_ca_topic_score_codex":0.00010625762,"about_ca_topic_score_gemma":0.00005125432,"teacher_disagreement_score":0.2159233,"about_ca_system_score_codex":0.00016270753,"about_ca_system_score_gemma":0.0001582109,"threshold_uncertainty_score":0.9999754},"labels":[],"label_agreement":null},{"id":"W4398845599","doi":"10.7910/dvn/udgofr","title":"Replication Data for: \"Placebo Statements in List Experiments. Evidence from a Face-to-Face Survey in Singapore\"","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","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":"University of British Columbia","funders":"","keywords":"Replication (statistics); Face (sociological concept); Placebo; Psychology; Computer science; Information retrieval; World Wide Web; Medicine; Linguistics; Alternative medicine; Philosophy; Virology","score_opus":0.4106014237309066,"score_gpt":0.468032571270361,"score_spread":0.05743114753945444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398845599","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007024205,0.0000040929776,0.024783997,0.000029809513,0.00020793757,0.002050464,0.97207934,0.00013789618,0.0000040365976],"genre_scores_gemma":[0.00028275096,0.0002833397,0.03297913,0.0002200663,0.00005575793,0.0004100007,0.9656748,0.00005653835,0.000037622263],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995555,0.00065981114,0.0011826508,0.0016554247,0.000534174,0.00041298446],"domain_scores_gemma":[0.9900156,0.0028123797,0.00059278856,0.006292906,0.000112177586,0.00017413261],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0048743626,0.00046114944,0.00074406917,0.0003266444,0.000073696414,0.00020322023,0.002480403,0.00030215667,0.00062445685],"category_scores_gemma":[0.026993249,0.0005148497,0.000048978312,0.00047107445,0.000045492456,0.00088177144,0.0015067826,0.0004353457,0.0039191996],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004356657,0.0001787669,0.000457701,0.0002211198,0.000038684946,0.000013525417,0.00030060112,0.000017017523,0.000059507325,0.0000035131168,0.9979601,0.00031380917],"study_design_scores_gemma":[0.0007268711,0.00006413798,0.0005536222,0.001215435,0.000045788813,7.848788e-7,0.00014012774,0.0013493359,0.0003445949,0.00040574008,0.99464285,0.00051070907],"about_ca_topic_score_codex":0.017093277,"about_ca_topic_score_gemma":0.009238956,"teacher_disagreement_score":0.022118885,"about_ca_system_score_codex":0.00034048723,"about_ca_system_score_gemma":0.000212009,"threshold_uncertainty_score":0.9997303},"labels":[],"label_agreement":null},{"id":"W4398933564","doi":"10.7910/dvn/s6b7se/xcoorc","title":"Data_PSLE_Riambau_Ostwald_PSRM.tab","year":2020,"lang":"fi","type":"dataset","venue":"Harvard Dataverse","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":"University of British Columbia","funders":"","keywords":"Replication (statistics); Placebo; Face (sociological concept); Face-to-face; Computer science; Psychology; Medicine; Sociology; Alternative medicine; Virology; Epistemology; Social science; Philosophy; Pathology","score_opus":0.08684099561615144,"score_gpt":0.3247428955954667,"score_spread":0.23790189997931527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398933564","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000010850403,0.000004308643,0.012589145,0.00006190338,0.0019543401,0.0010216517,0.9827282,0.0008623927,0.0007672045],"genre_scores_gemma":[0.000021985992,0.0014520908,0.03689903,0.0011468161,0.0017442389,0.00010429325,0.9574782,0.00018708262,0.0009662456],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99377406,0.0006949195,0.0016736431,0.0016787393,0.0011744072,0.001004229],"domain_scores_gemma":[0.9912901,0.001701429,0.0011319903,0.004886552,0.00027294748,0.0007169845],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018357293,0.0012612863,0.0016102471,0.00039744095,0.00044591335,0.0006286243,0.0027231995,0.001087916,0.05456021],"category_scores_gemma":[0.006609386,0.0013381533,0.0004113402,0.00065433345,0.00030845744,0.0008189733,0.0019112129,0.0017652324,0.6942369],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001483567,0.00036384744,0.000010322864,0.0016012992,0.00036432117,0.0002491808,0.0001776064,0.000002502714,0.000026492575,0.001096903,0.9940072,0.001951981],"study_design_scores_gemma":[0.00079513347,0.00019008946,0.000014093951,0.0007935909,0.00079002633,0.000064226966,0.00019007013,0.00045700316,0.00020584035,0.0017874594,0.99336356,0.0013488872],"about_ca_topic_score_codex":0.00065650145,"about_ca_topic_score_gemma":0.00009116816,"teacher_disagreement_score":0.6396767,"about_ca_system_score_codex":0.00022673713,"about_ca_system_score_gemma":0.00046201976,"threshold_uncertainty_score":0.9989068},"labels":[],"label_agreement":null},{"id":"W4398985696","doi":"10.7910/dvn/s6b7se/p5hdzq","title":"Data_R_PSLE.tab","year":2020,"lang":"kn","type":"dataset","venue":"Harvard Dataverse","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":"University of British Columbia","funders":"","keywords":"Replication (statistics); Face (sociological concept); Placebo; Face-to-face; Survey data collection; Psychology; Computer science; Information retrieval; Library science; Medicine; Sociology; Alternative medicine; Virology; Statistics; Philosophy; Mathematics; Social science; Epistemology","score_opus":0.08840977342534861,"score_gpt":0.32251619040623175,"score_spread":0.23410641698088314,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398985696","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000022260981,0.000002444755,0.0125749605,0.000036678746,0.0013797083,0.000816503,0.9837147,0.0007838209,0.0006688946],"genre_scores_gemma":[0.000049806193,0.0009279747,0.04046045,0.0010313364,0.0012343542,0.000079948106,0.9556388,0.00015437536,0.00042293806],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947353,0.0005235447,0.0014255465,0.0014472903,0.0010345869,0.0008337252],"domain_scores_gemma":[0.99244183,0.0013204337,0.00096950243,0.0044488567,0.00023643915,0.0005829623],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001554357,0.0010670397,0.001364565,0.0003437516,0.00038050502,0.00055649586,0.0024660747,0.0007259727,0.057829477],"category_scores_gemma":[0.0065244352,0.0011291152,0.00033752614,0.0005394947,0.00025952052,0.00073384505,0.0018125605,0.0014682455,0.699376],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011011855,0.00031733862,0.000014039119,0.0012936485,0.00027968216,0.00020210752,0.00013717565,0.0000029951007,0.00003933461,0.00092555303,0.99605834,0.0006196903],"study_design_scores_gemma":[0.0006459422,0.0001574221,0.000015438965,0.00060561986,0.000634414,0.00004924707,0.00017863752,0.0006630887,0.00026809055,0.0025562467,0.99309045,0.0011354272],"about_ca_topic_score_codex":0.00056842517,"about_ca_topic_score_gemma":0.000110052664,"teacher_disagreement_score":0.6415465,"about_ca_system_score_codex":0.0001933428,"about_ca_system_score_gemma":0.00038143297,"threshold_uncertainty_score":0.9991159},"labels":[],"label_agreement":null},{"id":"W4399006464","doi":"10.7910/dvn/s6b7se","title":"Replication Data for: \"Placebo Statements in List Experiments. Evidence from a Face-to-Face Survey in Singapore\"","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","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":"University of British Columbia","funders":"","keywords":"Replication (statistics); Face (sociological concept); Placebo; Face-to-face; Internet privacy; Computer science; Psychology; World Wide Web; Medicine; Sociology; Alternative medicine; Virology; Social science; Philosophy","score_opus":0.4106014237309066,"score_gpt":0.468032571270361,"score_spread":0.05743114753945444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399006464","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007024205,0.0000040929776,0.024783997,0.000029809513,0.00020793757,0.002050464,0.97207934,0.00013789618,0.0000040365976],"genre_scores_gemma":[0.00028275096,0.0002833397,0.03297913,0.0002200663,0.00005575793,0.0004100007,0.9656748,0.00005653835,0.000037622263],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995555,0.00065981114,0.0011826508,0.0016554247,0.000534174,0.00041298446],"domain_scores_gemma":[0.9900156,0.0028123797,0.00059278856,0.006292906,0.000112177586,0.00017413261],"candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0048743626,0.00046114944,0.00074406917,0.0003266444,0.000073696414,0.00020322023,0.002480403,0.00030215667,0.00062445685],"category_scores_gemma":[0.026993249,0.0005148497,0.000048978312,0.00047107445,0.000045492456,0.00088177144,0.0015067826,0.0004353457,0.0039191996],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004356657,0.0001787669,0.000457701,0.0002211198,0.000038684946,0.000013525417,0.00030060112,0.000017017523,0.000059507325,0.0000035131168,0.9979601,0.00031380917],"study_design_scores_gemma":[0.0007268711,0.00006413798,0.0005536222,0.001215435,0.000045788813,7.848788e-7,0.00014012774,0.0013493359,0.0003445949,0.00040574008,0.99464285,0.00051070907],"about_ca_topic_score_codex":0.017093277,"about_ca_topic_score_gemma":0.009238956,"teacher_disagreement_score":0.022118885,"about_ca_system_score_codex":0.00034048723,"about_ca_system_score_gemma":0.000212009,"threshold_uncertainty_score":0.9997303},"labels":[],"label_agreement":null},{"id":"W4401080173","doi":"10.28924/2291-8639-22-2024-121","title":"Performance Comparison of Three Ratio Estimators of the Population Ratio in Simple Random Sampling Without Replacement","year":2024,"lang":"en","type":"article","venue":"International Journal of Analysis and Applications","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics; Statistics; Estimator; Bivariate analysis; Poisson distribution; Simple random sample; Mean squared error; Sample size determination; Correlation; Population; Ratio estimator; Efficiency; Efficient estimator; Minimum-variance unbiased estimator","score_opus":0.07315749033180145,"score_gpt":0.41045169014280186,"score_spread":0.3372941998110004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401080173","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":[0.5385684,0.000079932295,0.4610409,0.00013186362,0.000031678763,0.00010053148,0.000008780947,0.000007206919,0.000030733732],"genre_scores_gemma":[0.98661137,0.00004311297,0.013245902,0.0000059087542,0.000043163385,0.000016826778,0.000016751233,0.0000058812875,0.000011079723],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985456,0.000042497075,0.00090725935,0.0000956103,0.0003572126,0.000051830095],"domain_scores_gemma":[0.99850106,0.00041347422,0.0005999013,0.00014444893,0.00032102864,0.000020061361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009055599,0.00007348854,0.00029508054,0.00038968885,0.00004472842,0.000040591633,0.0001934439,0.00003356669,0.00001890211],"category_scores_gemma":[0.00016810899,0.00005201945,0.00014817814,0.0004949287,0.000039448416,0.0001289614,0.00003151145,0.000109720546,2.465197e-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":[0.00007376491,0.00013118176,0.9480851,0.000069538044,0.00062547607,1.1503594e-7,0.00039905412,0.020206938,0.0009254149,0.013322631,0.00006057095,0.016100183],"study_design_scores_gemma":[0.00066695915,0.000063061554,0.27815282,0.0003637634,0.0007778549,0.000009462823,0.00017502627,0.67319757,0.009494638,0.03670717,0.00025780377,0.00013387176],"about_ca_topic_score_codex":0.000098704324,"about_ca_topic_score_gemma":0.00014350904,"teacher_disagreement_score":0.6699323,"about_ca_system_score_codex":0.000046630124,"about_ca_system_score_gemma":0.000039152572,"threshold_uncertainty_score":0.21212916},"labels":[],"label_agreement":null},{"id":"W4401769650","doi":"10.18280/isi.290407","title":"An Efficient Poisson-Distributed Adaptive Cluster Sampling Model Using Randomized Response Strategy","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Poisson distribution; Randomized response; Poisson sampling; Cluster (spacecraft); Sampling (signal processing); Computer science; Mathematics; Statistics; Importance sampling; Monte Carlo method; Slice sampling; Telecommunications","score_opus":0.09884237291510807,"score_gpt":0.35479551400530196,"score_spread":0.2559531410901939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401769650","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":[0.3744424,0.0000512734,0.62366813,0.000016513748,0.000114109585,0.000515997,0.000118184245,0.0008259774,0.00024743107],"genre_scores_gemma":[0.8564349,0.0000044084304,0.14316835,0.000038077338,0.000038609825,0.00008620228,0.00018435625,0.000030698076,0.000014448997],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997502,0.0005265262,0.0010439119,0.00020853413,0.00037062907,0.0003483559],"domain_scores_gemma":[0.9972841,0.0015626304,0.00029382954,0.0003426317,0.00040567378,0.000111094094],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005437487,0.00028361994,0.0004788302,0.00046491093,0.0003084134,0.0006622234,0.00018351826,0.00020112153,0.00002228127],"category_scores_gemma":[0.0020206526,0.00024917195,0.00016822535,0.00045311672,0.00015618003,0.0017517247,0.00004498269,0.00022815006,0.00002748078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01829407,0.00006570801,0.0000035738906,0.000596568,0.000129266,0.0000037051805,0.01318002,0.92368466,0.00054046186,0.032805048,0.0002550558,0.010441843],"study_design_scores_gemma":[0.0035267298,0.00005877052,0.00001551598,0.00048125352,0.00006482277,0.00003706855,0.0008173849,0.8921906,0.0008712358,0.10165086,0.000021944701,0.00026384759],"about_ca_topic_score_codex":0.00007381659,"about_ca_topic_score_gemma":0.0000025254058,"teacher_disagreement_score":0.48199245,"about_ca_system_score_codex":0.00051749276,"about_ca_system_score_gemma":0.0002560425,"threshold_uncertainty_score":0.99999607},"labels":[],"label_agreement":null},{"id":"W4401896384","doi":"10.2139/ssrn.4936419","title":"Scalable Estimation of Multinomial Response Models with Random Consideration Sets","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Multinomial distribution; Estimation; Scalability; Computer science; Econometrics; Mathematics; Economics; Database; Management","score_opus":0.05303111110758951,"score_gpt":0.3386719632714297,"score_spread":0.28564085216384016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401896384","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":[0.42381552,0.0007086793,0.57405,0.00028015146,0.00023597511,0.00049135415,0.000023074266,0.00022191163,0.00017333937],"genre_scores_gemma":[0.9199655,0.00030391774,0.07902797,0.000011174918,0.00011176021,0.000047678346,0.000029821967,0.000071519695,0.0004306248],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969446,0.00054286094,0.00080942654,0.00032604494,0.00046912374,0.00090794504],"domain_scores_gemma":[0.99722236,0.0010854707,0.00068373245,0.00036042408,0.0005850188,0.000062966785],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008565753,0.0003199991,0.0005714451,0.00036970625,0.00014571729,0.00016397514,0.00020892512,0.000319446,0.000013804692],"category_scores_gemma":[0.0018663924,0.00026040996,0.00018018403,0.0001346125,0.0000756835,0.00014684864,0.00013578197,0.003102572,0.0000076245224],"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":[0.019372797,0.0005479534,0.00008677485,0.0017381201,0.0022167813,0.000026260834,0.004267649,0.531854,0.0007232427,0.39616904,0.0038941784,0.039103206],"study_design_scores_gemma":[0.0009942832,0.00019837997,0.0000065391637,0.0006331018,0.00017489027,0.00018150453,0.00017243919,0.20642233,0.001593591,0.7894084,0.000004367747,0.00021020648],"about_ca_topic_score_codex":0.00012928681,"about_ca_topic_score_gemma":0.00019549749,"teacher_disagreement_score":0.49615002,"about_ca_system_score_codex":0.00085878355,"about_ca_system_score_gemma":0.004993155,"threshold_uncertainty_score":0.9999848},"labels":[],"label_agreement":null},{"id":"W4402239537","doi":"10.1007/s13253-024-00652-8","title":"Estimating the Negative Binomial Dispersion Parameter with a Stratum-Effects Model and Many Strata","year":2024,"lang":"en","type":"article","venue":"Journal of Agricultural Biological and Environmental Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Fisheries and Oceans Canada; Memorial University of Newfoundland","funders":"Ocean Frontier Institute","keywords":"Negative binomial distribution; Stratum; Binomial (polynomial); Statistics; Mathematics; Econometrics; Dispersion (optics); Binomial distribution; Geology; Poisson distribution; Physics","score_opus":0.03904203197960769,"score_gpt":0.2703376540590092,"score_spread":0.23129562207940152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402239537","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":[0.90262836,0.0002091665,0.096776254,0.00011748243,0.000039937902,0.0001084473,0.000095573756,0.000013369828,0.000011395961],"genre_scores_gemma":[0.8125181,0.0001316954,0.18724637,0.000017819635,0.000047073758,0.0000024467395,0.000012055479,0.0000035533162,0.000020852902],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9993558,0.000060885282,0.00022404555,0.00011763373,0.00013251473,0.000109121414],"domain_scores_gemma":[0.99867284,0.0011017527,0.00011354097,0.000037795096,0.000009502279,0.00006455135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019338647,0.00013267409,0.00016974696,0.000014885616,0.00011614933,0.00010098357,0.000059257243,0.000057277524,0.000010435779],"category_scores_gemma":[0.00012798625,0.00004847594,0.00002918447,0.000033847846,0.0001883529,0.00010453046,0.000040579984,0.00022184014,8.5536266e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021004418,0.002212835,0.039500028,0.0023955395,0.0026147864,0.0011220737,0.016878154,0.015283903,0.20522213,0.084150545,0.035325944,0.59319365],"study_design_scores_gemma":[0.0013236584,0.005679861,0.39623418,0.0010526746,0.0005576031,0.0023579686,0.0029327846,0.2718525,0.0034127932,0.31355032,0.000073539566,0.00097211753],"about_ca_topic_score_codex":0.0000027897493,"about_ca_topic_score_gemma":0.0000011449313,"teacher_disagreement_score":0.5922215,"about_ca_system_score_codex":0.000027435624,"about_ca_system_score_gemma":0.000004930072,"threshold_uncertainty_score":0.19767915},"labels":[],"label_agreement":null},{"id":"W4405419030","doi":"10.48550/arxiv.2408.11808","title":"Distance Correlation in Multiple Biased Sampling Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","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","keywords":"Correlation; Distance sampling; Sampling (signal processing); Statistics; Mathematics; Statistical physics; Computer science; Physics; Geometry; Biology; Computer vision; Abundance (ecology)","score_opus":0.3945868581052651,"score_gpt":0.2763573893743377,"score_spread":0.11822946873092743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405419030","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":[0.3369371,0.00005374001,0.66079104,0.000014458957,0.00025294308,0.0002741352,0.000044293574,0.0005323719,0.0010999293],"genre_scores_gemma":[0.9864244,0.00006262677,0.01259838,0.000011812595,0.000038302624,0.000004002864,0.0000810703,0.000046699006,0.000732713],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998567,0.00011658035,0.0003158921,0.000681328,0.00008305128,0.00023616197],"domain_scores_gemma":[0.9981944,0.0008616566,0.0001969385,0.00057878444,0.00010120839,0.000067038825],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058751897,0.00026942792,0.0003400595,0.00037798085,0.000074483745,0.000063375366,0.0003145599,0.00035501362,0.000031743424],"category_scores_gemma":[0.00038787696,0.00032037942,0.00015181312,0.0004422714,0.000056623292,0.00012394483,0.0004213322,0.0007737387,0.000041001516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054503995,0.00008849814,0.0033707998,0.00044471407,0.000036321097,0.00005032579,0.000534011,0.81443036,0.00001067988,0.18033986,0.00028599388,0.000353947],"study_design_scores_gemma":[0.00012305874,0.000005094933,0.00012339232,0.00041094003,0.00002364662,4.8364404e-7,0.000056977657,0.50871027,0.000028685297,0.49032226,0.00001884125,0.00017634565],"about_ca_topic_score_codex":0.00041105234,"about_ca_topic_score_gemma":0.0003688652,"teacher_disagreement_score":0.6494873,"about_ca_system_score_codex":0.0003413637,"about_ca_system_score_gemma":0.00009756913,"threshold_uncertainty_score":0.99992484},"labels":[],"label_agreement":null},{"id":"W4408316394","doi":"10.1111/sjos.12776","title":"On high‐dimensional variance estimation in survey sampling","year":2025,"lang":"en","type":"article","venue":"Scandinavian Journal of Statistics","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":"University of Ottawa; McGill University","funders":"","keywords":"Mathematics; Statistics; Variance (accounting); Sampling (signal processing); Estimation; Stratified sampling; Econometrics","score_opus":0.07441039387871845,"score_gpt":0.38121668560969874,"score_spread":0.3068062917309803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408316394","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":[0.09472734,0.000028952674,0.9043349,0.0000882685,0.0004231527,0.00008973522,0.00015113168,0.000022015965,0.0001344927],"genre_scores_gemma":[0.61431515,0.000008176897,0.38548896,0.000054335174,0.0000139269605,0.000001746539,0.000021984819,0.000009751967,0.000085983425],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984398,0.000228517,0.0007295599,0.00012369118,0.00030446405,0.00017397631],"domain_scores_gemma":[0.99545366,0.003541858,0.00042078557,0.00015806194,0.00036724115,0.000058406564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022805957,0.00013523694,0.0003319704,0.00040421425,0.000078755904,0.00004660814,0.00015770944,0.00007577909,0.000049794755],"category_scores_gemma":[0.005780845,0.00012402942,0.000035154517,0.00036704,0.000047318325,0.00009332165,0.000019420859,0.0003074765,0.0000051485727],"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":[0.00073336274,0.00052142487,0.036090598,0.00025996435,0.00011841955,0.00008202546,0.0003182641,0.016353698,0.00008808021,0.8709833,0.027605917,0.046844963],"study_design_scores_gemma":[0.00059711415,0.0001525408,0.14271095,0.00095162954,0.000021540449,0.000015353427,0.000010526463,0.0071583902,0.00020795524,0.84804755,0.000010456291,0.00011599385],"about_ca_topic_score_codex":0.000088054876,"about_ca_topic_score_gemma":0.000047736794,"teacher_disagreement_score":0.5195878,"about_ca_system_score_codex":0.00016759387,"about_ca_system_score_gemma":0.00013824238,"threshold_uncertainty_score":0.6920629},"labels":[],"label_agreement":null},{"id":"W4412013084","doi":"10.1142/s0217590825420032","title":"COMPARISONS OF CONCLUSIONS FROM IDENTICAL QUESTIONS IN FIVE DIFFERENT TYPES OF SURVEY: EVIDENCE OF SIGNIFICANT BETWEEN-SURVEY INCONSISTENCIES FROM CHINA AND VIETNAM","year":2025,"lang":"en","type":"article","venue":"The Singapore Economic Review","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":"Simon Fraser University","funders":"National Natural Science Foundation of China; Đại học Kinh tế Thành phố Hồ Chí Minh","keywords":"China; Survey data collection; Psychology; Geography; Demography; Statistics; Mathematics; Sociology","score_opus":0.17320083707469391,"score_gpt":0.3985477753741123,"score_spread":0.22534693829941838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412013084","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":[0.9738185,0.020667415,0.0037089123,0.00039012232,0.000070492715,0.000471656,0.0007925941,0.000020923948,0.00005940054],"genre_scores_gemma":[0.9886404,0.00893891,0.0022754516,0.000017195809,0.00000802341,0.000014807903,0.00008265338,0.000008782311,0.000013731826],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99700886,0.0012546566,0.0013282194,0.00021290965,0.000089665926,0.000105678075],"domain_scores_gemma":[0.9865948,0.012071922,0.00068384694,0.0005143246,0.000102329635,0.000032783464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034157666,0.00015647513,0.0011646065,0.00007892151,0.000058358735,0.00001167368,0.0003003457,0.00006796696,0.00004935668],"category_scores_gemma":[0.0047660274,0.00011313512,0.0000999112,0.00014586978,0.00034760172,0.000058450536,0.00019780386,0.00015989278,0.0000017492438],"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":[0.000036857524,0.0001247584,0.9895878,0.0014924345,0.00018993995,2.2582292e-7,0.00038224785,0.000015236303,0.00018186077,0.0032861067,0.0018623631,0.002840198],"study_design_scores_gemma":[0.00011375864,0.00003266651,0.9593325,0.012464734,0.00019580095,1.6955275e-7,0.000045731667,0.0004125721,0.0006718867,0.02661771,0.000013739567,0.00009868205],"about_ca_topic_score_codex":0.016056493,"about_ca_topic_score_gemma":0.0041093915,"teacher_disagreement_score":0.030255223,"about_ca_system_score_codex":0.00005156541,"about_ca_system_score_gemma":0.00012533957,"threshold_uncertainty_score":0.9904957},"labels":[],"label_agreement":null},{"id":"W4412467607","doi":"10.61171/v02.01.52","title":"A Comprehensive Analysis of Cluster Sampling versus Multi-Stage Sampling Techniques: Methodologies, Applications, and Comparative Insights","year":2024,"lang":"en","type":"article","venue":"Pioneer Journal of Biostatistics and Medical Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","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":"","keywords":"Sampling (signal processing); Computer science; Cluster sampling; Cluster (spacecraft); Data science; Data mining; Medicine; Telecommunications","score_opus":0.7156535250035579,"score_gpt":0.6031988047156345,"score_spread":0.11245472028792347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412467607","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":[0.018333863,0.0043306025,0.97660553,0.00022337069,0.000068285655,0.00025082065,0.00009369154,0.000039045834,0.000054775206],"genre_scores_gemma":[0.19797021,0.0041786768,0.7976907,0.000023213144,0.000058354817,0.000020791105,0.000021080503,0.000012791106,0.000024207264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99741954,0.00046438156,0.00076985994,0.00021333397,0.00092395867,0.00020891886],"domain_scores_gemma":[0.9720181,0.026358768,0.00019830192,0.00015776115,0.0010344438,0.00023260467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005076806,0.00013285148,0.00058876164,0.0010792469,0.00013378127,0.000088507004,0.00017885891,0.00015468341,0.000032151027],"category_scores_gemma":[0.0065502096,0.00009883644,0.00007957705,0.0009005672,0.00046329727,0.00007556124,0.0001473904,0.0007078351,6.431171e-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":[0.0012538857,0.00064174493,0.00062709296,0.00453823,0.0064559914,0.0001222402,0.013559451,0.00012513492,0.0066437516,0.37966475,0.0037795713,0.58258814],"study_design_scores_gemma":[0.0060253544,0.0039812005,0.010077415,0.0071010618,0.004944873,0.00027587355,0.02505909,0.38238057,0.017366838,0.34009138,0.20086671,0.0018296033],"about_ca_topic_score_codex":0.00005208575,"about_ca_topic_score_gemma":0.000021192396,"teacher_disagreement_score":0.5807586,"about_ca_system_score_codex":0.000059037666,"about_ca_system_score_gemma":0.00019104357,"threshold_uncertainty_score":0.7841686},"labels":[],"label_agreement":null},{"id":"W4413077203","doi":"10.6000/1929-6029.2025.14.36","title":"A Refined Population Mean Estimator Using Median and Skewness: Applications to Breast Cancer and Brain Tumor Data","year":2025,"lang":"en","type":"article","venue":"International Journal of Statistics in Medical Research","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Estimator; Skewness; Statistics; Population; Mathematics; Sampling (signal processing); Simple random sample; Computer science; Medicine","score_opus":0.24914940791752882,"score_gpt":0.5780527026165511,"score_spread":0.32890329469902224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413077203","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":[0.06814791,0.0001315189,0.9098207,0.020707427,0.00020278805,0.00026228823,0.0006558605,0.000016409218,0.000055128694],"genre_scores_gemma":[0.5821993,0.00023414697,0.4167331,0.00044728408,0.00024054197,0.00003169271,0.000053503605,0.00001796324,0.000042487707],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975137,0.00018780424,0.0005842895,0.00018811846,0.0013634634,0.00016262052],"domain_scores_gemma":[0.9943396,0.0041784444,0.00013870407,0.00018008887,0.00096537743,0.00019778911],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0054877643,0.00007859656,0.00019883768,0.0006867891,0.00008282335,0.00009636582,0.00057373266,0.000062845575,0.000050723025],"category_scores_gemma":[0.015939139,0.000069403,0.000009828687,0.00031318233,0.00014253131,0.00012886188,0.0003469291,0.00044044107,6.782582e-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":[0.00031061453,0.00028931422,0.03612371,0.0002738349,0.00015356795,0.00017879589,0.00052131264,0.00004012921,0.00021107148,0.22580549,0.017237585,0.71885455],"study_design_scores_gemma":[0.0012102749,0.00005960883,0.06788763,0.0027949207,0.000029971225,0.00032949034,0.00036169717,0.10360439,0.000049080896,0.8212091,0.002275214,0.00018862031],"about_ca_topic_score_codex":0.00093875395,"about_ca_topic_score_gemma":0.0009841935,"teacher_disagreement_score":0.71866596,"about_ca_system_score_codex":0.00018891749,"about_ca_system_score_gemma":0.00042585845,"threshold_uncertainty_score":0.99235004},"labels":[],"label_agreement":null},{"id":"W4416202304","doi":"10.1016/j.heliyon.2025.e43866","title":"Corrigendum to “Modified median quartile double ranked set sampling for estimation of population mean” [Heliyon Volume 10, Issue 14, July 2024, Article e34627]","year":2025,"lang":"en","type":"article","venue":"Heliyon","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":"University of Ottawa","funders":"","keywords":"Quartile; Estimation; Volume (thermodynamics); Sampling (signal processing); Population; Set (abstract data type)","score_opus":0.12937447280873096,"score_gpt":0.38852106355029276,"score_spread":0.25914659074156177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416202304","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":[0.12263678,0.00016458468,0.8712315,0.0007557762,0.0014430538,0.0017061563,0.00012903662,0.00055952877,0.0013736105],"genre_scores_gemma":[0.8140039,0.00002595811,0.17268366,0.0002049716,0.00016772198,0.0004554763,0.00038548553,0.000069879155,0.012002975],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789953,0.000092774404,0.0008853085,0.0003992111,0.00034878872,0.0003743638],"domain_scores_gemma":[0.9982365,0.00044474503,0.0002863572,0.00054221775,0.0003701914,0.00012000499],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012763838,0.00024856642,0.00046579138,0.0003769192,0.00021342048,0.000077768,0.00020999016,0.00022053892,0.0002924783],"category_scores_gemma":[0.0012872664,0.00026028077,0.00013639356,0.0005580755,0.0000318114,0.00022051654,0.000050892762,0.00013934799,0.00016573962],"study_design_candidate":"not_applicable","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":[0.008285354,0.0023034236,0.0051299706,0.028037759,0.00086472416,0.00000619797,0.024466695,0.070460595,0.038792867,0.095088884,0.58601564,0.1405479],"study_design_scores_gemma":[0.008138143,0.001174371,0.0072870813,0.007085932,0.00074760756,0.000008358264,0.0013245927,0.3502765,0.27230307,0.32024422,0.0292432,0.0021669276],"about_ca_topic_score_codex":0.00021918549,"about_ca_topic_score_gemma":0.00023928889,"teacher_disagreement_score":0.69854784,"about_ca_system_score_codex":0.00017612716,"about_ca_system_score_gemma":0.000059757454,"threshold_uncertainty_score":0.9999849},"labels":[],"label_agreement":null},{"id":"W625778914","doi":"","title":"Weighted empirical likelihood-based inference for quantiles under stratified random sampling","year":2013,"lang":"en","type":"article","venue":"Economics bulletin","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":"University of Guelph","funders":"","keywords":"Quantile; Stratified sampling; Inference; Statistics; Empirical likelihood; Econometrics; Sampling design; Sampling (signal processing); Focus (optics); Mathematics; Simple random sample; Survey sampling; Computer science; Population; Artificial intelligence; Demography","score_opus":0.1466785640292375,"score_gpt":0.37059769338061854,"score_spread":0.22391912935138103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W625778914","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":[0.43559793,0.00001647508,0.55954283,0.0032180853,0.00012317066,0.00065339904,0.000028103326,0.0003083512,0.0005116604],"genre_scores_gemma":[0.65450096,0.000010596556,0.34412348,0.0007038037,0.000093706076,0.00033340097,0.00006209092,0.00004447012,0.00012751034],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986687,0.00007061457,0.00056812103,0.0003193455,0.00005783856,0.00031539728],"domain_scores_gemma":[0.9950396,0.0041545527,0.000218322,0.00034135167,0.00014360789,0.00010258876],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007739,0.00020934003,0.0003688258,0.000098826386,0.00016882503,0.00018429864,0.00020795518,0.00016284919,0.0010271599],"category_scores_gemma":[0.000721961,0.00020163972,0.00013778653,0.00004604221,0.000053832286,0.0000589682,0.000028053333,0.00013658922,0.00026687887],"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":[0.0018246507,0.0027358856,0.0152434185,0.001591568,0.00084406836,0.0000022900488,0.002327355,0.009755943,0.0027847819,0.4204267,0.45039776,0.09206559],"study_design_scores_gemma":[0.0029506797,0.00014962068,0.001296726,0.00010561923,0.00004337737,0.0000018294172,0.00017224696,0.089358464,0.0067615043,0.87899977,0.019478358,0.0006817802],"about_ca_topic_score_codex":0.000099099336,"about_ca_topic_score_gemma":0.000033402266,"teacher_disagreement_score":0.4585731,"about_ca_system_score_codex":0.00005969434,"about_ca_system_score_gemma":0.00010020457,"threshold_uncertainty_score":0.99988604},"labels":[],"label_agreement":null},{"id":"W6920798416","doi":"10.6084/m9.figshare.14955975","title":"Additional file 1 of Survey design and analysis considerations when utilizing misclassified sampling strata","year":2021,"lang":"en","type":"article","venue":"Open MIND","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":"University of Toronto","funders":"","keywords":"Sampling (signal processing); Sampling design; Survey research; Data collection; Data file","score_opus":0.5224998504400117,"score_gpt":0.41550797580447163,"score_spread":0.10699187463554005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920798416","genre_codex":"dataset","genre_gemma":"methods","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":[0.00319499,0.000027706481,0.26078147,0.00008528659,0.000021019127,0.00036820528,0.7274354,0.000016028363,0.008069875],"genre_scores_gemma":[0.010024453,0.0000014641655,0.93619424,0.000013046292,0.000007709779,0.000052332005,0.05280884,0.000008998106,0.00088894286],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988788,0.00031661836,0.00033117973,0.00023772831,0.00013324239,0.00010246968],"domain_scores_gemma":[0.9819903,0.017256293,0.00016446228,0.00025340263,0.0002869951,0.000048568334],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000803642,0.000091649534,0.00027547567,0.00008957266,0.00013452483,0.00018801785,0.0000963552,0.0000632777,0.72172606],"category_scores_gemma":[0.008959627,0.00009489097,0.000047950085,0.00024888854,0.00005066458,0.00013267233,0.00008891644,0.00007426102,0.000017679258],"study_design_candidate":"not_applicable","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":[0.000012518545,0.00009951229,0.0002417341,0.000012694411,0.00035303732,0.000004667302,0.00030814725,0.00006379994,0.00019967798,0.00029756816,0.99274844,0.005658203],"study_design_scores_gemma":[0.0023371174,0.00033804166,0.13284779,0.0023792563,0.0029159233,0.00019223131,0.0050793416,0.08247872,0.07611023,0.5109873,0.18121932,0.0031147683],"about_ca_topic_score_codex":0.000055745797,"about_ca_topic_score_gemma":0.0005046893,"teacher_disagreement_score":0.8115291,"about_ca_system_score_codex":0.0000120875675,"about_ca_system_score_gemma":0.0002332382,"threshold_uncertainty_score":0.99938834},"labels":[],"label_agreement":null},{"id":"W6929762169","doi":"10.5281/zenodo.11346048","title":"Procyon lotor","year":2005,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Subspecies; Significant difference; Captivity; Endangered species","score_opus":0.12629836857848792,"score_gpt":0.3283855342486389,"score_spread":0.202087165670151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6929762169","genre_codex":"other","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":[0.10889315,0.00014709958,0.30539507,0.0041617462,0.00021114598,0.0019389968,0.0002630805,0.016072562,0.5629172],"genre_scores_gemma":[0.94856334,0.000040114945,0.04456831,0.00025027324,0.00041932822,1.4315535e-7,0.0006304183,0.0021823295,0.0033457219],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988283,0.00018663793,0.00022880058,0.00024306633,0.00026672476,0.00024647196],"domain_scores_gemma":[0.9990044,0.00006042033,0.00008785948,0.00036060056,0.0003817353,0.00010498392],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00097477937,0.000106330226,0.00011645557,0.0001505231,0.0010792474,0.00035184372,0.0005241665,0.00005743543,0.007833875],"category_scores_gemma":[0.0016769915,0.0001073949,0.000041012096,0.0002695775,0.00006795218,0.00020715159,0.00032707347,0.00016945085,0.0059903744],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050075338,0.0002626312,0.000004649839,0.000105326195,0.000030296302,0.000002910877,0.0013153269,0.000025076326,0.0023185196,0.03579306,0.6233427,0.3367494],"study_design_scores_gemma":[0.00023448387,0.00009297309,0.00010961748,0.000030528947,0.000007854677,0.00004958745,0.00007033123,0.0006424988,0.0031569777,0.005238257,0.9902213,0.00014556514],"about_ca_topic_score_codex":0.0000044416315,"about_ca_topic_score_gemma":2.0163934e-7,"teacher_disagreement_score":0.8396702,"about_ca_system_score_codex":0.0001112094,"about_ca_system_score_gemma":0.0000021095034,"threshold_uncertainty_score":0.9947836},"labels":[],"label_agreement":null},{"id":"W6930477828","doi":"10.5281/zenodo.14105327","title":"PM_073397_E_Covarrubias","year":2012,"lang":"es","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Tower; Period (music); Table (database); Quarter (Canadian coin); Thematic map","score_opus":0.12655568897766598,"score_gpt":0.31759750825935573,"score_spread":0.19104181928168976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930477828","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028625992,0.00050929235,0.043416634,0.00039178782,0.00043159383,0.0010748022,0.00084156636,0.004807148,0.94824094],"genre_scores_gemma":[0.1042163,0.0035082747,0.053518377,0.00079277065,0.006458579,8.230844e-7,0.025750585,0.09417652,0.7115778],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961712,0.0009797151,0.00064231496,0.00069427025,0.00069823384,0.00081431796],"domain_scores_gemma":[0.99682415,0.0001898904,0.0005388085,0.0012938959,0.0007831583,0.00037009604],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0024820864,0.00050209154,0.0005495241,0.00068588683,0.0022764336,0.0013838081,0.0017487762,0.00046623708,0.21654895],"category_scores_gemma":[0.003372551,0.0005364101,0.0001913842,0.0006534851,0.00028654424,0.0002341811,0.0015171687,0.00073657825,0.0971069],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036675992,0.00031491535,0.000003186024,0.0005573556,0.00015867788,0.000006346976,0.0007941015,0.000003141333,0.00024387833,0.022252176,0.8139755,0.16165401],"study_design_scores_gemma":[0.00038037702,0.00015212015,0.000108414075,0.00044540016,0.000098128956,0.00011265474,0.0001253384,0.00010553893,0.0003133986,0.0020737567,0.99552476,0.00056013017],"about_ca_topic_score_codex":0.00003284238,"about_ca_topic_score_gemma":2.400056e-7,"teacher_disagreement_score":0.23666315,"about_ca_system_score_codex":0.00026748917,"about_ca_system_score_gemma":0.000007480831,"threshold_uncertainty_score":0.9997088},"labels":[],"label_agreement":null},{"id":"W6931221412","doi":"10.5281/zenodo.3942647","title":"TO ZERO AND BEYOND: Zero Energy Residential Buildings Study. 2018 Inventory of residential projects on the path to zero in the U.S. and Canada","year":2019,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Zero (linguistics); Path (computing); Energy (signal processing); Interpretation (philosophy); Zero-energy building","score_opus":0.05183919830892099,"score_gpt":0.27751284349172367,"score_spread":0.2256736451828027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931221412","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":[0.9912037,0.000015756628,0.0025342386,0.0011465047,0.00006828964,0.0009890831,0.00004395325,0.00011970167,0.0038787196],"genre_scores_gemma":[0.99855727,0.00001243914,0.00036950197,0.00042623264,0.000025949565,4.8353587e-7,0.000025452193,0.00025645553,0.00032620208],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998041,0.0006062206,0.000287926,0.0003107929,0.0005306587,0.00022342983],"domain_scores_gemma":[0.9989249,0.00021300085,0.00010710779,0.0004589554,0.00020981966,0.000086188345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019413946,0.00012718295,0.00016432587,0.00021164755,0.00051192666,0.00028555925,0.0005930719,0.000038244332,0.00024153618],"category_scores_gemma":[0.0015913909,0.00009461382,0.000017721346,0.00037216858,0.000058074686,0.00009141139,0.00062578026,0.00016212963,0.000049180057],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029041627,0.0002667793,0.00048506077,0.00014346017,0.000051138966,0.000014634658,0.013393403,0.000035628193,0.003268672,0.029804958,0.94538885,0.006856969],"study_design_scores_gemma":[0.005157517,0.009087095,0.05139783,0.0012607418,0.00018608454,0.00021019888,0.021618301,0.00074902724,0.02081543,0.07278505,0.81457454,0.0021581722],"about_ca_topic_score_codex":0.03505836,"about_ca_topic_score_gemma":0.0026983093,"teacher_disagreement_score":0.13081433,"about_ca_system_score_codex":0.00009078,"about_ca_system_score_gemma":0.00001735444,"threshold_uncertainty_score":0.97136724},"labels":[],"label_agreement":null},{"id":"W6931868759","doi":"10.5683/sp2/pqde0o","title":"Data from: The genetic architecture of UV floral patterning in sunflower","year":2021,"lang":"en","type":"dataset","venue":"Borealis","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":"University of British Columbia","funders":"","keywords":"Quantitative trait locus; Genetic architecture; Population; Trait; Domestication; Sunflower; Phenotype; Genetic variation","score_opus":0.15256267104860477,"score_gpt":0.3691578293580432,"score_spread":0.21659515830943843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931868759","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044616792,0.00029541043,0.0034417673,0.00013362369,0.00009374145,0.00017107156,0.9953481,0.000043116906,0.000027000273],"genre_scores_gemma":[0.000042294,0.00012512806,0.016504016,0.00014068988,0.00019497809,0.000021237181,0.98293775,0.000026374131,0.0000075012144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99836767,0.000294079,0.00049031386,0.00035834571,0.00031185156,0.00017775907],"domain_scores_gemma":[0.99567425,0.0014463101,0.00026832303,0.0025195295,0.000060470382,0.000031126052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006705424,0.00021755842,0.00041914935,0.00008106416,0.000035730718,0.00004686647,0.0011882214,0.00023229314,0.00021960486],"category_scores_gemma":[0.0017999129,0.00015722276,0.00006308641,0.00013499596,0.00005563618,0.000030961466,0.0004748265,0.00047447535,0.0000033086255],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006795162,0.000042267635,0.00032229847,0.00010907698,0.000036185767,0.000020778682,0.00008887851,0.000009730747,0.0000020069588,0.000003083411,0.99814063,0.0012182638],"study_design_scores_gemma":[0.00015459431,0.000014819789,0.0041207145,0.0007449579,0.00010478755,0.0000068373893,0.000041466126,0.00013435243,0.0000581262,0.006331697,0.98804194,0.00024570082],"about_ca_topic_score_codex":0.0664736,"about_ca_topic_score_gemma":0.08142903,"teacher_disagreement_score":0.014955423,"about_ca_system_score_codex":0.000020418469,"about_ca_system_score_gemma":0.00009001048,"threshold_uncertainty_score":0.9397428},"labels":[],"label_agreement":null},{"id":"W6958369042","doi":"10.6084/m9.figshare.14955975.v1","title":"Additional file 1 of Survey design and analysis considerations when utilizing misclassified sampling strata","year":2021,"lang":"en","type":"article","venue":"Figshare","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":"University of Toronto","funders":"","keywords":"Sampling (signal processing); Sampling design; Survey research; Data collection; Data file","score_opus":0.5183500284634033,"score_gpt":0.3784286276263828,"score_spread":0.13992140083702048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958369042","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015541247,0.000024903955,0.005921801,0.000013679453,0.0000038971757,0.000080753525,0.9931942,0.00008989527,0.0006553258],"genre_scores_gemma":[0.0018944765,4.0053493e-7,0.28430405,0.000022180764,0.000009772813,0.0001449391,0.7134552,0.000009076138,0.00015990212],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990433,0.00022383567,0.00027474077,0.00019924049,0.00015054508,0.0001083339],"domain_scores_gemma":[0.9733981,0.025719894,0.00015645832,0.00022574476,0.00045081944,0.000048971455],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017715353,0.000097114615,0.0002290764,0.00010131449,0.00011577116,0.000073776144,0.0000530136,0.00007667161,0.9803261],"category_scores_gemma":[0.043657765,0.000103263395,0.00006901789,0.00026661513,0.000010811656,0.00008200952,0.00004663807,0.00008673207,0.000044764627],"study_design_candidate":"not_applicable","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":[0.0000017881878,0.000022797516,0.000017148954,0.000047809346,0.00010959018,0.0000021264636,0.000045935343,0.000029112922,0.000012493943,0.00007315208,0.9994397,0.00019832033],"study_design_scores_gemma":[0.0012861806,0.00021872122,0.22123192,0.016303616,0.0012151579,0.00016499644,0.0012518513,0.10186497,0.019894268,0.33515096,0.29831275,0.003104578],"about_ca_topic_score_codex":0.000009956979,"about_ca_topic_score_gemma":0.00011204558,"teacher_disagreement_score":0.98028135,"about_ca_system_score_codex":0.000012365944,"about_ca_system_score_gemma":0.00017639708,"threshold_uncertainty_score":0.9643979},"labels":[],"label_agreement":null},{"id":"W6981556733","doi":"","title":"E21 (Policy on Assignment or Transfer of Tenure-Track Faculty)- Only quarter to semester edits","year":2013,"lang":"en","type":"article","venue":"RIT Scholar Works (Rochester Institute of Technology)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Transfer (computing); Class (philosophy); Transfer of training; Data collection","score_opus":0.06722665852239097,"score_gpt":0.3512924607416788,"score_spread":0.28406580221928784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981556733","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":[0.92558426,0.000047463098,0.0636421,0.00699977,0.00034049727,0.0014134041,0.000056827932,0.0007883608,0.0011273079],"genre_scores_gemma":[0.87260145,0.000019670097,0.12594503,0.00041530942,0.00011254636,0.00023026299,0.000024200268,0.00005418333,0.0005973626],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99755424,0.00005919157,0.00092352653,0.0005014528,0.00049462274,0.00046697556],"domain_scores_gemma":[0.99815613,0.00012636399,0.00019951412,0.000993764,0.0003781357,0.00014607552],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006326566,0.00040482456,0.0006813733,0.0009424462,0.0001238722,0.00008680033,0.0006432531,0.0007181203,0.00007192738],"category_scores_gemma":[0.0011513149,0.00031657613,0.0001726609,0.0010067871,0.00027089773,0.00066457666,0.00011313771,0.00084008696,0.00011045182],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010561341,0.006518542,0.013841753,0.0024762712,0.0013401812,0.000092742564,0.005250202,0.00043680202,0.09015209,0.137584,0.1188639,0.6223874],"study_design_scores_gemma":[0.005059256,0.003967952,0.020686397,0.009879768,0.00032110722,0.00022552993,0.0015071244,0.00012522911,0.6923046,0.10908594,0.15407626,0.0027608126],"about_ca_topic_score_codex":0.000044452463,"about_ca_topic_score_gemma":0.000033913326,"teacher_disagreement_score":0.6196266,"about_ca_system_score_codex":0.000113802394,"about_ca_system_score_gemma":0.00017582107,"threshold_uncertainty_score":0.99992865},"labels":[],"label_agreement":null},{"id":"W6981750129","doi":"","title":"Explorations the status of women economists.","year":2006,"lang":"en","type":"article","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Work (physics); Women's work; Women's history; Distribution (mathematics); Socioeconomic status","score_opus":0.08010816071741839,"score_gpt":0.3043045756444143,"score_spread":0.22419641492699593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981750129","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":[0.8543141,0.000022017599,0.07877559,0.00060086104,0.00003457267,0.0005516919,0.00041528116,0.0001467855,0.06513914],"genre_scores_gemma":[0.95312566,0.0007233699,0.041444033,0.0000068517757,0.000029968676,8.703633e-7,0.00010843223,0.000022879953,0.004537916],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99765015,0.00051592075,0.0002066098,0.00030205792,0.00046660454,0.0008586681],"domain_scores_gemma":[0.99684185,0.0016099585,0.0002468381,0.00061048515,0.00045456324,0.00023633523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014647853,0.00015390383,0.00034369956,0.0006230534,0.0008044755,0.000023256183,0.00092497776,0.00008901885,0.00027766215],"category_scores_gemma":[0.00035496237,0.0001656732,0.00016920386,0.0006977444,0.0010826888,0.00042021656,0.00048968615,0.00039052404,0.000006301131],"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":[0.0017124009,0.0012647314,0.044673514,0.0005410091,0.00043863812,0.000071385664,0.023561856,0.00060232973,0.0018906614,0.85977983,0.050116748,0.015346917],"study_design_scores_gemma":[0.002123572,0.000705665,0.03872113,0.00013820488,0.0000739683,0.0000062655163,0.06657544,0.0036021888,0.00081033027,0.40711933,0.4796167,0.0005072055],"about_ca_topic_score_codex":0.0034799862,"about_ca_topic_score_gemma":0.0021888926,"teacher_disagreement_score":0.45266047,"about_ca_system_score_codex":0.0005433266,"about_ca_system_score_gemma":0.00043469307,"threshold_uncertainty_score":0.67559576},"labels":[],"label_agreement":null},{"id":"W6984668016","doi":"","title":"The Anti-Olympics","year":2011,"lang":"en","type":"article","venue":"CommonKnowledge Research Repository (Pacific University Oregon)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Spectacle; Cold war; Focus (optics); Order (exchange); Indigenous","score_opus":0.3444855250394478,"score_gpt":0.37397497897859955,"score_spread":0.029489453939151755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6984668016","genre_codex":"other","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":[0.24173586,0.0005057525,0.00777558,0.00021735937,0.00076480466,0.00071084243,0.000010696611,0.0010553419,0.74722373],"genre_scores_gemma":[0.96572244,0.00016024016,0.004274651,0.0000020558368,0.00011357311,0.000004876638,0.0000042474576,0.00003469886,0.029683245],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99696463,0.0012427964,0.00026803312,0.00036842175,0.00055314484,0.00060298335],"domain_scores_gemma":[0.99530834,0.0022528477,0.000114801674,0.0011786232,0.00091850164,0.00022690301],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0029849561,0.00018642588,0.00023867482,0.000281203,0.0026490104,0.00011841423,0.0011684082,0.00017631601,0.000034301866],"category_scores_gemma":[0.0007905971,0.00015304667,0.00014080622,0.00072501734,0.0009492786,0.00022116143,0.00040619142,0.000668479,0.0001508827],"study_design_candidate":"not_applicable","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":[0.00052973395,0.0013209884,0.036631297,0.00027735066,0.000348208,0.0005127472,0.014058211,6.357294e-7,0.0016036931,0.6351805,0.2812577,0.028278967],"study_design_scores_gemma":[0.0015982115,0.0007559636,0.025736593,0.00046889813,0.00013237109,0.00023574573,0.027043939,0.0018572282,0.067920536,0.13862425,0.7341602,0.0014660637],"about_ca_topic_score_codex":0.00015284198,"about_ca_topic_score_gemma":0.00006570078,"teacher_disagreement_score":0.72398657,"about_ca_system_score_codex":0.00026574507,"about_ca_system_score_gemma":0.0002082567,"threshold_uncertainty_score":0.9986494},"labels":[],"label_agreement":null},{"id":"W7011789344","doi":"","title":"A NEW COMPRIMISE ALLOCATION METHOD IN STRATIFIED RANDOM SAMPLING","year":2017,"lang":"en","type":"article","venue":"DergiPark (Istanbul University)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Diafiltration; Liquation; Dysgeusia; Triacetin; Emperipolesis; Hyporeflexia","score_opus":0.15691769389832932,"score_gpt":0.3802230484040487,"score_spread":0.22330535450571937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7011789344","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":[0.041264158,0.000012333022,0.934784,0.00031600212,0.000090353606,0.00026290395,0.000006094941,0.00023492132,0.023029244],"genre_scores_gemma":[0.44269118,0.00002123884,0.55373275,0.000021366113,0.000038762515,0.0000013965235,0.000015078517,0.00002019047,0.0034580752],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989329,0.00016422333,0.00023590194,0.00028245716,0.00017178271,0.00021271393],"domain_scores_gemma":[0.9981102,0.00077142887,0.00026806397,0.00064968166,0.00009656322,0.00010411005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007944527,0.00015521713,0.000286802,0.00026012317,0.00037163764,0.00014544888,0.0004843166,0.000117214215,0.0000784581],"category_scores_gemma":[0.0008321699,0.00017903163,0.00007861627,0.00016065144,0.000044513064,0.00033093852,0.00008394331,0.00017645751,0.000010361634],"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":[0.0021684603,0.00052603637,0.0070117684,0.00037481295,0.00025548288,0.00022884378,0.006679256,0.0018423185,0.00495602,0.89151734,0.013584925,0.070854716],"study_design_scores_gemma":[0.024828479,0.00025496123,0.0367503,0.001216268,0.00044004194,0.00004870482,0.0057447557,0.027886778,0.02119958,0.7812997,0.09750318,0.0028272076],"about_ca_topic_score_codex":0.0009300367,"about_ca_topic_score_gemma":0.0008838163,"teacher_disagreement_score":0.401427,"about_ca_system_score_codex":0.00014044148,"about_ca_system_score_gemma":0.0001364238,"threshold_uncertainty_score":0.7300698},"labels":[],"label_agreement":null},{"id":"W7028418430","doi":"","title":"Exploring First-Year University Students’ Barriers and Facilitators to Meeting the Recommendations of the Canadian 24-Hour Movement Guidelines for Adult","year":2020,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Thematic analysis; Focus group; Intervention (counseling); Knowledge translation; Implementation research; Qualitative research; Behaviour change; Intervention mapping; Best practice; Evidence-based practice","score_opus":0.09415294767916509,"score_gpt":0.2905966691298907,"score_spread":0.19644372145072558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7028418430","genre_codex":"commentary","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":[0.4755219,0.0000152537705,0.0028425716,0.5081612,0.0012187549,0.0044580493,0.0021289552,0.00071641564,0.0049369433],"genre_scores_gemma":[0.38849375,0.0022574416,0.35284415,0.003966885,0.00041630943,0.00008493124,0.0018360886,0.00050398835,0.24959646],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99877894,0.0001545357,0.00023414042,0.00032488626,0.00027873268,0.00022875021],"domain_scores_gemma":[0.9982403,0.00045985385,0.000259526,0.00034648686,0.00042906424,0.0002647745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021608574,0.00023328597,0.00027512526,0.0002617746,0.0009640399,0.00007092568,0.0007082036,0.00013295765,0.000032832435],"category_scores_gemma":[0.0014724014,0.00020691639,0.00015111652,0.00046821387,0.000046106605,0.00041053866,0.000183163,0.00023386447,0.0000020755465],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025050686,0.000032965447,0.020717204,0.0006344999,0.00037578755,0.00000510253,0.021365382,0.00011953522,0.000003820385,0.027551632,0.9283528,0.00059076806],"study_design_scores_gemma":[0.0010738764,0.00021573664,0.005273476,0.0018785537,0.0005119131,1.09641014e-7,0.37742186,0.0001135392,0.0042427504,0.005749221,0.602482,0.0010369318],"about_ca_topic_score_codex":0.07568002,"about_ca_topic_score_gemma":0.062973216,"teacher_disagreement_score":0.50419426,"about_ca_system_score_codex":0.00020778924,"about_ca_system_score_gemma":0.00036874966,"threshold_uncertainty_score":0.9541251},"labels":[],"label_agreement":null},{"id":"W7039216715","doi":"","title":"Le mentorat : les perceptions des enseignants débutants dans un contexte scolaire francophone minoritaire","year":2011,"lang":"fr","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"French; Cultural environment; Context (archaeology); Sociological research","score_opus":0.017740542526511548,"score_gpt":0.184470737258695,"score_spread":0.16673019473218345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039216715","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14044118,0.002641188,0.008425215,0.0005223944,0.0007043019,0.00071574596,0.002055163,0.000105462386,0.8443894],"genre_scores_gemma":[0.76518595,0.00043338782,0.01540393,0.00018566361,0.00012120121,0.00003738011,0.000029955458,0.0001760653,0.21842648],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99671364,0.00027502654,0.00067163375,0.00047797884,0.0013173681,0.0005443413],"domain_scores_gemma":[0.99811655,0.0004899428,0.0005000203,0.00046836564,0.0000033694844,0.00042177615],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0000420834,0.00056529476,0.00072925276,0.00005997461,0.0007966255,0.000046654484,0.00042638186,0.00017880696,0.0021914],"category_scores_gemma":[0.000027082004,0.0005883831,0.00009265907,0.0001441097,0.00055769616,0.0003177461,0.00018763222,0.00031124282,1.059207e-7],"study_design_candidate":"design_other","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":[0.00095575047,0.0010005714,0.0690035,0.0065407874,0.0017075572,0.0004903069,0.02115358,0.000027403781,0.026022162,0.34063154,0.016122263,0.51634455],"study_design_scores_gemma":[0.0034942948,0.00092406955,0.3366481,0.015064263,0.0006481452,0.00017725758,0.14583062,0.0019441714,0.2986955,0.1140052,0.07771131,0.004857083],"about_ca_topic_score_codex":0.04757183,"about_ca_topic_score_gemma":0.25661582,"teacher_disagreement_score":0.62596285,"about_ca_system_score_codex":0.0000286955,"about_ca_system_score_gemma":0.0029696485,"threshold_uncertainty_score":0.99965674},"labels":[],"label_agreement":null},{"id":"W7095885915","doi":"","title":"Likelihood-based estimation methods for models for concurrent continuous and discrete responses (Research Report 05-04","year":2005,"lang":"en","type":"article","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Discretion; Agency (philosophy); Accreditation; Estimation; Common law","score_opus":0.33045437191208493,"score_gpt":0.5560565448302276,"score_spread":0.22560217291814266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095885915","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":[0.00554171,0.00012375889,0.9904272,0.0013165849,0.00008308991,0.0016951225,0.000051851865,0.0004164232,0.00034428883],"genre_scores_gemma":[0.12486357,0.000007012221,0.87298054,0.00006883993,0.00005963334,0.00092580204,0.000071442606,0.000036668695,0.0009864771],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981504,0.00033682492,0.000567527,0.0003595132,0.00022775779,0.00035799606],"domain_scores_gemma":[0.9882962,0.010417698,0.00017398597,0.0003482892,0.0006582648,0.00010556985],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00996784,0.00016539014,0.00032835844,0.00020451122,0.000244277,0.000106544976,0.00011928278,0.00012249174,0.000015315416],"category_scores_gemma":[0.009065691,0.0001393683,0.00009848322,0.00011827954,0.00009664436,0.00019812716,0.000037022553,0.00011771059,0.0000013140312],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051172054,0.00026802733,0.000082899955,0.00068358856,0.000071125905,0.0000022399622,0.0006676989,0.0011143618,0.0013531472,0.11583668,0.031372804,0.8480357],"study_design_scores_gemma":[0.0005504304,0.0001988535,0.000014604035,0.00006551691,0.000027726537,0.000013105063,0.000053579657,0.6694617,0.024085945,0.30113983,0.004246334,0.00014235979],"about_ca_topic_score_codex":0.00003237376,"about_ca_topic_score_gemma":0.000017121489,"teacher_disagreement_score":0.84789336,"about_ca_system_score_codex":0.00006777867,"about_ca_system_score_gemma":0.00013147673,"threshold_uncertainty_score":0.99928135},"labels":[],"label_agreement":null},{"id":"W7096161689","doi":"","title":"SARA SHANIAN Selective Sampling for Classification","year":2015,"lang":"en","type":"article","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sampling (signal processing); Bayesian probability; Statistical analysis; Pattern recognition (psychology)","score_opus":0.6149135938518991,"score_gpt":0.4774388685104899,"score_spread":0.13747472534140925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096161689","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":[0.015626157,0.00000666362,0.97178227,0.00019743378,0.00007168671,0.00030856222,0.0000062826452,0.00059005275,0.011410866],"genre_scores_gemma":[0.4850314,6.619277e-7,0.51393336,0.000060922284,0.000054956985,0.000087828616,0.000017437244,0.000015593918,0.00079784496],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9994304,0.000027833301,0.00017229136,0.0001411148,0.00010445384,0.00012388767],"domain_scores_gemma":[0.99890906,0.00050267583,0.00006956859,0.00015506832,0.00030247966,0.00006116338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008278382,0.00007415007,0.000106891806,0.00005861583,0.00005980928,0.000032876433,0.00007761777,0.000062233696,0.000012405752],"category_scores_gemma":[0.0017224307,0.00006543774,0.000034548655,0.000106867185,0.000012882903,0.0000829305,0.000010412048,0.00004719686,0.000020158484],"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":[0.00014304016,0.00028588728,0.0026350766,0.00012941206,0.00007231634,2.3411624e-7,0.0033114399,0.000047511636,0.0047570216,0.8073136,0.13657768,0.04472676],"study_design_scores_gemma":[0.0003357181,0.0001069097,0.0008052772,0.000021200936,0.00001728779,0.0000023183736,0.00038956376,0.022354415,0.011345765,0.95897007,0.005469842,0.00018160777],"about_ca_topic_score_codex":0.000027481456,"about_ca_topic_score_gemma":0.000015790174,"teacher_disagreement_score":0.46940526,"about_ca_system_score_codex":0.000070659786,"about_ca_system_score_gemma":0.000048871418,"threshold_uncertainty_score":0.26684737},"labels":[],"label_agreement":null},{"id":"W7097620051","doi":"","title":"Biases And Variances Of Survey Estimators Based On Nearest Neighbor Imputation","year":2007,"lang":"en","type":"article","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Estimator; Imputation (statistics); k-nearest neighbors algorithm; Population; Variance (accounting); Sample (material)","score_opus":0.18898117780257742,"score_gpt":0.40056378109899726,"score_spread":0.21158260329641984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097620051","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":[0.4088123,0.00000801336,0.58919036,0.000032806376,0.00004543083,0.00011297702,0.00001768413,0.00018170176,0.0015987251],"genre_scores_gemma":[0.8429031,0.0000016474892,0.15697505,0.000048560767,0.000009727487,0.0000025791337,0.000019916006,0.00001065243,0.00002880855],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992508,0.000079248486,0.0002701966,0.0001284003,0.00015958796,0.000111729416],"domain_scores_gemma":[0.993756,0.0058162967,0.00012182252,0.00014526391,0.000115353636,0.000045295932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002097794,0.00009071507,0.00015154568,0.00012630281,0.000046471716,0.000021409449,0.00005280106,0.00005673758,0.000046436046],"category_scores_gemma":[0.0037993162,0.00007428431,0.000021872513,0.00018156183,0.000048644684,0.000060248833,0.000009619322,0.00004661679,0.0000026519106],"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":[0.00064314983,0.000948476,0.82830024,0.00051657815,0.000067899,0.000010360508,0.0005979432,0.0027154486,0.0006132176,0.06022113,0.0067650434,0.09860049],"study_design_scores_gemma":[0.00055093056,0.0003729265,0.81221145,0.00023250277,0.00002158512,0.000003070811,0.0000660809,0.114813365,0.031165246,0.04022017,0.00004993176,0.00029270945],"about_ca_topic_score_codex":0.00060473976,"about_ca_topic_score_gemma":0.00021794271,"teacher_disagreement_score":0.43409073,"about_ca_system_score_codex":0.000011205329,"about_ca_system_score_gemma":0.000026254937,"threshold_uncertainty_score":0.45484108},"labels":[],"label_agreement":null},{"id":"W7101129696","doi":"","title":"LSAC RESEARCH REPORT SERIES � Item Response Theory Parameter Estimation with Response Times as Collateral Information","year":2006,"lang":"en","type":"article","venue":"","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Discretion; Government (linguistics); Estimation; Collateral; Agency (philosophy); Series (stratigraphy); Item response theory; Accreditation","score_opus":0.0656504827893746,"score_gpt":0.39121305070139173,"score_spread":0.3255625679120171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7101129696","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":[0.8551357,0.000007519757,0.12768306,0.00091216335,0.000051276,0.0006927752,0.000010896896,0.0009823479,0.014524271],"genre_scores_gemma":[0.71225,0.0000012151455,0.26808813,0.00007135004,0.00002498393,0.00015373419,0.00008183328,0.000031527812,0.019297218],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99615103,0.0018028952,0.0007061467,0.00023618403,0.0007479759,0.00035574523],"domain_scores_gemma":[0.98919,0.009176395,0.00025095433,0.0006321957,0.0006823025,0.00006814049],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015845511,0.0002057138,0.0002461994,0.0005295941,0.00032712464,0.00031785725,0.00016221183,0.00016780998,0.00034724714],"category_scores_gemma":[0.010328385,0.00015642367,0.000052272437,0.0005505251,0.00020570538,0.0012695392,0.000057963734,0.00023496828,0.00018582457],"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":[0.2316393,0.0009092493,0.006865698,0.00063570385,0.00028646062,0.0006460406,0.009676503,0.0018858277,0.0046232445,0.5055255,0.21189444,0.025412008],"study_design_scores_gemma":[0.00078853744,0.001164666,0.015219965,0.00024032767,0.00003396222,0.001246667,0.00089102855,0.005937684,0.049077168,0.91397154,0.010859077,0.00056939793],"about_ca_topic_score_codex":0.00017256157,"about_ca_topic_score_gemma":0.000021741744,"teacher_disagreement_score":0.40844598,"about_ca_system_score_codex":0.00015113779,"about_ca_system_score_gemma":0.00026395952,"threshold_uncertainty_score":0.998008},"labels":[],"label_agreement":null},{"id":"W7128139598","doi":"","title":"Σφάλματα δημοσκοπήσεων: αιτίες και αντιμετώπιση","year":2025,"lang":"","type":"article","venue":"Open MIND","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Polling; Legitimacy; Context (archaeology); Transparency (behavior); Presidential system; Weighting; Social media; Survey data collection","score_opus":0.2118168822727588,"score_gpt":0.4656206441026905,"score_spread":0.2538037618299317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7128139598","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11155992,0.0012242062,0.09938585,0.003678479,0.0022386624,0.0036482555,0.00027069863,0.000085049,0.77790886],"genre_scores_gemma":[0.42194793,0.00024189088,0.42482135,0.0005307397,0.00023537627,0.00017978012,0.00009541148,0.000112893664,0.15183462],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99641335,0.000385385,0.001250919,0.0008978504,0.0003961605,0.0006563318],"domain_scores_gemma":[0.9961245,0.0013848232,0.00043824417,0.0015130759,0.00035367243,0.0001857049],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0031422875,0.00052651967,0.0008785371,0.0003483098,0.00049574336,0.0012745069,0.0017666101,0.00048795337,0.013219721],"category_scores_gemma":[0.002059,0.0005463524,0.00022517864,0.000915604,0.00020287577,0.0004977702,0.001107522,0.00054251833,0.0031958153],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019016524,0.0010662756,0.0016396692,0.0003472112,0.000436477,0.00003142601,0.0028094044,0.000025555417,0.0005584512,0.008078012,0.1100764,0.87474096],"study_design_scores_gemma":[0.0022199356,0.0002852189,0.0011639381,0.0033233443,0.00064575404,0.000026778269,0.0014882924,0.005093562,0.09698249,0.123726,0.7635018,0.001542854],"about_ca_topic_score_codex":0.00025676104,"about_ca_topic_score_gemma":0.00009867441,"teacher_disagreement_score":0.8731981,"about_ca_system_score_codex":0.0001894522,"about_ca_system_score_gemma":0.00068585813,"threshold_uncertainty_score":0.99976224},"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},{"id":"W7133507461","doi":"10.22024/unikent/01.02.113288","title":"Statistical approaches for wildlife conservation","year":2025,"lang":"en","type":"article","venue":"Kent Academic Repository (University of Kent)","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Cluster analysis; Identification (biology); Hierarchical clustering; Variation (astronomy); Key (lock)","score_opus":0.12291042972767297,"score_gpt":0.3185509691691119,"score_spread":0.19564053944143894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133507461","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":[0.24801388,0.000068963636,0.74688756,0.0010641371,0.00017396893,0.00045673846,0.000025244495,0.00020868663,0.0031007999],"genre_scores_gemma":[0.83391124,0.00005018776,0.15863146,0.00017476876,0.00005338512,0.0000060583175,0.00006603153,0.000015648879,0.0070912023],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991976,0.00008465073,0.000229475,0.00020306338,0.00015525437,0.00012994156],"domain_scores_gemma":[0.9986069,0.0008609998,0.00019640871,0.00018525662,0.00010587859,0.000044536228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004898289,0.00009502914,0.00020930027,0.00009941432,0.00020116924,0.000008790738,0.00022264075,0.00018473966,0.000010111824],"category_scores_gemma":[0.0003540035,0.00011385373,0.000074624375,0.00012241057,0.00013398263,0.00012026211,0.000044562225,0.00017291107,0.0000017036571],"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":[0.00038431483,0.0002207307,0.06182631,0.0011246158,0.00023894949,0.000004731454,0.001727494,0.0000504547,0.0018909351,0.4470405,0.47934273,0.0061482247],"study_design_scores_gemma":[0.0044910237,0.00039366508,0.102564126,0.0015675147,0.0010307858,0.000026109477,0.007377165,0.06987529,0.020148473,0.7210762,0.070288554,0.001161094],"about_ca_topic_score_codex":0.00007057016,"about_ca_topic_score_gemma":0.000003638808,"teacher_disagreement_score":0.5882561,"about_ca_system_score_codex":0.000088717556,"about_ca_system_score_gemma":0.00009467901,"threshold_uncertainty_score":0.46428207},"labels":[],"label_agreement":null}]}