{"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12887727,0.0032761618,0.83862346,0.0033573115,0.0011714033,0.0038437434,0.001502903,0.0002921324,0.019055681],"genre_scores_gemma":[0.75050217,0.0020464791,0.22199105,0.0024887868,0.0009709027,0.008085152,0.0013288778,0.00018592719,0.012400658],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.78331757,0.17816494,0.008279606,0.01426938,0.014137962,0.0018305113],"domain_scores_gemma":[0.76020867,0.18675746,0.012200559,0.034816753,0.005289285,0.00072734745],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11510364,0.00073276734,0.0023950613,0.0015161833,0.0006973619,0.0019410795,0.0022322151,0.0024125583,0.009968424],"category_scores_gemma":[0.26983863,0.00054295064,0.0014125354,0.0029955364,0.0047308137,0.0032228213,0.0042390963,0.002601997,0.0018646306],"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":[0.002028506,0.00036330058,0.0520999,0.002960648,0.0008920738,0.0006097087,0.0030877811,0.0062302123,0.0040667253,0.6617263,0.0051921066,0.26074278],"study_design_scores_gemma":[0.0008764966,0.0042701983,0.090457365,0.001988641,0.001534228,0.0026081128,0.002683223,0.051188298,0.0151655,0.7479303,0.08098843,0.00030923216],"about_ca_topic_score_codex":0.00034089328,"about_ca_topic_score_gemma":0.00042908164,"teacher_disagreement_score":0.88489634,"about_ca_system_score_codex":0.0013537239,"about_ca_system_score_gemma":0.0010627785,"threshold_uncertainty_score":0.60873353},"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":"review","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007526344,0.5950148,0.3478398,0.031462967,0.0044079307,0.00058296794,0.002757351,0.0010295851,0.009378262],"genre_scores_gemma":[0.032629684,0.54401785,0.4073124,0.0041820505,0.0039794054,0.0011324293,0.0025798588,0.00070057175,0.003465726],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9397014,0.035855036,0.0061975643,0.0020851474,0.015926508,0.00023437382],"domain_scores_gemma":[0.4101872,0.5296148,0.00985326,0.01457229,0.034879167,0.00089314545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.094232075,0.0013237826,0.0037091642,0.011691731,0.0006202461,0.0046756626,0.0039228755,0.0017958123,0.0042607347],"category_scores_gemma":[0.2882972,0.0014917268,0.0020899882,0.022112824,0.0049106195,0.008241023,0.0021459637,0.0043073315,0.0016133961],"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":[0.00007869053,0.00008051369,0.0051945015,0.0097363945,0.00021577609,0.00008023085,0.0005302847,0.0021906176,0.00031062396,0.0144732725,0.029747486,0.93736166],"study_design_scores_gemma":[0.00013817607,0.00072416937,0.089060865,0.03245906,0.00083892985,0.0022670687,0.0021575512,0.029485434,0.002182563,0.13096556,0.70932347,0.00039716245],"about_ca_topic_score_codex":0.006923626,"about_ca_topic_score_gemma":0.010339159,"teacher_disagreement_score":0.094232075,"about_ca_system_score_codex":0.004345682,"about_ca_system_score_gemma":0.006112509,"threshold_uncertainty_score":0.49835283},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009396154,0.00045266538,0.9981269,0.00008686302,0.000041729472,0.000034454224,0.000021749911,0.00008623909,0.00020968965],"genre_scores_gemma":[0.068869516,0.0020438484,0.92524177,0.00042173354,0.0003687631,0.00074614986,0.0002621754,0.00018603134,0.0018601413],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95391345,0.03848102,0.0012262256,0.0019939288,0.0039379974,0.00044743053],"domain_scores_gemma":[0.88327163,0.09731553,0.005440246,0.006423918,0.0070995293,0.00044918252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046220638,0.0012437074,0.0025055944,0.003322821,0.00044633984,0.0017330091,0.003539976,0.0030164432,0.0030904026],"category_scores_gemma":[0.17715213,0.00090602995,0.0020298953,0.0025724054,0.0017904941,0.0044894842,0.0018755704,0.0037621437,0.0014898075],"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":[0.00049459975,0.00018829342,0.008531276,0.0015200153,0.000812572,0.0002528652,0.0005954918,0.13433412,0.00372989,0.52465075,0.004691708,0.32019842],"study_design_scores_gemma":[0.00021445163,0.00048532628,0.0042901863,0.0005367276,0.00026933453,0.0008090836,0.00017196788,0.72570384,0.0064611356,0.23998518,0.020805188,0.00026767293],"about_ca_topic_score_codex":0.00047783062,"about_ca_topic_score_gemma":0.00042981998,"teacher_disagreement_score":0.046220638,"about_ca_system_score_codex":0.0009316826,"about_ca_system_score_gemma":0.00076185743,"threshold_uncertainty_score":0.24444103},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4294633,0.00028871017,0.567875,0.000562939,0.000026727348,0.000085032305,0.00016025754,0.00008252624,0.0014554438],"genre_scores_gemma":[0.9488358,0.00019180226,0.049966652,0.000052537485,0.0000499801,0.000086435975,0.000120579665,0.000017226534,0.000678926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99683243,0.0018425374,0.00010217168,0.00073313166,0.00025562628,0.00023405516],"domain_scores_gemma":[0.916246,0.07201338,0.0042527365,0.004885116,0.0014804093,0.0011222188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012142583,0.00054709666,0.0022860016,0.0034794738,0.0011665174,0.0028977108,0.0038503162,0.0026988639,0.0020347948],"category_scores_gemma":[0.06404222,0.0010190124,0.0015443586,0.001895984,0.006319929,0.0057391264,0.003965529,0.0025099444,0.00014466513],"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":[0.00028795903,0.00043495896,0.12611696,0.0002835944,0.00073579035,0.0004925299,0.0043611145,0.16321714,0.0036527873,0.6416378,0.0014077076,0.057371683],"study_design_scores_gemma":[0.000031833817,0.00010522281,0.019731712,0.000055258584,0.00011164138,0.00018804455,0.0008438565,0.74256665,0.0006359578,0.23521888,0.00044159003,0.00006939604],"about_ca_topic_score_codex":0.0035146934,"about_ca_topic_score_gemma":0.0033928568,"teacher_disagreement_score":0.012142583,"about_ca_system_score_codex":0.0014309998,"about_ca_system_score_gemma":0.0012573632,"threshold_uncertainty_score":0.06421691},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019036299,0.00057747716,0.9758051,0.0010385413,0.000052324,0.00031301042,0.00028569667,0.00018322727,0.002708315],"genre_scores_gemma":[0.4713952,0.0016330973,0.510818,0.0008300757,0.0007445939,0.0039720256,0.001411,0.00031363434,0.008882392],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.912597,0.06899552,0.0027275735,0.005215753,0.008453498,0.0020106754],"domain_scores_gemma":[0.49347627,0.46536198,0.008707695,0.021677354,0.008033104,0.0027435378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07789442,0.0017089638,0.007137421,0.0045861946,0.0035107192,0.007816972,0.007512408,0.0038685552,0.009366144],"category_scores_gemma":[0.29190433,0.0037741421,0.0032672847,0.007298631,0.010824947,0.014752403,0.0094137145,0.0060705673,0.00094300124],"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":[0.00021824437,0.00009961414,0.0023433112,0.00027141272,0.00009878955,0.000105575135,0.0007376236,0.025462605,0.00009806434,0.94405836,0.0023155406,0.024190908],"study_design_scores_gemma":[0.00007152981,0.00005592513,0.00042709286,0.000079870355,0.000056093766,0.000105564286,0.0001292842,0.18494207,0.00022565873,0.81223375,0.0016511106,0.00002206742],"about_ca_topic_score_codex":0.003599067,"about_ca_topic_score_gemma":0.0027593486,"teacher_disagreement_score":0.07789442,"about_ca_system_score_codex":0.0039758617,"about_ca_system_score_gemma":0.004347372,"threshold_uncertainty_score":0.41195},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007342448,0.00049017614,0.98903334,0.0005203932,0.00004848928,0.00003406091,0.000052501662,0.0001657994,0.0023128407],"genre_scores_gemma":[0.2649029,0.0012847724,0.72290623,0.00087378465,0.00022335943,0.00035366352,0.00030992628,0.00029894777,0.008846484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99383026,0.0039474885,0.00016899798,0.0010708198,0.0007162048,0.00026632592],"domain_scores_gemma":[0.9901603,0.006991333,0.0006901079,0.0010359382,0.00089055364,0.00023174942],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008773848,0.0008426403,0.0018460795,0.001318165,0.00063265825,0.0010556369,0.0018815795,0.0026539278,0.0052910773],"category_scores_gemma":[0.04222895,0.0009832451,0.0010071622,0.0013581397,0.0024655366,0.002514991,0.0032345224,0.002578876,0.0017791764],"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":[0.00021254623,0.00010080192,0.0019364242,0.00044562886,0.000096128635,0.00009879568,0.00030220608,0.14414674,0.0047475304,0.6575159,0.0056552356,0.18474218],"study_design_scores_gemma":[0.00011489785,0.00027544325,0.0016120311,0.00018616779,0.00007802684,0.00031440382,0.00009513972,0.55654794,0.005239866,0.42373037,0.011712577,0.000093169205],"about_ca_topic_score_codex":0.0014482526,"about_ca_topic_score_gemma":0.0011774802,"teacher_disagreement_score":0.99122614,"about_ca_system_score_codex":0.0014379929,"about_ca_system_score_gemma":0.0024327093,"threshold_uncertainty_score":0.046401083},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007908366,0.00028850316,0.9876431,0.00013076457,0.00006704986,0.00031766357,0.00013733134,0.0001240354,0.003383177],"genre_scores_gemma":[0.10788935,0.0004746852,0.8851824,0.00027187247,0.000083268016,0.0016823771,0.0002635885,0.00005910829,0.004093394],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9854671,0.011125809,0.00039450187,0.0014999895,0.0013521371,0.0001605522],"domain_scores_gemma":[0.9677737,0.025155168,0.0012177082,0.003883477,0.0017665676,0.00020329822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024453545,0.0009962346,0.0009430148,0.0009118471,0.00038845363,0.0013524616,0.002084116,0.001210833,0.006900707],"category_scores_gemma":[0.051724836,0.0006687836,0.0009579485,0.0009382667,0.0013028944,0.002292281,0.0018032934,0.0013557923,0.0011487281],"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":[0.0006478804,0.00023034561,0.011221451,0.00094086415,0.00039155615,0.00011733025,0.00073030026,0.09024521,0.004141066,0.34840897,0.0043546837,0.53857034],"study_design_scores_gemma":[0.0003294982,0.0013609397,0.007980681,0.00042219213,0.0002348127,0.00027159258,0.0001539266,0.38219404,0.004100255,0.5678208,0.03502587,0.00010540509],"about_ca_topic_score_codex":0.000619567,"about_ca_topic_score_gemma":0.0011840628,"teacher_disagreement_score":0.024453545,"about_ca_system_score_codex":0.0009432449,"about_ca_system_score_gemma":0.0010030187,"threshold_uncertainty_score":0.12932426},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0076638917,0.0030011146,0.9827002,0.0025057334,0.00034599486,0.0005839886,0.0001750376,0.00012755016,0.002896467],"genre_scores_gemma":[0.15044253,0.00596965,0.83611214,0.0017429935,0.0007386178,0.0026558894,0.00032508312,0.00015821091,0.0018548683],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.86252415,0.11461172,0.0038270385,0.0062150583,0.012298998,0.0005230113],"domain_scores_gemma":[0.87363523,0.092646524,0.0076940516,0.016022881,0.009017955,0.0009833059],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.072689034,0.0006405773,0.0016453336,0.0025356503,0.0017534897,0.0025479624,0.0026067558,0.0017168965,0.0026361584],"category_scores_gemma":[0.14621519,0.00076572894,0.0010132225,0.006572523,0.0072126896,0.0030142085,0.0033832816,0.0029619471,0.00079012796],"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":[0.00021815351,0.00011118912,0.026718348,0.0032534783,0.0005059406,0.00017757266,0.004958034,0.008519939,0.002053848,0.48989218,0.013795151,0.44979617],"study_design_scores_gemma":[0.00015505239,0.0011026873,0.024618745,0.0033899746,0.0003090639,0.0009797735,0.0032659865,0.04288331,0.004906346,0.76955515,0.14855212,0.00028188695],"about_ca_topic_score_codex":0.0034571558,"about_ca_topic_score_gemma":0.0043680314,"teacher_disagreement_score":0.92731094,"about_ca_system_score_codex":0.0019230822,"about_ca_system_score_gemma":0.004010055,"threshold_uncertainty_score":0.38442093},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043158936,0.00005495888,0.99346536,0.00012593645,0.000042659067,0.0014337975,0.00010422184,0.00007803235,0.00037917795],"genre_scores_gemma":[0.14885807,0.0003315076,0.8316718,0.00029875018,0.00010938019,0.015970107,0.00041394905,0.000037619637,0.0023089335],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.873081,0.10917528,0.003125247,0.005636867,0.007948166,0.0010333606],"domain_scores_gemma":[0.9249433,0.059642866,0.003274886,0.00553004,0.006165071,0.0004438326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06357374,0.0014409011,0.00231075,0.0018556047,0.0009177095,0.0011794048,0.0033676366,0.0014735437,0.0068858997],"category_scores_gemma":[0.10499257,0.0010622006,0.0025610388,0.0019386543,0.0018223928,0.0026814563,0.0027041156,0.0022048918,0.00076689577],"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":[0.0015315517,0.0008905795,0.019970106,0.0034063496,0.00092274003,0.00044826974,0.005204091,0.098893,0.0050890655,0.52783895,0.0065201907,0.3292852],"study_design_scores_gemma":[0.0009864178,0.002355047,0.0073233224,0.00037468883,0.00040955367,0.00037460236,0.00061653147,0.78281075,0.004636527,0.18737385,0.01256467,0.00017404037],"about_ca_topic_score_codex":0.0029559445,"about_ca_topic_score_gemma":0.0020677438,"teacher_disagreement_score":0.06357374,"about_ca_system_score_codex":0.0017784964,"about_ca_system_score_gemma":0.0027134973,"threshold_uncertainty_score":0.33621407},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004335176,0.0000794392,0.9950028,0.00005132861,0.000028729517,0.00004487909,0.000044755096,0.00011611943,0.0002967256],"genre_scores_gemma":[0.22662905,0.00017681437,0.76891994,0.00025507397,0.00019291563,0.0007221363,0.0005171535,0.00021810144,0.002368843],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98246884,0.011054661,0.0006685969,0.0022391966,0.0032419953,0.00032661716],"domain_scores_gemma":[0.9527655,0.030088205,0.0027284913,0.008623568,0.0053498684,0.0004442802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018765138,0.0006487438,0.0018144837,0.0021856532,0.0007131202,0.0016648815,0.004342572,0.002323629,0.0031286562],"category_scores_gemma":[0.0964402,0.00075881067,0.0017526086,0.0019677633,0.0016582562,0.0024011312,0.0025550069,0.0022059733,0.0008312791],"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":[0.0004832888,0.00035646226,0.027982019,0.00045500652,0.0011422597,0.00033912162,0.00066407234,0.14196023,0.011843896,0.31052262,0.006443062,0.49780792],"study_design_scores_gemma":[0.00017618724,0.00042097055,0.0063277273,0.00012275807,0.00028687035,0.000517059,0.00009961237,0.8410585,0.008404942,0.13187718,0.010585646,0.00012251596],"about_ca_topic_score_codex":0.0015666308,"about_ca_topic_score_gemma":0.001340722,"teacher_disagreement_score":0.018765138,"about_ca_system_score_codex":0.0010563803,"about_ca_system_score_gemma":0.0014164236,"threshold_uncertainty_score":0.09924072},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24415095,0.00087278895,0.7490403,0.00074173935,0.00011149815,0.0010553824,0.00012753079,0.00016236813,0.003737467],"genre_scores_gemma":[0.8046076,0.00027939893,0.19255476,0.00026536392,0.000046352925,0.0012017486,0.00013364399,0.00005408993,0.00085699774],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.75635564,0.2308934,0.0018008546,0.003541966,0.0058707,0.0015374783],"domain_scores_gemma":[0.18295848,0.78855455,0.007641652,0.015373807,0.004770102,0.0007013157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.18471882,0.0008986784,0.0015628233,0.0017125999,0.0009158328,0.0021751015,0.0028366498,0.00266346,0.0034195762],"category_scores_gemma":[0.46618316,0.0008898642,0.0021308064,0.0014405876,0.0036964144,0.005932014,0.0023035444,0.002707667,0.00037768635],"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":[0.012502639,0.0021524448,0.042194616,0.0011284496,0.0021292372,0.000315745,0.0035497406,0.51800436,0.0016397266,0.29469723,0.0016699217,0.12001589],"study_design_scores_gemma":[0.0014614034,0.0056154802,0.0072510084,0.00029822552,0.00049010233,0.00047647348,0.0007207174,0.9117938,0.0025329583,0.06715374,0.0020502966,0.00015573717],"about_ca_topic_score_codex":0.0014576772,"about_ca_topic_score_gemma":0.00097611593,"teacher_disagreement_score":0.18471882,"about_ca_system_score_codex":0.002903191,"about_ca_system_score_gemma":0.0016950236,"threshold_uncertainty_score":0.97689813},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34792694,0.00034872568,0.65040696,0.00007326318,0.000011486539,0.0000344885,0.000114656956,0.00023009937,0.0008533671],"genre_scores_gemma":[0.88410676,0.00035612442,0.11425927,0.000025991843,0.00001742138,0.00004719284,0.00027048655,0.000054825836,0.0008619436],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99799466,0.0010382672,0.0001313742,0.00039236931,0.00032631046,0.00011705452],"domain_scores_gemma":[0.98145753,0.013595105,0.0020726146,0.0017365154,0.0009933271,0.00014482054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0062662493,0.00039331248,0.0010615971,0.0012031788,0.00022091514,0.00064473023,0.00085840886,0.00046402702,0.00052679406],"category_scores_gemma":[0.03193629,0.0004501388,0.00060074107,0.0013727929,0.00068813993,0.001387039,0.0012411571,0.00056016777,0.00022064864],"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":[0.00065574533,0.00008798442,0.43069744,0.00032407677,0.00058464805,0.0009792582,0.0010106863,0.22060987,0.015204166,0.013401666,0.0008823757,0.31556204],"study_design_scores_gemma":[0.000041634245,0.00045642644,0.15934297,0.000048171445,0.0001715261,0.0012381348,0.00043570768,0.8016645,0.009533773,0.02523172,0.0017470586,0.00008849749],"about_ca_topic_score_codex":0.0020901433,"about_ca_topic_score_gemma":0.0019331449,"teacher_disagreement_score":0.0062662493,"about_ca_system_score_codex":0.00036081907,"about_ca_system_score_gemma":0.00033857525,"threshold_uncertainty_score":0.033139527},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041426247,0.0000993134,0.9990552,0.00005511048,0.000019233858,0.000027309936,0.0000320393,0.00007878305,0.00021876856],"genre_scores_gemma":[0.05067012,0.0006822157,0.9440585,0.00028751144,0.00024599148,0.0008346463,0.00047631515,0.00018175798,0.00256307],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97559345,0.01831351,0.0008662914,0.0018229071,0.0029550763,0.00044877717],"domain_scores_gemma":[0.97950053,0.013347865,0.0013174291,0.0032921864,0.0023841595,0.00015785382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024205796,0.0011553895,0.0024650616,0.0026277907,0.000939357,0.0021651066,0.0038909488,0.0015447093,0.0038933982],"category_scores_gemma":[0.06563828,0.0011508968,0.002983002,0.0045338003,0.0017153273,0.0026928692,0.0034587332,0.003481604,0.0019780651],"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":[0.00008907896,0.00013695941,0.003874563,0.00056027167,0.0007085376,0.00024652152,0.0011982672,0.0726381,0.0019108743,0.6135717,0.0071736183,0.29789162],"study_design_scores_gemma":[0.00008809725,0.00024363864,0.0028973133,0.00023882807,0.0003091869,0.00033033558,0.00020188118,0.4459743,0.0035378933,0.5184002,0.02759677,0.00018158801],"about_ca_topic_score_codex":0.002503537,"about_ca_topic_score_gemma":0.002726442,"teacher_disagreement_score":0.024205796,"about_ca_system_score_codex":0.0013647934,"about_ca_system_score_gemma":0.0028791297,"threshold_uncertainty_score":0.12801397},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0098931305,0.000086643086,0.9883513,0.0001250275,0.000060438186,0.00094415806,0.000076319535,0.00009407915,0.00036883692],"genre_scores_gemma":[0.17096555,0.000103889135,0.8236182,0.00017249562,0.000053586587,0.004544254,0.00019274905,0.000039156883,0.0003102274],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8573244,0.1242169,0.0037623737,0.0064903484,0.007189472,0.0010166113],"domain_scores_gemma":[0.6522802,0.31885386,0.0061807344,0.012849334,0.008761302,0.0010745008],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10184751,0.0011037524,0.0034100944,0.0024958253,0.0008826597,0.0015095545,0.0037300491,0.0025481537,0.005386179],"category_scores_gemma":[0.32868478,0.0012438624,0.002653563,0.0018850035,0.00336881,0.0026047195,0.0029425581,0.0028772028,0.00043599616],"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":[0.007987051,0.0014530631,0.028535202,0.003062313,0.0018425352,0.0005096766,0.0027292485,0.09293255,0.0071238233,0.34937805,0.005678535,0.49876797],"study_design_scores_gemma":[0.0026243438,0.0041078487,0.0064509683,0.00042514448,0.0006156654,0.0006298197,0.0005269197,0.7921403,0.004912346,0.18298168,0.004438669,0.00014632486],"about_ca_topic_score_codex":0.0021207773,"about_ca_topic_score_gemma":0.0015404534,"teacher_disagreement_score":0.8981525,"about_ca_system_score_codex":0.0015350305,"about_ca_system_score_gemma":0.0039469833,"threshold_uncertainty_score":0.5386275},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030584345,0.0004959358,0.99231887,0.00070587255,0.00011427205,0.00069902017,0.00011901466,0.0001534142,0.0023352064],"genre_scores_gemma":[0.21304703,0.0012287603,0.77255255,0.0014243827,0.0005053515,0.009033543,0.0003350401,0.00034897515,0.0015244156],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.5543028,0.41488937,0.004305012,0.00858814,0.016873611,0.0010410193],"domain_scores_gemma":[0.22586891,0.73150694,0.010357273,0.026342021,0.0052774604,0.00064740545],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2755057,0.0025067506,0.0036846288,0.006426738,0.0016927304,0.0047375606,0.0039927484,0.003828015,0.010561097],"category_scores_gemma":[0.69462687,0.001787536,0.0048305034,0.0060455417,0.009682613,0.0107063865,0.0070145186,0.0071949633,0.0015614876],"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":[0.00045152457,0.00023952953,0.005489983,0.0013944046,0.0012529211,0.00022233349,0.0031057138,0.019219263,0.0009280211,0.7469597,0.006049796,0.21468686],"study_design_scores_gemma":[0.0002500035,0.0009899767,0.0034793813,0.00069083006,0.00046772906,0.00049837603,0.00071118685,0.13979638,0.0019403164,0.8355834,0.015434237,0.0001581086],"about_ca_topic_score_codex":0.00081886083,"about_ca_topic_score_gemma":0.0004636892,"teacher_disagreement_score":0.2755057,"about_ca_system_score_codex":0.0027920152,"about_ca_system_score_gemma":0.0027638425,"threshold_uncertainty_score":0.8934305},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0060829436,0.00013363185,0.99318624,0.00004270202,0.000022289165,0.000065854394,0.00003395854,0.00011428841,0.00031806392],"genre_scores_gemma":[0.23498657,0.00031693903,0.7617071,0.00011943571,0.00013646363,0.0010536694,0.0004356337,0.00028904824,0.00095506065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9735786,0.01936446,0.0009062956,0.0023474474,0.0033433232,0.0004598442],"domain_scores_gemma":[0.73379785,0.22560886,0.007817503,0.017736603,0.013588704,0.0014505418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.055861466,0.0010788784,0.002583192,0.0034153296,0.0011163342,0.0019726935,0.0064650546,0.0028692165,0.0048262323],"category_scores_gemma":[0.24537104,0.0011217897,0.0016145309,0.0033516798,0.0037618235,0.0030573923,0.0027511953,0.003472784,0.000736191],"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":[0.002145352,0.00034214888,0.008338751,0.0007298786,0.00081012124,0.0002940714,0.0014631195,0.16610843,0.004478465,0.55517906,0.0047662472,0.25534436],"study_design_scores_gemma":[0.0003250216,0.0003097414,0.0038641335,0.00017985106,0.0001983258,0.00023093818,0.00011843004,0.78941405,0.0030183017,0.19920257,0.003049345,0.00008928841],"about_ca_topic_score_codex":0.0013051343,"about_ca_topic_score_gemma":0.0011217245,"teacher_disagreement_score":0.055861466,"about_ca_system_score_codex":0.0013262022,"about_ca_system_score_gemma":0.001661174,"threshold_uncertainty_score":0.29542714},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017071372,0.00029749158,0.9795257,0.00059725373,0.00003771685,0.00015210854,0.00016357022,0.00015538726,0.0019993759],"genre_scores_gemma":[0.30931604,0.0005813464,0.6849887,0.00037572562,0.00020461412,0.0013130493,0.0009174288,0.0001688428,0.002134254],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9257453,0.06296776,0.0015226764,0.0036108766,0.00508716,0.0010661649],"domain_scores_gemma":[0.7925245,0.15456462,0.010075399,0.030919623,0.010293351,0.001622422],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07716065,0.00074524345,0.0028785027,0.0043948125,0.002316867,0.0041857567,0.0035710335,0.0025504502,0.00394859],"category_scores_gemma":[0.20029038,0.0011111065,0.0026422949,0.0045865756,0.0055057197,0.005975038,0.006922685,0.0037495808,0.00079294055],"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":[0.00020075591,0.000088646906,0.012175277,0.00017936839,0.00015822564,0.000050520226,0.0008145733,0.05220517,0.00023325032,0.8050208,0.0031279777,0.12574546],"study_design_scores_gemma":[0.000050283757,0.00007963094,0.0032270562,0.00016095927,0.000044973764,0.00007330016,0.00015622936,0.33381277,0.00054011564,0.65666133,0.0051534115,0.000039993283],"about_ca_topic_score_codex":0.0023840284,"about_ca_topic_score_gemma":0.0016661199,"teacher_disagreement_score":0.92283934,"about_ca_system_score_codex":0.0024489977,"about_ca_system_score_gemma":0.0021825326,"threshold_uncertainty_score":0.40806937},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020539602,0.00016094628,0.9969463,0.00007217533,0.000042652093,0.00012960659,0.000035746216,0.000068471476,0.0004901622],"genre_scores_gemma":[0.13631167,0.0007190151,0.8570187,0.00034226122,0.00017346592,0.0015212169,0.00042444575,0.00012880054,0.0033604484],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96952796,0.02373636,0.0008148949,0.0021771987,0.0031017554,0.00064181257],"domain_scores_gemma":[0.9453884,0.042772118,0.0020900564,0.006566057,0.0029535878,0.00022984251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035103153,0.001052555,0.0017643177,0.001998714,0.000648823,0.0020992735,0.0027127194,0.0019179161,0.004777838],"category_scores_gemma":[0.119436674,0.0009591234,0.0021118,0.00282045,0.0017912808,0.003174339,0.0027843004,0.002034545,0.001178003],"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":[0.00023577627,0.00013826536,0.008825065,0.000399705,0.0004656196,0.00020503222,0.00058684935,0.08777265,0.0015447926,0.65647405,0.0039930763,0.23935913],"study_design_scores_gemma":[0.0001029258,0.00027409947,0.0027723392,0.00015346521,0.00015396935,0.00016979827,0.00012780768,0.65145516,0.0017627818,0.33299348,0.0099619925,0.00007220611],"about_ca_topic_score_codex":0.0035535574,"about_ca_topic_score_gemma":0.002881511,"teacher_disagreement_score":0.035103153,"about_ca_system_score_codex":0.0017864616,"about_ca_system_score_gemma":0.002095123,"threshold_uncertainty_score":0.18564546},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9100591,0.009123323,0.062563546,0.002214593,0.00045771262,0.00045555359,0.0058931904,0.00029367703,0.00893942],"genre_scores_gemma":[0.98189056,0.0007354653,0.014070713,0.00074871053,0.00012376606,0.00026024066,0.0017382145,0.00004575966,0.00038663106],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9460443,0.032000523,0.007044907,0.0048064757,0.009155865,0.00094801886],"domain_scores_gemma":[0.8388612,0.08545853,0.04049174,0.011874621,0.02262914,0.00068480114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07091466,0.00057623733,0.0005477831,0.002965952,0.0006819125,0.0013091356,0.000984159,0.00056843285,0.000972891],"category_scores_gemma":[0.18159392,0.0003371268,0.000879011,0.004149007,0.0010755407,0.0010790578,0.0019736052,0.00062136294,0.00019228579],"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":[0.00014043288,0.000017055721,0.9535664,0.00032880748,0.0009230702,0.000068329355,0.0015136292,0.0012199514,0.00031964126,0.0010397001,0.0019706008,0.038892314],"study_design_scores_gemma":[0.000022214947,0.00014040119,0.97438747,0.00052373635,0.00054559455,0.00041837094,0.0010593631,0.005030319,0.0015653663,0.0033022424,0.012946896,0.000058050966],"about_ca_topic_score_codex":0.020936832,"about_ca_topic_score_gemma":0.01818727,"teacher_disagreement_score":0.07091466,"about_ca_system_score_codex":0.0016472733,"about_ca_system_score_gemma":0.0016195809,"threshold_uncertainty_score":0.37503707},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037271183,0.00016656665,0.9872365,0.00071099313,0.00028499446,0.00034102864,0.00094920903,0.0008252563,0.00575837],"genre_scores_gemma":[0.2425981,0.00053628144,0.70868605,0.0015880225,0.0007587078,0.0037775158,0.0051052133,0.0012185107,0.035731547],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.938489,0.047677524,0.0021753968,0.006191759,0.0042238347,0.0012424791],"domain_scores_gemma":[0.86541075,0.05928052,0.0031987384,0.06565633,0.0058953525,0.0005583547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05203066,0.001144087,0.0034320594,0.0029532518,0.0017479258,0.0035361703,0.004227238,0.0024599875,0.037349895],"category_scores_gemma":[0.2187194,0.0015121044,0.003718388,0.007081875,0.002046868,0.0045870286,0.003823995,0.0043540914,0.010947768],"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":[0.0006205152,0.00028153358,0.01219168,0.0004306726,0.00070159056,0.0003600308,0.001018624,0.0129912635,0.0005510867,0.4720139,0.062377527,0.43646166],"study_design_scores_gemma":[0.00025994316,0.00019198966,0.0043062354,0.00014507752,0.00031293006,0.0006171739,0.0002018469,0.08295003,0.0016596689,0.8689098,0.040401395,0.000043911074],"about_ca_topic_score_codex":0.0015101072,"about_ca_topic_score_gemma":0.0011977501,"teacher_disagreement_score":0.05203066,"about_ca_system_score_codex":0.00094534527,"about_ca_system_score_gemma":0.0026826349,"threshold_uncertainty_score":0.27516776},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075561674,0.0002914101,0.9914505,0.0001311573,0.000021417132,0.000034416542,0.00006652576,0.00011483182,0.00033360015],"genre_scores_gemma":[0.4204862,0.0009177409,0.57480496,0.0002288964,0.00016776797,0.0004876145,0.0007499071,0.00018376923,0.0019731568],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94781274,0.041360583,0.0016461295,0.0029807838,0.005336912,0.00086286274],"domain_scores_gemma":[0.8049035,0.15791456,0.011630492,0.017759062,0.007135824,0.00065645354],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.044843327,0.0008118168,0.002604534,0.0029143142,0.00063890027,0.0020956395,0.00443326,0.002243142,0.0019682823],"category_scores_gemma":[0.2357392,0.0011556415,0.0022710552,0.0034475175,0.0026612112,0.0028012628,0.003115112,0.0023886613,0.0005561853],"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":[0.00035904007,0.00015489438,0.015639165,0.0005038919,0.0011365862,0.00074972026,0.00062017137,0.39313382,0.0012932731,0.44736695,0.0026348121,0.1364078],"study_design_scores_gemma":[0.000051053892,0.00010077879,0.0033886237,0.000107059335,0.0001375637,0.00018986125,0.00007073505,0.7820389,0.0011105953,0.21091035,0.0018244898,0.000069983136],"about_ca_topic_score_codex":0.0052085402,"about_ca_topic_score_gemma":0.0027901041,"teacher_disagreement_score":0.9551567,"about_ca_system_score_codex":0.0014358254,"about_ca_system_score_gemma":0.0017457029,"threshold_uncertainty_score":0.23715705},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047556185,0.00025840872,0.9939277,0.00009495036,0.00003794396,0.000025671181,0.000055342556,0.00008713409,0.00075729523],"genre_scores_gemma":[0.1627824,0.00073609245,0.83062565,0.00022692503,0.00017316312,0.00029459185,0.00049780856,0.00013368623,0.004529719],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966691,0.0016430153,0.00013141835,0.0003728681,0.0010391135,0.00014447555],"domain_scores_gemma":[0.9885408,0.006461519,0.0010756577,0.0016340013,0.0021362794,0.0001517526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007392324,0.00053206674,0.0012533846,0.0016013256,0.00050069275,0.0010885653,0.0019437437,0.001166524,0.0046563162],"category_scores_gemma":[0.03522332,0.00046448104,0.00070199615,0.001657628,0.00088400097,0.0016242014,0.0017841442,0.0013755917,0.0022236141],"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":[0.0002196499,0.00016348997,0.012434501,0.0005595747,0.0002548201,0.0002831945,0.00042094145,0.16840643,0.014897577,0.24139504,0.0073725577,0.5535922],"study_design_scores_gemma":[0.00007028891,0.00015638671,0.0063579245,0.00020344397,0.000108695036,0.00096229115,0.000076274904,0.80183107,0.008971324,0.16538857,0.015757155,0.0001165973],"about_ca_topic_score_codex":0.0011558083,"about_ca_topic_score_gemma":0.0010368056,"teacher_disagreement_score":0.007392324,"about_ca_system_score_codex":0.0007532089,"about_ca_system_score_gemma":0.0013284044,"threshold_uncertainty_score":0.039094806},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001956654,0.00040799467,0.99431145,0.0014732736,0.00012093815,0.00016903225,0.000101739475,0.00012441272,0.0013345716],"genre_scores_gemma":[0.107725985,0.0013423198,0.87019557,0.0017020261,0.0006304276,0.002934635,0.00039648355,0.0002766636,0.014795847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8964929,0.09374592,0.001714253,0.0033343914,0.003422699,0.0012897627],"domain_scores_gemma":[0.7585207,0.21922283,0.003316795,0.013230436,0.004728416,0.0009808083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09346999,0.002974266,0.0063091274,0.0039652972,0.0021412494,0.0045056287,0.012521355,0.006954516,0.018151907],"category_scores_gemma":[0.23226796,0.0032667522,0.005535816,0.0066861245,0.0072107543,0.012261471,0.0044629257,0.008336532,0.002135902],"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":[0.00018917838,0.00006811967,0.0006604447,0.0001550177,0.00018926463,0.00008314166,0.00053001265,0.02123744,0.00007207975,0.94181854,0.0043432005,0.030653473],"study_design_scores_gemma":[0.00018566992,0.00008270669,0.00017896344,0.00007041787,0.000099995734,0.0000698794,0.00011959752,0.20012216,0.00014724093,0.79392225,0.004949621,0.000051437073],"about_ca_topic_score_codex":0.0072833453,"about_ca_topic_score_gemma":0.008337627,"teacher_disagreement_score":0.09346999,"about_ca_system_score_codex":0.0037943474,"about_ca_system_score_gemma":0.00437862,"threshold_uncertainty_score":0.49432248},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002428022,0.00021670203,0.99625504,0.00016943633,0.000038569673,0.00012384057,0.000038009166,0.00004146273,0.0006889677],"genre_scores_gemma":[0.10262144,0.00078883115,0.8889616,0.00036228917,0.00025702745,0.0015685866,0.00022247732,0.00014506493,0.0050727543],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97748375,0.018187445,0.0005729492,0.0014919265,0.0016045504,0.0006593815],"domain_scores_gemma":[0.9662765,0.027940001,0.0008477738,0.0024011086,0.0020329454,0.0005015768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02624939,0.0019304658,0.006468112,0.0032413786,0.0015123067,0.0025844579,0.005950299,0.0031764717,0.008591264],"category_scores_gemma":[0.0643869,0.0032828583,0.0043282825,0.004151179,0.0041165766,0.0052246195,0.0041894033,0.00374178,0.0011867225],"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":[0.00048527276,0.00020622615,0.0018993354,0.0005251109,0.00051880465,0.00015605979,0.00057167595,0.27769396,0.0010494785,0.6365522,0.0046120854,0.07572973],"study_design_scores_gemma":[0.00012857918,0.00017171763,0.0005062271,0.000075944816,0.0001441776,0.00008172818,0.00006193407,0.73140055,0.00037781865,0.26335552,0.0036511808,0.000044660603],"about_ca_topic_score_codex":0.003177293,"about_ca_topic_score_gemma":0.0037218798,"teacher_disagreement_score":0.02624939,"about_ca_system_score_codex":0.0027404923,"about_ca_system_score_gemma":0.0037744215,"threshold_uncertainty_score":0.13882172},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9750807,0.00007959393,0.023066223,0.000039123417,0.0000068510776,0.00086439925,0.0001558843,0.00008391807,0.00062329706],"genre_scores_gemma":[0.9473137,0.00008476339,0.050849237,0.000033321958,0.0000028561358,0.00095675193,0.00029608473,0.000012040433,0.00045129884],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.98941153,0.008197589,0.00041622773,0.00068480294,0.0010162905,0.00027354967],"domain_scores_gemma":[0.9644424,0.020753903,0.0031626206,0.0026481445,0.0081675155,0.00082539424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013290512,0.0005736743,0.00050093356,0.00068476464,0.000760037,0.00048990594,0.001225798,0.00052095205,0.00084362325],"category_scores_gemma":[0.037594415,0.00047835422,0.0004928384,0.00071113853,0.0007954786,0.0003044751,0.00068283663,0.00034903325,0.00009490848],"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":[0.00656524,0.0011525361,0.24168196,0.00052591064,0.0006862822,0.00017700961,0.0010966387,0.6078368,0.016614435,0.0024676584,0.0006251231,0.120570384],"study_design_scores_gemma":[0.0020003607,0.014792862,0.25943765,0.00013482626,0.0005966859,0.00018153968,0.0008554735,0.6994702,0.017404266,0.0014303912,0.003506747,0.00018894808],"about_ca_topic_score_codex":0.1712222,"about_ca_topic_score_gemma":0.2664264,"teacher_disagreement_score":0.8287778,"about_ca_system_score_codex":0.0050163255,"about_ca_system_score_gemma":0.004377608,"threshold_uncertainty_score":0.34045118},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5146818,0.000466001,0.4829596,0.00010248121,0.00004181556,0.000518622,0.00011128253,0.00016444844,0.000953854],"genre_scores_gemma":[0.7548083,0.00028766834,0.24355006,0.00007555283,0.000029323288,0.0006143451,0.0002437836,0.000024769028,0.00036611716],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9805006,0.01604225,0.0007260895,0.0012881651,0.0012386912,0.00020422017],"domain_scores_gemma":[0.9120335,0.07080951,0.0043330733,0.007846751,0.0044822106,0.0004949766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02421491,0.00056588644,0.000902577,0.001292056,0.0003604883,0.0004853984,0.0013115328,0.0006775309,0.000725781],"category_scores_gemma":[0.062251657,0.0004252507,0.00078229955,0.0011944353,0.00091719197,0.0013390911,0.0015600758,0.0006114446,0.00010783875],"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":[0.0047943634,0.0008253277,0.22937816,0.0007522754,0.001872515,0.00011235941,0.001974396,0.2965483,0.004801037,0.015733398,0.00045538734,0.44275248],"study_design_scores_gemma":[0.00063458935,0.006064367,0.08171576,0.000113240625,0.00047214358,0.00022380883,0.0006046537,0.8900762,0.0045437664,0.013533277,0.0018871027,0.00013111536],"about_ca_topic_score_codex":0.0031848124,"about_ca_topic_score_gemma":0.003173306,"teacher_disagreement_score":0.02421491,"about_ca_system_score_codex":0.00062304264,"about_ca_system_score_gemma":0.00075224665,"threshold_uncertainty_score":0.12806219},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036223337,0.0017633828,0.9599045,0.0002539781,0.0001246641,0.00027197663,0.00028175916,0.00050351856,0.0006728752],"genre_scores_gemma":[0.16201118,0.00197911,0.8325769,0.00012039794,0.000101599326,0.0010385714,0.0009613715,0.00032461053,0.0008863337],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9349316,0.049792133,0.003254695,0.0022688697,0.0091674775,0.00058514014],"domain_scores_gemma":[0.6411071,0.32204416,0.007483379,0.012991687,0.015636258,0.00073734444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.081162855,0.0013964343,0.0015911872,0.006076445,0.00047426662,0.0016487513,0.0030309197,0.0014612817,0.0012869396],"category_scores_gemma":[0.21584651,0.0008770641,0.0020986353,0.004491492,0.00092027325,0.0022124683,0.0021698466,0.0017975818,0.00054823596],"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":[0.0027979317,0.0004727525,0.06005945,0.002788914,0.004511724,0.00023503686,0.0021996053,0.11940113,0.0049393754,0.020646006,0.0036031145,0.7783449],"study_design_scores_gemma":[0.0005583187,0.0015890159,0.09404262,0.0007710317,0.00087941374,0.0013801503,0.0011049862,0.82529706,0.014835928,0.046515588,0.012347371,0.0006785584],"about_ca_topic_score_codex":0.002127289,"about_ca_topic_score_gemma":0.00249289,"teacher_disagreement_score":0.081162855,"about_ca_system_score_codex":0.0009396434,"about_ca_system_score_gemma":0.0013479481,"threshold_uncertainty_score":0.42923534},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002438103,0.00016217255,0.99640155,0.00020502896,0.000022100048,0.000027923572,0.000050540788,0.00006647403,0.0006261593],"genre_scores_gemma":[0.36542287,0.0014629713,0.6290347,0.0005271063,0.00029064785,0.00067038176,0.0005577832,0.000083301595,0.0019502228],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99128366,0.0067695696,0.00018808187,0.00072037464,0.0008584831,0.00017979738],"domain_scores_gemma":[0.9876165,0.008151803,0.000924327,0.0023469883,0.00083849765,0.00012193898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012892667,0.0010847589,0.0016266389,0.002002771,0.00066811184,0.0015915548,0.0026001686,0.0021262688,0.0026350352],"category_scores_gemma":[0.054783773,0.0008371506,0.0014247416,0.0032566553,0.0020548953,0.0039666947,0.002983389,0.0026486772,0.00050257164],"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":[0.00010298909,0.00014967115,0.0037070313,0.0004092876,0.00038503576,0.00017495961,0.00050552696,0.35809898,0.00096352125,0.50110143,0.0021708915,0.1322307],"study_design_scores_gemma":[0.000060840463,0.00014700307,0.0012252212,0.00009724541,0.0000841247,0.0001910559,0.00008702428,0.59653074,0.0016544447,0.39377618,0.0060762702,0.00006979712],"about_ca_topic_score_codex":0.0013272959,"about_ca_topic_score_gemma":0.0011944853,"teacher_disagreement_score":0.012892667,"about_ca_system_score_codex":0.001079104,"about_ca_system_score_gemma":0.0023185087,"threshold_uncertainty_score":0.06818372},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039049268,0.000111106776,0.9952884,0.00008727311,0.00001445461,0.000024791769,0.000033413093,0.00006434729,0.00047132847],"genre_scores_gemma":[0.28423572,0.0006416275,0.7121273,0.0002996528,0.0001394288,0.0003414405,0.00047006988,0.00018807843,0.0015566975],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9702551,0.02178411,0.00095935405,0.002477551,0.0040199705,0.0005040183],"domain_scores_gemma":[0.89588034,0.07714853,0.0066049653,0.014832833,0.0052017616,0.00033156783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034012377,0.0012767385,0.0022873767,0.0017553346,0.0006824395,0.0023221846,0.0028831034,0.0026485943,0.0024759185],"category_scores_gemma":[0.14767754,0.0012749109,0.0017378771,0.0021689516,0.0019349765,0.0052931686,0.002994608,0.0052834437,0.0008972594],"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":[0.00014414542,0.00016392431,0.0056635546,0.00047121794,0.0002870548,0.000120872624,0.0006585832,0.4440537,0.00426539,0.39161977,0.0014854923,0.1510664],"study_design_scores_gemma":[0.00005370478,0.00012562462,0.0023055235,0.00011975473,0.000042789183,0.00018501742,0.00007226465,0.8004158,0.005341196,0.18672195,0.0045055253,0.00011086568],"about_ca_topic_score_codex":0.0012499819,"about_ca_topic_score_gemma":0.001580295,"teacher_disagreement_score":0.034012377,"about_ca_system_score_codex":0.001735559,"about_ca_system_score_gemma":0.0024512366,"threshold_uncertainty_score":0.1798768},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019877907,0.018219111,0.87005985,0.08117457,0.0032732144,0.00035580233,0.00024298021,0.00035653432,0.006439978],"genre_scores_gemma":[0.46272132,0.029415391,0.4404508,0.043415546,0.013851797,0.0016038963,0.00043975937,0.00053192314,0.007569643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.8392239,0.13584964,0.0065006474,0.007381515,0.0100131575,0.001031144],"domain_scores_gemma":[0.39202887,0.53954864,0.017819917,0.03311216,0.015778713,0.0017117588],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27688912,0.0011012695,0.0029921918,0.0020602744,0.0014716177,0.0036862693,0.0061198804,0.004769248,0.003929007],"category_scores_gemma":[0.61737156,0.0017001535,0.0016481056,0.0047879796,0.011893814,0.012768116,0.0033971516,0.0043656994,0.0010076324],"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":[0.00041921472,0.000120607874,0.033831544,0.0032120661,0.0005938322,0.0003348462,0.00372297,0.014088212,0.00039027605,0.53055865,0.018283654,0.3944441],"study_design_scores_gemma":[0.00031136593,0.00062850036,0.018043187,0.0026948403,0.0004521215,0.002122816,0.0018200594,0.06759613,0.0012373363,0.8137051,0.09121058,0.00017808512],"about_ca_topic_score_codex":0.00911483,"about_ca_topic_score_gemma":0.009396144,"teacher_disagreement_score":0.7231109,"about_ca_system_score_codex":0.0029337993,"about_ca_system_score_gemma":0.0039448277,"threshold_uncertainty_score":0.89172447},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071168304,0.0007898221,0.9908489,0.00021758556,0.00007429157,0.000023517308,0.0000530698,0.000116363124,0.0007596916],"genre_scores_gemma":[0.45498216,0.0040230015,0.532177,0.0010548127,0.00073014863,0.00042251113,0.00067834917,0.00036446226,0.0055675074],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9857573,0.009343015,0.00056307286,0.0014445974,0.0024235265,0.00046851198],"domain_scores_gemma":[0.9274023,0.056845378,0.0046548,0.006071673,0.0047123223,0.0003135943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031450264,0.0011822934,0.0015514105,0.0022376666,0.00056875474,0.0018586622,0.0026474283,0.0022405356,0.0019786817],"category_scores_gemma":[0.1443383,0.00062114,0.0015519675,0.0026355807,0.0021480895,0.0025923427,0.002310151,0.002782139,0.00078452576],"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":[0.0002293834,0.0000852711,0.015185251,0.00060413906,0.00054355327,0.00080903206,0.00071839005,0.2969792,0.0050416538,0.4925851,0.0039173774,0.18330164],"study_design_scores_gemma":[0.000044074546,0.000101066384,0.003417959,0.00021099026,0.0001221677,0.00059804006,0.0000650348,0.6880532,0.0029795016,0.29707083,0.007239533,0.00009762721],"about_ca_topic_score_codex":0.002427594,"about_ca_topic_score_gemma":0.0014477479,"teacher_disagreement_score":0.031450264,"about_ca_system_score_codex":0.0011898833,"about_ca_system_score_gemma":0.0014618929,"threshold_uncertainty_score":0.16632682},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0058583408,0.000036309637,0.9937317,0.000037883692,0.0000043388636,0.0000113373735,0.00002277538,0.000043001928,0.00025431425],"genre_scores_gemma":[0.36619753,0.00039436814,0.62914026,0.0001296633,0.000066028835,0.00030624509,0.0005801122,0.00008253613,0.0031031978],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969085,0.0021148622,0.00008599806,0.0003791054,0.00040944747,0.000102065635],"domain_scores_gemma":[0.9811034,0.014830034,0.0013214317,0.0018586712,0.00074907695,0.00013735238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009560149,0.0006062626,0.0010801026,0.0010250644,0.0003106028,0.0011161434,0.0019740334,0.00075657666,0.0013918305],"category_scores_gemma":[0.04053445,0.0005307609,0.0006566516,0.0012903658,0.0013714189,0.0025145318,0.00209341,0.0014737066,0.00033391514],"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":[0.00009832901,0.00007602815,0.005222668,0.00021058062,0.00011864408,0.00012030025,0.00028126323,0.5139615,0.0023551155,0.34380117,0.0013883491,0.13236608],"study_design_scores_gemma":[0.000014440232,0.000032041913,0.0009907444,0.000014190472,0.000010745396,0.000048389506,0.000022841894,0.9016089,0.0010433773,0.095256366,0.0009398706,0.000018010105],"about_ca_topic_score_codex":0.000964919,"about_ca_topic_score_gemma":0.0013013727,"teacher_disagreement_score":0.009560149,"about_ca_system_score_codex":0.0006683003,"about_ca_system_score_gemma":0.0011013624,"threshold_uncertainty_score":0.05055952},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035604976,0.00053921854,0.95901275,0.0007990365,0.00014361022,0.0017304407,0.0006386507,0.0003725264,0.0011588874],"genre_scores_gemma":[0.3479591,0.0011879937,0.62861955,0.0007099723,0.0002713958,0.01676775,0.0017219541,0.00013515998,0.0026270917],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.75124204,0.23629785,0.0029686377,0.0047921594,0.0036316565,0.0010677143],"domain_scores_gemma":[0.7091579,0.25212765,0.017018666,0.016425265,0.0045456984,0.0007248705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11656998,0.0025685288,0.0030479566,0.003260972,0.00094528036,0.0022508393,0.0052834786,0.0042969086,0.009413243],"category_scores_gemma":[0.22933328,0.0014936386,0.0043747183,0.005349999,0.0030662839,0.0038607658,0.002726826,0.004275323,0.0021752631],"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":[0.0028198864,0.0024768375,0.11139309,0.0031515728,0.005110951,0.0005829401,0.0068075988,0.24028753,0.0013793054,0.37264666,0.008394578,0.24494903],"study_design_scores_gemma":[0.00073848735,0.0027250054,0.023340737,0.00069586607,0.00082949834,0.00041518232,0.0016464308,0.6513327,0.0011103869,0.30618533,0.010649477,0.00033090802],"about_ca_topic_score_codex":0.0022056513,"about_ca_topic_score_gemma":0.0018056649,"teacher_disagreement_score":0.11656998,"about_ca_system_score_codex":0.0020791157,"about_ca_system_score_gemma":0.0018001125,"threshold_uncertainty_score":0.61648834},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017782042,0.00023147732,0.9810954,0.00012417021,0.000019632571,0.000057166173,0.000048859107,0.000048515976,0.000592765],"genre_scores_gemma":[0.4900936,0.0005673457,0.5062121,0.00009683534,0.00011003376,0.00048553105,0.00032430628,0.000034128763,0.0020761304],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9882359,0.008641567,0.00029356062,0.0014574211,0.0011139823,0.00025750807],"domain_scores_gemma":[0.97145116,0.020812128,0.002850061,0.0026219462,0.0020409145,0.00022375368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017561749,0.00075740844,0.0013373296,0.0015175223,0.0005325094,0.001163965,0.0017607321,0.0011669775,0.0032785283],"category_scores_gemma":[0.06119928,0.00073948485,0.0008964826,0.0017908349,0.0010579928,0.0023241618,0.0019096533,0.0010961466,0.00039678637],"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":[0.00033858398,0.00021023076,0.037660386,0.0005598596,0.0004000896,0.00027069647,0.000868856,0.28688258,0.0027385822,0.3352289,0.0033042715,0.331537],"study_design_scores_gemma":[0.000080289086,0.0002468283,0.009764986,0.00015292615,0.00008054693,0.00022617969,0.00017444856,0.80352986,0.0015894034,0.17729618,0.0068150936,0.000043382],"about_ca_topic_score_codex":0.004394149,"about_ca_topic_score_gemma":0.003685266,"teacher_disagreement_score":0.017561749,"about_ca_system_score_codex":0.0012718502,"about_ca_system_score_gemma":0.00085923745,"threshold_uncertainty_score":0.092876494},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033473673,0.00032704056,0.9954619,0.00011379647,0.000021906151,0.000042938005,0.000060561244,0.00016426825,0.00046031305],"genre_scores_gemma":[0.23868357,0.0010366191,0.75456405,0.0002538461,0.0003840919,0.0013469881,0.0010956284,0.00045616436,0.0021790066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96581215,0.025821209,0.0011072329,0.002916604,0.0037231392,0.00061959506],"domain_scores_gemma":[0.47408515,0.4833875,0.007544042,0.023417149,0.009873301,0.0016928297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06713825,0.0016329677,0.003310932,0.004355946,0.0013589612,0.0037230651,0.009247007,0.0032195493,0.005787916],"category_scores_gemma":[0.40313077,0.0017288753,0.0019443961,0.005004568,0.006693634,0.006138668,0.0048610237,0.007008237,0.0009141986],"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":[0.00046810164,0.000115180126,0.0045990357,0.0004096444,0.00043053483,0.00016106134,0.00086304935,0.17439549,0.00056639983,0.71414137,0.004090137,0.099760056],"study_design_scores_gemma":[0.000104844265,0.000049652466,0.001254218,0.000108933586,0.00008108438,0.00014101653,0.00007458482,0.5801554,0.00046049897,0.41552678,0.0020026097,0.000040370367],"about_ca_topic_score_codex":0.0034733764,"about_ca_topic_score_gemma":0.0019451791,"teacher_disagreement_score":0.06713825,"about_ca_system_score_codex":0.0024659212,"about_ca_system_score_gemma":0.0023187923,"threshold_uncertainty_score":0.35506523},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009905671,0.0010931799,0.9903094,0.0038560363,0.00028379558,0.000100442616,0.000057151065,0.00007065969,0.0032387332],"genre_scores_gemma":[0.06634887,0.0021762906,0.91804576,0.0044599,0.0024792978,0.001228363,0.0001109188,0.0003064451,0.0048441594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8916405,0.088417545,0.0023224351,0.006305912,0.010428956,0.000884664],"domain_scores_gemma":[0.77640265,0.18971136,0.0055500004,0.020417934,0.006975681,0.0009424496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09068739,0.0018025408,0.0029623653,0.0025003979,0.0020703697,0.006359049,0.004947589,0.0060856645,0.00927556],"category_scores_gemma":[0.22171134,0.0019934278,0.003163721,0.0031745788,0.013708413,0.012946539,0.007482723,0.01598572,0.0015125163],"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":[0.000046907146,0.00004036259,0.0009328489,0.00016383306,0.00006416793,0.00007143202,0.0005583717,0.0063063246,0.00011732921,0.9501929,0.0029498828,0.038555592],"study_design_scores_gemma":[0.00007550695,0.00013385898,0.0003917793,0.0002297678,0.00003197873,0.0001337124,0.00013070977,0.035059698,0.0003775913,0.9262996,0.037060786,0.00007497039],"about_ca_topic_score_codex":0.0029680987,"about_ca_topic_score_gemma":0.0020260718,"teacher_disagreement_score":0.09068739,"about_ca_system_score_codex":0.0038999652,"about_ca_system_score_gemma":0.0038972264,"threshold_uncertainty_score":0.47960645},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91262746,0.00021151011,0.08540924,0.000062275256,0.000004821807,0.000039476443,0.000115479605,0.000059327765,0.0014704195],"genre_scores_gemma":[0.9501733,0.00023878444,0.048947133,0.000006211354,0.000006792132,0.000029294773,0.00012078534,0.000003128309,0.0004745647],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997558,0.00012893727,0.000016156222,0.000038492293,0.000048567483,0.000011890175],"domain_scores_gemma":[0.99826175,0.001125638,0.00037360858,0.000089855406,0.00012115757,0.000027975037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061838713,0.0001450375,0.000117540534,0.0008926713,0.00011530222,0.00016847964,0.00027317833,0.00010572384,0.0007037699],"category_scores_gemma":[0.0043059536,0.000106116444,0.00008491454,0.00049941003,0.00020459857,0.00043117563,0.00026615287,0.00011284611,0.00013587558],"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":[0.00010957839,0.00007185689,0.6399789,0.00015818582,0.00006678803,0.00041670774,0.0012914871,0.029988468,0.023544088,0.0039295666,0.0005800739,0.29986438],"study_design_scores_gemma":[0.000021987722,0.0004729459,0.75169736,0.000057849382,0.000050141974,0.0018000784,0.0011590065,0.22734915,0.010624921,0.0034187008,0.0033123402,0.000035593916],"about_ca_topic_score_codex":0.0065663517,"about_ca_topic_score_gemma":0.011335281,"teacher_disagreement_score":0.0065663517,"about_ca_system_score_codex":0.00018873501,"about_ca_system_score_gemma":0.00015478698,"threshold_uncertainty_score":0.013056278},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021375623,0.00020086848,0.99717087,0.000070092836,0.000012283371,0.000027087393,0.00002932697,0.00015541377,0.00019648201],"genre_scores_gemma":[0.27540398,0.0015072889,0.71718276,0.00024831836,0.00020925964,0.0009009282,0.00082264654,0.00040336486,0.003321478],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9727332,0.022066385,0.0007568049,0.0020465334,0.0018800906,0.0005171167],"domain_scores_gemma":[0.8307621,0.13217025,0.005664532,0.024445307,0.0062387506,0.00071895256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046262834,0.0013742992,0.0037105759,0.003627813,0.0012190064,0.0027532591,0.0057240343,0.0036168417,0.004944407],"category_scores_gemma":[0.22545497,0.0020706248,0.002270686,0.0045822714,0.003922337,0.008405996,0.004467364,0.005158532,0.0013468215],"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":[0.00027656672,0.00023578154,0.0053083315,0.0005702791,0.00053886743,0.0001305479,0.0005272613,0.27063096,0.001013278,0.5669789,0.0042549735,0.14953434],"study_design_scores_gemma":[0.000052959906,0.00006065916,0.000887214,0.00006939343,0.000086961445,0.00010677962,0.000070176335,0.722087,0.0006026637,0.27376294,0.0021706107,0.000042558902],"about_ca_topic_score_codex":0.0030936308,"about_ca_topic_score_gemma":0.0025021003,"teacher_disagreement_score":0.046262834,"about_ca_system_score_codex":0.0020023086,"about_ca_system_score_gemma":0.0025191405,"threshold_uncertainty_score":0.24466413},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46360436,0.0011818124,0.5263906,0.0013181391,0.00030958318,0.00090731075,0.0038577756,0.00038832464,0.0020421017],"genre_scores_gemma":[0.8449485,0.00053703703,0.1437404,0.0002487257,0.00015881173,0.0024475076,0.0039436235,0.000078861485,0.0038964394],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9001277,0.08210018,0.004086534,0.007206066,0.0051233754,0.0013560461],"domain_scores_gemma":[0.6328714,0.28452986,0.040236793,0.030781578,0.010594139,0.0009862264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08029693,0.0012442399,0.0018172485,0.0022128779,0.0008833892,0.00348285,0.004254949,0.0021514476,0.0038483997],"category_scores_gemma":[0.2524312,0.001463103,0.002081557,0.004853885,0.0020532326,0.00244524,0.003596438,0.0025630032,0.0009306592],"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":[0.0015947103,0.00053824706,0.7094571,0.0012213851,0.004402943,0.002076516,0.018202452,0.07070814,0.0011530893,0.055741496,0.0036650868,0.13123892],"study_design_scores_gemma":[0.0003436451,0.0015873631,0.22476861,0.00089434825,0.0017724992,0.0016168812,0.0063768784,0.6494456,0.003204712,0.09323103,0.01634271,0.0004157303],"about_ca_topic_score_codex":0.014290509,"about_ca_topic_score_gemma":0.008950107,"teacher_disagreement_score":0.08029693,"about_ca_system_score_codex":0.0017249032,"about_ca_system_score_gemma":0.0012304737,"threshold_uncertainty_score":0.42465585},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.071394525,0.00013468844,0.92731017,0.000054231914,0.000017585062,0.00018324214,0.00003287698,0.00036495138,0.0005077846],"genre_scores_gemma":[0.28435692,0.00009289803,0.7145819,0.00005582444,0.00002426091,0.00047175938,0.00007903621,0.00004735717,0.0002899634],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9714606,0.021657621,0.0014796956,0.0023832468,0.002657283,0.00036155918],"domain_scores_gemma":[0.9359865,0.039979592,0.006471089,0.010267337,0.006929732,0.0003657182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026748033,0.00075050385,0.0010650139,0.0019971784,0.00055376085,0.00068358576,0.0012307697,0.00070949085,0.000766093],"category_scores_gemma":[0.07342518,0.0008407607,0.0006415246,0.0014584763,0.00077857444,0.00096479896,0.001524848,0.00079683436,0.0003358201],"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":[0.0011569001,0.0004256874,0.09400533,0.00040786446,0.00041812242,0.00007507305,0.0013931409,0.15440018,0.027159244,0.0058614193,0.00094496756,0.7137519],"study_design_scores_gemma":[0.0009530273,0.0032405679,0.13296784,0.00018906886,0.00045288398,0.00042392957,0.0003164985,0.79777557,0.036902644,0.017287862,0.009250664,0.00023945625],"about_ca_topic_score_codex":0.0024223824,"about_ca_topic_score_gemma":0.0041946685,"teacher_disagreement_score":0.026748033,"about_ca_system_score_codex":0.0008811056,"about_ca_system_score_gemma":0.001251623,"threshold_uncertainty_score":0.14145881},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061655072,0.000092437585,0.9931172,0.00003756929,0.000010334463,0.00006456563,0.000064716485,0.0001221352,0.00032553336],"genre_scores_gemma":[0.16583256,0.00028013205,0.8311205,0.00009821967,0.000048934584,0.0007065048,0.0006781488,0.00009338826,0.0011416468],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97462326,0.020592654,0.0006914462,0.0015646196,0.0020655154,0.00046256112],"domain_scores_gemma":[0.95162374,0.033518657,0.0036276837,0.006873336,0.0041183988,0.00023820886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026347805,0.00090621813,0.0018893632,0.0024998293,0.00074517564,0.0011488069,0.0022874735,0.0014522881,0.0019528377],"category_scores_gemma":[0.11662388,0.0007642683,0.0013765156,0.0029863634,0.0012266051,0.0022494467,0.0016747015,0.0014168635,0.00068805274],"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":[0.0002702306,0.00016991913,0.02732815,0.00048369923,0.0007593593,0.00036171786,0.0009052018,0.17889589,0.002362918,0.37516075,0.0060930927,0.40720907],"study_design_scores_gemma":[0.00007706809,0.00012945343,0.008934418,0.00018281802,0.00013767701,0.00020394979,0.0001632719,0.6753485,0.0031441788,0.30432457,0.007284938,0.00006907588],"about_ca_topic_score_codex":0.0051678536,"about_ca_topic_score_gemma":0.004766049,"teacher_disagreement_score":0.026347805,"about_ca_system_score_codex":0.0012398415,"about_ca_system_score_gemma":0.0014678073,"threshold_uncertainty_score":0.13934213},"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":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5799915,0.003511213,0.39384693,0.0077873254,0.00049972837,0.0034700348,0.0006154116,0.00024339014,0.010034407],"genre_scores_gemma":[0.93681437,0.0005368384,0.057659857,0.0012990207,0.00022910605,0.0024439075,0.00018218435,0.00005251855,0.0007821212],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.3030477,0.6605954,0.009884136,0.0076047727,0.016966034,0.0019019747],"domain_scores_gemma":[0.05109061,0.8646666,0.05193455,0.027233372,0.004676048,0.00039877658],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.42720094,0.0010855368,0.0027179902,0.0019743275,0.0013211085,0.0025565934,0.0046880306,0.004356285,0.008012354],"category_scores_gemma":[0.7454994,0.0013149687,0.0034466397,0.0034471278,0.008058442,0.006565798,0.0025071595,0.004372274,0.0012620258],"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":[0.014160019,0.007453977,0.22848317,0.006982931,0.011130287,0.0008768485,0.013403187,0.02446577,0.0018328886,0.29782057,0.009427222,0.3839631],"study_design_scores_gemma":[0.008365746,0.021797443,0.19918889,0.00454215,0.006792594,0.0016127742,0.0073911804,0.27544063,0.009299979,0.43767127,0.02737054,0.0005267883],"about_ca_topic_score_codex":0.0010992127,"about_ca_topic_score_gemma":0.00055341073,"teacher_disagreement_score":0.5727991,"about_ca_system_score_codex":0.00204013,"about_ca_system_score_gemma":0.00304382,"threshold_uncertainty_score":0.7063632},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013030881,0.0005346618,0.9826115,0.0006048583,0.00008033403,0.00023416661,0.0004575899,0.00025544228,0.002190661],"genre_scores_gemma":[0.43340573,0.0022137589,0.55288404,0.0007705264,0.00044641286,0.00197144,0.0035458636,0.00022252514,0.0045397896],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9484553,0.043553043,0.0011579997,0.0027330986,0.0032389853,0.0008616298],"domain_scores_gemma":[0.7704386,0.19976701,0.0069088475,0.016109806,0.0057879267,0.0009878946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.055225853,0.0012145205,0.0037808584,0.0038553197,0.0011331685,0.0036219317,0.0034877604,0.002219302,0.0076265787],"category_scores_gemma":[0.27451983,0.001635778,0.0032910598,0.004843228,0.003440948,0.00512281,0.003591853,0.003596395,0.0017611537],"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":[0.00067090703,0.00020239642,0.01611752,0.00076221034,0.0010246509,0.00047903822,0.0008645216,0.14050493,0.00050970307,0.71185106,0.009980055,0.11703315],"study_design_scores_gemma":[0.00018745176,0.00014776351,0.0027054907,0.00024306645,0.00022036069,0.0002032165,0.00014197154,0.40963876,0.0005715847,0.58257955,0.003306763,0.000053972566],"about_ca_topic_score_codex":0.0060544764,"about_ca_topic_score_gemma":0.004324883,"teacher_disagreement_score":0.055225853,"about_ca_system_score_codex":0.0024410703,"about_ca_system_score_gemma":0.0039465837,"threshold_uncertainty_score":0.29206568},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064695715,0.00007589095,0.9930034,0.00006577775,0.000025031552,0.00007753049,0.000041669886,0.000082315404,0.00015884408],"genre_scores_gemma":[0.22958998,0.00023599916,0.7665793,0.000119568904,0.00012497918,0.0008577361,0.0005633672,0.0001623385,0.0017667752],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95701647,0.03325922,0.0012215348,0.0042712344,0.0030238044,0.0012078125],"domain_scores_gemma":[0.79120046,0.17758024,0.00474012,0.016650155,0.0087022,0.001126759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.054693073,0.0013366753,0.0041875658,0.0022854775,0.001701989,0.002881888,0.008090859,0.0029817033,0.002546689],"category_scores_gemma":[0.18556106,0.0027298776,0.0031819753,0.00396506,0.004080796,0.0045319195,0.0040881163,0.0033447647,0.0004067099],"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":[0.0016329243,0.0005125297,0.0156192435,0.0009869781,0.0019502694,0.0004060052,0.0017828259,0.31031752,0.0018109505,0.49664056,0.0047216676,0.16361849],"study_design_scores_gemma":[0.00012181427,0.00012329956,0.0014613378,0.00004817138,0.00015547583,0.00009533895,0.00009280204,0.84225464,0.0006462071,0.15416247,0.00078856904,0.000049943297],"about_ca_topic_score_codex":0.007078798,"about_ca_topic_score_gemma":0.005574189,"teacher_disagreement_score":0.054693073,"about_ca_system_score_codex":0.0017260737,"about_ca_system_score_gemma":0.005080584,"threshold_uncertainty_score":0.28924805},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001982879,0.0009827864,0.995858,0.00006262142,0.00006852222,0.00005060642,0.0000580237,0.00014466062,0.00079180184],"genre_scores_gemma":[0.17035559,0.0031752253,0.8220509,0.00025988443,0.0005503543,0.00076122564,0.00057616166,0.00028991097,0.0019807618],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97366625,0.0164581,0.001139157,0.0029024228,0.005453069,0.00038103774],"domain_scores_gemma":[0.94712216,0.041213088,0.0031775786,0.0037509468,0.0045123133,0.00022391208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01912198,0.0014546383,0.0026280908,0.006234083,0.0004857833,0.002111144,0.0021328877,0.001540716,0.0020296508],"category_scores_gemma":[0.124503344,0.0006296901,0.0015353705,0.005562469,0.0014794166,0.0037369803,0.001766247,0.0019243996,0.0009595416],"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":[0.00016948231,0.00011090779,0.013905978,0.0010952003,0.0011926555,0.00022202745,0.00045097267,0.1298123,0.0040642447,0.34175315,0.0055877827,0.50163525],"study_design_scores_gemma":[0.00010101216,0.00047466013,0.008848562,0.00046454743,0.00070394157,0.0010507125,0.00024252619,0.62996066,0.006864512,0.31160608,0.039428305,0.00025457866],"about_ca_topic_score_codex":0.0014946766,"about_ca_topic_score_gemma":0.00065403647,"teacher_disagreement_score":0.01912198,"about_ca_system_score_codex":0.0008797425,"about_ca_system_score_gemma":0.0013684396,"threshold_uncertainty_score":0.10112786},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004543077,0.0002818775,0.9941654,0.00004314478,0.000044696964,0.00003329509,0.000038905197,0.0001091373,0.0007404281],"genre_scores_gemma":[0.26443607,0.0008384295,0.7303452,0.00017349623,0.00028405973,0.00038618618,0.00048542902,0.00013082127,0.0029203524],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9941187,0.0032555256,0.00024326457,0.000960998,0.0011862993,0.000235279],"domain_scores_gemma":[0.99127954,0.0053862426,0.0008305581,0.0013318459,0.0009823141,0.00018941979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071530663,0.000882987,0.0018467885,0.0023212833,0.0005600434,0.0016707758,0.0018027013,0.0011458517,0.003926962],"category_scores_gemma":[0.033098582,0.0005549862,0.0011835609,0.0016929922,0.0008689021,0.002764334,0.0022928831,0.0012933243,0.00091606315],"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":[0.0007309582,0.0001463473,0.00887936,0.0005661285,0.00039092885,0.00021553614,0.0003188344,0.1710051,0.0060980753,0.20251833,0.0043042363,0.6048261],"study_design_scores_gemma":[0.00010125929,0.00034599696,0.0024544967,0.00013020886,0.00008975329,0.00032527142,0.00008167245,0.86884356,0.0055267354,0.10894702,0.013084478,0.00006962582],"about_ca_topic_score_codex":0.0009848019,"about_ca_topic_score_gemma":0.0008080802,"teacher_disagreement_score":0.0071530663,"about_ca_system_score_codex":0.00067720097,"about_ca_system_score_gemma":0.0009328644,"threshold_uncertainty_score":0.03782946},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051923147,0.00007573276,0.9940655,0.00004306596,0.000015657966,0.000057817,0.000039408744,0.00013251214,0.000377879],"genre_scores_gemma":[0.22342029,0.00029742133,0.77141964,0.00018475908,0.00008173496,0.0009329277,0.0007218525,0.00017833193,0.0027630285],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9408494,0.045235034,0.0017372827,0.004522121,0.006344643,0.0013114029],"domain_scores_gemma":[0.90719116,0.06325155,0.008595945,0.013653773,0.0068172836,0.0004903218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.049011104,0.00086630945,0.001995456,0.0018886098,0.0008891781,0.0016570361,0.00416797,0.0014251365,0.0024404502],"category_scores_gemma":[0.18384638,0.0013171704,0.0017932284,0.0035103457,0.0024974346,0.003049783,0.0027358008,0.002809508,0.0009762397],"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":[0.00044892414,0.00031274388,0.030118732,0.00055130944,0.001060487,0.00043823718,0.001012641,0.24161673,0.0017630532,0.34109622,0.008095066,0.37348592],"study_design_scores_gemma":[0.00008690591,0.0002196522,0.006647104,0.00017839317,0.0001278181,0.00022824321,0.00014825266,0.84660715,0.003619474,0.13631573,0.005720227,0.00010092632],"about_ca_topic_score_codex":0.0050458806,"about_ca_topic_score_gemma":0.005663782,"teacher_disagreement_score":0.049011104,"about_ca_system_score_codex":0.0012587539,"about_ca_system_score_gemma":0.002699887,"threshold_uncertainty_score":0.25919855},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20982629,0.00034507102,0.7830291,0.0015370725,0.00014938078,0.0012572233,0.00033086498,0.00035859662,0.003166325],"genre_scores_gemma":[0.81121814,0.00030983696,0.18209532,0.0005705854,0.00018000575,0.0022496805,0.00037035058,0.00005642362,0.0029497202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.91171426,0.07347311,0.0023211213,0.006365209,0.0049459864,0.0011803746],"domain_scores_gemma":[0.56022924,0.3473911,0.056962214,0.026761502,0.007795024,0.00086096703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09545525,0.0014528048,0.0013689597,0.0020263195,0.0009079215,0.0039749043,0.0029542742,0.0025998335,0.0017554548],"category_scores_gemma":[0.30800936,0.001220318,0.002044738,0.0019752316,0.002993441,0.0027638567,0.0023280028,0.0028434924,0.00046568047],"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":[0.00089683366,0.00094472413,0.11932314,0.00097260135,0.0013842778,0.0011514656,0.007954794,0.30861908,0.0020498033,0.42739812,0.0037813946,0.1255237],"study_design_scores_gemma":[0.00014786224,0.00034533744,0.014084205,0.00015340866,0.00023807623,0.00028309782,0.0006398124,0.8623407,0.0015928467,0.11697833,0.003101119,0.00009525233],"about_ca_topic_score_codex":0.0029812849,"about_ca_topic_score_gemma":0.002291884,"teacher_disagreement_score":0.09545525,"about_ca_system_score_codex":0.0026944345,"about_ca_system_score_gemma":0.0016646445,"threshold_uncertainty_score":0.50482166},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008782754,0.00040154197,0.9858246,0.00055388326,0.00031571538,0.0005818148,0.00012494046,0.00037118205,0.0030436125],"genre_scores_gemma":[0.27055126,0.0006258197,0.7172443,0.0009663628,0.00048314518,0.0024868299,0.00054037134,0.00037501677,0.0067267977],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8698018,0.11100285,0.002957234,0.0050512664,0.010302322,0.00088454445],"domain_scores_gemma":[0.87333184,0.08421801,0.007029994,0.02087617,0.014094786,0.0004491468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0439286,0.0011857423,0.0020828072,0.0034726637,0.0007010127,0.002098827,0.0030486858,0.0018473978,0.009067626],"category_scores_gemma":[0.22877145,0.00080950017,0.0016633787,0.004568956,0.0014054171,0.0024472787,0.002734534,0.003209839,0.002372902],"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":[0.0004604407,0.00035403718,0.012386839,0.0010731388,0.0008103721,0.00011939033,0.0007609795,0.03612788,0.0035482766,0.20518945,0.010694628,0.7284745],"study_design_scores_gemma":[0.0006242058,0.0014531079,0.041852385,0.0010496437,0.00080802006,0.00070820714,0.00052991323,0.47816488,0.021275906,0.32441884,0.12869382,0.00042114774],"about_ca_topic_score_codex":0.0013883753,"about_ca_topic_score_gemma":0.000723978,"teacher_disagreement_score":0.0439286,"about_ca_system_score_codex":0.0016436278,"about_ca_system_score_gemma":0.0012533612,"threshold_uncertainty_score":0.23231947},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054339166,0.000030228943,0.99386865,0.000012007168,0.000024799341,0.00018899597,0.00002858331,0.00020628363,0.00020651687],"genre_scores_gemma":[0.11008208,0.000038743503,0.8874316,0.00005244086,0.000046859885,0.0012405089,0.00012952257,0.00004535198,0.00093291875],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9895493,0.006568111,0.0006054241,0.0016678112,0.0013666531,0.00024287679],"domain_scores_gemma":[0.9882178,0.0066131866,0.00094054785,0.001857045,0.0020809511,0.0002905835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006686299,0.00068815966,0.00094676175,0.00080677867,0.00042746108,0.00078372995,0.0019950923,0.0011329078,0.0036872993],"category_scores_gemma":[0.015468767,0.0005244308,0.0008266282,0.0009681111,0.0009484876,0.00089916756,0.0011533743,0.001058141,0.00073200685],"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":[0.0037498947,0.00085195625,0.010377502,0.00072400767,0.0003739579,0.00024290606,0.00054794224,0.1594554,0.07196422,0.051608257,0.0024248816,0.69767904],"study_design_scores_gemma":[0.0010233171,0.0050455756,0.007156919,0.00006903179,0.00020576328,0.00050324417,0.0000584465,0.92281693,0.023861354,0.01952139,0.019617274,0.00012072678],"about_ca_topic_score_codex":0.00064856483,"about_ca_topic_score_gemma":0.00067647756,"teacher_disagreement_score":0.006686299,"about_ca_system_score_codex":0.00051116437,"about_ca_system_score_gemma":0.0006824957,"threshold_uncertainty_score":0.035360932},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9709839,0.0007775485,0.024972657,0.00010682899,0.00001010283,0.00003383871,0.00011890684,0.000118701995,0.0028776021],"genre_scores_gemma":[0.9720647,0.0004364021,0.025234964,0.000075741074,0.000008893014,0.000046692276,0.00013329112,0.00001479368,0.0019845117],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99985945,0.00002499698,0.0000074713043,0.000058680005,0.00003561625,0.000013726246],"domain_scores_gemma":[0.9988625,0.00038470147,0.00043413724,0.000085442356,0.00012529879,0.000107929656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035189875,0.00027634675,0.00033270352,0.00044176134,0.00026369625,0.00045103734,0.00025369253,0.00028990617,0.0006064568],"category_scores_gemma":[0.0010392952,0.00025523143,0.00012026851,0.00025598105,0.0002800833,0.0004234738,0.00031903718,0.00023029273,0.0003319001],"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":[0.0005829319,0.00022068471,0.32149303,0.00046303376,0.00012885984,0.0001841995,0.0011358397,0.0035669443,0.44865066,0.001185714,0.0013317275,0.22105645],"study_design_scores_gemma":[0.000042717777,0.0012579561,0.90597564,0.000059983282,0.0001341761,0.00089548423,0.00094470184,0.026543917,0.05460747,0.0025916635,0.006898871,0.000047446796],"about_ca_topic_score_codex":0.0053533926,"about_ca_topic_score_gemma":0.016279355,"teacher_disagreement_score":0.0053533926,"about_ca_system_score_codex":0.00022215504,"about_ca_system_score_gemma":0.00018067184,"threshold_uncertainty_score":0.010644436},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08284062,0.00017898997,0.9143833,0.00023024317,0.000097594624,0.00114095,0.00015667056,0.00014031703,0.0008313454],"genre_scores_gemma":[0.5812753,0.00020265716,0.41192025,0.0002331918,0.00008870847,0.00482249,0.00035282056,0.000047867314,0.0010567047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.74522465,0.22579175,0.0045882976,0.013623503,0.008631583,0.0021402454],"domain_scores_gemma":[0.450882,0.4765006,0.011682258,0.05218229,0.0076835947,0.0010693293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16952121,0.0012981268,0.0039780014,0.002755593,0.0018041811,0.0030406702,0.0064660595,0.004611708,0.003321844],"category_scores_gemma":[0.43543395,0.002011014,0.0032449283,0.003478583,0.0061756046,0.0040048896,0.0040202686,0.0038692914,0.00056197506],"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":[0.0031081964,0.0015889261,0.10435954,0.001426305,0.0025789265,0.00034366263,0.0068499763,0.075786434,0.0038779196,0.5423563,0.004309383,0.25341454],"study_design_scores_gemma":[0.0007639038,0.002120982,0.034488484,0.00037115903,0.0010373666,0.0005157554,0.0021112147,0.6640721,0.0073595988,0.28264782,0.0042895423,0.00022199683],"about_ca_topic_score_codex":0.0025289357,"about_ca_topic_score_gemma":0.0020213008,"teacher_disagreement_score":0.16952121,"about_ca_system_score_codex":0.0022666524,"about_ca_system_score_gemma":0.0025475514,"threshold_uncertainty_score":0.89652455},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006434862,0.00070953864,0.9918494,0.00013629034,0.00004608113,0.000054329157,0.00007617474,0.00013011602,0.00056321645],"genre_scores_gemma":[0.46548116,0.0021030784,0.5268018,0.0002210618,0.000529964,0.0011307801,0.00091992196,0.00019532307,0.0026168912],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9597632,0.031687118,0.00097363815,0.003093289,0.0036677902,0.0008148508],"domain_scores_gemma":[0.71372515,0.25359496,0.0067816232,0.016781228,0.007885466,0.0012316083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044161033,0.0015302066,0.0032675099,0.003936112,0.0012748812,0.0040571443,0.0061244294,0.002646649,0.0045166095],"category_scores_gemma":[0.252397,0.0014794461,0.0021075497,0.0044090957,0.005922826,0.0063008913,0.00440625,0.0048381584,0.0006231415],"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":[0.0005676397,0.00013906503,0.0042854394,0.00053174444,0.0002993858,0.00014145882,0.00050692854,0.108341515,0.0009678764,0.7996214,0.0024550406,0.08214254],"study_design_scores_gemma":[0.00011075092,0.00015944756,0.0016329221,0.00015682248,0.000105278705,0.00017591698,0.00011838305,0.6843024,0.0010621523,0.30886677,0.0032466156,0.00006253991],"about_ca_topic_score_codex":0.0024333494,"about_ca_topic_score_gemma":0.0013916256,"teacher_disagreement_score":0.044161033,"about_ca_system_score_codex":0.002075325,"about_ca_system_score_gemma":0.00204649,"threshold_uncertainty_score":0.2335487},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006940244,0.0012013059,0.9906657,0.000153432,0.00018143927,0.000068017805,0.0001584514,0.0002333244,0.00039813403],"genre_scores_gemma":[0.036665987,0.0011615152,0.95884806,0.000073597104,0.00017849448,0.00025403776,0.00061704987,0.00011236922,0.0020889665],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9959053,0.0025188685,0.0002507722,0.0005466457,0.0006890073,0.0000893819],"domain_scores_gemma":[0.9926212,0.0052146222,0.00028049113,0.0011080032,0.00060580246,0.00016991698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007514189,0.00089854875,0.0010237854,0.0035962602,0.0007459835,0.0007718211,0.002222926,0.00084278645,0.003453179],"category_scores_gemma":[0.018007126,0.0008766079,0.0016260651,0.003932261,0.0013273685,0.0017298037,0.0019728811,0.0029737952,0.0016426663],"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":[0.00033408398,0.00015569052,0.009320698,0.0005997824,0.00042723797,0.0001895839,0.00044093572,0.08421882,0.007776906,0.057715673,0.011897576,0.8269231],"study_design_scores_gemma":[0.000108502696,0.00029457844,0.012656967,0.00013329588,0.0001748779,0.00062118383,0.00010781718,0.83017796,0.007266646,0.10643936,0.041888826,0.000130078],"about_ca_topic_score_codex":0.00684821,"about_ca_topic_score_gemma":0.009831397,"teacher_disagreement_score":0.007514189,"about_ca_system_score_codex":0.00064653315,"about_ca_system_score_gemma":0.0013592837,"threshold_uncertainty_score":0.03973931},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008805547,0.00013850718,0.9981249,0.00011117038,0.000021576083,0.00013424858,0.0001222866,0.0002216059,0.00024514497],"genre_scores_gemma":[0.035085995,0.0008995832,0.9581592,0.00013237394,0.000108470456,0.0027518189,0.0010409628,0.0001534809,0.0016681085],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9691835,0.025820617,0.0010040933,0.0013225732,0.0023159257,0.00035328083],"domain_scores_gemma":[0.8832342,0.094879776,0.0073100054,0.009555918,0.00454744,0.00047257514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035525158,0.0017171893,0.0022663365,0.0052452865,0.0009539316,0.0020994921,0.0052610743,0.0024816426,0.0123259425],"category_scores_gemma":[0.22032203,0.0013907247,0.0025277524,0.008652432,0.0015316716,0.0037092878,0.0026978601,0.004980209,0.005175923],"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":[0.00014001818,0.00024865734,0.007865612,0.0010620287,0.0006960851,0.00029284233,0.00083947234,0.09454374,0.0011069132,0.3531084,0.010969399,0.5291269],"study_design_scores_gemma":[0.00012734775,0.00017220607,0.003786054,0.00032874284,0.00022008776,0.00042345014,0.00022876843,0.40897673,0.0014246115,0.5732263,0.010976651,0.00010901671],"about_ca_topic_score_codex":0.0028987702,"about_ca_topic_score_gemma":0.0032709048,"teacher_disagreement_score":0.035525158,"about_ca_system_score_codex":0.0013992531,"about_ca_system_score_gemma":0.0032441204,"threshold_uncertainty_score":0.18787724},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15899171,0.0017970329,0.8338682,0.0011362141,0.00023314834,0.0015699739,0.0009946357,0.00053520635,0.0008738645],"genre_scores_gemma":[0.756926,0.0009296152,0.23659435,0.00035245568,0.00019920878,0.0029642393,0.0010162361,0.00009319391,0.0009246923],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9061195,0.08037709,0.002506981,0.0060293367,0.0038709017,0.0010962021],"domain_scores_gemma":[0.63645285,0.3199779,0.023772618,0.013553311,0.0048267576,0.0014165402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1324485,0.0015755766,0.0025764583,0.0029256814,0.0008358585,0.0017711661,0.003943507,0.002049574,0.002770411],"category_scores_gemma":[0.20686203,0.0010045824,0.0065155076,0.0022962606,0.0018855454,0.0031511574,0.0031686875,0.0026602536,0.0002771087],"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":[0.004416608,0.0009222813,0.40477645,0.0027415704,0.017606935,0.0006354307,0.0012481303,0.3413566,0.0015832605,0.044868663,0.0033282472,0.17651586],"study_design_scores_gemma":[0.00055396464,0.0022048615,0.083069585,0.00042015634,0.003453458,0.0002827519,0.0004594235,0.8554201,0.0013586504,0.04966504,0.002873417,0.00023859875],"about_ca_topic_score_codex":0.007324865,"about_ca_topic_score_gemma":0.0051558604,"teacher_disagreement_score":0.1324485,"about_ca_system_score_codex":0.001555413,"about_ca_system_score_gemma":0.002878749,"threshold_uncertainty_score":0.70046294},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034909672,0.0001860359,0.99570364,0.00025271025,0.000028085775,0.000020457052,0.000024724344,0.000051082356,0.00024232114],"genre_scores_gemma":[0.22034152,0.0008398802,0.775015,0.000525896,0.00032921735,0.0006165266,0.00028037434,0.0002016376,0.0018499255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9594039,0.03686959,0.0006450635,0.0010688967,0.0015882945,0.0004243285],"domain_scores_gemma":[0.7395434,0.24597028,0.004235852,0.0062651644,0.003271117,0.00071429677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052966848,0.0011828509,0.0027533756,0.0025126403,0.0010741932,0.0031821446,0.0042618127,0.0028330996,0.0030025584],"category_scores_gemma":[0.1743961,0.0017629822,0.002401893,0.0031581346,0.00604087,0.0044127647,0.0050163474,0.0037731829,0.0004456067],"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":[0.00019224419,0.0000784247,0.0028620067,0.00023508088,0.00036375472,0.00024293044,0.00054348184,0.22328456,0.0005395911,0.7278406,0.0012858878,0.042531446],"study_design_scores_gemma":[0.00004924408,0.00004233764,0.0004423923,0.000046959598,0.000030900235,0.000053141197,0.00003800794,0.67830455,0.00019634464,0.3197876,0.0009729248,0.000035554694],"about_ca_topic_score_codex":0.0063838484,"about_ca_topic_score_gemma":0.00447744,"teacher_disagreement_score":0.052966848,"about_ca_system_score_codex":0.001938299,"about_ca_system_score_gemma":0.0023927141,"threshold_uncertainty_score":0.28011882},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069879927,0.00018709927,0.9923596,0.000086829445,0.00001484188,0.000018477924,0.000040703977,0.000098281205,0.00020618542],"genre_scores_gemma":[0.5266123,0.0009928079,0.4656386,0.00025431652,0.0002516465,0.00052865135,0.0011369026,0.00020852422,0.0043761246],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99338055,0.00460313,0.000205616,0.0008615626,0.0006379824,0.0003113073],"domain_scores_gemma":[0.96184134,0.032620646,0.00090018474,0.0023349973,0.0019024097,0.00040035954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011234493,0.0012067229,0.003992104,0.0011028217,0.0007688434,0.0014808028,0.003929425,0.001549945,0.001788004],"category_scores_gemma":[0.035290718,0.0018587578,0.0017406788,0.0017158346,0.0014643715,0.0038365526,0.0026660198,0.0031508638,0.00043661942],"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":[0.00027319792,0.00010684798,0.0030276165,0.00017311543,0.00022108231,0.00012826343,0.00018141548,0.88113177,0.0009472492,0.0461713,0.001560294,0.06607785],"study_design_scores_gemma":[0.000004527368,0.000012025317,0.00013041843,0.0000037229895,0.000009367809,0.000010971178,0.0000043986006,0.9943936,0.00012284672,0.005202769,0.0001004397,0.0000049050705],"about_ca_topic_score_codex":0.008582644,"about_ca_topic_score_gemma":0.007253206,"teacher_disagreement_score":0.011234493,"about_ca_system_score_codex":0.0013844301,"about_ca_system_score_gemma":0.0017467212,"threshold_uncertainty_score":0.059414387},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015018125,0.0001074819,0.9844151,0.000032694083,0.000014342609,0.000055242268,0.0000711716,0.0001582098,0.00012765349],"genre_scores_gemma":[0.27789623,0.00034094395,0.7184049,0.00006109233,0.00009320533,0.00066157244,0.0009879852,0.0001713148,0.0013827292],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9935749,0.0047370973,0.00019914132,0.0007034512,0.00060605677,0.00017935432],"domain_scores_gemma":[0.9316066,0.05755164,0.0016744866,0.005989442,0.0026745526,0.00050319126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013769349,0.0008981883,0.0018925115,0.0029448506,0.0010994944,0.0009464812,0.005104485,0.0013085154,0.0021025445],"category_scores_gemma":[0.062591195,0.0012232146,0.0016208135,0.003174152,0.0016140222,0.0014774476,0.0017257665,0.0021727402,0.00043038846],"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":[0.0009688132,0.00023386953,0.013043825,0.0003306149,0.0007294921,0.0001160163,0.0005827814,0.6623404,0.0041687256,0.0857574,0.0029168334,0.22881122],"study_design_scores_gemma":[0.000045078225,0.000035331253,0.0017792876,0.0000120369705,0.000033165295,0.000036317146,0.000022766235,0.96972173,0.0007021147,0.02710026,0.00049401046,0.000017938386],"about_ca_topic_score_codex":0.013254747,"about_ca_topic_score_gemma":0.009538794,"teacher_disagreement_score":0.013769349,"about_ca_system_score_codex":0.0013266273,"about_ca_system_score_gemma":0.0016400957,"threshold_uncertainty_score":0.07282013},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044928476,0.000072507435,0.9517128,0.00019345185,0.000025553367,0.0016088373,0.000086502485,0.00021372423,0.0011581485],"genre_scores_gemma":[0.32965317,0.00012541242,0.664157,0.00013043528,0.000038720016,0.004844297,0.0002272752,0.000036671474,0.0007870523],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9789924,0.016916364,0.00049065094,0.0012092434,0.0020046383,0.00038672617],"domain_scores_gemma":[0.9051428,0.07639868,0.004867377,0.007829279,0.0046472643,0.0011145874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031694286,0.00066471746,0.0009674057,0.0019323658,0.0006614547,0.0010086457,0.0015533092,0.0010717639,0.0024986833],"category_scores_gemma":[0.091954574,0.00090586423,0.0005472273,0.001011976,0.001463126,0.001713001,0.0016834851,0.001211864,0.0005455051],"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":[0.0016830037,0.0009899433,0.035487875,0.0006213083,0.00028256667,0.0002795145,0.0020080719,0.33231148,0.010243824,0.21592264,0.0048697987,0.39529994],"study_design_scores_gemma":[0.00081954995,0.002029163,0.00846425,0.00020754416,0.00013727882,0.00020011625,0.0005212599,0.8145488,0.00799583,0.15624739,0.008733338,0.000095436764],"about_ca_topic_score_codex":0.0014538178,"about_ca_topic_score_gemma":0.0015268386,"teacher_disagreement_score":0.031694286,"about_ca_system_score_codex":0.0011867712,"about_ca_system_score_gemma":0.0027401706,"threshold_uncertainty_score":0.16761738},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034911057,0.0000932135,0.9943539,0.000042450927,0.00004961024,0.00035149636,0.00013530935,0.00024495195,0.0012379901],"genre_scores_gemma":[0.16071187,0.0003615947,0.8290717,0.00026812826,0.00018574935,0.004095926,0.00067426666,0.00015870387,0.0044721174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9842461,0.011524067,0.0005181072,0.0015426258,0.0018250161,0.00034415582],"domain_scores_gemma":[0.9643092,0.02350575,0.0014126868,0.008132201,0.0021550548,0.00048512302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016971152,0.0009623395,0.0014195221,0.0022188681,0.0010820806,0.0015306014,0.0033227263,0.0014587451,0.0093469275],"category_scores_gemma":[0.05043092,0.00080881314,0.001408578,0.0023651416,0.001803103,0.0020778687,0.002764339,0.0018212142,0.0018437401],"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":[0.0009892181,0.00038334212,0.010574286,0.00047606707,0.00036472673,0.00028105266,0.000541248,0.098355055,0.003961148,0.37223396,0.0076050535,0.50423485],"study_design_scores_gemma":[0.0005421258,0.00074359396,0.0032148727,0.00017837016,0.00015452618,0.00049993023,0.000117092735,0.62610245,0.0034119978,0.33764315,0.027298871,0.000093065486],"about_ca_topic_score_codex":0.0014201609,"about_ca_topic_score_gemma":0.0016494642,"teacher_disagreement_score":0.016971152,"about_ca_system_score_codex":0.00075834047,"about_ca_system_score_gemma":0.001505613,"threshold_uncertainty_score":0.08975315},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004458082,0.000080605794,0.99496365,0.000056047294,0.000010041618,0.000023819486,0.000029360059,0.000041370968,0.00033700003],"genre_scores_gemma":[0.37939674,0.0005697497,0.61597973,0.00016864158,0.00007068197,0.0006150747,0.00045591014,0.00008706659,0.0026563655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9863259,0.010420638,0.00026216145,0.001241257,0.0014031322,0.00034676577],"domain_scores_gemma":[0.9340024,0.055456474,0.0031288676,0.004536202,0.0025542458,0.00032178196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020163074,0.0006449208,0.0016935589,0.00157229,0.00038775883,0.0015598573,0.002553034,0.0013544416,0.0022335928],"category_scores_gemma":[0.104034156,0.00062885834,0.001205166,0.0015832122,0.0022384492,0.0024729478,0.002275704,0.0019480379,0.000488314],"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":[0.00011236191,0.00009231266,0.004777192,0.00022927347,0.0002119583,0.00009448998,0.00026772707,0.36787626,0.00091848604,0.5244866,0.0020585596,0.09887486],"study_design_scores_gemma":[0.000037178976,0.000083293125,0.0016004767,0.00007170838,0.000041857373,0.00006774117,0.000042675856,0.7551255,0.00072140276,0.23999895,0.0021726592,0.000036604106],"about_ca_topic_score_codex":0.0043220567,"about_ca_topic_score_gemma":0.0032338735,"teacher_disagreement_score":0.020163074,"about_ca_system_score_codex":0.0014960619,"about_ca_system_score_gemma":0.0021432196,"threshold_uncertainty_score":0.10663378},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006642596,0.0001102435,0.99828184,0.00012901389,0.00001783373,0.00016475873,0.000023890812,0.00006594753,0.0005422749],"genre_scores_gemma":[0.025289096,0.00032268555,0.97125185,0.00018545866,0.00010077925,0.001977884,0.00013707193,0.00008850814,0.00064661895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91342956,0.07660911,0.0016367503,0.0032080384,0.004389898,0.0007267754],"domain_scores_gemma":[0.7908676,0.18363975,0.0034863257,0.016152302,0.0053177006,0.0005362452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07742239,0.0022128695,0.0038419727,0.0042742696,0.0016272019,0.0023886191,0.004023411,0.0026265138,0.0060529043],"category_scores_gemma":[0.2606179,0.0017376746,0.002146182,0.006339868,0.004629883,0.0042150235,0.007695396,0.00487922,0.0022696261],"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":[0.00046756657,0.00019140891,0.0023589265,0.0006066984,0.0002570817,0.00019761299,0.00091726216,0.13984735,0.0022088906,0.54004407,0.0047187144,0.30818444],"study_design_scores_gemma":[0.0002471304,0.0002232737,0.0009334852,0.00024560542,0.00008852118,0.00018588,0.00014169082,0.48924032,0.0021372745,0.4965679,0.009929055,0.000059818674],"about_ca_topic_score_codex":0.0023503352,"about_ca_topic_score_gemma":0.0017120709,"teacher_disagreement_score":0.07742239,"about_ca_system_score_codex":0.0020812727,"about_ca_system_score_gemma":0.0034976702,"threshold_uncertainty_score":0.40945363},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023558384,0.00018942145,0.9964653,0.00008296498,0.000063006555,0.0001576218,0.00008258977,0.00009766504,0.0005055369],"genre_scores_gemma":[0.19100413,0.000662396,0.800167,0.00039046365,0.00032402447,0.002181022,0.0014724965,0.00019853505,0.0035999306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9466013,0.040253747,0.0016433232,0.004830203,0.005715433,0.0009560145],"domain_scores_gemma":[0.88375026,0.09613197,0.0036103195,0.007891467,0.00812203,0.0004939034],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034442827,0.0016352758,0.0028939794,0.0033844523,0.001023584,0.002783305,0.0035657876,0.002429462,0.004746709],"category_scores_gemma":[0.15196468,0.0014759395,0.002929501,0.004055133,0.0021275217,0.0032142207,0.0029409565,0.0036293282,0.001208381],"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":[0.000644596,0.0003688491,0.013146812,0.0010917003,0.0011542575,0.00048406454,0.00083219906,0.2082961,0.0020237062,0.46219182,0.008406652,0.30135918],"study_design_scores_gemma":[0.00016136261,0.000257564,0.0021595762,0.000112534995,0.00011484805,0.00014037034,0.00007642917,0.80539984,0.0009337353,0.18374473,0.006831754,0.00006730919],"about_ca_topic_score_codex":0.0035249642,"about_ca_topic_score_gemma":0.002047326,"teacher_disagreement_score":0.034442827,"about_ca_system_score_codex":0.0015237769,"about_ca_system_score_gemma":0.0023630993,"threshold_uncertainty_score":0.18215328},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002056992,0.00016629115,0.89459276,0.00044561556,0.00061165856,0.0014362542,0.033084452,0.06106803,0.0065380423],"genre_scores_gemma":[0.013111873,0.0002874125,0.93564224,0.00036962752,0.00024738236,0.0074720816,0.019889751,0.017557403,0.0054223],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919361,0.0047320654,0.0010634669,0.00060700043,0.0013362546,0.0003251099],"domain_scores_gemma":[0.9549174,0.032842595,0.0018453395,0.0054740664,0.004408083,0.0005125359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011673898,0.0013329338,0.0013346417,0.0024264073,0.00059735903,0.0015513033,0.0022366364,0.00077319,0.06329212],"category_scores_gemma":[0.052853227,0.001719947,0.0017872324,0.0026148777,0.0005125236,0.0014441919,0.0017303037,0.0047293655,0.0309102],"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":[0.0010082391,0.00026645703,0.0046655773,0.0017344696,0.000819348,0.0006464353,0.0007083471,0.012562755,0.009701012,0.04205737,0.5841146,0.34171537],"study_design_scores_gemma":[0.000587925,0.00044414683,0.010020423,0.00057762396,0.0002561402,0.0007022962,0.00022688953,0.05334938,0.014936046,0.043413687,0.875228,0.0002573277],"about_ca_topic_score_codex":0.0028820126,"about_ca_topic_score_gemma":0.0031353692,"teacher_disagreement_score":0.06329212,"about_ca_system_score_codex":0.00083831756,"about_ca_system_score_gemma":0.0036033206,"threshold_uncertainty_score":0.21173322},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007633511,0.0002552715,0.99058425,0.00012776857,0.00008285389,0.0005536221,0.00007663909,0.0001304451,0.0005555974],"genre_scores_gemma":[0.18815573,0.00030039818,0.8067202,0.0001397685,0.00008448333,0.002577139,0.0002899594,0.000120963356,0.001611418],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.84632224,0.13025333,0.0039584017,0.009092614,0.009214932,0.0011584804],"domain_scores_gemma":[0.8088495,0.12122221,0.012194849,0.041992918,0.014968526,0.0007720307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.092183284,0.0014002575,0.0029285427,0.0021217281,0.0013259731,0.0020179006,0.0044625127,0.0023269553,0.0037527797],"category_scores_gemma":[0.31580576,0.0011861399,0.002898383,0.0039172173,0.003315086,0.0024347573,0.0032413632,0.0026209012,0.0012488782],"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":[0.0013108971,0.000481363,0.023886105,0.0018152985,0.002171268,0.0008707916,0.0031092756,0.06381946,0.005767169,0.33650318,0.0073404135,0.55292463],"study_design_scores_gemma":[0.00062865095,0.001298673,0.018666053,0.0008100309,0.0010772529,0.00094532024,0.0006266652,0.5457918,0.010596646,0.40111837,0.018095542,0.00034507288],"about_ca_topic_score_codex":0.004014083,"about_ca_topic_score_gemma":0.0030009728,"teacher_disagreement_score":0.092183284,"about_ca_system_score_codex":0.00175307,"about_ca_system_score_gemma":0.0042053,"threshold_uncertainty_score":0.48751765},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02417619,0.00032829779,0.9747439,0.00009639123,0.000018519086,0.000049730326,0.000041491803,0.000059930695,0.0004855063],"genre_scores_gemma":[0.34572098,0.0006110665,0.6512234,0.00015184053,0.00011701233,0.00046040263,0.00025357233,0.00006914211,0.0013926763],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9709075,0.023043595,0.000663106,0.002620686,0.002436413,0.00032858748],"domain_scores_gemma":[0.89627826,0.08611974,0.0052502877,0.008732873,0.0033150213,0.000303798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027981713,0.00069607043,0.0011602101,0.0017366913,0.0004689524,0.0011730767,0.0017275442,0.0018143367,0.0009765634],"category_scores_gemma":[0.1456059,0.00070254493,0.0010665247,0.0019633519,0.0021981846,0.0018402376,0.0023469476,0.0014266879,0.00032883903],"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":[0.0002676986,0.00018313316,0.06935796,0.00074965745,0.00065835455,0.00026065108,0.0013350873,0.19975859,0.007136935,0.4050557,0.0018854252,0.3133508],"study_design_scores_gemma":[0.00011112975,0.00052255,0.026970118,0.00019612079,0.00018370769,0.0006547973,0.00016637635,0.6165845,0.0060275807,0.3424632,0.0059825554,0.00013735812],"about_ca_topic_score_codex":0.0014644001,"about_ca_topic_score_gemma":0.0012257653,"teacher_disagreement_score":0.027981713,"about_ca_system_score_codex":0.0011327378,"about_ca_system_score_gemma":0.00098592,"threshold_uncertainty_score":0.1479832},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029040445,0.00024644335,0.9690437,0.00024275451,0.00006127017,0.00015425133,0.0001662373,0.00015177984,0.0008931905],"genre_scores_gemma":[0.4505736,0.00033247424,0.54478717,0.00019796424,0.00013982067,0.00073006283,0.0008805445,0.0001241903,0.0022341926],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9441998,0.044586845,0.0020057613,0.0042460365,0.0042549935,0.00070655136],"domain_scores_gemma":[0.83730483,0.116862655,0.011029625,0.026109425,0.0077553242,0.00093822205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06456508,0.00102975,0.0021054347,0.0044565997,0.00083176355,0.0038360257,0.0026784902,0.0016732233,0.0035097788],"category_scores_gemma":[0.2428991,0.0011855729,0.0018772627,0.0057411618,0.0024252257,0.0039348225,0.006647127,0.0027804729,0.0006732964],"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":[0.0008055144,0.00033930197,0.16341536,0.0009002756,0.0019433032,0.00037576578,0.0037333933,0.106011614,0.003299947,0.21306995,0.0042950525,0.5018106],"study_design_scores_gemma":[0.00016805992,0.0004747351,0.05008066,0.0005198794,0.00058168615,0.00037542786,0.0013415163,0.5726143,0.00461421,0.34993714,0.019092051,0.00020040787],"about_ca_topic_score_codex":0.0056199674,"about_ca_topic_score_gemma":0.004499078,"teacher_disagreement_score":0.06456508,"about_ca_system_score_codex":0.0014378382,"about_ca_system_score_gemma":0.0011871505,"threshold_uncertainty_score":0.34145683},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019779678,0.00021283202,0.9784847,0.0003729463,0.000023836976,0.00006186157,0.00012609904,0.00009462079,0.0008434392],"genre_scores_gemma":[0.676312,0.0004909594,0.31899792,0.0003424309,0.00015829837,0.00070179685,0.0010061543,0.00014615346,0.0018442557],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96959406,0.023477169,0.0012469469,0.0020230922,0.0030488018,0.00060991675],"domain_scores_gemma":[0.7294692,0.2378238,0.0103662545,0.0125130415,0.008745364,0.0010823446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04881576,0.0006302963,0.0018877722,0.0017623587,0.00044457294,0.0027199374,0.003294631,0.0022137614,0.0032383143],"category_scores_gemma":[0.23868681,0.0012325688,0.00132125,0.0015764657,0.0035358914,0.0040731,0.0041289865,0.0027344546,0.0005671389],"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":[0.0005994808,0.0001522757,0.010429309,0.0004304926,0.000480243,0.00021274104,0.00059579633,0.19690767,0.0021142,0.72493005,0.002393969,0.060753733],"study_design_scores_gemma":[0.00014654083,0.00009200468,0.002433677,0.000082064566,0.000041096293,0.00014298166,0.00006889748,0.6094522,0.0011240063,0.38489112,0.0014749586,0.000050469393],"about_ca_topic_score_codex":0.0008376561,"about_ca_topic_score_gemma":0.0004950589,"teacher_disagreement_score":0.04881576,"about_ca_system_score_codex":0.0010557229,"about_ca_system_score_gemma":0.0014633916,"threshold_uncertainty_score":0.25816548},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032262506,0.00046899877,0.99544466,0.00023775328,0.000027717437,0.00003649721,0.000027037408,0.00005383444,0.00047722858],"genre_scores_gemma":[0.26200825,0.0028427304,0.72958887,0.00065685005,0.000618663,0.0011318508,0.0004840369,0.00021976419,0.0024489642],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92937505,0.06291409,0.0010701432,0.0024107518,0.003373805,0.000856148],"domain_scores_gemma":[0.70271415,0.27298492,0.0069587175,0.011210976,0.005582003,0.0005492677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08115849,0.0013939795,0.003036973,0.0036177782,0.0009521613,0.0026588002,0.0039521363,0.002966681,0.0014113649],"category_scores_gemma":[0.2429376,0.0012324073,0.0022952317,0.0051125768,0.0053016003,0.0044846153,0.004845189,0.0034529855,0.00043613982],"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":[0.00016022233,0.00006852575,0.006042727,0.0005166016,0.00044923296,0.00020712332,0.00052339776,0.15129736,0.0006094368,0.7722707,0.0017479825,0.06610679],"study_design_scores_gemma":[0.00007023363,0.00011812326,0.001055827,0.00016853638,0.00008904404,0.00012611192,0.00007063034,0.51655054,0.0007826406,0.47828338,0.002637855,0.0000470303],"about_ca_topic_score_codex":0.002225819,"about_ca_topic_score_gemma":0.0012973481,"teacher_disagreement_score":0.08115849,"about_ca_system_score_codex":0.0017949663,"about_ca_system_score_gemma":0.0021039085,"threshold_uncertainty_score":0.42921227},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04215929,0.0014472002,0.9383875,0.0029774613,0.0006038152,0.0040888945,0.0042151287,0.002398804,0.003721809],"genre_scores_gemma":[0.44838634,0.0022606796,0.47352752,0.0025572884,0.0007506367,0.02461026,0.0055173384,0.00054297387,0.041846965],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8925887,0.089785576,0.0027187802,0.008790125,0.0034610915,0.0026557846],"domain_scores_gemma":[0.75659347,0.21090318,0.012466545,0.012339609,0.0069153784,0.00078187825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.086787336,0.0044754897,0.0056983293,0.0042512026,0.0013569419,0.0045384853,0.011164883,0.007194211,0.030318294],"category_scores_gemma":[0.18603115,0.0027759958,0.006703104,0.004603352,0.0046327845,0.006105077,0.0041070455,0.008153626,0.01057189],"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":[0.0049561434,0.0014184937,0.040216863,0.0037620377,0.0047484892,0.0012791395,0.0053306865,0.31369084,0.0009903362,0.45230925,0.022092225,0.14920548],"study_design_scores_gemma":[0.0010505681,0.0010909968,0.003469306,0.0004108528,0.00086438557,0.0004839916,0.0005866892,0.7812199,0.00054887444,0.1986518,0.0114092585,0.00021341612],"about_ca_topic_score_codex":0.008139554,"about_ca_topic_score_gemma":0.004072947,"teacher_disagreement_score":0.086787336,"about_ca_system_score_codex":0.0038923742,"about_ca_system_score_gemma":0.0024002802,"threshold_uncertainty_score":0.4589808},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0042069186,0.00015377955,0.994997,0.00013985907,0.000022702827,0.000048464164,0.000073757714,0.00014601841,0.0002114967],"genre_scores_gemma":[0.1624587,0.00032822567,0.834424,0.00017191292,0.00012304308,0.0006547448,0.00050239195,0.00016445413,0.0011724791],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9593013,0.033185143,0.0012598524,0.0020853886,0.0035813286,0.00058696995],"domain_scores_gemma":[0.8022032,0.15370566,0.012886646,0.020938395,0.009420284,0.0008458211],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051857654,0.0007982688,0.0022463226,0.0030691687,0.0012095533,0.002248566,0.0051831836,0.0027722623,0.0036072175],"category_scores_gemma":[0.21137905,0.00093775237,0.0022288444,0.0036103723,0.0021635364,0.0026652822,0.0036203815,0.0033998343,0.001039177],"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":[0.0004955137,0.00020869079,0.009265905,0.0004345604,0.00084188255,0.00051415595,0.00095957535,0.2964006,0.001724366,0.44254255,0.0061401404,0.240472],"study_design_scores_gemma":[0.00007471888,0.00011839737,0.0020125182,0.00014447852,0.000114415794,0.00019421992,0.00007107878,0.7868951,0.0010639847,0.2064575,0.0027658092,0.000087771914],"about_ca_topic_score_codex":0.0035189514,"about_ca_topic_score_gemma":0.0029075146,"teacher_disagreement_score":0.051857654,"about_ca_system_score_codex":0.0013987115,"about_ca_system_score_gemma":0.0023961894,"threshold_uncertainty_score":0.27425277},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032501664,0.002439669,0.96123695,0.0005488337,0.00012048093,0.00011326461,0.0005313599,0.000728918,0.0017788938],"genre_scores_gemma":[0.6574506,0.0026692646,0.33311564,0.0005049082,0.000528495,0.0009020667,0.0025093565,0.0004950121,0.0018246003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.93298155,0.04877465,0.0028197588,0.007064079,0.0065597137,0.0018002244],"domain_scores_gemma":[0.26901647,0.66876227,0.015849404,0.035155777,0.009544982,0.001671137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14958028,0.0019824433,0.0061934595,0.005360781,0.0013321032,0.0065839593,0.009786334,0.0047727823,0.0069788313],"category_scores_gemma":[0.54631805,0.0016481463,0.003508938,0.0064076637,0.0061316607,0.011151068,0.005174156,0.005961187,0.0009004068],"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":[0.0035744142,0.00035280184,0.021229388,0.0017253709,0.0022213333,0.0006510634,0.0021479684,0.1602622,0.0013327128,0.63005614,0.0059287236,0.17051788],"study_design_scores_gemma":[0.00028069387,0.0003763832,0.008289987,0.00078370556,0.00074289425,0.00081731967,0.0005165336,0.53572756,0.0018170318,0.44718692,0.003296784,0.00016420062],"about_ca_topic_score_codex":0.0022381947,"about_ca_topic_score_gemma":0.0010657558,"teacher_disagreement_score":0.14958028,"about_ca_system_score_codex":0.002140534,"about_ca_system_score_gemma":0.0018817917,"threshold_uncertainty_score":0.79106563},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009912648,0.00019168718,0.98800755,0.00008372476,0.000031163596,0.00007838825,0.00003439857,0.00004090042,0.0016195348],"genre_scores_gemma":[0.34115317,0.0005275469,0.6531552,0.00025666718,0.00014388096,0.0006702464,0.00026564952,0.00008105864,0.0037465626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9867061,0.009068644,0.00041654974,0.0015626984,0.0019032591,0.00034281932],"domain_scores_gemma":[0.9817774,0.012598782,0.0008170183,0.002501607,0.0021408382,0.00016429793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015259085,0.00047317526,0.0013235008,0.0018012801,0.00074887887,0.001017914,0.0024268136,0.0010394155,0.0020875095],"category_scores_gemma":[0.053260315,0.00044006205,0.0012267043,0.0019016133,0.0023257113,0.0020587202,0.0026573795,0.0014733346,0.00038272273],"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":[0.00024338491,0.00008741558,0.021110734,0.00054871704,0.00054218207,0.00032216997,0.0015592828,0.124595985,0.0052703824,0.5980336,0.0027266892,0.24495937],"study_design_scores_gemma":[0.00008615576,0.0003582634,0.01348963,0.00018714274,0.00027324498,0.00092640606,0.0003592275,0.6811168,0.0075152796,0.27358606,0.021976514,0.00012529253],"about_ca_topic_score_codex":0.0023816288,"about_ca_topic_score_gemma":0.0016834491,"teacher_disagreement_score":0.015259085,"about_ca_system_score_codex":0.0009281425,"about_ca_system_score_gemma":0.0012189059,"threshold_uncertainty_score":0.08069873},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031901724,0.00012774601,0.9952591,0.00007581546,0.000025976155,0.000056607638,0.00003327953,0.000077622244,0.0011537418],"genre_scores_gemma":[0.14291191,0.00074412866,0.8458799,0.000329703,0.00022852479,0.001224475,0.000312707,0.0002503108,0.0081182625],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99198335,0.0054080905,0.00030376925,0.00045170714,0.0015886404,0.00026440577],"domain_scores_gemma":[0.95593405,0.035421636,0.0015881807,0.0031535293,0.0033516008,0.0005510442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024562733,0.0010392086,0.0012094624,0.002264379,0.0005738851,0.0013516827,0.0024841262,0.0014464526,0.007495603],"category_scores_gemma":[0.079144515,0.0008088964,0.0016674458,0.0019861562,0.0025880495,0.0031543707,0.002420749,0.0033541739,0.0015126639],"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":[0.00012004096,0.000085802334,0.0016299427,0.00019237633,0.000059386628,0.00022282083,0.0006217487,0.05613102,0.0018168365,0.869329,0.0031130868,0.06667795],"study_design_scores_gemma":[0.000040283212,0.0001189779,0.0014486102,0.00009685334,0.000039601648,0.0001470751,0.00009853498,0.60441196,0.0012770481,0.38684115,0.0054240907,0.000055850465],"about_ca_topic_score_codex":0.0018939052,"about_ca_topic_score_gemma":0.00304428,"teacher_disagreement_score":0.024562733,"about_ca_system_score_codex":0.0015031906,"about_ca_system_score_gemma":0.0014215723,"threshold_uncertainty_score":0.1299017},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1079149,0.00015238022,0.88774353,0.00023583988,0.00004388906,0.0011406892,0.00023766536,0.00040901089,0.002122043],"genre_scores_gemma":[0.76829666,0.00017836993,0.22721224,0.00010608753,0.00003980096,0.0013130717,0.00045281902,0.000040564333,0.0023604038],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.990193,0.0077797184,0.0002546944,0.00067899463,0.00063524424,0.00045826394],"domain_scores_gemma":[0.9567908,0.03411155,0.0019158154,0.004887475,0.001873281,0.00042097285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015100664,0.00064463814,0.0012263067,0.0007591676,0.000615047,0.0008647063,0.002027804,0.0007684032,0.004681507],"category_scores_gemma":[0.040611204,0.00054598734,0.00085650524,0.0010551653,0.0013714286,0.0012513269,0.0017208806,0.0011489016,0.0005109619],"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":[0.0029282942,0.00033373208,0.012817989,0.00027823861,0.00020498376,0.00016517517,0.00031227572,0.7551714,0.0018440097,0.1181883,0.0019607958,0.105794795],"study_design_scores_gemma":[0.00030526938,0.0003524318,0.00084845594,0.000027752993,0.000042469022,0.000031245694,0.000059833375,0.9791534,0.0015519123,0.016842388,0.0007688229,0.000015989604],"about_ca_topic_score_codex":0.008908028,"about_ca_topic_score_gemma":0.009669152,"teacher_disagreement_score":0.015100664,"about_ca_system_score_codex":0.0014264766,"about_ca_system_score_gemma":0.003345803,"threshold_uncertainty_score":0.079860866},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0074537224,0.00019968818,0.9909787,0.0002005118,0.000032492113,0.00008274663,0.00003584366,0.0000530513,0.00096329954],"genre_scores_gemma":[0.41344848,0.00078750914,0.5785112,0.000776083,0.00025361453,0.002139179,0.00032960885,0.000106676365,0.003647613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94308466,0.04487919,0.0015342125,0.0036001788,0.0061221803,0.0007795427],"domain_scores_gemma":[0.7874263,0.1798038,0.010694274,0.014892603,0.0063760662,0.0008070051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06563755,0.0012777348,0.0018439455,0.0020843728,0.0007863438,0.0021393949,0.0027690518,0.0019887213,0.0027866145],"category_scores_gemma":[0.24738273,0.00082402583,0.0014324917,0.0018568919,0.0044611334,0.0031367096,0.0036710317,0.0025956293,0.0006015609],"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":[0.0001555213,0.00007413717,0.005992519,0.0004562467,0.00025641837,0.0001414669,0.0006052002,0.048190482,0.0018711895,0.87343454,0.0012986851,0.06752351],"study_design_scores_gemma":[0.00008455886,0.00033371753,0.0016006812,0.000217656,0.000112191316,0.00012988098,0.00010846768,0.2164918,0.0024189882,0.7740003,0.0044543264,0.0000474486],"about_ca_topic_score_codex":0.0007531407,"about_ca_topic_score_gemma":0.0006767359,"teacher_disagreement_score":0.06563755,"about_ca_system_score_codex":0.0017587978,"about_ca_system_score_gemma":0.0021901994,"threshold_uncertainty_score":0.3471287},"labels":[],"label_agreement":null},{"id":"W2196855157","doi":"10.1093/jssam/smv022","title":"Clarifying Some Aspects of Variance Estimation in Two-Phase Sampling","year":2015,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Estimator; Jackknife resampling; Variance (accounting); Mathematics; Statistics; Sampling (signal processing); Bias of an estimator; Minimum-variance unbiased estimator; Computer science; Applied mathematics","score_opus":0.6371680919234616,"score_gpt":0.5436168220745937,"score_spread":0.09355126984886786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2196855157","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004781648,0.0006666347,0.991342,0.001232965,0.00010835676,0.000071469476,0.00003466063,0.000034334364,0.0017280752],"genre_scores_gemma":[0.23784725,0.0020115527,0.75301456,0.0021336994,0.001110062,0.00093561324,0.00015666921,0.00012014984,0.0026704485],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94368804,0.045586087,0.0018343674,0.0032536031,0.004759948,0.0008779557],"domain_scores_gemma":[0.80314815,0.16878761,0.008373334,0.012504604,0.0066455165,0.0005407486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07277423,0.0011409101,0.0020489653,0.0019794162,0.0009978085,0.0028714084,0.0027527958,0.0033440178,0.0038608063],"category_scores_gemma":[0.23359299,0.0009895831,0.0018464598,0.003289538,0.0063316063,0.0061910413,0.0034404264,0.005256986,0.00052068377],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042163017,0.000041518007,0.0014763838,0.00027893615,0.000067772184,0.00015564807,0.000551512,0.012349974,0.0006658935,0.9547664,0.0011759903,0.028427683],"study_design_scores_gemma":[0.000067765824,0.00013803095,0.001311825,0.00015479197,0.00004113189,0.00013972197,0.00013928706,0.07387768,0.0009372903,0.9166383,0.0065098573,0.000044326487],"about_ca_topic_score_codex":0.0015688026,"about_ca_topic_score_gemma":0.0008983193,"teacher_disagreement_score":0.07277423,"about_ca_system_score_codex":0.0018023357,"about_ca_system_score_gemma":0.0022431763,"threshold_uncertainty_score":0.38487154},"labels":[],"label_agreement":null},{"id":"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002874734,0.000021034892,0.996227,0.000081621285,0.000017396365,0.00037180897,0.000025877924,0.000066040775,0.00031444663],"genre_scores_gemma":[0.08784437,0.000072535666,0.9086558,0.00014771387,0.00007000285,0.0022287855,0.00013072904,0.00003787674,0.00081210065],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97657144,0.016840087,0.0007745029,0.0019509551,0.0034156838,0.00044730073],"domain_scores_gemma":[0.9367844,0.04870828,0.002112648,0.006897662,0.005123993,0.0003730651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03069323,0.0007582649,0.0016734813,0.0017206274,0.00076887815,0.0011223755,0.0024049913,0.002131666,0.0031465353],"category_scores_gemma":[0.15396975,0.00097049365,0.0010298318,0.0016344618,0.0017788606,0.002758677,0.0024507095,0.0023167548,0.00077559974],"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":[0.0007660208,0.0007852379,0.013187473,0.0007711608,0.0002748454,0.00048632422,0.0013024446,0.061850242,0.018114379,0.4946777,0.006036433,0.40174773],"study_design_scores_gemma":[0.00084154843,0.0014576057,0.007813804,0.0001666974,0.00013174141,0.0008281653,0.00021806748,0.6648363,0.016072014,0.29764822,0.009844358,0.00014152189],"about_ca_topic_score_codex":0.00073430134,"about_ca_topic_score_gemma":0.0008923928,"teacher_disagreement_score":0.03069323,"about_ca_system_score_codex":0.0006819246,"about_ca_system_score_gemma":0.0025354624,"threshold_uncertainty_score":0.1623233},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019015133,0.00036826197,0.97934705,0.00033886018,0.00004109431,0.00004135,0.00021683046,0.00018020539,0.00045115518],"genre_scores_gemma":[0.65066916,0.0009283151,0.34382486,0.0003078411,0.00024740424,0.0005175926,0.0012663895,0.00021091933,0.0020275374],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9715314,0.023292458,0.00084992714,0.0017858954,0.001970121,0.0005701626],"domain_scores_gemma":[0.7647467,0.20642799,0.009876747,0.013248905,0.0048226356,0.00087704253],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.047618177,0.0006071245,0.002724695,0.003282927,0.0007581287,0.0021843216,0.004370336,0.0021074424,0.00346891],"category_scores_gemma":[0.22594574,0.00094442203,0.0018975124,0.0026846,0.0026898228,0.0035015566,0.00261517,0.0028330078,0.00063854444],"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":[0.00048248208,0.00027089257,0.02548463,0.0006761205,0.0012454999,0.00084300747,0.0006727887,0.3433804,0.001104274,0.5190391,0.0042967596,0.10250399],"study_design_scores_gemma":[0.00007051302,0.000090784255,0.0028009869,0.00013236042,0.0001211863,0.00016256547,0.00009857706,0.7792431,0.00078088185,0.21496557,0.0014850599,0.00004842667],"about_ca_topic_score_codex":0.0045843143,"about_ca_topic_score_gemma":0.0023117804,"teacher_disagreement_score":0.047618177,"about_ca_system_score_codex":0.0014747363,"about_ca_system_score_gemma":0.001799293,"threshold_uncertainty_score":0.251832},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99877304,0.000060671373,0.00003934851,0.000024210605,0.000002342692,0.0000064860583,0.0005103649,0.0000042143647,0.00057920866],"genre_scores_gemma":[0.997191,0.000033793855,0.000113338865,0.000027887685,0.0000019964284,0.000007922412,0.00054289977,0.0000020099344,0.0020791925],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99986243,0.000015246042,0.0000045034813,0.000045846667,0.000032801774,0.000039173916],"domain_scores_gemma":[0.99933356,0.000054801578,0.00016675478,0.000026188378,0.0002196401,0.00019898715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020923432,0.00018116778,0.00015012213,0.00049034995,0.0007453585,0.00039601096,0.00039216757,0.00024201353,0.0021564818],"category_scores_gemma":[0.00044980893,0.000095216856,0.00011110019,0.00029925862,0.00020570983,0.00017034571,0.00022981566,0.00016780612,0.00028550843],"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":[0.000121405086,0.00003152068,0.9908144,0.000006961419,0.00003476997,0.000084510655,0.00025068255,0.00012630958,0.0030452632,0.000021770094,0.0006330588,0.004829359],"study_design_scores_gemma":[0.0000015708681,0.000024599265,0.9993937,0.0000030318458,0.0000035763485,0.000015584243,0.000107868276,0.00014556573,0.000085936226,0.0000020925431,0.00021482223,0.0000015924954],"about_ca_topic_score_codex":0.8402818,"about_ca_topic_score_gemma":0.9638994,"teacher_disagreement_score":0.15971822,"about_ca_system_score_codex":0.0044135083,"about_ca_system_score_gemma":0.0010519585,"threshold_uncertainty_score":0.3213176},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048929816,0.002029703,0.98866886,0.00025177316,0.00016822778,0.0003444268,0.00024330005,0.00054988277,0.0028508152],"genre_scores_gemma":[0.2700403,0.0026244672,0.71855336,0.00069274113,0.0006108617,0.0044409,0.0010120148,0.00043755033,0.0015877362],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.85989946,0.10024154,0.006244108,0.011523174,0.020159312,0.0019324123],"domain_scores_gemma":[0.36792722,0.56459075,0.021486744,0.02727862,0.017406603,0.0013100781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11439364,0.002377264,0.004267047,0.008275115,0.0012080295,0.0044793496,0.005744832,0.004844812,0.010178589],"category_scores_gemma":[0.5782365,0.0013509144,0.002859873,0.008255642,0.0054238173,0.011009438,0.0043755034,0.0063729333,0.0021403886],"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":[0.00094171026,0.00020225738,0.005009873,0.0021450045,0.000756175,0.00048613836,0.0014457008,0.083573386,0.0008937906,0.65047455,0.0057965517,0.24827495],"study_design_scores_gemma":[0.0004771628,0.00078139734,0.002985183,0.0014741143,0.00041354587,0.0008832009,0.0005431724,0.417908,0.0023916003,0.55618155,0.01566841,0.00029262548],"about_ca_topic_score_codex":0.0014776052,"about_ca_topic_score_gemma":0.000629515,"teacher_disagreement_score":0.11439364,"about_ca_system_score_codex":0.0026527948,"about_ca_system_score_gemma":0.0026168197,"threshold_uncertainty_score":0.60497856},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046029785,0.0009181499,0.986479,0.0016919884,0.00018453998,0.00017269443,0.000091768066,0.00008883666,0.0057702027],"genre_scores_gemma":[0.23204334,0.003985008,0.75160164,0.002561469,0.00089862966,0.0034338918,0.00019252543,0.0003094645,0.004973955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.84410024,0.13022931,0.0038855772,0.0071971053,0.013124422,0.0014632855],"domain_scores_gemma":[0.33636987,0.6069384,0.020349199,0.024557084,0.010926719,0.0008586349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16927877,0.0013513776,0.0021411525,0.003493632,0.00096783944,0.0032062377,0.003867054,0.0035755103,0.013098531],"category_scores_gemma":[0.49599677,0.0010925386,0.0029622838,0.0046230713,0.009479353,0.010012081,0.0054670833,0.008434582,0.0012715765],"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":[0.00006658118,0.000024713796,0.0015709847,0.00031343068,0.00009420485,0.000051524483,0.00030121955,0.0057921424,0.00017965402,0.947713,0.0014827834,0.042409666],"study_design_scores_gemma":[0.00010767989,0.0002925896,0.0019461645,0.00040309646,0.00026608896,0.00018581071,0.00009827732,0.04595529,0.0009521545,0.9402288,0.009500869,0.000063095555],"about_ca_topic_score_codex":0.0012923871,"about_ca_topic_score_gemma":0.0013816449,"teacher_disagreement_score":0.16927877,"about_ca_system_score_codex":0.0028753374,"about_ca_system_score_gemma":0.002155215,"threshold_uncertainty_score":0.8952424},"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":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02930324,0.0037919253,0.8995759,0.0044659646,0.0027855067,0.026096676,0.0019783543,0.0011182138,0.030884242],"genre_scores_gemma":[0.45093843,0.0012369816,0.48379892,0.005948501,0.0011345445,0.045915045,0.0019720148,0.0005655421,0.00848997],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.2158642,0.6715904,0.034902,0.02821666,0.04669653,0.0027302203],"domain_scores_gemma":[0.15296097,0.6466991,0.03122324,0.13453051,0.033185214,0.0014010082],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6041839,0.0031036588,0.00324006,0.007374679,0.0030095205,0.00483076,0.0053757317,0.00400652,0.00917579],"category_scores_gemma":[0.80172974,0.0020158985,0.004143474,0.011131857,0.007943933,0.0054221787,0.007619555,0.006560292,0.0027410174],"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":[0.002980256,0.0012199683,0.14481004,0.008248003,0.009131397,0.0010537456,0.018905515,0.014704049,0.0024359273,0.27777562,0.057710793,0.4610247],"study_design_scores_gemma":[0.0023437478,0.0030038103,0.1209515,0.0062086796,0.0058666244,0.001569033,0.0051285173,0.14116068,0.010638343,0.5359731,0.16649915,0.0006568372],"about_ca_topic_score_codex":0.008053287,"about_ca_topic_score_gemma":0.009153866,"teacher_disagreement_score":0.3958161,"about_ca_system_score_codex":0.005828884,"about_ca_system_score_gemma":0.007913612,"threshold_uncertainty_score":0.48811173},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026288448,0.0011573058,0.9687694,0.00036292436,0.00023576399,0.00010651402,0.0007124754,0.0011846307,0.0011825977],"genre_scores_gemma":[0.41195774,0.0009935893,0.57222617,0.0007525651,0.00046822045,0.00083055184,0.0046053096,0.00087439606,0.007291559],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96834373,0.011047916,0.0024868408,0.011577542,0.005215927,0.0013279972],"domain_scores_gemma":[0.8921634,0.06550502,0.0079676295,0.02291156,0.010586187,0.00086629693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027184386,0.00160744,0.004214009,0.0022479873,0.0015377525,0.0059943916,0.004175008,0.0026394124,0.0043987697],"category_scores_gemma":[0.112830386,0.0016829298,0.0038297607,0.001987985,0.0019383482,0.004039522,0.00368068,0.0038904038,0.0019041436],"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":[0.0031235826,0.00040193496,0.116422415,0.0032224867,0.0042222147,0.0013815324,0.00410188,0.13589476,0.03165167,0.08036529,0.012788835,0.6064233],"study_design_scores_gemma":[0.00025144796,0.0006649549,0.048766483,0.0009641367,0.0021604577,0.0015326682,0.001085856,0.6829856,0.050656624,0.15674475,0.053719077,0.00046795214],"about_ca_topic_score_codex":0.009214584,"about_ca_topic_score_gemma":0.009637079,"teacher_disagreement_score":0.027184386,"about_ca_system_score_codex":0.0017020379,"about_ca_system_score_gemma":0.0034754667,"threshold_uncertainty_score":0.14376646},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008076947,0.0002848089,0.9911327,0.000052535837,0.000016372609,0.000022943854,0.000013382241,0.000047734808,0.00035272626],"genre_scores_gemma":[0.41452762,0.0006994186,0.5831206,0.00013838978,0.000111902285,0.00024866214,0.00016492503,0.000060305647,0.0009281331],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9882244,0.008193006,0.00044878776,0.0011227556,0.0017345331,0.0002764685],"domain_scores_gemma":[0.97004247,0.0229818,0.0018474374,0.0024583957,0.0023937402,0.00027618493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012347271,0.00061947014,0.0019003493,0.0017302987,0.00040516668,0.0013174746,0.0011981175,0.0008581542,0.0011874044],"category_scores_gemma":[0.05262885,0.0005167742,0.0008661283,0.0014660221,0.0013547326,0.0028001121,0.001855346,0.0015324221,0.00024313339],"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":[0.0006328951,0.00022954687,0.025633011,0.0008905194,0.0003754259,0.00030067,0.0006974526,0.17055397,0.0083982805,0.4223313,0.0014142811,0.36854255],"study_design_scores_gemma":[0.000107315835,0.00049033563,0.005973647,0.00017971385,0.0001491582,0.0004275372,0.00015466129,0.85190827,0.0059799454,0.12729675,0.0072666802,0.00006600096],"about_ca_topic_score_codex":0.0005689855,"about_ca_topic_score_gemma":0.00052202924,"teacher_disagreement_score":0.012347271,"about_ca_system_score_codex":0.0005430179,"about_ca_system_score_gemma":0.0009468411,"threshold_uncertainty_score":0.06529939},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003939904,0.00014165322,0.99535096,0.00009501236,0.000021050395,0.00011912289,0.000036836762,0.000112330614,0.00018318268],"genre_scores_gemma":[0.2742105,0.0004479193,0.7212605,0.00025588245,0.00021113192,0.0014654447,0.00033279348,0.0001408345,0.0016749386],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9264994,0.062720604,0.0015826774,0.0042617195,0.004020883,0.00091475464],"domain_scores_gemma":[0.70313865,0.25596917,0.012899361,0.020070752,0.006838468,0.0010835356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09705268,0.0015496026,0.0040191533,0.0025836786,0.00093308755,0.0017493347,0.0051327692,0.0037593208,0.0040877806],"category_scores_gemma":[0.25875977,0.0020661347,0.0024782715,0.003328359,0.0035188557,0.003244515,0.0045971856,0.00395086,0.0006736632],"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":[0.0008979989,0.00045109377,0.0054416577,0.0009512968,0.00088526984,0.00032172122,0.0006217153,0.3856452,0.0026888112,0.4464769,0.0022017257,0.15341654],"study_design_scores_gemma":[0.00022657224,0.00026925397,0.0008332095,0.000073878095,0.000101902675,0.000066999346,0.000041117313,0.86155075,0.0012160024,0.13416187,0.0014069304,0.000051559975],"about_ca_topic_score_codex":0.0019248275,"about_ca_topic_score_gemma":0.0012503935,"teacher_disagreement_score":0.09705268,"about_ca_system_score_codex":0.0017878328,"about_ca_system_score_gemma":0.0019962832,"threshold_uncertainty_score":0.5132698},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008590592,0.00022192212,0.98997986,0.00018377016,0.00002959249,0.00007073682,0.00021758968,0.00014448159,0.0005614883],"genre_scores_gemma":[0.3254821,0.0017417591,0.6566728,0.0004934184,0.00062557356,0.002743469,0.0032226944,0.00048164747,0.008536591],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9818708,0.011703065,0.0009070731,0.0026433899,0.0021886483,0.00068702747],"domain_scores_gemma":[0.77615345,0.19287194,0.005597969,0.018295038,0.0054776166,0.0016040325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043824203,0.0013275386,0.0033168856,0.004613996,0.0018973128,0.0048779952,0.0049114795,0.002408394,0.008593839],"category_scores_gemma":[0.16758709,0.0025519622,0.0035570138,0.004285914,0.0050230534,0.0070446804,0.0041281595,0.005250841,0.0014553823],"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":[0.00034833953,0.00015014078,0.008090892,0.00037622332,0.000335757,0.00021122782,0.00095458224,0.056397032,0.0011927984,0.8604628,0.004719684,0.06676044],"study_design_scores_gemma":[0.00006869515,0.000055226963,0.0028726954,0.00011323865,0.00008299235,0.00026251777,0.00014123143,0.44353545,0.0006858175,0.5481622,0.0039702617,0.000049640672],"about_ca_topic_score_codex":0.0035540084,"about_ca_topic_score_gemma":0.0033355926,"teacher_disagreement_score":0.043824203,"about_ca_system_score_codex":0.0027032967,"about_ca_system_score_gemma":0.0021520988,"threshold_uncertainty_score":0.23176736},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019319138,0.044406354,0.61856925,0.23605573,0.010219999,0.00011215462,0.00029147541,0.0002762546,0.07074961],"genre_scores_gemma":[0.55718553,0.023603259,0.3215535,0.05838755,0.015231491,0.0003036102,0.00016497448,0.0005951058,0.022975031],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9852282,0.011311391,0.0003069522,0.0007194724,0.00217188,0.00026212982],"domain_scores_gemma":[0.95286995,0.039694015,0.0010016646,0.0017518939,0.0042496896,0.0004328612],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022063633,0.0005510408,0.0014050545,0.002397284,0.002651402,0.0030085538,0.0019835955,0.0030577353,0.0026764877],"category_scores_gemma":[0.07443197,0.0003059775,0.000562143,0.003144145,0.007047109,0.0051616407,0.0021927122,0.008416801,0.00066622114],"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":[0.000040999377,0.00001042283,0.0006697064,0.000087029344,0.00002128489,0.0001297003,0.00051618577,0.0009968943,0.00005933895,0.9527045,0.020646695,0.024117205],"study_design_scores_gemma":[0.00002689137,0.000041365634,0.0012723892,0.00027699006,0.000025567933,0.0002929261,0.00041623984,0.016762068,0.00023673788,0.8670301,0.113564335,0.00005439116],"about_ca_topic_score_codex":0.0080252355,"about_ca_topic_score_gemma":0.010237083,"teacher_disagreement_score":0.022063633,"about_ca_system_score_codex":0.0025504248,"about_ca_system_score_gemma":0.0020950902,"threshold_uncertainty_score":0.11668503},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20937382,0.00081229844,0.7755573,0.0017928133,0.0004993246,0.0022087975,0.0018753025,0.0005493357,0.0073309885],"genre_scores_gemma":[0.87017006,0.00033358275,0.121967375,0.0009327577,0.0004195623,0.0038358397,0.001137644,0.000119213495,0.0010839695],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5225875,0.4142076,0.015143766,0.019016221,0.02737989,0.001664984],"domain_scores_gemma":[0.19567905,0.66093045,0.056218177,0.07481265,0.011832212,0.0005274954],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27638167,0.0010433125,0.0018726136,0.0062360205,0.0015613113,0.0025955315,0.001963381,0.0015263974,0.0037244537],"category_scores_gemma":[0.6286774,0.0008743998,0.0022312626,0.0071655116,0.0077264295,0.0042863493,0.0044953465,0.0028934428,0.0007949015],"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":[0.0015639793,0.00046896902,0.3387244,0.0030498067,0.0057106493,0.000495424,0.017574862,0.013594179,0.0033055984,0.24545808,0.015339516,0.35471457],"study_design_scores_gemma":[0.00035131056,0.0020226699,0.30310443,0.0017904078,0.0021621562,0.001419,0.007992398,0.20071599,0.01716176,0.4177391,0.04512724,0.00041355455],"about_ca_topic_score_codex":0.0011759738,"about_ca_topic_score_gemma":0.00066198665,"teacher_disagreement_score":0.7236183,"about_ca_system_score_codex":0.0018422692,"about_ca_system_score_gemma":0.0018654678,"threshold_uncertainty_score":0.89235026},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008940707,0.0010250928,0.9958835,0.00043239855,0.00011852726,0.000052657484,0.00006138034,0.000059304766,0.0014730305],"genre_scores_gemma":[0.06442431,0.004203423,0.9210812,0.0011123668,0.001693431,0.0007114756,0.00040552966,0.00023418182,0.0061341515],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96139526,0.03030457,0.0012831615,0.0023909996,0.004113457,0.00051253627],"domain_scores_gemma":[0.82392347,0.1486447,0.0028100808,0.016392987,0.0074322983,0.0007965009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.056172602,0.0019947763,0.0030944103,0.004126411,0.002047704,0.0037772467,0.006249638,0.0034753873,0.007892597],"category_scores_gemma":[0.21505241,0.0024305417,0.002982812,0.008911345,0.006198451,0.007657337,0.004609826,0.00646206,0.0014232498],"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":[0.000077790246,0.0000946454,0.002356416,0.00043598545,0.00017132954,0.000105359875,0.00056479336,0.018160429,0.00030676622,0.88199216,0.0054076994,0.09032662],"study_design_scores_gemma":[0.000043454627,0.00004994128,0.0008208335,0.00014297731,0.000091232476,0.00014512047,0.00009252293,0.113581136,0.00035886123,0.8661616,0.018459674,0.000052679734],"about_ca_topic_score_codex":0.004879942,"about_ca_topic_score_gemma":0.0051911236,"teacher_disagreement_score":0.056172602,"about_ca_system_score_codex":0.002345994,"about_ca_system_score_gemma":0.0026325402,"threshold_uncertainty_score":0.29707265},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011216987,0.00029395107,0.98733133,0.00018599453,0.00003063706,0.0002782404,0.000042196007,0.00018669757,0.00043388002],"genre_scores_gemma":[0.1636726,0.0003842117,0.8335814,0.00019411699,0.00008570403,0.0011977366,0.00018813837,0.00006377151,0.0006323341],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.81377995,0.16794857,0.004259646,0.0053556846,0.007955019,0.0007011441],"domain_scores_gemma":[0.58717835,0.3478638,0.012688022,0.040656682,0.011052559,0.00056064484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.114657894,0.0017342584,0.002213024,0.0032643897,0.00081414514,0.00155611,0.0034403545,0.0024949294,0.0031237316],"category_scores_gemma":[0.34569177,0.0011263255,0.0016346112,0.0028503977,0.0022698715,0.0039711455,0.003600478,0.0017624324,0.0012478224],"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":[0.0012443641,0.000614446,0.023130309,0.0020258483,0.000851035,0.0002196959,0.003266407,0.064485185,0.0065379087,0.12778512,0.0028328416,0.7670069],"study_design_scores_gemma":[0.0006850166,0.0019145044,0.013522479,0.0006652376,0.0004610057,0.0005013928,0.00067367713,0.7636337,0.013352992,0.19431627,0.010035209,0.00023850161],"about_ca_topic_score_codex":0.00078005035,"about_ca_topic_score_gemma":0.0007269443,"teacher_disagreement_score":0.114657894,"about_ca_system_score_codex":0.00088300294,"about_ca_system_score_gemma":0.0015532641,"threshold_uncertainty_score":0.6063762},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046207914,0.0050051087,0.010231123,0.010502129,0.018852806,0.00048746463,0.011242125,0.0020509507,0.9370075],"genre_scores_gemma":[0.013197542,0.0022148588,0.0036766909,0.0014341982,0.0015302075,0.0001403424,0.0061633848,0.00076619425,0.97087663],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977471,0.00052837044,0.00015113031,0.00062497694,0.00068494206,0.00026332668],"domain_scores_gemma":[0.99582326,0.0007296636,0.00020862331,0.0011235039,0.001371487,0.0007435314],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002473962,0.0009831899,0.001339452,0.002265363,0.0018333783,0.0071065184,0.0022384396,0.0030004408,0.7437564],"category_scores_gemma":[0.011981154,0.0005490614,0.0010388725,0.0022874398,0.0011970412,0.002221213,0.0046754433,0.0024630644,0.6316859],"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":[0.0005098688,0.00022537693,0.0018130359,0.00089878903,0.00007168601,0.0007547228,0.0003898934,0.0004320944,0.0020529318,0.042143762,0.5967094,0.35399848],"study_design_scores_gemma":[0.000027052285,0.000042700533,0.00059714133,0.0001272547,0.000007397186,0.00016333858,0.00006446586,0.00014380556,0.0004387246,0.0038118456,0.9945687,0.0000074771265],"about_ca_topic_score_codex":0.0016757152,"about_ca_topic_score_gemma":0.0026398583,"teacher_disagreement_score":0.2562436,"about_ca_system_score_codex":0.0013560066,"about_ca_system_score_gemma":0.002116496,"threshold_uncertainty_score":0.36550033},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006286706,0.00010461088,0.9928439,0.00014742513,0.000022669972,0.00009937095,0.00007233701,0.00012960157,0.00029334315],"genre_scores_gemma":[0.33581987,0.00029213526,0.6607105,0.00025800793,0.00012401181,0.0009115147,0.00054617465,0.00010762984,0.0012302005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9540354,0.039632406,0.0006889358,0.0033004617,0.0018861088,0.0004566667],"domain_scores_gemma":[0.8862568,0.09690589,0.0052267634,0.008207305,0.0029549482,0.00044832184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045304377,0.0013842441,0.0027120474,0.0030269974,0.0013163233,0.0023572026,0.0044343565,0.0017780453,0.0026211017],"category_scores_gemma":[0.13450775,0.0013044663,0.0026541208,0.0038721506,0.0034681088,0.002398266,0.002808773,0.0033005972,0.0004649652],"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":[0.00037857256,0.00016427177,0.009831049,0.0004524767,0.0010735274,0.0003949599,0.0006378687,0.5542072,0.00062728097,0.34061417,0.0026824202,0.088936105],"study_design_scores_gemma":[0.000064233194,0.000058147794,0.0009361754,0.000048561742,0.00007676358,0.000046561065,0.00005520501,0.86147857,0.00036710867,0.13604328,0.00080001773,0.000025360214],"about_ca_topic_score_codex":0.01070872,"about_ca_topic_score_gemma":0.007001656,"teacher_disagreement_score":0.045304377,"about_ca_system_score_codex":0.002524536,"about_ca_system_score_gemma":0.0026538947,"threshold_uncertainty_score":0.2395953},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0057369024,0.00009839907,0.99342656,0.00015981666,0.0000100847365,0.00007439717,0.000036072382,0.0001490472,0.00030872138],"genre_scores_gemma":[0.19769032,0.00022124517,0.799514,0.0002295151,0.000088227105,0.0007534893,0.00033583384,0.00009989253,0.0010674202],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9868499,0.010559501,0.00037797214,0.001113612,0.00085372967,0.00024532265],"domain_scores_gemma":[0.9675589,0.027090197,0.0017819387,0.0018266394,0.0013959239,0.0003464219],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015657967,0.0011617806,0.002279224,0.0019311374,0.0007381362,0.0013456271,0.0027575071,0.0020985992,0.0019669833],"category_scores_gemma":[0.051484834,0.0009447563,0.0013289333,0.0020557353,0.0016434753,0.002182085,0.0021854711,0.002057486,0.0004598632],"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":[0.00019480598,0.0001833446,0.0048553604,0.0002907224,0.00021570131,0.00006652307,0.00021446013,0.76111704,0.0009189674,0.06865047,0.0017709929,0.1615217],"study_design_scores_gemma":[0.000019266365,0.0000449317,0.0003299147,0.000018174056,0.0000115127705,0.0000110047295,0.000017406874,0.96835136,0.00031970572,0.030342175,0.00052461115,0.000009822913],"about_ca_topic_score_codex":0.0025593173,"about_ca_topic_score_gemma":0.0020905898,"teacher_disagreement_score":0.98434204,"about_ca_system_score_codex":0.0015998604,"about_ca_system_score_gemma":0.0017260129,"threshold_uncertainty_score":0.0828082},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930648,0.0006516805,0.004863002,0.00012776886,0.000035925896,0.00029546442,0.0002111738,0.000011507842,0.00073875964],"genre_scores_gemma":[0.99452776,0.00023498421,0.004336453,0.00009095791,0.000027447153,0.0003369025,0.00027329213,0.0000076172214,0.00016455277],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9268221,0.053139873,0.0061296183,0.0033216213,0.009177319,0.0014094042],"domain_scores_gemma":[0.9476006,0.024527354,0.012127776,0.0057738875,0.009417563,0.00055271277],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04179918,0.0006339351,0.00064393936,0.0026166814,0.0008238504,0.0011364548,0.0012525085,0.0006142128,0.00045554535],"category_scores_gemma":[0.076477215,0.0005008863,0.0011782707,0.0023162179,0.0010942938,0.00091362733,0.0018164254,0.0004784817,0.0000778325],"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":[0.00012349276,0.00007510587,0.9827177,0.00020183293,0.00031960427,0.000031619136,0.0029318386,0.00012019271,0.00028306,0.000114361355,0.000091682894,0.012989364],"study_design_scores_gemma":[0.00001903443,0.00033055473,0.99207205,0.00015865725,0.00027048727,0.00016218598,0.0041687535,0.0011440373,0.0009125342,0.00012331517,0.0006172661,0.000021207972],"about_ca_topic_score_codex":0.010132664,"about_ca_topic_score_gemma":0.012632494,"teacher_disagreement_score":0.9582008,"about_ca_system_score_codex":0.0010725091,"about_ca_system_score_gemma":0.0013894473,"threshold_uncertainty_score":0.22105777},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032968916,0.0013453343,0.9623163,0.00044456642,0.000039062936,0.00008549928,0.00010593173,0.000137428,0.0025570993],"genre_scores_gemma":[0.7008207,0.002598128,0.29062277,0.00046146958,0.000255324,0.00037372086,0.0006599954,0.00023408412,0.003973792],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9876359,0.009713132,0.00024093445,0.0010521096,0.0010825448,0.00027544747],"domain_scores_gemma":[0.8825853,0.10640302,0.0030933367,0.004630649,0.0029061397,0.0003815543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032318074,0.00076737313,0.0018439929,0.0015514902,0.0005501117,0.0016330681,0.0021821556,0.001627907,0.0036482706],"category_scores_gemma":[0.14385961,0.0002992943,0.0010161371,0.002098659,0.0016086969,0.003982007,0.0020286147,0.0018970005,0.00046552537],"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":[0.0005336033,0.00017047962,0.014260175,0.0006866117,0.0005673794,0.00023673287,0.0005139542,0.43172503,0.002122581,0.3758589,0.0029654682,0.17035903],"study_design_scores_gemma":[0.00007981705,0.0006141837,0.0060688355,0.00018308993,0.00026849206,0.00031971122,0.00033402795,0.8616993,0.0017356568,0.125031,0.0035944285,0.00007148684],"about_ca_topic_score_codex":0.0030084134,"about_ca_topic_score_gemma":0.0024374514,"teacher_disagreement_score":0.032318074,"about_ca_system_score_codex":0.0010775785,"about_ca_system_score_gemma":0.0020332392,"threshold_uncertainty_score":0.17091632},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0022845278,0.00039516907,0.98614097,0.0002870125,0.00017622512,0.00010045344,0.00014321045,0.0002553421,0.010217139],"genre_scores_gemma":[0.3275563,0.0031742887,0.63842696,0.0010807547,0.00093930506,0.0017505413,0.0011044258,0.0011424328,0.02482492],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9894838,0.0049843527,0.00053317106,0.0022529499,0.0023893495,0.00035640472],"domain_scores_gemma":[0.9797376,0.009453788,0.0016234728,0.0056530503,0.003385517,0.00014665553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013863356,0.0012701482,0.0014365044,0.0032068,0.000876595,0.0033082897,0.0019722888,0.0018110125,0.016279751],"category_scores_gemma":[0.078576796,0.0006335561,0.0019764279,0.005010503,0.0026077614,0.004756008,0.0040775184,0.0034104167,0.005476913],"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":[0.000077077435,0.00007291945,0.0032446033,0.00043816434,0.00015837993,0.00022763295,0.00072855916,0.05407675,0.0017426088,0.55035937,0.008979902,0.37989402],"study_design_scores_gemma":[0.000056849647,0.0002544692,0.00424438,0.00035688165,0.00013659571,0.00074906874,0.00041530977,0.21348453,0.0041185245,0.68464917,0.0914244,0.0001097725],"about_ca_topic_score_codex":0.0012136012,"about_ca_topic_score_gemma":0.00058230915,"teacher_disagreement_score":0.016279751,"about_ca_system_score_codex":0.0013270533,"about_ca_system_score_gemma":0.0018597463,"threshold_uncertainty_score":0.07331729},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009066677,0.00015525633,0.98882526,0.00027498472,0.000044565077,0.00016973501,0.000099915946,0.00011798005,0.0012455112],"genre_scores_gemma":[0.42842752,0.0005841523,0.56371206,0.00066375115,0.00035535425,0.001413772,0.0007478953,0.00010236224,0.003993106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9607112,0.030031089,0.0010476671,0.0032347878,0.0042749154,0.000700353],"domain_scores_gemma":[0.90110767,0.07007089,0.0064377026,0.017833713,0.0038539362,0.0006960354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044339873,0.0012264287,0.0029534246,0.0030902296,0.0010677095,0.0031133355,0.004982553,0.002527561,0.0048175375],"category_scores_gemma":[0.16390604,0.0012039508,0.001910575,0.004827309,0.0026091062,0.0059340782,0.006693298,0.0022820074,0.001400537],"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":[0.0004603436,0.00034063737,0.026901215,0.00053302036,0.0007980017,0.0004155098,0.0011526797,0.07342136,0.0010821889,0.64760226,0.002955559,0.24433726],"study_design_scores_gemma":[0.00011541299,0.00044001348,0.005310322,0.000207641,0.00023647584,0.000319804,0.0002668029,0.3497747,0.0016471475,0.63460916,0.0070108096,0.000061822924],"about_ca_topic_score_codex":0.0010802735,"about_ca_topic_score_gemma":0.0010140463,"teacher_disagreement_score":0.044339873,"about_ca_system_score_codex":0.0012186749,"about_ca_system_score_gemma":0.0014756907,"threshold_uncertainty_score":0.2344945},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21611795,0.00039527548,0.78041303,0.00041594918,0.000023111217,0.00054541876,0.00028314607,0.00022556983,0.0015805472],"genre_scores_gemma":[0.845392,0.0002529515,0.15136272,0.00018183775,0.00003750781,0.0013640426,0.00079862046,0.00006723301,0.00054322166],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.82652164,0.16094781,0.0023993212,0.0034340108,0.0058434797,0.000853746],"domain_scores_gemma":[0.53221804,0.42343977,0.016825054,0.017354768,0.009407344,0.0007549536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10672809,0.0011492869,0.0015729391,0.0037385463,0.0006304991,0.0022067388,0.0024115453,0.0026709996,0.0025997953],"category_scores_gemma":[0.34263697,0.0010406604,0.0021243778,0.0042148493,0.0022166544,0.0045314874,0.002369989,0.002607904,0.00060950447],"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":[0.0018991844,0.0017796416,0.29334873,0.0014130474,0.0026954692,0.00023405958,0.007311865,0.23991297,0.0021013026,0.19602685,0.0024776154,0.25079933],"study_design_scores_gemma":[0.0000964933,0.0009974407,0.06682347,0.0003361241,0.00026167734,0.00016980627,0.0011652586,0.8124901,0.0009903489,0.114851505,0.0016834445,0.00013433538],"about_ca_topic_score_codex":0.0023114986,"about_ca_topic_score_gemma":0.0015339149,"teacher_disagreement_score":0.10672809,"about_ca_system_score_codex":0.0015238551,"about_ca_system_score_gemma":0.0010824569,"threshold_uncertainty_score":0.5644388},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028977864,0.00009199811,0.99610776,0.000041197025,0.00003275717,0.00018219465,0.000067607114,0.00017946701,0.0003993366],"genre_scores_gemma":[0.08280926,0.00021752341,0.91195005,0.0002213072,0.00007833748,0.0018571134,0.00044959804,0.00016219632,0.0022546689],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9177851,0.0647706,0.002031283,0.008038582,0.006148761,0.001225666],"domain_scores_gemma":[0.89137095,0.07625655,0.0044777025,0.01936029,0.0078023947,0.0007321068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06388301,0.0014125078,0.0040574716,0.0032944588,0.0017380259,0.0022974953,0.0047514616,0.0029898738,0.006417303],"category_scores_gemma":[0.17314142,0.0018620207,0.00282688,0.0036330407,0.0030851068,0.0031928003,0.0025937904,0.003579709,0.0017371072],"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":[0.0015709811,0.00062371755,0.024405556,0.0011670556,0.0026403605,0.0005136347,0.0018800265,0.110723935,0.007235064,0.39816833,0.01237971,0.43869165],"study_design_scores_gemma":[0.00055820536,0.0012603728,0.0123402225,0.0007405783,0.0012276638,0.0014336713,0.0006510125,0.698912,0.0074368846,0.25164285,0.023590088,0.00020635998],"about_ca_topic_score_codex":0.003908826,"about_ca_topic_score_gemma":0.0046007237,"teacher_disagreement_score":0.06388301,"about_ca_system_score_codex":0.001747814,"about_ca_system_score_gemma":0.0035184398,"threshold_uncertainty_score":0.33784968},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049648946,0.00015127899,0.99399287,0.000054022912,0.000020292333,0.00002187512,0.000044128814,0.000153164,0.0005974992],"genre_scores_gemma":[0.2993371,0.00048626823,0.69453835,0.00017266418,0.00008464238,0.0002465746,0.0006059612,0.00017993075,0.0043485025],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951611,0.0030281032,0.00012334317,0.00075081835,0.00081935426,0.000117184376],"domain_scores_gemma":[0.98861736,0.0076717846,0.0010274395,0.0012173073,0.0013246336,0.00014149124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006717658,0.00040930187,0.0012915301,0.0011871199,0.00027930172,0.0010760075,0.0019438373,0.0010495951,0.0022366745],"category_scores_gemma":[0.030588215,0.00030308173,0.0008241114,0.0012907695,0.00080366916,0.0018648498,0.0014217192,0.0015429439,0.0008238566],"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":[0.00028347087,0.00020269999,0.011665297,0.00066437764,0.00029032983,0.00028673236,0.0003591501,0.2567657,0.014193241,0.2178032,0.0042936928,0.4931921],"study_design_scores_gemma":[0.000041258318,0.00033511632,0.0043399734,0.000086881286,0.00007100437,0.0004164511,0.00009047658,0.93315876,0.0055817263,0.047926776,0.00788594,0.00006559845],"about_ca_topic_score_codex":0.00087985763,"about_ca_topic_score_gemma":0.0007246296,"teacher_disagreement_score":0.006717658,"about_ca_system_score_codex":0.00053730275,"about_ca_system_score_gemma":0.0011575491,"threshold_uncertainty_score":0.035526752},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046102935,0.010255146,0.97112817,0.0048960084,0.0006118642,0.000051373572,0.00031730352,0.00020405736,0.007925733],"genre_scores_gemma":[0.40760022,0.021875735,0.5214196,0.004410915,0.006920069,0.0008289725,0.0011911173,0.00038187776,0.03537153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99124956,0.005785652,0.00023509246,0.0010303967,0.0014096203,0.0002896533],"domain_scores_gemma":[0.9729337,0.019150726,0.000953911,0.005106527,0.0014440529,0.00041096497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0132121565,0.0012636376,0.0016230869,0.0022854828,0.0012362936,0.0019144525,0.00267704,0.0018777436,0.005505837],"category_scores_gemma":[0.047805846,0.0008362306,0.0009261012,0.0044499026,0.0038867486,0.0065436214,0.0034508232,0.0059432886,0.0018402],"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":[0.000089986446,0.00006037672,0.0011561295,0.00024857666,0.00010015687,0.000030554686,0.00012859784,0.008564204,0.00026561652,0.9078033,0.009694945,0.071857624],"study_design_scores_gemma":[0.00004076565,0.000040998915,0.0004938137,0.0001000079,0.000037981317,0.00005980436,0.000032664066,0.052366365,0.00041428828,0.93276954,0.0136292,0.000014610056],"about_ca_topic_score_codex":0.0015834633,"about_ca_topic_score_gemma":0.0017676651,"teacher_disagreement_score":0.0132121565,"about_ca_system_score_codex":0.002350259,"about_ca_system_score_gemma":0.0019477635,"threshold_uncertainty_score":0.06987339},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0144370785,0.00014698172,0.98395455,0.0002937769,0.000024274948,0.00017343553,0.00016058102,0.00014227246,0.00066709373],"genre_scores_gemma":[0.3302763,0.0007217815,0.65915024,0.0005402209,0.00031194076,0.0022331758,0.0021135402,0.00020789845,0.004444876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9473603,0.043392096,0.0011444751,0.0033075025,0.0038899998,0.0009057053],"domain_scores_gemma":[0.729915,0.24016088,0.009174876,0.013189581,0.0066832085,0.0008765258],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06332731,0.0016460826,0.0036482015,0.0034392606,0.0010271134,0.0025898966,0.0036061397,0.0025559827,0.005781866],"category_scores_gemma":[0.24708526,0.0017536818,0.0024686581,0.0037148655,0.0036269738,0.004984374,0.0035674875,0.0041565616,0.00080332],"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":[0.00064836355,0.0002714583,0.011138438,0.0007480547,0.0005481179,0.0003919883,0.0013798035,0.16799402,0.0013466255,0.6841117,0.0037661807,0.12765521],"study_design_scores_gemma":[0.00013340154,0.000101039506,0.0028437506,0.00010099442,0.0000823399,0.00009097307,0.00010149524,0.63426226,0.0004862827,0.3591485,0.0025961206,0.000052905205],"about_ca_topic_score_codex":0.0040996936,"about_ca_topic_score_gemma":0.003467852,"teacher_disagreement_score":0.06332731,"about_ca_system_score_codex":0.0020421243,"about_ca_system_score_gemma":0.001969986,"threshold_uncertainty_score":0.33491087},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000766851,0.0001092872,0.9987527,0.000058981946,0.00002136313,0.000021798403,0.000018008457,0.00003289998,0.00021806253],"genre_scores_gemma":[0.07788722,0.0010439537,0.91725904,0.00028576766,0.00024448993,0.0006046102,0.00028026794,0.000108382446,0.002286282],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.991198,0.006578289,0.00033137403,0.0007673015,0.0009651774,0.00015996593],"domain_scores_gemma":[0.97111905,0.023554537,0.0013013715,0.0018187593,0.001978693,0.0002276188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023022825,0.0008978166,0.0012821376,0.0018420097,0.0003992751,0.0014707933,0.0031819013,0.0016416376,0.0034429675],"category_scores_gemma":[0.067341566,0.0006599806,0.00158287,0.0020263714,0.001585814,0.0032179353,0.0021760312,0.002290974,0.0008475629],"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":[0.0002091856,0.00008824681,0.0061683278,0.0006749326,0.0002395289,0.00026462332,0.0006473788,0.2127291,0.0023184465,0.550429,0.0027387275,0.2234925],"study_design_scores_gemma":[0.000050634866,0.00019552045,0.001067843,0.00013508298,0.00007075098,0.00028069154,0.00008647882,0.82286394,0.0017316372,0.1654484,0.008020934,0.000048024045],"about_ca_topic_score_codex":0.00086524815,"about_ca_topic_score_gemma":0.0007680184,"teacher_disagreement_score":0.023022825,"about_ca_system_score_codex":0.00079583074,"about_ca_system_score_gemma":0.0013045197,"threshold_uncertainty_score":0.121757805},"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":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016353964,0.016464517,0.94403124,0.003360222,0.0006271859,0.0001848219,0.00046981496,0.0003014292,0.032925386],"genre_scores_gemma":[0.17087622,0.087880954,0.68184316,0.005216567,0.0031123501,0.0027903263,0.0016597285,0.00051033386,0.046110407],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995972,0.0015307378,0.00028361558,0.0007366323,0.0012625932,0.00021442898],"domain_scores_gemma":[0.99474525,0.0034662827,0.000369228,0.00045264047,0.0009019774,0.00006458223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004603933,0.0018909799,0.0016527522,0.0027772381,0.00095079024,0.0041683693,0.0041233674,0.0036480404,0.0068250243],"category_scores_gemma":[0.007822766,0.0010227317,0.0023049794,0.0029423777,0.003938672,0.0044779144,0.0024748459,0.004371066,0.002453279],"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":[0.000013442639,0.00003857974,0.0004374831,0.00089314795,0.000051940908,0.00012017798,0.0002923615,0.043619834,0.00058565417,0.91318214,0.004642519,0.036122687],"study_design_scores_gemma":[0.0000143953375,0.00006674962,0.00033938786,0.0005561745,0.00004439992,0.0002328267,0.00015363785,0.10221786,0.0009295751,0.7546807,0.14069553,0.00006875141],"about_ca_topic_score_codex":0.005480527,"about_ca_topic_score_gemma":0.00208206,"teacher_disagreement_score":0.0068250243,"about_ca_system_score_codex":0.0034565167,"about_ca_system_score_gemma":0.003992337,"threshold_uncertainty_score":0.025078893},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058749758,0.0039453404,0.9335892,0.00042784458,0.00012051298,0.00008996983,0.00008652884,0.00017926814,0.0028115895],"genre_scores_gemma":[0.4739818,0.0021190024,0.52157325,0.00023693855,0.00018704419,0.0002858259,0.00037497794,0.00014379647,0.0010973935],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9655826,0.027201392,0.00082026457,0.0017050835,0.004305711,0.0003849703],"domain_scores_gemma":[0.84607637,0.13755503,0.002887516,0.0071027162,0.00609106,0.00028729206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.039949603,0.0005443069,0.0010451787,0.0025700636,0.0005134174,0.0017117611,0.0014032564,0.0016826742,0.0010859185],"category_scores_gemma":[0.19957541,0.0003712412,0.0008793096,0.0017179078,0.0012770043,0.0035163504,0.0015700602,0.0010079709,0.0002885121],"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":[0.0007374606,0.00026855725,0.051458925,0.0009246464,0.001542091,0.00020345712,0.0009558369,0.1984357,0.0027293006,0.23080046,0.004045621,0.5078979],"study_design_scores_gemma":[0.00031962077,0.0013300481,0.029422903,0.00091586116,0.00066402147,0.0008961422,0.00091739005,0.7864449,0.009954553,0.15325518,0.015659127,0.00022025447],"about_ca_topic_score_codex":0.0010739123,"about_ca_topic_score_gemma":0.0011485766,"teacher_disagreement_score":0.039949603,"about_ca_system_score_codex":0.001030009,"about_ca_system_score_gemma":0.0010564327,"threshold_uncertainty_score":0.21127623},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035531756,0.00020558419,0.99546957,0.000101066755,0.000016243743,0.00014291378,0.000041249943,0.000074433585,0.0003957133],"genre_scores_gemma":[0.113786876,0.0004477104,0.881492,0.00015053454,0.0000741098,0.0018872037,0.00022193675,0.00015753513,0.0017819867],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9834432,0.013912345,0.00035691768,0.00082557887,0.000900336,0.00056168303],"domain_scores_gemma":[0.9564403,0.039680317,0.0012976778,0.0009826185,0.001149922,0.00044911576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020881455,0.00215106,0.0067798067,0.003490045,0.0010655036,0.0019923646,0.0037697307,0.002962374,0.005686174],"category_scores_gemma":[0.0542243,0.0034944192,0.0032576092,0.003991082,0.002675014,0.0028942283,0.0032035261,0.0027693664,0.0007491612],"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":[0.0001564873,0.000109916546,0.00067801913,0.00027850995,0.00018300032,0.000029230721,0.00012049576,0.9367036,0.0002766302,0.028063076,0.00085294485,0.03254806],"study_design_scores_gemma":[0.000031715776,0.000046651774,0.00015542332,0.00002350129,0.00002306153,0.000008495101,0.000016459984,0.98311794,0.00009949872,0.016154174,0.00031345218,0.000009548894],"about_ca_topic_score_codex":0.0077386973,"about_ca_topic_score_gemma":0.006060933,"teacher_disagreement_score":0.020881455,"about_ca_system_score_codex":0.0033358699,"about_ca_system_score_gemma":0.003629466,"threshold_uncertainty_score":0.11043304},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011361688,0.000048974245,0.98782045,0.000020870026,0.000011341309,0.00023163058,0.00006414275,0.00008459465,0.00035620652],"genre_scores_gemma":[0.18647122,0.00016385561,0.81053567,0.000053590597,0.000020075327,0.0013242908,0.00046511967,0.00003540643,0.00093072123],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9885239,0.009065279,0.00025436963,0.0005723393,0.0013694555,0.00021463563],"domain_scores_gemma":[0.98834467,0.0074220165,0.0006044882,0.0014518409,0.0020213292,0.00015563039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008534097,0.0006186014,0.001348793,0.0015985745,0.0005121598,0.0007740105,0.0017606852,0.0006935156,0.0030980217],"category_scores_gemma":[0.027031925,0.00048741695,0.00083098124,0.0017045764,0.0006834952,0.0009973253,0.0011514362,0.00085689384,0.00050700427],"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":[0.0011103218,0.00035821757,0.011145052,0.00087781396,0.00038451812,0.00026578843,0.00043567954,0.33289438,0.014558088,0.13288787,0.0029325737,0.5021497],"study_design_scores_gemma":[0.00015796832,0.0007745115,0.003942692,0.000068626265,0.00007430409,0.00017033811,0.00014697807,0.94233525,0.0070828605,0.04159622,0.0035836932,0.00006651079],"about_ca_topic_score_codex":0.0018599763,"about_ca_topic_score_gemma":0.0020188545,"teacher_disagreement_score":0.008534097,"about_ca_system_score_codex":0.00062848144,"about_ca_system_score_gemma":0.0014820866,"threshold_uncertainty_score":0.045133173},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023159834,0.00003962082,0.9972395,0.00003472612,0.000014988055,0.00006053975,0.00002669826,0.00007875627,0.00018915272],"genre_scores_gemma":[0.09381294,0.00014504668,0.90397316,0.000119771,0.0000762995,0.0009474319,0.00022802273,0.00012025825,0.0005770634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96380836,0.028690241,0.00079015415,0.0017810814,0.0045462945,0.00038393933],"domain_scores_gemma":[0.90304977,0.07776277,0.0038020152,0.008633214,0.006273589,0.00047859558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034300517,0.0009220233,0.0015860958,0.0030314415,0.0010165491,0.0015178757,0.0027947035,0.0017219473,0.0029373402],"category_scores_gemma":[0.13575177,0.0006695961,0.0013853962,0.002776451,0.0034207383,0.0018371169,0.0020345778,0.0030736276,0.0007787172],"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":[0.0006138336,0.00033930322,0.013851271,0.00054112996,0.0006146203,0.00035608897,0.0010314011,0.13094765,0.0071574748,0.5125147,0.005260614,0.3267719],"study_design_scores_gemma":[0.00020434505,0.00061054184,0.00577497,0.00020598959,0.00015318653,0.00040322266,0.00019559436,0.7399343,0.008149342,0.23517434,0.009052658,0.00014146566],"about_ca_topic_score_codex":0.0020750535,"about_ca_topic_score_gemma":0.0013939416,"teacher_disagreement_score":0.034300517,"about_ca_system_score_codex":0.0010328036,"about_ca_system_score_gemma":0.0022989102,"threshold_uncertainty_score":0.18140066},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01496262,0.00015410973,0.9836422,0.00019292654,0.00004968884,0.00019311505,0.00016117557,0.00008608294,0.0005579617],"genre_scores_gemma":[0.501688,0.00039548744,0.49038532,0.0004245784,0.00020878817,0.0021743067,0.0008016537,0.000069627225,0.0038522338],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9454219,0.042558864,0.0015600716,0.0054421118,0.0040416024,0.00097554614],"domain_scores_gemma":[0.7802644,0.1893602,0.009675672,0.014295575,0.0055266656,0.00087753613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0578238,0.0010117476,0.0029316843,0.0017635798,0.0007888772,0.0018662829,0.0032972123,0.0027008578,0.005953157],"category_scores_gemma":[0.17135108,0.0015678,0.002634122,0.002286169,0.0029120718,0.0027009065,0.002253012,0.0027282382,0.0005557344],"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":[0.0009287294,0.00029502506,0.02406018,0.0010984952,0.0014897472,0.00053814903,0.00085062283,0.20665412,0.0024847784,0.65628105,0.003060133,0.102258936],"study_design_scores_gemma":[0.00028752536,0.0004417782,0.00408466,0.00012986346,0.0001642165,0.00013937832,0.000082530496,0.7256392,0.0011238051,0.2654227,0.0024196021,0.00006464747],"about_ca_topic_score_codex":0.0029762434,"about_ca_topic_score_gemma":0.0020710346,"teacher_disagreement_score":0.0578238,"about_ca_system_score_codex":0.0015429623,"about_ca_system_score_gemma":0.0017709858,"threshold_uncertainty_score":0.3058051},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00041367384,0.0012477825,0.9911972,0.0004997998,0.00013003443,0.00006181966,0.0001295008,0.00007464557,0.0062454753],"genre_scores_gemma":[0.058607683,0.0061120978,0.9112421,0.0011260441,0.0011695725,0.0016887111,0.0006387327,0.00030858096,0.019106546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98138523,0.013390183,0.0006197442,0.0014041057,0.0028333059,0.0003675643],"domain_scores_gemma":[0.96008813,0.03223242,0.0008398417,0.0045600766,0.0020054914,0.00027400302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016668806,0.001343328,0.0024198822,0.0028707378,0.0013276044,0.0042871353,0.004639685,0.002552139,0.01639285],"category_scores_gemma":[0.0637892,0.0015115393,0.0018457035,0.005618973,0.005040007,0.0058652996,0.0034097151,0.005439427,0.0038810703],"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":[0.000008754905,0.000014798418,0.00029661093,0.00011159502,0.0000222215,0.000025495447,0.00012785918,0.0042424006,0.00009312001,0.96268404,0.004067096,0.028306047],"study_design_scores_gemma":[0.000009371007,0.000009222591,0.00017734228,0.000066551765,0.000015369673,0.000096700285,0.000032308475,0.021978753,0.000118288524,0.96479046,0.01269242,0.000013175999],"about_ca_topic_score_codex":0.0026760688,"about_ca_topic_score_gemma":0.0022555853,"teacher_disagreement_score":0.016668806,"about_ca_system_score_codex":0.0025409563,"about_ca_system_score_gemma":0.0027335302,"threshold_uncertainty_score":0.08815414},"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":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019971943,0.05048752,0.30136472,0.010941974,0.0036788173,0.00013895851,0.0031389801,0.0015204144,0.62673134],"genre_scores_gemma":[0.042564683,0.046969093,0.08314934,0.003945634,0.004662657,0.00050675764,0.002828228,0.0008628998,0.81451076],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993729,0.00025349428,0.000020440573,0.00010893767,0.00022007103,0.000024188326],"domain_scores_gemma":[0.9984054,0.0009239976,0.000056912864,0.00031108875,0.00025585995,0.00004674783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010658416,0.00092972687,0.0011888585,0.0017698861,0.00056866073,0.0024083583,0.00065948605,0.0011177815,0.06154112],"category_scores_gemma":[0.0055998918,0.0006251786,0.00037325386,0.0036076321,0.00079113716,0.0025093644,0.0008535112,0.0018646964,0.025368327],"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":[0.000009939919,0.000027442851,0.00038848186,0.00016644258,0.00001730662,0.000016207581,0.000074660034,0.002119174,0.00014295975,0.31782368,0.43455893,0.24465482],"study_design_scores_gemma":[0.0000054531274,0.000015983214,0.00089389633,0.00010708944,0.000012822852,0.000091548674,0.00005260152,0.0062257852,0.00010770798,0.3948158,0.59765977,0.000011512552],"about_ca_topic_score_codex":0.0019730793,"about_ca_topic_score_gemma":0.00458001,"teacher_disagreement_score":0.06154112,"about_ca_system_score_codex":0.00095496274,"about_ca_system_score_gemma":0.0009105999,"threshold_uncertainty_score":0.20587558},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005198841,0.0022127272,0.8564956,0.0034749834,0.0011734895,0.00046999153,0.0029777216,0.0007041474,0.12729244],"genre_scores_gemma":[0.23945637,0.006945904,0.39373565,0.0052114576,0.002369041,0.0034466807,0.010861277,0.000726974,0.3372467],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99437344,0.0030028073,0.00015720213,0.00082722114,0.0015145061,0.00012486338],"domain_scores_gemma":[0.9868232,0.0076231128,0.00030280178,0.0042415704,0.0008827823,0.0001265956],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.007256678,0.00064188207,0.0014294874,0.0012779569,0.00083594816,0.0023660688,0.0018472878,0.0009920015,0.047165968],"category_scores_gemma":[0.033948705,0.00081311085,0.00080447143,0.002195351,0.0011592772,0.003321312,0.001847106,0.0024464033,0.012655258],"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":[0.000055843197,0.00007949395,0.0017812222,0.00027136027,0.000064432235,0.000063730484,0.00018915666,0.002530011,0.00023333196,0.71114075,0.0694423,0.21414833],"study_design_scores_gemma":[0.000040409108,0.00006836569,0.0027175164,0.00016786577,0.00004089507,0.00032777188,0.00015332575,0.021464996,0.0005937458,0.8057793,0.16862597,0.000019845731],"about_ca_topic_score_codex":0.0009400935,"about_ca_topic_score_gemma":0.0023539192,"teacher_disagreement_score":0.9927433,"about_ca_system_score_codex":0.0009361971,"about_ca_system_score_gemma":0.0011893082,"threshold_uncertainty_score":0.15778583},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010245154,0.00037011126,0.99037725,0.000080030804,0.00017191628,0.00033882476,0.000307723,0.0003523472,0.0069773667],"genre_scores_gemma":[0.05009811,0.0010062644,0.89338404,0.0003500292,0.00037302208,0.0019117899,0.0010508305,0.00033666537,0.0514892],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9926543,0.0043594805,0.00031672066,0.00091445097,0.0015494152,0.0002054606],"domain_scores_gemma":[0.98885113,0.006201621,0.00028907924,0.0033512106,0.0011856173,0.00012133532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007416408,0.0012759569,0.0021727993,0.0012775358,0.0007985766,0.0013684742,0.003303832,0.0012815179,0.034811687],"category_scores_gemma":[0.026888782,0.0012043971,0.0018983533,0.0024687639,0.00082824327,0.0023531076,0.001976042,0.001942915,0.011873429],"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":[0.0003062279,0.00023563494,0.0018548323,0.00079611555,0.00027054534,0.00008158826,0.0003711455,0.015425842,0.0020842876,0.30444556,0.03185059,0.64227754],"study_design_scores_gemma":[0.00028550377,0.0005703267,0.004627846,0.000264927,0.00034541494,0.0005772606,0.00018273068,0.2481775,0.0037827145,0.59693605,0.14412637,0.00012334969],"about_ca_topic_score_codex":0.0017097929,"about_ca_topic_score_gemma":0.004818173,"teacher_disagreement_score":0.034811687,"about_ca_system_score_codex":0.00074847724,"about_ca_system_score_gemma":0.0014703226,"threshold_uncertainty_score":0.11645663},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93326235,0.0037424965,0.032700866,0.0064071375,0.0011607349,0.0038741468,0.0013129809,0.00020906144,0.017330183],"genre_scores_gemma":[0.9891802,0.0006307324,0.0045721317,0.0019175408,0.00024648235,0.0019120836,0.0003012414,0.000028120523,0.0012115624],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.69996375,0.27010152,0.009222477,0.006676727,0.012362287,0.0016732787],"domain_scores_gemma":[0.2803855,0.59787786,0.07490744,0.034153085,0.010714309,0.0019617823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17697093,0.0009460737,0.001548691,0.0007502239,0.0021374116,0.0030316762,0.0021916346,0.004594446,0.013269067],"category_scores_gemma":[0.37708277,0.000693386,0.0016844111,0.001264086,0.007060084,0.0037845767,0.00200124,0.0037727226,0.0020816638],"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":[0.14564015,0.0414817,0.25434768,0.016143687,0.00916591,0.0017923946,0.028334409,0.003491364,0.0054300874,0.041317176,0.022119094,0.43073636],"study_design_scores_gemma":[0.04130429,0.14013383,0.54923457,0.010758213,0.011769049,0.0016187961,0.018317465,0.030195067,0.024541209,0.09007098,0.08116873,0.0008878163],"about_ca_topic_score_codex":0.0011437268,"about_ca_topic_score_gemma":0.00069809036,"teacher_disagreement_score":0.17697093,"about_ca_system_score_codex":0.001314394,"about_ca_system_score_gemma":0.0014178501,"threshold_uncertainty_score":0.9359229},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99814916,0.000106927975,0.0002222922,0.000110270696,0.0000070810647,0.0000101837495,0.000072815696,0.0000013340018,0.0013199733],"genre_scores_gemma":[0.9997681,0.000032965578,0.00005693394,0.000013688939,0.0000030929639,0.000003704276,0.000050260987,0.000001012069,0.000070374525],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99765104,0.0012571772,0.00027549278,0.00018423077,0.0002529663,0.00037916514],"domain_scores_gemma":[0.96413124,0.014796735,0.015553989,0.0023593938,0.0014844523,0.0016741876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003726119,0.0001570382,0.00025392,0.0010785799,0.00078154216,0.0011982208,0.00019319216,0.00032222018,0.0034010008],"category_scores_gemma":[0.026249664,0.00013688316,0.00030416378,0.0011044476,0.0009056394,0.00069974683,0.0013170727,0.00062503264,0.00028863066],"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":[0.00008555437,0.00004488193,0.9957066,0.000013310009,0.00003245132,0.00003924607,0.0006730371,0.000084831765,0.00006666763,0.00015694776,0.000089671325,0.0030069037],"study_design_scores_gemma":[0.0000020580096,0.000028834478,0.99782974,0.00001982411,0.000012179828,0.000062767846,0.0014512208,0.00021504192,0.00007340958,0.000102137936,0.00019843338,0.000004342321],"about_ca_topic_score_codex":0.002888985,"about_ca_topic_score_gemma":0.0023962394,"teacher_disagreement_score":0.003726119,"about_ca_system_score_codex":0.00031876384,"about_ca_system_score_gemma":0.0002649192,"threshold_uncertainty_score":0.019705892},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019882675,0.0006377839,0.97306067,0.0017211514,0.00015153768,0.0001810867,0.00013800728,0.00025579802,0.003971313],"genre_scores_gemma":[0.40943235,0.0016734787,0.58014274,0.0015999847,0.0006723944,0.0015356835,0.0005625566,0.00028544528,0.004095412],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9243609,0.06207899,0.0018983054,0.005024337,0.0052994825,0.0013381056],"domain_scores_gemma":[0.8827135,0.08107825,0.0060955654,0.023670128,0.005558519,0.0008840414],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.063889734,0.001033686,0.0024328597,0.0021011662,0.001384852,0.0022213631,0.0037821971,0.003339958,0.005012396],"category_scores_gemma":[0.26290143,0.0015998122,0.00093717314,0.0041234163,0.003975992,0.006147632,0.005896393,0.0045318576,0.0019153657],"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":[0.00035000342,0.00017635687,0.0062844213,0.00067801034,0.00023042527,0.000088388544,0.0009394901,0.039169896,0.0010567334,0.6701987,0.006650192,0.27417752],"study_design_scores_gemma":[0.00013966166,0.00014634419,0.0031386076,0.0002128869,0.000078111065,0.00018526157,0.0002265832,0.10009874,0.0016811184,0.88785625,0.006185129,0.00005125244],"about_ca_topic_score_codex":0.0010768109,"about_ca_topic_score_gemma":0.00077371224,"teacher_disagreement_score":0.93611026,"about_ca_system_score_codex":0.0016278032,"about_ca_system_score_gemma":0.0018316872,"threshold_uncertainty_score":0.3378852},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020750837,0.0002999644,0.9777029,0.0002397624,0.000017399865,0.00007812668,0.000055996676,0.00013281826,0.0007222144],"genre_scores_gemma":[0.35250294,0.00033186894,0.6454574,0.00012182469,0.000089990885,0.0003015158,0.00019443019,0.00006484446,0.00093510904],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95211184,0.039872907,0.0011870693,0.0016312223,0.004589942,0.0006069512],"domain_scores_gemma":[0.85712767,0.11463007,0.0096103195,0.012771595,0.005410129,0.00045024516],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.034332246,0.00052141404,0.0018975675,0.0017744926,0.00081150467,0.001655728,0.002155572,0.0019483884,0.0020349738],"category_scores_gemma":[0.15061042,0.0006814373,0.0013411542,0.003911391,0.001431077,0.0016274329,0.0028447758,0.0018768777,0.00042584178],"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":[0.0005444247,0.00021893956,0.028348144,0.0005607272,0.0008902059,0.0009311008,0.0013307545,0.2780908,0.0031670819,0.31906885,0.003534102,0.3633149],"study_design_scores_gemma":[0.00008594077,0.00025051477,0.0059883287,0.0001791115,0.00016564742,0.00047990176,0.00016143058,0.84837705,0.0034529557,0.13601272,0.004775412,0.00007098269],"about_ca_topic_score_codex":0.0023010515,"about_ca_topic_score_gemma":0.001984111,"teacher_disagreement_score":0.9656677,"about_ca_system_score_codex":0.0008684666,"about_ca_system_score_gemma":0.0012641738,"threshold_uncertainty_score":0.18156844},"labels":[],"label_agreement":null},{"id":"W3097049086","doi":"10.1093/jssam/smaa016","title":"Targeting Key Survey Variables at the Unit Nonresponse Treatment Stage","year":2020,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Estimator; Non-response bias; Weighting; Missing data; Statistics; Propensity score matching; Computer science; Econometrics; Inverse probability weighting; Set (abstract data type); Mathematics; Medicine","score_opus":0.6424708043159415,"score_gpt":0.4784392389837912,"score_spread":0.1640315653321503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097049086","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030456113,0.0003371737,0.9629795,0.0010539995,0.00022841233,0.0016668602,0.0003884945,0.00021233999,0.0026770798],"genre_scores_gemma":[0.5502732,0.0005201657,0.43587494,0.0011106502,0.00024143948,0.0059976033,0.00072641793,0.00010143227,0.0051541314],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9643867,0.029897664,0.0010309702,0.001954475,0.0020505618,0.000679477],"domain_scores_gemma":[0.9640807,0.020430027,0.0044750846,0.007896169,0.0027356595,0.00038241394],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.034617614,0.00072104036,0.0015263467,0.001352248,0.0010679679,0.0014827529,0.00251941,0.0018146901,0.0075283386],"category_scores_gemma":[0.09535882,0.0004901005,0.0014916728,0.0030429214,0.0013762343,0.0016479613,0.0026393912,0.0025589583,0.001525198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071025704,0.0011693368,0.059109047,0.0015378107,0.00080013345,0.000267492,0.0016839061,0.03711893,0.0042279935,0.25310305,0.01307106,0.62720096],"study_design_scores_gemma":[0.00080670294,0.0019000245,0.06569655,0.00103821,0.00089194684,0.00031019753,0.0015179935,0.45784047,0.026197292,0.3909906,0.052622132,0.00018785028],"about_ca_topic_score_codex":0.0016687186,"about_ca_topic_score_gemma":0.001826222,"teacher_disagreement_score":0.9653824,"about_ca_system_score_codex":0.0011404016,"about_ca_system_score_gemma":0.0027114644,"threshold_uncertainty_score":0.18307763},"labels":[],"label_agreement":null},{"id":"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040106278,0.00036179385,0.9569389,0.00045622786,0.000036261874,0.00007855875,0.00020857855,0.00026817695,0.0015452628],"genre_scores_gemma":[0.7959887,0.000669566,0.19999908,0.0003255095,0.00015083297,0.000458483,0.0005287321,0.00017411938,0.0017049622],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97636163,0.017256048,0.0008266843,0.0025020144,0.0024380889,0.0006155503],"domain_scores_gemma":[0.88938934,0.09614007,0.0046142885,0.006838258,0.0022049793,0.00081319397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025830552,0.0010054925,0.0027238324,0.0025748916,0.00090857194,0.0021336307,0.0030311963,0.001902657,0.00725888],"category_scores_gemma":[0.16033907,0.0006380518,0.0022854155,0.0030407624,0.003179958,0.004957802,0.0034066818,0.0030923428,0.0006608281],"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":[0.0004602164,0.00028125677,0.081732325,0.0011217695,0.0015341167,0.0013496238,0.0016441579,0.10232454,0.0052680075,0.5627862,0.0035975776,0.23790026],"study_design_scores_gemma":[0.00010615518,0.00051754137,0.016173007,0.00015392258,0.00025965727,0.000518892,0.0003755529,0.37768957,0.002418543,0.59755427,0.004156966,0.00007601023],"about_ca_topic_score_codex":0.0015810408,"about_ca_topic_score_gemma":0.001090673,"teacher_disagreement_score":0.025830552,"about_ca_system_score_codex":0.000768428,"about_ca_system_score_gemma":0.0015968181,"threshold_uncertainty_score":0.13660663},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028068878,0.00031248672,0.97021824,0.00017676812,0.00006213921,0.000102754944,0.00019882232,0.00022995798,0.00062991574],"genre_scores_gemma":[0.60417426,0.0005621279,0.38860244,0.00024364385,0.0001906717,0.00066898146,0.000843701,0.00023698925,0.004477202],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98169553,0.013830492,0.0005680858,0.0016693238,0.0017903354,0.00044631472],"domain_scores_gemma":[0.91232973,0.06728059,0.006999478,0.008372805,0.004378361,0.0006390978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022965236,0.0007387629,0.0017839225,0.0028499705,0.00048311235,0.0013318857,0.0049013924,0.001393842,0.004723137],"category_scores_gemma":[0.10572776,0.00067936716,0.0021680116,0.0036381364,0.0018577069,0.0027363081,0.0022447438,0.0020351433,0.00089924375],"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":[0.00039862652,0.00018499214,0.0257683,0.000775402,0.0006685167,0.00094681646,0.0009854996,0.42632478,0.0024961724,0.39064604,0.004069245,0.14673556],"study_design_scores_gemma":[0.000033804143,0.000081810686,0.0031752621,0.00008123915,0.000051924922,0.00017977567,0.000103067185,0.9103381,0.00054963893,0.08350979,0.0018537593,0.000041874402],"about_ca_topic_score_codex":0.004784232,"about_ca_topic_score_gemma":0.002637889,"teacher_disagreement_score":0.022965236,"about_ca_system_score_codex":0.0011847471,"about_ca_system_score_gemma":0.0010781119,"threshold_uncertainty_score":0.121453226},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007235769,0.8550812,0.107236646,0.0036952642,0.0015600254,0.015200477,0.007273323,0.0009843382,0.0017330822],"genre_scores_gemma":[0.37525475,0.26860628,0.21773644,0.006084558,0.00081256777,0.12189703,0.007318487,0.0008025789,0.001487371],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.73651123,0.17563042,0.052864496,0.014031775,0.019392347,0.001569776],"domain_scores_gemma":[0.648477,0.29802415,0.02337365,0.018543674,0.010649747,0.0009317345],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24850069,0.0047780992,0.023624007,0.02433211,0.0014651547,0.0076588583,0.0065712123,0.004150087,0.008049787],"category_scores_gemma":[0.38689157,0.0029618065,0.069236875,0.018329069,0.00274391,0.0069720144,0.005517209,0.0039582057,0.00083281],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009497329,0.00003741506,0.0069168415,0.37030444,0.58924395,0.00016606228,0.00039180947,0.0015882653,0.00020908625,0.0022795503,0.0020521686,0.0258606],"study_design_scores_gemma":[0.0013182922,0.00049049564,0.0057261847,0.11672969,0.8481802,0.00022479708,0.00028133453,0.003724197,0.0005225508,0.009922634,0.012666375,0.00021327271],"about_ca_topic_score_codex":0.005280703,"about_ca_topic_score_gemma":0.0114477,"teacher_disagreement_score":0.24850069,"about_ca_system_score_codex":0.005627695,"about_ca_system_score_gemma":0.012292069,"threshold_uncertainty_score":0.9267324},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0065738126,0.00019354152,0.99242216,0.000043316526,0.000031064097,0.00014419123,0.00006841807,0.00010178691,0.00042172804],"genre_scores_gemma":[0.30729172,0.0010292691,0.6888175,0.00012676856,0.000091463444,0.0009870608,0.0004834989,0.00004114466,0.0011316763],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9884878,0.008445316,0.00036779203,0.00093873765,0.0014959826,0.00026442175],"domain_scores_gemma":[0.9901743,0.0062835696,0.00092598057,0.0011095612,0.001428327,0.000078236415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01070166,0.000725928,0.0013816522,0.0013436327,0.00040203577,0.00093801325,0.0013120815,0.00081734493,0.0016041243],"category_scores_gemma":[0.03481828,0.0003510778,0.001292074,0.0014908492,0.00082883623,0.0011964713,0.0009660416,0.00071793335,0.00039789075],"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":[0.00048873166,0.00018299109,0.052196097,0.001235531,0.00095691014,0.0007380592,0.0013338507,0.18386427,0.010132728,0.32011455,0.005009069,0.42374715],"study_design_scores_gemma":[0.00016229534,0.0006415488,0.017134268,0.0003792753,0.00051121565,0.0007584171,0.00033373872,0.8079476,0.010294484,0.14998306,0.011733378,0.000120660356],"about_ca_topic_score_codex":0.003321231,"about_ca_topic_score_gemma":0.002109461,"teacher_disagreement_score":0.01070166,"about_ca_system_score_codex":0.00076611753,"about_ca_system_score_gemma":0.0017510359,"threshold_uncertainty_score":0.056596458},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03392159,0.00009954282,0.9651189,0.00012031227,0.000013263746,0.00013767336,0.00010245329,0.00010803468,0.00037811464],"genre_scores_gemma":[0.4885344,0.00022516819,0.5074997,0.00016071401,0.00006873283,0.000666661,0.000544451,0.00008823207,0.002211996],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9757568,0.01898298,0.00042080387,0.0020769085,0.00212558,0.000636748],"domain_scores_gemma":[0.8971095,0.08610124,0.005587962,0.0061685774,0.0041475766,0.00088518375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02982697,0.000834037,0.0018428365,0.0025832301,0.00074452575,0.0016649544,0.0039853975,0.0016102784,0.0028887927],"category_scores_gemma":[0.08240901,0.0011171327,0.0026804032,0.0028787574,0.0023203602,0.0020476426,0.0024964213,0.0023045682,0.0002861657],"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":[0.00051610795,0.0003586232,0.026518533,0.0004318806,0.0008625203,0.00042132725,0.0011836598,0.61927,0.0022015672,0.2860402,0.0016950067,0.060500447],"study_design_scores_gemma":[0.0000420599,0.00009900101,0.003113625,0.000023401177,0.00005842447,0.00003558385,0.000060628383,0.95204455,0.00036124777,0.043668926,0.00045861874,0.000034064946],"about_ca_topic_score_codex":0.006337108,"about_ca_topic_score_gemma":0.0050706537,"teacher_disagreement_score":0.02982697,"about_ca_system_score_codex":0.0021816078,"about_ca_system_score_gemma":0.0018400766,"threshold_uncertainty_score":0.15774196},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002053552,0.00016196976,0.99623436,0.0003281917,0.00010267823,0.00026676018,0.0001434264,0.00020102941,0.000508092],"genre_scores_gemma":[0.050283786,0.00038133812,0.94376975,0.00060931005,0.0002463338,0.003365939,0.00033663097,0.00014495561,0.00086184224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7776044,0.1999312,0.0048812986,0.0077249096,0.008785894,0.0010723148],"domain_scores_gemma":[0.67371804,0.26633605,0.013702873,0.0360607,0.00914125,0.0010411496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15835005,0.002161428,0.0039987736,0.003263611,0.0019954655,0.002973302,0.005001568,0.004222277,0.011278499],"category_scores_gemma":[0.36234924,0.0014806371,0.0034042525,0.004875547,0.005033283,0.004716023,0.005865258,0.0052100946,0.0020802815],"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":[0.0008601201,0.00032375855,0.011030604,0.002061602,0.0018264623,0.0005764342,0.0030956075,0.032626156,0.00226629,0.6240699,0.010622075,0.310641],"study_design_scores_gemma":[0.00046996048,0.0008027132,0.0032389213,0.0006443438,0.000415155,0.00031730277,0.0003490825,0.106694095,0.00293954,0.86768234,0.016294882,0.00015161667],"about_ca_topic_score_codex":0.0009945527,"about_ca_topic_score_gemma":0.00091570057,"teacher_disagreement_score":0.15835005,"about_ca_system_score_codex":0.0013898589,"about_ca_system_score_gemma":0.0037091363,"threshold_uncertainty_score":0.83744514},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13812298,0.0003072917,0.8599229,0.00026865935,0.000042795087,0.00023660428,0.00011313791,0.00013296737,0.0008526585],"genre_scores_gemma":[0.7413165,0.00027202725,0.25536507,0.000090851456,0.00010047318,0.0008152412,0.00043203132,0.00007864653,0.0015291802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9586194,0.032335777,0.0010515264,0.004025891,0.0030716432,0.0008956818],"domain_scores_gemma":[0.622508,0.3387887,0.008181299,0.021062445,0.007950395,0.0015090761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037579987,0.00084286754,0.0026325353,0.0023123787,0.0026127035,0.0027288806,0.0036381814,0.0016685136,0.0021007464],"category_scores_gemma":[0.19898707,0.0015688146,0.0024240136,0.0032081783,0.0042216396,0.0044019707,0.0037646072,0.003017575,0.000199349],"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":[0.0016345761,0.0006162052,0.11579156,0.00061076763,0.0016649032,0.0005862005,0.0038622527,0.17440031,0.0022918778,0.56188595,0.00316618,0.1334891],"study_design_scores_gemma":[0.00009451792,0.00022178175,0.017362645,0.000055431854,0.00028649456,0.00015938959,0.0003942813,0.80975115,0.0009976155,0.16944116,0.0011420534,0.000093457034],"about_ca_topic_score_codex":0.0075559714,"about_ca_topic_score_gemma":0.008915077,"teacher_disagreement_score":0.037579987,"about_ca_system_score_codex":0.0022187277,"about_ca_system_score_gemma":0.003166557,"threshold_uncertainty_score":0.1987443},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011560959,0.000339234,0.98686314,0.00020952946,0.00003263858,0.0002544283,0.000045724322,0.00020753576,0.0004868466],"genre_scores_gemma":[0.17121677,0.00040743602,0.8260769,0.0002037764,0.000095384195,0.0011137136,0.00019872702,0.00007383263,0.00061347557],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.8009195,0.17973927,0.004451428,0.006017092,0.008103136,0.0007696092],"domain_scores_gemma":[0.5730622,0.3696542,0.0119748525,0.034447704,0.010354729,0.00050632993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.119217165,0.0017462316,0.0024355797,0.0031152733,0.00087128807,0.0018087012,0.0037777652,0.0026801722,0.0032795335],"category_scores_gemma":[0.34164917,0.0012039314,0.0017488552,0.0028577514,0.0022926433,0.0042514107,0.0036930495,0.0017536343,0.0013373361],"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":[0.0011617672,0.00054479163,0.020761522,0.002127021,0.0008004825,0.00019813645,0.0026550742,0.061602093,0.0053397575,0.11177833,0.002568785,0.7904622],"study_design_scores_gemma":[0.00050450343,0.0014982603,0.011705054,0.0005733385,0.00037454633,0.00040316608,0.00055074197,0.79618627,0.010789903,0.1689517,0.008262537,0.00020000622],"about_ca_topic_score_codex":0.00093739317,"about_ca_topic_score_gemma":0.00084010325,"teacher_disagreement_score":0.119217165,"about_ca_system_score_codex":0.00095645513,"about_ca_system_score_gemma":0.0016939008,"threshold_uncertainty_score":0.63048816},"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":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005319681,0.018468019,0.103469655,0.0012581169,0.0038861646,0.00020730868,0.0015951085,0.0019721396,0.8638238],"genre_scores_gemma":[0.030303245,0.009496546,0.037821416,0.00056510576,0.00036629368,0.00012534855,0.0015281433,0.00083569007,0.9189582],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99954385,0.000023477429,0.000013594835,0.0001110092,0.00027383905,0.000034202647],"domain_scores_gemma":[0.9998141,0.000032991375,0.000007605758,0.000049484086,0.00008213255,0.00001376764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035077284,0.00078041136,0.0008769112,0.001298358,0.0011207733,0.0018734041,0.00090986537,0.00078714296,0.06796897],"category_scores_gemma":[0.0007340694,0.000674743,0.00041745842,0.0016956086,0.00048138233,0.0014299211,0.0016260992,0.0015519556,0.04105444],"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":[0.00008704706,0.00005578508,0.00042494474,0.00095623836,0.0000337183,0.00020034442,0.00021182635,0.0011662227,0.070714235,0.094791636,0.24603237,0.58532566],"study_design_scores_gemma":[0.000006709069,0.000038893286,0.00079821463,0.00011625096,0.000016768956,0.0005706188,0.00007840231,0.0017232205,0.04247968,0.00993986,0.944212,0.000019308074],"about_ca_topic_score_codex":0.0010934576,"about_ca_topic_score_gemma":0.0036268116,"teacher_disagreement_score":0.06796897,"about_ca_system_score_codex":0.0008924451,"about_ca_system_score_gemma":0.0005989418,"threshold_uncertainty_score":0.22737885},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003069001,0.0011900745,0.9228089,0.00109285,0.0004907176,0.00067915086,0.0017114274,0.0008140408,0.06814389],"genre_scores_gemma":[0.19713828,0.006025539,0.5845567,0.0021522322,0.0016364905,0.0052673733,0.008518845,0.0011473,0.19355723],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965669,0.0018571625,0.00009146039,0.00064452377,0.00068974984,0.00015016127],"domain_scores_gemma":[0.99212885,0.0040181885,0.00023772936,0.0022805177,0.0011330539,0.00020165728],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043490524,0.0008942458,0.0011756675,0.002060508,0.0012595563,0.0019892154,0.0019498847,0.0009286189,0.039671816],"category_scores_gemma":[0.025822472,0.00050010177,0.0007277057,0.0029427232,0.0008809646,0.0027454372,0.0019682073,0.0015982982,0.01099071],"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":[0.00012171016,0.00008445809,0.001892654,0.00035809417,0.000060177448,0.000048179805,0.00023085541,0.013249446,0.00047123616,0.449741,0.105273224,0.42846897],"study_design_scores_gemma":[0.000072368726,0.000090117435,0.0015147019,0.00032247402,0.00007163135,0.00027831097,0.00029434505,0.10677336,0.0012470868,0.64645505,0.24284858,0.000032082695],"about_ca_topic_score_codex":0.0031121476,"about_ca_topic_score_gemma":0.005122234,"teacher_disagreement_score":0.039671816,"about_ca_system_score_codex":0.0013509446,"about_ca_system_score_gemma":0.0016408844,"threshold_uncertainty_score":0.1327154},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003965915,0.0034944464,0.006696364,0.25163335,0.20488201,0.0021181877,0.0037842088,0.0020811444,0.52134436],"genre_scores_gemma":[0.010972513,0.0012688613,0.0025136746,0.024805767,0.028142877,0.000878259,0.0015888724,0.0009390041,0.9288902],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97833055,0.0046030628,0.0010818999,0.0018273278,0.011976048,0.0021810587],"domain_scores_gemma":[0.8783582,0.013412055,0.0028857698,0.0074908626,0.088036954,0.0098161055],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014906673,0.0009652679,0.0013757723,0.0052357092,0.005911467,0.01103269,0.0027598331,0.00802042,0.4355052],"category_scores_gemma":[0.123186074,0.00051840796,0.001176176,0.0020730025,0.0020073643,0.0047441144,0.005027813,0.007945888,0.24715218],"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":[0.000032326883,0.000022969627,0.00016311448,0.00013968484,0.000006508235,0.00008665969,0.00022621336,0.00002208578,0.0003082093,0.0052813976,0.96919507,0.02451575],"study_design_scores_gemma":[0.000011371751,0.000010175594,0.00032298412,0.00013504566,0.000005765798,0.0000412327,0.00039206733,0.000064945765,0.00020747473,0.0028511474,0.9959468,0.00001106163],"about_ca_topic_score_codex":0.0022223177,"about_ca_topic_score_gemma":0.0035451252,"teacher_disagreement_score":0.5644948,"about_ca_system_score_codex":0.0036576735,"about_ca_system_score_gemma":0.01072296,"threshold_uncertainty_score":0.8051833},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038556028,0.0015840082,0.8845032,0.000642673,0.00069267704,0.00080229854,0.0009946713,0.0010833081,0.10584162],"genre_scores_gemma":[0.14404036,0.002830835,0.6645603,0.0011588959,0.0009761795,0.0035160026,0.0037118315,0.0010962645,0.17810932],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99549896,0.0023116502,0.00013373155,0.0007008097,0.0011851777,0.00016962175],"domain_scores_gemma":[0.9911141,0.0039058279,0.00021822116,0.0035231002,0.0010398416,0.00019898787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045672953,0.0011095755,0.0016490095,0.002226336,0.0011605092,0.0024712004,0.002014807,0.0010169768,0.065281674],"category_scores_gemma":[0.024375957,0.0008343669,0.0010493861,0.0026787922,0.0012539213,0.0023187525,0.0028669038,0.002299316,0.014556996],"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":[0.00019182415,0.00013347788,0.0023210084,0.00053414935,0.00009737338,0.00007957713,0.0003732034,0.0046873563,0.0008275865,0.39835396,0.067020655,0.5253798],"study_design_scores_gemma":[0.00018097252,0.0002974856,0.0026340676,0.00046155867,0.0001898883,0.0009145435,0.00030680647,0.060039055,0.0025647613,0.6022494,0.330108,0.000053525833],"about_ca_topic_score_codex":0.0013246023,"about_ca_topic_score_gemma":0.0032535815,"teacher_disagreement_score":0.065281674,"about_ca_system_score_codex":0.00089340046,"about_ca_system_score_gemma":0.001981832,"threshold_uncertainty_score":0.21838897},"labels":[],"label_agreement":null},{"id":"W4248615235","doi":"10.1093/jssam/smab047","title":"A Rescaling Bootstrap Approach For Imputed Survey Data","year":2021,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Imputation (statistics); Estimator; Statistics; Mathematics; Econometrics; Variance (accounting); Computer science; Missing data","score_opus":0.8566941241856907,"score_gpt":0.5528146051570141,"score_spread":0.3038795190286766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248615235","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002481619,0.00013821045,0.9968208,0.00005513504,0.000026896438,0.000027798456,0.000040137234,0.00017423416,0.00023519716],"genre_scores_gemma":[0.1884731,0.0004660548,0.8088207,0.00018921531,0.00018044308,0.0004274081,0.00043239837,0.00018020955,0.00083038537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9890282,0.0078977235,0.00041432423,0.00091416115,0.0015224355,0.00022309505],"domain_scores_gemma":[0.98704404,0.0077598304,0.00077469193,0.0026858295,0.00155455,0.00018096589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009453639,0.0006697754,0.0013438687,0.0023422674,0.0005600858,0.0007783429,0.0027040283,0.0010208436,0.0025156885],"category_scores_gemma":[0.042208258,0.00045764976,0.0010394611,0.0030210756,0.0010383663,0.0013121658,0.0018236196,0.0017605611,0.0007151063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029898007,0.00021905413,0.008560794,0.0005754995,0.000511213,0.0008226168,0.0007146913,0.16413228,0.008979416,0.1914281,0.0060956897,0.61766154],"study_design_scores_gemma":[0.00004976302,0.000120338394,0.0025737104,0.000083410516,0.0000686132,0.0003031907,0.00008599492,0.9018056,0.0033618787,0.08369855,0.007789481,0.000059443344],"about_ca_topic_score_codex":0.001068551,"about_ca_topic_score_gemma":0.0008008559,"teacher_disagreement_score":0.009453639,"about_ca_system_score_codex":0.00047084887,"about_ca_system_score_gemma":0.0006441947,"threshold_uncertainty_score":0.049996197},"labels":[],"label_agreement":null},{"id":"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030541841,0.0011738008,0.9086349,0.0010818196,0.00045836627,0.0007029502,0.0015532237,0.0007680119,0.08257272],"genre_scores_gemma":[0.18571572,0.005835827,0.57792526,0.0019232231,0.0013491639,0.0048500765,0.0072819944,0.0010145354,0.2141042],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99694663,0.0016696308,0.000079199446,0.00053272874,0.0006400364,0.00013182315],"domain_scores_gemma":[0.99371696,0.0031704959,0.00019173326,0.0018130785,0.00093898067,0.00016858517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003943863,0.000792139,0.0010184728,0.0019543308,0.0011811766,0.0017190835,0.0017655459,0.0008073047,0.03873023],"category_scores_gemma":[0.021880645,0.0004510513,0.0006272616,0.0027912026,0.0008145137,0.0023924774,0.0017783704,0.0014244803,0.01004668],"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":[0.00009849368,0.00007404457,0.0016610714,0.00030121047,0.000049099795,0.000044715252,0.00022534012,0.011507815,0.00042259254,0.4175889,0.10362698,0.4643997],"study_design_scores_gemma":[0.000067125606,0.00008580667,0.0015555586,0.00032052555,0.00006390685,0.00030220067,0.0003157143,0.09371464,0.0012852001,0.6208922,0.28136548,0.000031665466],"about_ca_topic_score_codex":0.0032252762,"about_ca_topic_score_gemma":0.005617774,"teacher_disagreement_score":0.03873023,"about_ca_system_score_codex":0.0012593642,"about_ca_system_score_gemma":0.0015521063,"threshold_uncertainty_score":0.12956554},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0027285884,0.00025849548,0.9857905,0.00020004647,0.00015855976,0.0007564168,0.0004353669,0.00030062598,0.009371387],"genre_scores_gemma":[0.12058058,0.0007504301,0.806124,0.000571626,0.00030371093,0.00358046,0.002196933,0.00032534398,0.06556696],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98757035,0.007946046,0.00037811536,0.0015782387,0.002028891,0.00049834943],"domain_scores_gemma":[0.9803919,0.00992366,0.00038788316,0.0069622262,0.0020292494,0.0003050507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011156621,0.0012092746,0.0020381652,0.0014077217,0.0011844018,0.0020261102,0.0036839617,0.0017106063,0.027462732],"category_scores_gemma":[0.038483586,0.0013337053,0.0017898038,0.0026793147,0.001321858,0.0029901338,0.0031730793,0.0026100755,0.007385047],"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":[0.0006226088,0.00032234512,0.003214081,0.0006881225,0.00018856427,0.00011206749,0.00075125595,0.013693302,0.002455716,0.5517406,0.0340161,0.39219525],"study_design_scores_gemma":[0.00048579826,0.00082050846,0.004346094,0.00027971133,0.00022642645,0.00058722484,0.00037845157,0.23597488,0.0047570453,0.6364842,0.11552009,0.00013959789],"about_ca_topic_score_codex":0.0024975818,"about_ca_topic_score_gemma":0.005042705,"teacher_disagreement_score":0.027462732,"about_ca_system_score_codex":0.0011300608,"about_ca_system_score_gemma":0.0027354925,"threshold_uncertainty_score":0.09187198},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006989157,0.9879292,0.005963025,0.0048333425,0.0005139557,0.000010332185,0.000017966628,0.000011051114,0.00065118587],"genre_scores_gemma":[0.0029019876,0.9876889,0.0060970853,0.0015314963,0.0015251737,0.000036906247,0.000021226566,0.000015667229,0.00018167449],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98876894,0.006253325,0.0008812758,0.0007238134,0.003193403,0.0001792691],"domain_scores_gemma":[0.9067904,0.07994926,0.001242801,0.0012961496,0.010214518,0.0005069061],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03140048,0.001153359,0.0028760254,0.009569979,0.0010062534,0.0026899623,0.002972496,0.0032670018,0.0016329134],"category_scores_gemma":[0.06074097,0.00092818006,0.0010027866,0.007911704,0.0072849696,0.005675793,0.0017711745,0.0065050735,0.00086890825],"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":[0.00008336763,0.00007041473,0.0005156083,0.01765761,0.00028146262,0.00016636176,0.000606765,0.0028625436,0.00023582665,0.22585846,0.04695926,0.7047024],"study_design_scores_gemma":[0.000037619528,0.00012204627,0.0018106613,0.026011284,0.00024804677,0.0005787086,0.00040824027,0.0026433514,0.0004658401,0.24691084,0.7206145,0.00014886135],"about_ca_topic_score_codex":0.010439809,"about_ca_topic_score_gemma":0.008012801,"teacher_disagreement_score":0.9685995,"about_ca_system_score_codex":0.0060262373,"about_ca_system_score_gemma":0.008279363,"threshold_uncertainty_score":0.1660636},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27806985,0.000046148296,0.71702766,0.00018335695,0.000037227215,0.0017490047,0.0002551186,0.0006573,0.001974238],"genre_scores_gemma":[0.79131556,0.000024861547,0.20545039,0.00014140045,0.000021022994,0.0017067279,0.00042247903,0.00006250442,0.00085499237],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97642267,0.015995713,0.0012581453,0.0031221735,0.0027008385,0.0005004764],"domain_scores_gemma":[0.93278146,0.04350198,0.0067882775,0.011319429,0.004896697,0.0007121276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033610523,0.0006356824,0.0007292659,0.0014142711,0.0007830644,0.0011627388,0.0017544709,0.0011758069,0.0015392049],"category_scores_gemma":[0.095752224,0.0005038696,0.0006921712,0.0010729255,0.001700036,0.0016402683,0.001818312,0.0012018472,0.0006468746],"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":[0.0020784084,0.0011517958,0.46439895,0.00050334574,0.0004954372,0.0001839231,0.007991171,0.028031534,0.018026777,0.029732859,0.004368402,0.44303736],"study_design_scores_gemma":[0.00020603437,0.0010858739,0.21813461,0.00017782491,0.0001510851,0.0005162684,0.0021597005,0.6865774,0.034569472,0.048563767,0.007672351,0.00018553981],"about_ca_topic_score_codex":0.0011978694,"about_ca_topic_score_gemma":0.0014361085,"teacher_disagreement_score":0.033610523,"about_ca_system_score_codex":0.0008917633,"about_ca_system_score_gemma":0.00088817003,"threshold_uncertainty_score":0.17775154},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00203174,0.000070275506,0.99746776,0.00007934656,0.000005658529,0.000036331316,0.000013813609,0.00003239186,0.00026279967],"genre_scores_gemma":[0.09819544,0.00035376367,0.89971715,0.00009030764,0.000060245355,0.0006503642,0.00008905087,0.00006642441,0.00077730574],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9711901,0.023367004,0.00074856565,0.0017627779,0.0024849363,0.00044647304],"domain_scores_gemma":[0.9619468,0.030338809,0.0027850554,0.0023539627,0.0021719302,0.0004034313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026922071,0.0011794391,0.0021678787,0.0019628485,0.00060002116,0.00152394,0.0024673657,0.0018912851,0.0020447683],"category_scores_gemma":[0.079620354,0.0011803994,0.0011632057,0.0018829366,0.0031625542,0.0039417488,0.0024696763,0.002080354,0.00046837228],"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":[0.00015293184,0.00009396238,0.0030275148,0.0003486581,0.000109229804,0.00006530719,0.00042977906,0.3162465,0.001739083,0.5504649,0.0013606171,0.12596148],"study_design_scores_gemma":[0.00006268603,0.0002704497,0.0010082896,0.000083789,0.000036920726,0.00005359366,0.00006358059,0.77866125,0.0012247588,0.21543662,0.003053206,0.000044878965],"about_ca_topic_score_codex":0.0013636156,"about_ca_topic_score_gemma":0.0009023899,"teacher_disagreement_score":0.026922071,"about_ca_system_score_codex":0.0015539645,"about_ca_system_score_gemma":0.00259327,"threshold_uncertainty_score":0.14237922},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05937816,0.00005954251,0.93813545,0.00024989995,0.000028253859,0.00021572286,0.00012447963,0.0010076618,0.000800904],"genre_scores_gemma":[0.6826236,0.0000570102,0.3147635,0.00031080403,0.000042849108,0.0004750033,0.00041936905,0.0000963786,0.0012114282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9857675,0.009568752,0.0005457145,0.002255163,0.0014738853,0.0003890213],"domain_scores_gemma":[0.9055822,0.06763903,0.0067899907,0.015660444,0.0035906427,0.0007377522],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020952577,0.0007688697,0.0013629697,0.0018420289,0.00080451433,0.0015413073,0.002732036,0.0016931753,0.0016974952],"category_scores_gemma":[0.08793039,0.0006376508,0.0012336306,0.0014798294,0.0017340604,0.002514491,0.0019821941,0.0019443395,0.0010046537],"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":[0.0010341823,0.0012306977,0.18801478,0.00085611147,0.00059344387,0.00045744702,0.0027655442,0.17189522,0.018188933,0.07804708,0.008414742,0.52850175],"study_design_scores_gemma":[0.000048178063,0.00016190388,0.010960666,0.00005457463,0.000034375436,0.00026979,0.00027730616,0.9274839,0.0057612974,0.05334779,0.0015546235,0.000045581328],"about_ca_topic_score_codex":0.0011516156,"about_ca_topic_score_gemma":0.0016554814,"teacher_disagreement_score":0.9790474,"about_ca_system_score_codex":0.0008771941,"about_ca_system_score_gemma":0.001132992,"threshold_uncertainty_score":0.11080915},"labels":[],"label_agreement":null},{"id":"W4309622736","doi":"10.1093/jssam/smac027","title":"Jackknife Bias-Corrected Generalized Regression Estimator in Survey Sampling","year":2022,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Jackknife resampling; Estimator; Statistics; Mathematics; Mean squared error; Bias of an estimator; Population; Minimum-variance unbiased estimator; Sample size determination; Sample (material); Variance (accounting); Econometrics","score_opus":0.7039901809482423,"score_gpt":0.5070651107249131,"score_spread":0.19692507022332917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309622736","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008054975,0.00025303077,0.9908744,0.00006606098,0.000029747409,0.00005153217,0.00004990075,0.00020971608,0.00041072103],"genre_scores_gemma":[0.27570164,0.00039298434,0.7210756,0.00021840833,0.00007814714,0.00038488396,0.00030692943,0.0001651136,0.0016761806],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9709872,0.0241124,0.0005299925,0.0016634815,0.0022652699,0.00044162298],"domain_scores_gemma":[0.9586712,0.027835423,0.003977719,0.0051900945,0.0039849393,0.00034063382],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025143238,0.00086615974,0.0018622148,0.001852541,0.00053721596,0.00082272926,0.0028289063,0.001548239,0.001866535],"category_scores_gemma":[0.10219341,0.00060575345,0.00096964336,0.002518096,0.0012676724,0.0017155943,0.0016924604,0.0015517961,0.00066547876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045576648,0.00017710867,0.026789732,0.0007083539,0.00083978433,0.0003889695,0.00060803245,0.49888888,0.0036967874,0.16641061,0.006494174,0.29454184],"study_design_scores_gemma":[0.00009805144,0.00023809339,0.0055444627,0.00019769135,0.00011979374,0.00036755283,0.0001260768,0.9083502,0.0035861123,0.07462406,0.0066636326,0.00008412466],"about_ca_topic_score_codex":0.004361883,"about_ca_topic_score_gemma":0.003593879,"teacher_disagreement_score":0.025143238,"about_ca_system_score_codex":0.0009220726,"about_ca_system_score_gemma":0.0014514184,"threshold_uncertainty_score":0.1329717},"labels":[],"label_agreement":null},{"id":"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014507335,0.021078594,0.7951272,0.0038817092,0.0010124203,0.000329882,0.0012889734,0.0011379215,0.17469248],"genre_scores_gemma":[0.06371508,0.039533116,0.46640623,0.003001822,0.0022219452,0.0031829912,0.0030892987,0.0013595286,0.41748995],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99544287,0.0027243167,0.00019363321,0.00042319729,0.0011267291,0.00008916209],"domain_scores_gemma":[0.9882465,0.0085685365,0.00021442627,0.0017518245,0.0011062177,0.000112499125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005218534,0.0011835599,0.0021747355,0.0024033617,0.0009128412,0.0032115227,0.0012208901,0.0016346953,0.052201573],"category_scores_gemma":[0.022640392,0.0011480657,0.0006574738,0.004623212,0.0021442745,0.0026667425,0.0014269325,0.0024624236,0.020344969],"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":[0.000021848806,0.00004574065,0.0007222267,0.000631311,0.000039624094,0.00005591337,0.00037824616,0.0029683022,0.00025108294,0.39446276,0.1090365,0.4913864],"study_design_scores_gemma":[0.000025283649,0.000048544676,0.0013058092,0.00064575364,0.00004845462,0.00029713463,0.00023802549,0.013988038,0.00036432507,0.61977667,0.36323282,0.000029160672],"about_ca_topic_score_codex":0.0031642006,"about_ca_topic_score_gemma":0.004683029,"teacher_disagreement_score":0.052201573,"about_ca_system_score_codex":0.001401621,"about_ca_system_score_gemma":0.0020025412,"threshold_uncertainty_score":0.17463166},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011517487,0.00009987331,0.9876353,0.00003134969,0.000015957614,0.00005432649,0.00003877932,0.00009590562,0.0005109462],"genre_scores_gemma":[0.48031387,0.00022989584,0.5169588,0.000103553015,0.000058295813,0.00035423794,0.0002853231,0.000074453055,0.0016215388],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.992366,0.004996612,0.00022000312,0.000812803,0.001338805,0.00026568942],"domain_scores_gemma":[0.9869654,0.0076494543,0.0010058787,0.0015758406,0.0026604766,0.00014298833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008503174,0.00051324104,0.0009959888,0.0017168688,0.00044476625,0.0008171257,0.0015502837,0.00064243324,0.0015299954],"category_scores_gemma":[0.02927699,0.00047818146,0.00084755407,0.0019690017,0.0011239611,0.0008395492,0.0013928972,0.0008448919,0.0003302484],"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":[0.000546034,0.00010762635,0.015241716,0.0003814614,0.00039748754,0.00017936775,0.00050462177,0.45740333,0.0071767317,0.28348076,0.0025482785,0.23203264],"study_design_scores_gemma":[0.000029821565,0.000115287985,0.0027338588,0.000041952317,0.0000507325,0.000055646102,0.000043936187,0.9362986,0.0027513884,0.05566699,0.0021842418,0.000027609229],"about_ca_topic_score_codex":0.004815341,"about_ca_topic_score_gemma":0.0030195222,"teacher_disagreement_score":0.008503174,"about_ca_system_score_codex":0.0012075607,"about_ca_system_score_gemma":0.0015817815,"threshold_uncertainty_score":0.04496962},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00442998,0.00025146085,0.99427915,0.00010916894,0.000028521037,0.000016674676,0.00007350584,0.000043648026,0.00076788233],"genre_scores_gemma":[0.3755412,0.0023216293,0.6169564,0.00035115448,0.0004031473,0.00040936985,0.0007271168,0.00009353757,0.0031963987],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99654824,0.0019525081,0.0001566451,0.00071812794,0.00052097626,0.000103481005],"domain_scores_gemma":[0.9810812,0.01459982,0.0010746481,0.0021535547,0.00096066715,0.00013014252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008155307,0.0006695945,0.0012164534,0.0014472544,0.00046423983,0.0013424059,0.0017002611,0.0009332587,0.0027382388],"category_scores_gemma":[0.038617764,0.00036658955,0.00088191574,0.0014345578,0.0017777898,0.0036670102,0.00230229,0.0017605049,0.00048106306],"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":[0.000095074705,0.00005281691,0.01050233,0.00043881132,0.0002036463,0.00022080228,0.00049664476,0.050755173,0.003517325,0.7802948,0.0019503832,0.15147215],"study_design_scores_gemma":[0.000029091132,0.00027592108,0.0048447507,0.00022607807,0.00013243813,0.0005624218,0.0001593033,0.44807118,0.0040544565,0.5300399,0.01151328,0.00009112675],"about_ca_topic_score_codex":0.00063779484,"about_ca_topic_score_gemma":0.0006476133,"teacher_disagreement_score":0.008155307,"about_ca_system_score_codex":0.0005378169,"about_ca_system_score_gemma":0.0011451937,"threshold_uncertainty_score":0.04312986},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006808323,0.00018274039,0.99224526,0.000085262975,0.00003464334,0.000042588676,0.00007024821,0.00009664667,0.00043430546],"genre_scores_gemma":[0.20784228,0.00053446554,0.78850824,0.00020917038,0.00021417403,0.00029094616,0.00044070638,0.00006641259,0.0018936362],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9950671,0.0029054643,0.00020972056,0.00074004236,0.00093011075,0.00014750578],"domain_scores_gemma":[0.9880762,0.0073801833,0.0011928274,0.001326285,0.0018565789,0.00016790691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009717222,0.00052316795,0.00127847,0.0021187377,0.00027834048,0.0011170141,0.0018036419,0.0010418652,0.0021611988],"category_scores_gemma":[0.034166627,0.00037390858,0.00085522607,0.0017921304,0.0007556951,0.0024393778,0.0015753425,0.0012374888,0.00056953053],"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":[0.00036874026,0.00021823378,0.025495807,0.0008563761,0.00042981576,0.00021463863,0.0004712218,0.1688622,0.011705945,0.269793,0.00640902,0.51517504],"study_design_scores_gemma":[0.00010009522,0.00035573993,0.008122929,0.00011843175,0.00015115412,0.00031928215,0.00007237503,0.91364545,0.0047861184,0.063309,0.008930414,0.000089044705],"about_ca_topic_score_codex":0.00075617555,"about_ca_topic_score_gemma":0.0009430903,"teacher_disagreement_score":0.009717222,"about_ca_system_score_codex":0.0005750969,"about_ca_system_score_gemma":0.0012787294,"threshold_uncertainty_score":0.05139023},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008003355,0.00031887303,0.9912144,0.000029592966,0.000020465865,0.000020145806,0.00001665233,0.0000922992,0.00028414192],"genre_scores_gemma":[0.3135962,0.0012351598,0.68275833,0.00008796779,0.0002231018,0.0001883788,0.00019977691,0.00006980014,0.0016412316],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99729055,0.0014931775,0.00016040767,0.00048411076,0.00047892702,0.00009293198],"domain_scores_gemma":[0.9916087,0.006235891,0.00055094593,0.0005855983,0.00093826366,0.00008064595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007266241,0.0007879313,0.0011516392,0.0016130105,0.00020340408,0.00092193106,0.0012632416,0.00089353207,0.0009279665],"category_scores_gemma":[0.022045027,0.00044061444,0.0010758712,0.0017606163,0.0005879343,0.0025395574,0.0010909089,0.0008383097,0.0002545335],"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":[0.0003784391,0.00017555735,0.01071297,0.00052677677,0.0005110618,0.0002978813,0.00026557306,0.30924165,0.012251152,0.06968869,0.0012053258,0.5947449],"study_design_scores_gemma":[0.000021472544,0.00020832189,0.001423661,0.000018252698,0.00007442233,0.00019573241,0.00002944009,0.9840497,0.0026922051,0.009832227,0.0014199865,0.000034660072],"about_ca_topic_score_codex":0.0008263072,"about_ca_topic_score_gemma":0.0007505357,"teacher_disagreement_score":0.007266241,"about_ca_system_score_codex":0.00027937282,"about_ca_system_score_gemma":0.00057429716,"threshold_uncertainty_score":0.03842801},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35537434,0.00049212505,0.63348716,0.0016652409,0.00029997513,0.0017541863,0.00063488743,0.00031953544,0.0059726],"genre_scores_gemma":[0.90701234,0.000096716634,0.08949926,0.0004460583,0.000098125376,0.0020577977,0.0002443213,0.000035983543,0.0005093594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.6916833,0.2731602,0.008069917,0.012178688,0.013020888,0.0018869755],"domain_scores_gemma":[0.057262987,0.8913405,0.020921066,0.024830926,0.0051845554,0.00045999227],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.29478058,0.0010714552,0.0020985892,0.002503887,0.0016088753,0.0036957578,0.0037146448,0.0044257278,0.006409804],"category_scores_gemma":[0.68857557,0.0012548855,0.0024392097,0.0022469019,0.0095084775,0.007932161,0.0055257706,0.0041786036,0.0005912165],"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":[0.011884014,0.003509834,0.30875444,0.0032970784,0.0045119384,0.0006571754,0.008782383,0.05815852,0.0063103517,0.3385517,0.003940391,0.2516422],"study_design_scores_gemma":[0.003525865,0.01144435,0.09470897,0.0013801377,0.001864497,0.0008419412,0.003587746,0.4608632,0.015057455,0.3982119,0.007975655,0.00053829665],"about_ca_topic_score_codex":0.0012708609,"about_ca_topic_score_gemma":0.00073761586,"teacher_disagreement_score":0.7052194,"about_ca_system_score_codex":0.001840469,"about_ca_system_score_gemma":0.0015436478,"threshold_uncertainty_score":0.8696611},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19628075,0.21857378,0.3047719,0.18818976,0.008405568,0.004612133,0.0028963888,0.00042253075,0.07584721],"genre_scores_gemma":[0.7631666,0.04567143,0.16466956,0.0170972,0.00093928754,0.005494571,0.0013875396,0.00022518994,0.001348556],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.73980784,0.15707521,0.049028102,0.014050827,0.035410553,0.004627429],"domain_scores_gemma":[0.33869344,0.54258156,0.022136293,0.030476213,0.062096745,0.0040157945],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.36064035,0.00081431697,0.0023565297,0.009599867,0.004657059,0.012258821,0.0049137687,0.004003777,0.006230636],"category_scores_gemma":[0.4504898,0.0009689175,0.0034166735,0.009388527,0.010134635,0.012028627,0.017867088,0.0048888493,0.00075986533],"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":[0.0007927688,0.00027339256,0.04789211,0.03741281,0.0014007934,0.0003476839,0.113596514,0.0020461625,0.0011255837,0.14904612,0.011922561,0.6341435],"study_design_scores_gemma":[0.00030172637,0.0013796675,0.08267608,0.20063227,0.0033432723,0.0011537634,0.22617973,0.0076638963,0.003932911,0.21670856,0.25565818,0.00036995058],"about_ca_topic_score_codex":0.0052060946,"about_ca_topic_score_gemma":0.004793108,"teacher_disagreement_score":0.63935965,"about_ca_system_score_codex":0.01008196,"about_ca_system_score_gemma":0.04045569,"threshold_uncertainty_score":0.7884443},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8175158,0.000041496027,0.17496538,0.00016631195,0.000067131274,0.0018777889,0.0013405383,0.0006759753,0.0033495422],"genre_scores_gemma":[0.95542246,0.000020237045,0.040186897,0.0001477711,0.000014076065,0.0013600115,0.0011737933,0.000048997877,0.0016257839],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9874916,0.007991693,0.0006649343,0.0016387398,0.0016517959,0.0005611881],"domain_scores_gemma":[0.9478978,0.035470158,0.0036348708,0.0069466373,0.005329301,0.00072118023],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014545151,0.00045758236,0.00059670064,0.0007037249,0.0004093621,0.00091342104,0.001124292,0.0010578305,0.0022418245],"category_scores_gemma":[0.05279647,0.00033998856,0.00059204514,0.0005702274,0.000500661,0.0011310504,0.0008346754,0.0010180396,0.0015948527],"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":[0.0022861317,0.0037586875,0.6993363,0.00084283145,0.00049803517,0.00022275954,0.00602674,0.024222786,0.03328557,0.0071667936,0.010923648,0.21142977],"study_design_scores_gemma":[0.00016271442,0.0023665049,0.50644284,0.0001706324,0.00024303248,0.00043323694,0.0022511592,0.45442006,0.0195056,0.00680122,0.0070587606,0.00014417239],"about_ca_topic_score_codex":0.001229708,"about_ca_topic_score_gemma":0.0020538736,"teacher_disagreement_score":0.98545486,"about_ca_system_score_codex":0.0005942913,"about_ca_system_score_gemma":0.00084152777,"threshold_uncertainty_score":0.07692307},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0080046225,0.00011696768,0.9909479,0.00005969022,0.000018323139,0.00009112389,0.00004054766,0.000114578834,0.00060625264],"genre_scores_gemma":[0.3647585,0.00056905596,0.63034165,0.00017945528,0.00012321929,0.0007600771,0.00042482713,0.00012182987,0.002721354],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9940084,0.0027339528,0.00026630942,0.0009689548,0.0017530519,0.00026935813],"domain_scores_gemma":[0.9863564,0.007959962,0.0008724812,0.0018323807,0.002620737,0.0003581074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007901738,0.0010065895,0.0012901778,0.0023541567,0.00072897313,0.0013100441,0.0028966626,0.0012700509,0.0026714862],"category_scores_gemma":[0.023412606,0.00061207137,0.0015572231,0.002584673,0.0015190165,0.00283399,0.0018635927,0.0016829066,0.0006560567],"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":[0.0005718264,0.00031182976,0.016099164,0.00063569663,0.00023923266,0.0004682655,0.00097539416,0.29215413,0.016323114,0.3050413,0.005393999,0.361786],"study_design_scores_gemma":[0.000052973483,0.0002323678,0.0018262934,0.00003815115,0.000046207508,0.00034934672,0.00009362989,0.94913274,0.003674083,0.04041155,0.004081292,0.00006124835],"about_ca_topic_score_codex":0.0025559852,"about_ca_topic_score_gemma":0.0018915561,"teacher_disagreement_score":0.007901738,"about_ca_system_score_codex":0.0010928717,"about_ca_system_score_gemma":0.0014398873,"threshold_uncertainty_score":0.041788936},"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":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054900385,0.00038863154,0.9137138,0.0011315604,0.00051682134,0.017771937,0.0002539166,0.0009770866,0.010345959],"genre_scores_gemma":[0.28569108,0.00042706096,0.65518606,0.0020198207,0.00046473468,0.05084387,0.00024810137,0.00025708447,0.004862203],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.75509787,0.21867302,0.0048532705,0.007800931,0.01170239,0.0018726233],"domain_scores_gemma":[0.55474824,0.39727935,0.009241585,0.030651402,0.0072378125,0.00084167975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13896744,0.001280115,0.001977109,0.0024886606,0.0029521147,0.0024946136,0.0034505608,0.0032034349,0.011919042],"category_scores_gemma":[0.2903016,0.0011598185,0.0011791021,0.002409996,0.0040643797,0.0031998008,0.0038671347,0.0035719227,0.0024244932],"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":[0.0038249267,0.0051279985,0.011040014,0.0023855448,0.00042349868,0.00038720036,0.026122047,0.008589236,0.009413932,0.1012111,0.011527616,0.8199468],"study_design_scores_gemma":[0.008801187,0.028957821,0.0299953,0.003720487,0.0008784965,0.001575666,0.01345905,0.12948266,0.0649395,0.48743573,0.22989659,0.0008574532],"about_ca_topic_score_codex":0.0008510513,"about_ca_topic_score_gemma":0.00084610365,"teacher_disagreement_score":0.13896744,"about_ca_system_score_codex":0.002638494,"about_ca_system_score_gemma":0.0025238395,"threshold_uncertainty_score":0.73493886},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.50540155,0.00039262985,0.48269343,0.0016953322,0.00017857102,0.000999712,0.0007256567,0.0030996122,0.004813539],"genre_scores_gemma":[0.86376,0.00007841765,0.13278778,0.00079901755,0.00007897904,0.00041310038,0.00086720457,0.00010357203,0.0011119719],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9816155,0.011581564,0.00077291066,0.0035128314,0.0019848263,0.00053238904],"domain_scores_gemma":[0.87540025,0.07179179,0.011070105,0.031505384,0.009208687,0.0010237646],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0215671,0.00094506826,0.0015031383,0.0013146456,0.0012249477,0.0018223354,0.0027031153,0.0025121912,0.001200145],"category_scores_gemma":[0.108944,0.00052730273,0.00096831855,0.0012568401,0.0017582054,0.0027799204,0.0016905369,0.0024636574,0.0010810235],"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":[0.002532707,0.0022314952,0.3387352,0.000903625,0.00093851,0.00036952307,0.0019350753,0.20735878,0.012019103,0.02168609,0.021416256,0.38987365],"study_design_scores_gemma":[0.0001596457,0.00048217885,0.024600567,0.00009164831,0.00007076659,0.00029121857,0.00029665977,0.9431656,0.00670586,0.02161233,0.002466427,0.00005710209],"about_ca_topic_score_codex":0.0022463794,"about_ca_topic_score_gemma":0.0030520237,"teacher_disagreement_score":0.9784329,"about_ca_system_score_codex":0.0012457998,"about_ca_system_score_gemma":0.0018769081,"threshold_uncertainty_score":0.11405915},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16122137,0.0005417898,0.826385,0.0026841997,0.0006011636,0.0033279276,0.0010173358,0.0005193781,0.0037018044],"genre_scores_gemma":[0.7216207,0.0004776594,0.2507594,0.0014028357,0.0007641428,0.010805563,0.0011663066,0.00010703446,0.012896387],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.73931706,0.23141178,0.004175952,0.014648971,0.006514887,0.0039313463],"domain_scores_gemma":[0.4778482,0.44556695,0.033444837,0.030832576,0.009806951,0.0025004582],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22455886,0.003055287,0.005131659,0.0038071917,0.0021131418,0.004029214,0.005901427,0.0072068735,0.0315718],"category_scores_gemma":[0.24496028,0.002040776,0.004470538,0.0030473655,0.009736697,0.006438929,0.004324183,0.0067747068,0.003750762],"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":[0.007020745,0.0017620826,0.046927013,0.0016299048,0.0025792161,0.0011108029,0.0064980704,0.11646701,0.0016212497,0.71509475,0.008349483,0.09093964],"study_design_scores_gemma":[0.0020961468,0.0052276812,0.008151793,0.0005292681,0.000656694,0.0004921064,0.0011194492,0.68143016,0.0014779111,0.29281417,0.0056777066,0.0003269428],"about_ca_topic_score_codex":0.0023021891,"about_ca_topic_score_gemma":0.0015133186,"teacher_disagreement_score":0.22455886,"about_ca_system_score_codex":0.0025532856,"about_ca_system_score_gemma":0.002609929,"threshold_uncertainty_score":0.956257},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017738278,0.000056514124,0.9977969,0.00004324337,0.0000151623435,0.000034218006,0.000027349226,0.000039558032,0.00021323672],"genre_scores_gemma":[0.15574917,0.00027246683,0.84151596,0.0001267474,0.000062835774,0.00068173086,0.00029641503,0.000048671904,0.0012459656],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98753834,0.010416624,0.00026100973,0.00074468047,0.0009029167,0.0001363671],"domain_scores_gemma":[0.9702683,0.021710465,0.001911045,0.0037071067,0.0021482923,0.0002548738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017642679,0.0006225019,0.0010230727,0.0011192968,0.00043187308,0.00091234635,0.0015691746,0.0010858652,0.0029610025],"category_scores_gemma":[0.038013272,0.0004813397,0.0012455175,0.0011198343,0.0011405449,0.0011589631,0.0015435192,0.0013342795,0.0006060506],"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":[0.00033480726,0.00016070416,0.0058411835,0.00055593596,0.00029398344,0.00013973689,0.00045286288,0.48142576,0.003095804,0.34123224,0.0030413957,0.16342556],"study_design_scores_gemma":[0.000044441607,0.00025160314,0.0007522318,0.000056742676,0.00003492739,0.00016018238,0.000060404745,0.90282124,0.0015606977,0.08941265,0.0048137554,0.000031118583],"about_ca_topic_score_codex":0.0003044693,"about_ca_topic_score_gemma":0.00035371567,"teacher_disagreement_score":0.017642679,"about_ca_system_score_codex":0.0005975654,"about_ca_system_score_gemma":0.00080647663,"threshold_uncertainty_score":0.093304515},"labels":[],"label_agreement":null},{"id":"W4392712152","doi":"10.1093/jssam/smae002","title":"Estimation of a Population Total Under Nonresponse Using Follow-up","year":2024,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Statistics Canada","funders":"","keywords":"Estimation; Statistics; Econometrics; Computer science; Population; Mathematics; Medicine; Environmental health; Economics","score_opus":0.554927493029936,"score_gpt":0.5121732745467844,"score_spread":0.04275421848315164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392712152","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062339727,0.0001992264,0.93536335,0.00022638866,0.000030490968,0.00032893397,0.00014211911,0.00015712457,0.0012125608],"genre_scores_gemma":[0.6120263,0.00034236495,0.38306373,0.00026770166,0.00007309697,0.0013989214,0.00061623985,0.000047240752,0.0021644114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9753203,0.020113945,0.00064778194,0.0016013907,0.002034655,0.00028197074],"domain_scores_gemma":[0.94258183,0.041599844,0.005178969,0.0073068053,0.0029893355,0.00034319787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03570823,0.00056815334,0.0013860533,0.0029143323,0.00048915163,0.0010571651,0.0019946517,0.0009670279,0.0024173614],"category_scores_gemma":[0.10983529,0.0004771174,0.00094827206,0.0025106943,0.00086526095,0.0019657088,0.0019184063,0.0009622602,0.00033721342],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004420873,0.0006067135,0.08236342,0.00073918153,0.0009976077,0.00016086812,0.0016538259,0.087262444,0.002300905,0.105759144,0.0026106841,0.7151032],"study_design_scores_gemma":[0.00039779063,0.0020847162,0.08719757,0.00044877248,0.00076779036,0.00036931006,0.0009956377,0.6739724,0.0126343435,0.20438465,0.016593942,0.0001529985],"about_ca_topic_score_codex":0.0013252376,"about_ca_topic_score_gemma":0.0014471263,"teacher_disagreement_score":0.03570823,"about_ca_system_score_codex":0.0008023783,"about_ca_system_score_gemma":0.0011624979,"threshold_uncertainty_score":0.18884546},"labels":[],"label_agreement":null},{"id":"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97872704,0.00046027548,0.011463841,0.0021226732,0.00012403431,0.0033121447,0.00068732555,0.000054240507,0.0030484577],"genre_scores_gemma":[0.9812067,0.00018011093,0.012139492,0.0015036775,0.000060300903,0.003525283,0.00040362912,0.000053073145,0.000927508],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.83491313,0.13732962,0.005088446,0.0074769845,0.009854474,0.005337255],"domain_scores_gemma":[0.8463749,0.08383139,0.02004641,0.02454922,0.01798155,0.007216597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16095366,0.0007653878,0.00074612605,0.0012807229,0.0038857313,0.0024382805,0.0032282947,0.001462752,0.0029154713],"category_scores_gemma":[0.25426868,0.0010407293,0.0012121345,0.0019732257,0.003291044,0.0022524258,0.005064542,0.0016869074,0.00076176086],"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":[0.0005886676,0.0004653721,0.9240509,0.00026981486,0.00040260464,0.0003196118,0.034521434,0.0004420929,0.0005677411,0.0018932004,0.0027238217,0.033754725],"study_design_scores_gemma":[0.00036164853,0.0025313196,0.94051874,0.00082097505,0.00040039528,0.0005970468,0.034042973,0.008616953,0.001375207,0.0017840376,0.008822304,0.00012840697],"about_ca_topic_score_codex":0.086681336,"about_ca_topic_score_gemma":0.17469496,"teacher_disagreement_score":0.16095366,"about_ca_system_score_codex":0.0035781157,"about_ca_system_score_gemma":0.009160728,"threshold_uncertainty_score":0.85121447},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97872704,0.00046027548,0.011463841,0.0021226732,0.00012403431,0.0033121447,0.00068732555,0.000054240507,0.0030484577],"genre_scores_gemma":[0.9812067,0.00018011093,0.012139492,0.0015036775,0.000060300903,0.003525283,0.00040362912,0.000053073145,0.000927508],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.83491313,0.13732962,0.005088446,0.0074769845,0.009854474,0.005337255],"domain_scores_gemma":[0.8463749,0.08383139,0.02004641,0.02454922,0.01798155,0.007216597],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.16095366,0.0007653878,0.00074612605,0.0012807229,0.0038857313,0.0024382805,0.0032282947,0.001462752,0.0029154713],"category_scores_gemma":[0.25426868,0.0010407293,0.0012121345,0.0019732257,0.003291044,0.0022524258,0.005064542,0.0016869074,0.00076176086],"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":[0.0005886676,0.0004653721,0.9240509,0.00026981486,0.00040260464,0.0003196118,0.034521434,0.0004420929,0.0005677411,0.0018932004,0.0027238217,0.033754725],"study_design_scores_gemma":[0.00036164853,0.0025313196,0.94051874,0.00082097505,0.00040039528,0.0005970468,0.034042973,0.008616953,0.001375207,0.0017840376,0.008822304,0.00012840697],"about_ca_topic_score_codex":0.086681336,"about_ca_topic_score_gemma":0.17469496,"teacher_disagreement_score":0.83904636,"about_ca_system_score_codex":0.0035781157,"about_ca_system_score_gemma":0.009160728,"threshold_uncertainty_score":0.85121447},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021654216,0.000057648173,0.99747247,0.000019349629,0.000018013234,0.000061625906,0.000030048623,0.00010899317,0.00006645846],"genre_scores_gemma":[0.039576534,0.00012265093,0.9589919,0.000046777743,0.000063894746,0.00045145614,0.00016414448,0.00007480496,0.00050785457],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.97124743,0.021256747,0.0013112545,0.0028832143,0.0028645142,0.00043682105],"domain_scores_gemma":[0.89891016,0.07009576,0.0032369988,0.019069463,0.007988589,0.0006989854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06192979,0.0011367064,0.0030008815,0.0032700235,0.0019263192,0.0015451103,0.005430177,0.0026210868,0.0023189245],"category_scores_gemma":[0.13304935,0.0013349532,0.0029252127,0.0036334312,0.003107194,0.0034404458,0.002481593,0.0037767822,0.00064037985],"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":[0.0011943639,0.0004085823,0.007596185,0.0006475639,0.0009723932,0.00019268043,0.0016980192,0.23645195,0.013929033,0.17496543,0.0034573402,0.5584864],"study_design_scores_gemma":[0.00010264074,0.0002646164,0.0027526591,0.00006207121,0.0001732896,0.00015483944,0.00006602583,0.945672,0.0045464924,0.043597005,0.0025092196,0.00009913618],"about_ca_topic_score_codex":0.0066032517,"about_ca_topic_score_gemma":0.008481481,"teacher_disagreement_score":0.06192979,"about_ca_system_score_codex":0.0016020675,"about_ca_system_score_gemma":0.0022809913,"threshold_uncertainty_score":0.32751995},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0059396536,0.00017043744,0.0013311376,0.00085246685,0.00022811836,0.0006863371,0.9862302,0.0009587321,0.0036029702],"genre_scores_gemma":[0.013490529,0.00009285231,0.0030139398,0.0004505514,0.000054695523,0.003413519,0.97459227,0.00017917885,0.0047123674],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98899454,0.0051552313,0.0019485843,0.0012019083,0.0021224546,0.00057720137],"domain_scores_gemma":[0.94110835,0.017804448,0.00723588,0.023566274,0.008423184,0.0018618904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020460956,0.0012408781,0.0010879806,0.0031136316,0.0012175802,0.0022658857,0.0037294345,0.0026476937,0.06278371],"category_scores_gemma":[0.0830252,0.0008131004,0.0016704322,0.006168717,0.0012034482,0.0013472905,0.0033395865,0.002132209,0.033983156],"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":[0.0006767813,0.00021318565,0.009760286,0.0013528856,0.0002341067,0.00012559303,0.00023451829,0.00063835375,0.00017022985,0.0020007791,0.9742097,0.010383633],"study_design_scores_gemma":[0.006430467,0.00049715274,0.091558255,0.0008855863,0.00038630993,0.00031222962,0.0004996138,0.001900101,0.00110443,0.003732997,0.8925479,0.00014495717],"about_ca_topic_score_codex":0.020617224,"about_ca_topic_score_gemma":0.036870852,"teacher_disagreement_score":0.06278371,"about_ca_system_score_codex":0.001542437,"about_ca_system_score_gemma":0.0034804347,"threshold_uncertainty_score":0.21003246},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000061298124,0.000031580574,0.00013675027,0.000062919804,0.000014542262,0.00000844437,0.9977558,0.0007693092,0.0011593164],"genre_scores_gemma":[0.0009020756,0.00007084656,0.0006407566,0.00007941457,0.000017130686,0.00017831934,0.9957183,0.00051176886,0.0018813175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986117,0.0002767558,0.00015896827,0.0003992258,0.0003202937,0.00023306975],"domain_scores_gemma":[0.9929283,0.0028506122,0.00058707845,0.001991815,0.0011695174,0.00047270625],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0023319486,0.0015851143,0.0013370971,0.0050630723,0.00076536305,0.0035650306,0.0029892155,0.0019605379,0.30417368],"category_scores_gemma":[0.021770569,0.0011315024,0.00085900456,0.010098116,0.00047595162,0.0020820294,0.0020945808,0.0015037268,0.24229552],"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":[0.000019702842,0.000009149653,0.0004992988,0.00021456744,0.000013471442,0.000003900882,0.000014390814,0.00014985481,0.000021199396,0.0007458769,0.99582374,0.0024848958],"study_design_scores_gemma":[0.00019569142,0.000017358367,0.00411925,0.00032380488,0.000026505786,0.000027927796,0.0000619154,0.0005370658,0.00027485625,0.003045771,0.99133974,0.000029992685],"about_ca_topic_score_codex":0.025837135,"about_ca_topic_score_gemma":0.0300096,"teacher_disagreement_score":0.30417368,"about_ca_system_score_codex":0.0019275051,"about_ca_system_score_gemma":0.002354513,"threshold_uncertainty_score":0.9925118},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006630419,0.000044137498,0.00019770398,0.00007318983,0.000022879241,0.000013189601,0.99755716,0.0011903569,0.0008350777],"genre_scores_gemma":[0.00087530987,0.00008654261,0.00091743236,0.00014093588,0.000023748296,0.00025705708,0.99537694,0.0009260102,0.001395992],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976935,0.0005428616,0.00029500012,0.0006654052,0.00047957877,0.00032375703],"domain_scores_gemma":[0.9873144,0.006070853,0.000884821,0.0033818353,0.0016846507,0.00066346425],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0033439065,0.0024686123,0.0018871435,0.0053839725,0.00096707814,0.0043127034,0.0044532456,0.002637243,0.30014512],"category_scores_gemma":[0.033315286,0.0014454053,0.0014271906,0.010677863,0.00076506735,0.0022471105,0.0025059674,0.0021742128,0.26166913],"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":[0.000028018327,0.000012233813,0.00038493625,0.00042811825,0.000025904317,0.0000068224476,0.00001747858,0.00022330375,0.000026096162,0.0005546907,0.996646,0.0016463196],"study_design_scores_gemma":[0.00041542677,0.000024801675,0.0021914032,0.0004241072,0.00004534686,0.000043063206,0.00005983451,0.000712162,0.0003042588,0.004131185,0.99160844,0.000039982377],"about_ca_topic_score_codex":0.016930476,"about_ca_topic_score_gemma":0.028382024,"teacher_disagreement_score":0.69985485,"about_ca_system_score_codex":0.001996994,"about_ca_system_score_gemma":0.00300435,"threshold_uncertainty_score":0.99825805},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009572684,0.00027659303,0.0020957033,0.0013486915,0.00047208357,0.0013493476,0.9756055,0.00088051474,0.008398877],"genre_scores_gemma":[0.0403429,0.000160491,0.0029934442,0.0010518661,0.00015307355,0.0075826244,0.9316295,0.0002383536,0.01584776],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9898028,0.005808598,0.0012882551,0.0010791771,0.0015422637,0.00047897268],"domain_scores_gemma":[0.9140902,0.03360435,0.007840291,0.03267189,0.009719986,0.0020733199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021480417,0.0012048389,0.001274798,0.0016521362,0.001509284,0.0021008323,0.00371459,0.0023386134,0.09151232],"category_scores_gemma":[0.093638614,0.0006880075,0.0018221809,0.003073268,0.0014675676,0.0013418307,0.0024406128,0.0030047072,0.04528849],"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":[0.0019108292,0.0002553173,0.003989604,0.0008166041,0.00021901476,0.000056221474,0.00011264027,0.0004463972,0.00012128606,0.0019170681,0.98279035,0.007364684],"study_design_scores_gemma":[0.020918032,0.0015138809,0.114602566,0.0010375837,0.0009741975,0.00038692073,0.00078595005,0.0022959902,0.0020507006,0.009879184,0.84532994,0.0002251029],"about_ca_topic_score_codex":0.016186181,"about_ca_topic_score_gemma":0.03323651,"teacher_disagreement_score":0.09151232,"about_ca_system_score_codex":0.0013772551,"about_ca_system_score_gemma":0.0038803734,"threshold_uncertainty_score":0.30613923},"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":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06541562,0.0033515003,0.9286678,0.00015139558,0.00009010918,0.00024299705,0.00013400157,0.00076001463,0.0011865969],"genre_scores_gemma":[0.40283743,0.0020680577,0.59281456,0.00015349302,0.0001627443,0.00056437403,0.00046613417,0.00022562982,0.0007076174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.95605695,0.033079535,0.0017242084,0.0030051775,0.0057403655,0.0003936698],"domain_scores_gemma":[0.8388675,0.13920188,0.00830729,0.0056652557,0.0073724883,0.0005856115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04607276,0.0013740067,0.0021173297,0.0035633997,0.0003489113,0.001753236,0.003069338,0.0017169939,0.0012616694],"category_scores_gemma":[0.18201846,0.0006682048,0.0013132829,0.0020593766,0.0013076682,0.0031645603,0.0015727183,0.0011580521,0.0008133042],"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":[0.003311064,0.0004725304,0.06880383,0.0022569268,0.0024668367,0.0003184638,0.0012060975,0.21566471,0.0079103615,0.038460504,0.0025170576,0.6566116],"study_design_scores_gemma":[0.00036183046,0.0018281962,0.012707364,0.00019904424,0.0005915122,0.0007834172,0.0002628512,0.9601738,0.008976228,0.011511085,0.0024149388,0.00018982125],"about_ca_topic_score_codex":0.0014009106,"about_ca_topic_score_gemma":0.0006793905,"teacher_disagreement_score":0.04607276,"about_ca_system_score_codex":0.00078114757,"about_ca_system_score_gemma":0.0009424911,"threshold_uncertainty_score":0.24365896},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051162625,0.000098746386,0.9932736,0.00021450533,0.000035161593,0.00016789496,0.00007949803,0.00011014937,0.00090411666],"genre_scores_gemma":[0.5793318,0.00063591497,0.40717655,0.00040813838,0.00011878626,0.0017242323,0.00045574788,0.000108231034,0.010040635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9894889,0.0073742745,0.00023035808,0.0013246967,0.0011074939,0.00047428263],"domain_scores_gemma":[0.99032885,0.0064986283,0.0007664817,0.000720666,0.0014550268,0.00023033847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011058875,0.000894383,0.0018260559,0.0010856816,0.0005632736,0.0014894861,0.004092862,0.0017074496,0.004737684],"category_scores_gemma":[0.018739041,0.0006659961,0.001305501,0.0019481167,0.0014215539,0.0017255816,0.0015832175,0.0019051064,0.0009888546],"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":[0.00047362698,0.00013579815,0.001995643,0.00028113727,0.00013479007,0.00018276637,0.00024225532,0.69208604,0.0017025433,0.25541878,0.0034195385,0.043927096],"study_design_scores_gemma":[0.00005097083,0.00010355041,0.00018162296,0.000015809223,0.000026393003,0.000033818324,0.000037708905,0.9756595,0.00036029046,0.022219647,0.0012891102,0.000021668491],"about_ca_topic_score_codex":0.004749318,"about_ca_topic_score_gemma":0.0029456096,"teacher_disagreement_score":0.011058875,"about_ca_system_score_codex":0.0015612518,"about_ca_system_score_gemma":0.0023884315,"threshold_uncertainty_score":0.058485627},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00900195,0.00032608013,0.9890915,0.00031375457,0.00003189811,0.00011159504,0.00023811801,0.00039438132,0.00049063395],"genre_scores_gemma":[0.34559265,0.000860372,0.6455681,0.0003709086,0.00031429855,0.0013203584,0.0020576252,0.00025632884,0.003659443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9865649,0.010303305,0.00038481256,0.0013602951,0.00095123745,0.00043554063],"domain_scores_gemma":[0.9335011,0.05577709,0.0020536552,0.006724782,0.001347837,0.00059543864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016875163,0.0016338846,0.0049327537,0.0015795646,0.0008490276,0.0024958313,0.0051732645,0.0022332708,0.0053770035],"category_scores_gemma":[0.076441094,0.0026194393,0.0021214655,0.0029376112,0.0014905595,0.0045491466,0.0049132537,0.0030372068,0.0012762368],"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":[0.00077732885,0.00033140765,0.006761754,0.0006174375,0.00058488926,0.00029606474,0.00037311748,0.65742785,0.0012258401,0.17373255,0.007331385,0.15054032],"study_design_scores_gemma":[0.000052247284,0.00003292914,0.0003275086,0.000021322705,0.000025597641,0.000028685829,0.000029049555,0.9021292,0.00016500095,0.09659824,0.000581192,0.000008999494],"about_ca_topic_score_codex":0.005715774,"about_ca_topic_score_gemma":0.0058807703,"teacher_disagreement_score":0.016875163,"about_ca_system_score_codex":0.0017386219,"about_ca_system_score_gemma":0.0023706397,"threshold_uncertainty_score":0.08924544},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14592016,0.00022616552,0.85229415,0.00018053286,0.000034952533,0.00015354216,0.00033725085,0.00023150745,0.00062171114],"genre_scores_gemma":[0.58870757,0.000340612,0.40432355,0.00012838187,0.000048742626,0.00047587743,0.0013932718,0.00012484362,0.0044570244],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9915319,0.0058259214,0.00038616784,0.0013124298,0.000540237,0.00040332857],"domain_scores_gemma":[0.94373304,0.04536223,0.0021573673,0.0069020353,0.0014278692,0.00041751043],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023934303,0.0009436007,0.0022361395,0.0019496398,0.000969691,0.0018692857,0.0033993917,0.0024827218,0.002742912],"category_scores_gemma":[0.059988476,0.0018067876,0.0024079906,0.0028913883,0.0014820703,0.0030979337,0.002269582,0.0024136018,0.0005546123],"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":[0.0013215906,0.00074815785,0.14974932,0.00040752854,0.0015015183,0.0007053674,0.001553618,0.5543745,0.003356111,0.09196291,0.0027382243,0.19158112],"study_design_scores_gemma":[0.00012948703,0.00017586503,0.011043329,0.000048357353,0.0002602872,0.00023813582,0.00022731924,0.9164283,0.0008668115,0.06945571,0.0010628974,0.0000634681],"about_ca_topic_score_codex":0.014277974,"about_ca_topic_score_gemma":0.01828519,"teacher_disagreement_score":0.023934303,"about_ca_system_score_codex":0.0012190907,"about_ca_system_score_gemma":0.001920055,"threshold_uncertainty_score":0.12657821},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030697713,0.00077409303,0.96467775,0.00068537757,0.000051355935,0.00013358754,0.00014382346,0.000114220114,0.0027221167],"genre_scores_gemma":[0.74692607,0.0019634683,0.24147989,0.000700384,0.00035005627,0.0011268596,0.0006415676,0.00013447039,0.0066772243],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9746348,0.019601187,0.0005828002,0.0018903373,0.0025886227,0.00070220215],"domain_scores_gemma":[0.8621425,0.116139084,0.008362974,0.0082026245,0.0042265956,0.0009261533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03681335,0.0009635914,0.0021343536,0.0024515816,0.0010514411,0.002204553,0.0032725735,0.002201361,0.0036575694],"category_scores_gemma":[0.131878,0.0008185117,0.0014518574,0.003281119,0.004207399,0.0041496,0.003484979,0.00229934,0.0006114857],"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":[0.0001249165,0.00005916015,0.0098751895,0.00023221342,0.00020808629,0.00043585344,0.0004446525,0.12089826,0.00040147032,0.8206528,0.0018112778,0.044856146],"study_design_scores_gemma":[0.00005822053,0.00007837097,0.001941226,0.000087903674,0.000064983404,0.00022041393,0.00009251942,0.57421434,0.0003895648,0.42046168,0.0023541593,0.000036679645],"about_ca_topic_score_codex":0.00333284,"about_ca_topic_score_gemma":0.002424905,"teacher_disagreement_score":0.03681335,"about_ca_system_score_codex":0.0017273788,"about_ca_system_score_gemma":0.0016846916,"threshold_uncertainty_score":0.19468993},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071465713,0.00049494096,0.991277,0.00028537324,0.000031027426,0.000050648105,0.00003623,0.0000666837,0.0006115512],"genre_scores_gemma":[0.41652232,0.0018774036,0.57700527,0.000546166,0.00036881887,0.0008136778,0.0004169289,0.00011473224,0.0023346413],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9504614,0.04255627,0.00079647196,0.0021832106,0.0033171969,0.00068541366],"domain_scores_gemma":[0.79686975,0.17953707,0.0060165366,0.011118848,0.0057810186,0.0006767616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06956239,0.0009919183,0.001928597,0.0028104526,0.001043641,0.002076979,0.0032224937,0.0023959284,0.0020525788],"category_scores_gemma":[0.21299264,0.001189898,0.0014488898,0.0034942015,0.00415317,0.0036752545,0.0037096576,0.003036032,0.0005512935],"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":[0.00012515536,0.00011981423,0.012985839,0.0003358538,0.00027465558,0.00018945408,0.0006096957,0.1922407,0.00065335515,0.7157998,0.0022455005,0.0744202],"study_design_scores_gemma":[0.00004712777,0.00008415386,0.0021955788,0.00017738048,0.000055747892,0.0001277051,0.0000976781,0.6784387,0.00069295167,0.31560123,0.002434036,0.000047666243],"about_ca_topic_score_codex":0.003796915,"about_ca_topic_score_gemma":0.0026333227,"teacher_disagreement_score":0.06956239,"about_ca_system_score_codex":0.0018804595,"about_ca_system_score_gemma":0.001853353,"threshold_uncertainty_score":0.36788547},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98953944,0.00080513064,0.005321406,0.00021950119,0.00008994215,0.00026570057,0.0004303338,0.000013092304,0.0033154802],"genre_scores_gemma":[0.9962656,0.000240681,0.00206965,0.0002067894,0.000019597881,0.00025046538,0.00069227535,0.000009740853,0.00024508557],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.79380685,0.16388907,0.014520539,0.007868259,0.017691838,0.0022233634],"domain_scores_gemma":[0.6719618,0.225364,0.040278446,0.023987642,0.036795225,0.0016128903],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14081477,0.00044941867,0.0010531748,0.004111477,0.0013446996,0.0017244477,0.0019259646,0.00071287894,0.0011601273],"category_scores_gemma":[0.28599614,0.00062774424,0.0014257622,0.0069183623,0.0028699562,0.0015389734,0.0035051636,0.0010771808,0.00021265731],"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":[0.0013171358,0.00020296735,0.8738223,0.0016118503,0.0034926976,0.00038445424,0.051857553,0.00091419177,0.0015213728,0.0032956842,0.001345544,0.060234327],"study_design_scores_gemma":[0.00009904457,0.00066363707,0.9643877,0.00041673184,0.0008240183,0.0001688358,0.025068892,0.0010794429,0.002157725,0.0012284068,0.0038459115,0.00005956959],"about_ca_topic_score_codex":0.01257044,"about_ca_topic_score_gemma":0.014505898,"teacher_disagreement_score":0.8591852,"about_ca_system_score_codex":0.0020389578,"about_ca_system_score_gemma":0.0025880642,"threshold_uncertainty_score":0.74470854},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011114864,0.42316854,0.5179094,0.012751639,0.002889081,0.005552682,0.0028556997,0.00031948558,0.023438532],"genre_scores_gemma":[0.102263294,0.27605304,0.5957412,0.0058463677,0.0017347102,0.013190135,0.0017407797,0.0003742831,0.003056233],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8365384,0.13075313,0.007468403,0.0051917625,0.019163048,0.00088536926],"domain_scores_gemma":[0.72004527,0.2311297,0.009672413,0.010528442,0.027938465,0.0006857231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13088192,0.0014686462,0.0029693437,0.008204912,0.0016238759,0.0047225202,0.0024183413,0.0019135926,0.0046724817],"category_scores_gemma":[0.24738324,0.000765328,0.0036262826,0.016063713,0.0024035505,0.0058288723,0.0026625986,0.0024492305,0.0006999866],"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":[0.00031538183,0.00010321802,0.008317532,0.049158752,0.0037478975,0.00014175691,0.004747764,0.0035190617,0.00070477003,0.16866797,0.02446283,0.736113],"study_design_scores_gemma":[0.00024951118,0.0016414039,0.03527268,0.11375602,0.007892971,0.0008308316,0.008680836,0.015526634,0.0037407947,0.20920172,0.60275,0.0004566825],"about_ca_topic_score_codex":0.006885629,"about_ca_topic_score_gemma":0.009294913,"teacher_disagreement_score":0.13088192,"about_ca_system_score_codex":0.006691796,"about_ca_system_score_gemma":0.011699706,"threshold_uncertainty_score":0.692178},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022591641,0.00048569302,0.9761763,0.00015269782,0.000026245425,0.00004072654,0.0000647902,0.00017024716,0.0002916779],"genre_scores_gemma":[0.36913288,0.00086261384,0.62873524,0.00010361009,0.00011473055,0.00017263088,0.00029308093,0.000052556436,0.0005327278],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955842,0.0030894463,0.00020276701,0.00044435426,0.0005810356,0.00009820613],"domain_scores_gemma":[0.98226273,0.012578651,0.0012879652,0.0015547847,0.0021034651,0.00021240456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011760811,0.0004305801,0.00089439494,0.0019025999,0.00030380845,0.00066225196,0.000814007,0.0006120828,0.0005864232],"category_scores_gemma":[0.039724275,0.00024865696,0.00084600167,0.001861613,0.0005867861,0.0013912646,0.0012140162,0.0009813439,0.00016906623],"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":[0.00040814164,0.00016300453,0.03992652,0.0004402185,0.000379139,0.00036358004,0.0005603979,0.31310794,0.010388355,0.085864015,0.003034586,0.54536414],"study_design_scores_gemma":[0.0000553433,0.00023950674,0.0074765454,0.000055878358,0.00006941479,0.00036655835,0.00012190113,0.9521072,0.00357374,0.032334335,0.003537451,0.000062148414],"about_ca_topic_score_codex":0.001494932,"about_ca_topic_score_gemma":0.0012387242,"teacher_disagreement_score":0.011760811,"about_ca_system_score_codex":0.00042054217,"about_ca_system_score_gemma":0.0010329596,"threshold_uncertainty_score":0.062197864},"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":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032612524,0.0041389936,0.022788573,0.06330423,0.89790535,0.00008073709,0.0020606709,0.0017782466,0.0076170624],"genre_scores_gemma":[0.023943251,0.014887758,0.050940666,0.1257093,0.4247003,0.00086837495,0.00855478,0.0058967723,0.34449872],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99222285,0.0031823865,0.00062099047,0.00096403627,0.002611018,0.00039886447],"domain_scores_gemma":[0.97302693,0.010236173,0.0009176993,0.0017617381,0.013311894,0.00074552983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068336697,0.0027455313,0.0028682125,0.0035945843,0.002060301,0.003225388,0.0038047493,0.00455401,0.11300214],"category_scores_gemma":[0.07833459,0.001349005,0.0026886016,0.0034402614,0.0024342362,0.0030388345,0.0024144482,0.005910822,0.05199522],"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":[0.000021782073,0.000009115561,0.00008202722,0.00011365308,0.000025093785,0.000055432254,0.000023657409,0.00016113064,0.000046110796,0.0021518453,0.9907376,0.0065725944],"study_design_scores_gemma":[0.00004406462,0.000056270736,0.0016915225,0.00031251818,0.00008682431,0.0002797969,0.000082006045,0.0030011388,0.0004664532,0.010766547,0.98309535,0.00011743194],"about_ca_topic_score_codex":0.019020692,"about_ca_topic_score_gemma":0.033359643,"teacher_disagreement_score":0.11300214,"about_ca_system_score_codex":0.003855673,"about_ca_system_score_gemma":0.0033611804,"threshold_uncertainty_score":0.37802982},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002837793,0.00018621281,0.99629223,0.00010440533,0.000013838972,0.000047789574,0.00006593924,0.00009475539,0.00035710653],"genre_scores_gemma":[0.27883178,0.0016540894,0.7145862,0.00029405684,0.00018193743,0.0009687292,0.0010201508,0.00020716414,0.0022559336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9839056,0.012887361,0.0004966,0.001050243,0.0013144787,0.00034575223],"domain_scores_gemma":[0.934135,0.054497413,0.0031333345,0.005135996,0.0025939024,0.0005043272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024220869,0.0013065153,0.0021675683,0.003125838,0.0005882507,0.002322611,0.0026724162,0.0013921374,0.005349996],"category_scores_gemma":[0.13238765,0.00087127934,0.0016961957,0.0036918866,0.0023196891,0.004520702,0.0028659336,0.0024299049,0.0010934393],"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":[0.00023854476,0.00014318227,0.013080003,0.0005207621,0.0004692009,0.00024166204,0.00062133296,0.22839445,0.0013558094,0.5960251,0.0033134455,0.15559654],"study_design_scores_gemma":[0.000056315308,0.00008298911,0.0020243595,0.00011419681,0.000079604535,0.00012989082,0.00008116647,0.61580133,0.00073316006,0.3778867,0.002973748,0.000036586407],"about_ca_topic_score_codex":0.0030080345,"about_ca_topic_score_gemma":0.0025101462,"teacher_disagreement_score":0.024220869,"about_ca_system_score_codex":0.0014266811,"about_ca_system_score_gemma":0.0019464884,"threshold_uncertainty_score":0.12809372},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040970405,0.000030752984,0.0033181156,0.00028474227,0.00007248519,0.0007925209,0.99111253,0.0004208262,0.003558269],"genre_scores_gemma":[0.024607621,0.0003497087,0.042277202,0.0022276237,0.0003121654,0.03053035,0.8535749,0.0029027988,0.043217693],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99625057,0.0016609852,0.0006197542,0.00052346097,0.0007002077,0.00024505547],"domain_scores_gemma":[0.8068185,0.17077577,0.004485869,0.0056644087,0.011051661,0.001203859],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009173427,0.000982064,0.0011192898,0.0030984415,0.0010357241,0.0016301576,0.0021788627,0.0012737833,0.8999981],"category_scores_gemma":[0.16386579,0.000877727,0.00057379896,0.005860244,0.0003802289,0.0017922992,0.0012105134,0.0012194436,0.14826152],"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":[0.00016457279,0.00009021028,0.0013657936,0.0013617598,0.000024225044,0.00002891571,0.00010560519,0.00044787343,0.000031341166,0.0017600966,0.98100317,0.01361647],"study_design_scores_gemma":[0.0033990496,0.0003140348,0.014849719,0.0047749523,0.00018001338,0.00040927253,0.00085091847,0.003598543,0.000587771,0.024788659,0.9461321,0.00011495372],"about_ca_topic_score_codex":0.0064071864,"about_ca_topic_score_gemma":0.0128601575,"teacher_disagreement_score":0.99082655,"about_ca_system_score_codex":0.0017666229,"about_ca_system_score_gemma":0.0036400605,"threshold_uncertainty_score":0.14264053},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45035762,0.009366154,0.0057694647,0.0007401737,0.000589511,0.00039971172,0.013682873,0.003185979,0.5159085],"genre_scores_gemma":[0.6820148,0.0053742263,0.012328745,0.0013958012,0.00019248476,0.00033618987,0.017598242,0.000297802,0.28046164],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99993956,0.000004434774,0.0000045761767,0.000023901153,0.000016045433,0.000011424889],"domain_scores_gemma":[0.9999378,0.0000041801886,0.000022722277,0.000007077401,0.000013967091,0.000014247498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006295262,0.0007131916,0.00015961929,0.0010632509,0.00067012693,0.00030758907,0.00032583848,0.0001452854,0.030098993],"category_scores_gemma":[0.00008655617,0.00017828507,0.00020076532,0.00040734315,0.00015665144,0.00043103594,0.00083918724,0.00031928028,0.010478332],"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":[0.0005940588,0.00017259744,0.06428381,0.00092400226,0.00009518955,0.001153377,0.0009399057,0.0004793119,0.051248066,0.0063055186,0.065255515,0.8085486],"study_design_scores_gemma":[0.000088143635,0.00042613276,0.34195602,0.00035240946,0.0001345755,0.002917742,0.0007858899,0.00038352568,0.0055777603,0.0010560938,0.6462715,0.000050164377],"about_ca_topic_score_codex":0.01653686,"about_ca_topic_score_gemma":0.07163715,"teacher_disagreement_score":0.030098993,"about_ca_system_score_codex":0.00043994235,"about_ca_system_score_gemma":0.0004268047,"threshold_uncertainty_score":0.1006912},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00075726426,0.00030875363,0.0011544985,0.00059946,0.0007820554,0.00016778665,0.0976726,0.0068371254,0.8917205],"genre_scores_gemma":[0.0037171496,0.00040214666,0.0009165062,0.00019064429,0.00020766463,0.00021344227,0.027978785,0.0040431153,0.9623306],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99968576,0.000032721193,0.000014919774,0.00008937661,0.000118114694,0.000059182545],"domain_scores_gemma":[0.9983321,0.00030970073,0.00007490728,0.0003049013,0.0006979507,0.00028042626],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00044135956,0.0007816408,0.0007118118,0.0017711839,0.0010467138,0.0043745977,0.0014574379,0.00081593916,0.9270604],"category_scores_gemma":[0.0033397898,0.00047746295,0.0003703435,0.004571505,0.00032753777,0.0018830943,0.0018473442,0.0010482785,0.8608591],"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":[0.00003010907,0.000012922608,0.00013797739,0.000057714085,0.0000011604998,0.000012870889,0.00002434849,0.000021362686,0.000058955757,0.00051663356,0.9738442,0.025281709],"study_design_scores_gemma":[0.0000173827,0.000009393722,0.001486293,0.00007297941,0.0000016039407,0.000029599749,0.00008681756,0.000060957624,0.00016272567,0.00030115223,0.9977654,0.00000563009],"about_ca_topic_score_codex":0.011009547,"about_ca_topic_score_gemma":0.012639074,"teacher_disagreement_score":0.072939575,"about_ca_system_score_codex":0.0009035019,"about_ca_system_score_gemma":0.0009848155,"threshold_uncertainty_score":0.10403943},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85657424,0.0009871107,0.0006985628,0.0012423312,0.000025532063,0.00018401697,0.12700702,0.000057647463,0.013223591],"genre_scores_gemma":[0.9175003,0.001757256,0.0009921053,0.0003446233,0.000010288973,0.00013753041,0.0660941,0.000039369017,0.013124378],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994178,0.000026368625,0.000024271583,0.000056807756,0.0002499272,0.00022479863],"domain_scores_gemma":[0.99749076,0.00006532831,0.00024812,0.00009653978,0.0014050448,0.0006941921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043642838,0.00037642283,0.0003133149,0.0020257633,0.0029085004,0.0018047764,0.001377137,0.00026522472,0.003337789],"category_scores_gemma":[0.0013711603,0.00040428818,0.0005189716,0.006926676,0.00083380094,0.0006543046,0.001788947,0.0011202605,0.00060340593],"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":[0.000076998316,0.00009300277,0.948513,0.000080543774,0.00006650355,0.00008871906,0.003356298,0.00038670725,0.00018779551,0.0016332124,0.022749318,0.022767927],"study_design_scores_gemma":[0.0000036020103,0.00001619121,0.984891,0.00004116056,0.000016931,0.000024795254,0.0050764116,0.00020669185,0.0001353897,0.00010294062,0.00947331,0.000011618354],"about_ca_topic_score_codex":0.9968239,"about_ca_topic_score_gemma":0.99881566,"teacher_disagreement_score":0.02330501,"about_ca_system_score_codex":0.02330501,"about_ca_system_score_gemma":0.05156521,"threshold_uncertainty_score":0.16909051},"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":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842301,0.00011211,0.0024615373,0.000054757504,0.000018161785,0.000028837103,0.011705611,0.00018122589,0.0012075943],"genre_scores_gemma":[0.9612197,0.00011385649,0.004277283,0.0000853482,0.000020588994,0.000099166195,0.027445616,0.000099293946,0.0066391164],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998354,0.0000111598565,0.0000131758225,0.000072995004,0.000050906994,0.000016287124],"domain_scores_gemma":[0.99975127,0.000053590495,0.00008080464,0.00002885597,0.00002877817,0.000056770165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000292313,0.0001963314,0.00017410601,0.000542575,0.00026060303,0.00021349534,0.00023563877,0.00014809737,0.011070276],"category_scores_gemma":[0.00025068078,0.00009966719,0.00022969846,0.00036911655,0.00013889071,0.00012483893,0.00019706941,0.00021376563,0.00071438536],"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":[0.0018407049,0.00028769413,0.11962693,0.00019525156,0.00017526775,0.00041114318,0.00038720435,0.00069473503,0.829033,0.00042287973,0.0025743176,0.044350933],"study_design_scores_gemma":[0.000080823556,0.0002058555,0.96119785,0.000013964732,0.000050254024,0.0002857048,0.0000418299,0.0012646255,0.030666541,0.00015035023,0.0060243644,0.000017906514],"about_ca_topic_score_codex":0.0036363339,"about_ca_topic_score_gemma":0.0051757265,"teacher_disagreement_score":0.011070276,"about_ca_system_score_codex":0.00035908373,"about_ca_system_score_gemma":0.00019331415,"threshold_uncertainty_score":0.037033796},"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":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003065073,0.00002222272,0.0029856407,0.00021586922,0.00006386208,0.0004993626,0.99220675,0.0004924689,0.003207386],"genre_scores_gemma":[0.022111854,0.000285942,0.037028648,0.001695386,0.0002761804,0.019410318,0.8753336,0.003950723,0.039907333],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965323,0.001515415,0.0005418364,0.0005228166,0.00063027407,0.00025729238],"domain_scores_gemma":[0.8368968,0.14294451,0.0036569936,0.005607377,0.00975122,0.0011430788],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008794496,0.0010857815,0.0011759285,0.0032664353,0.0010565912,0.0017111681,0.0023213574,0.0012163584,0.9120738],"category_scores_gemma":[0.14199267,0.0009504863,0.00066666637,0.0065946337,0.00040116196,0.0020169732,0.0013051361,0.0012067369,0.19908896],"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":[0.00012970962,0.000059062495,0.00113727,0.0009811228,0.000021241622,0.000024424604,0.0000814082,0.0004535746,0.000026339845,0.0014588278,0.9856748,0.009952203],"study_design_scores_gemma":[0.0027468079,0.00025265187,0.013390333,0.0037971365,0.00015609655,0.00035118777,0.000743551,0.0038004115,0.00051296625,0.022804393,0.95133793,0.0001065147],"about_ca_topic_score_codex":0.006624295,"about_ca_topic_score_gemma":0.012772372,"teacher_disagreement_score":0.9912055,"about_ca_system_score_codex":0.0016688004,"about_ca_system_score_gemma":0.0032300365,"threshold_uncertainty_score":0.1254161},"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":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009607283,0.00032469185,0.013821182,0.029943792,0.05814758,0.003085383,0.028365497,0.025119495,0.8315851],"genre_scores_gemma":[0.010675974,0.00006873827,0.0026301732,0.0085802805,0.0021586504,0.0010099511,0.002361289,0.0024542192,0.97006065],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9900718,0.0019487347,0.0007209133,0.001208602,0.0033920011,0.0026579357],"domain_scores_gemma":[0.9370197,0.019463727,0.0022546751,0.015442507,0.014175477,0.011643911],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.011898954,0.0011242802,0.0022723197,0.004442774,0.0049455543,0.008887184,0.0037401095,0.01354834,0.6149465],"category_scores_gemma":[0.05719086,0.0013816772,0.0013671097,0.0030472858,0.0018298973,0.0041459603,0.004150654,0.0049980143,0.56787074],"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":[0.00023599617,0.00028633556,0.00036856683,0.00007801187,0.0000045531897,0.000054145883,0.000055910652,0.00011705096,0.0004950659,0.0032497137,0.96794665,0.027108034],"study_design_scores_gemma":[0.00023514363,0.00026001778,0.0070443563,0.00013930244,0.000009457068,0.000117430005,0.00023412105,0.0010188043,0.001974581,0.0040755924,0.98481977,0.00007142971],"about_ca_topic_score_codex":0.004225229,"about_ca_topic_score_gemma":0.011938832,"teacher_disagreement_score":0.6149465,"about_ca_system_score_codex":0.002205243,"about_ca_system_score_gemma":0.0073986175,"threshold_uncertainty_score":0.5492321},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6208019,0.05455987,0.021804575,0.07139002,0.0015921583,0.0002743468,0.0015077998,0.00011014679,0.22795913],"genre_scores_gemma":[0.93594676,0.017371224,0.004523651,0.006729664,0.00047510397,0.00022287243,0.00028033459,0.00006732427,0.03438311],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9918224,0.0035764643,0.00026628235,0.00068176695,0.0024338912,0.0012191986],"domain_scores_gemma":[0.9737809,0.017726973,0.0020778612,0.0013244295,0.0037822756,0.0013075644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016638251,0.00043044137,0.00054271496,0.008568252,0.0065643243,0.0063787242,0.00075606676,0.0010345273,0.0045168498],"category_scores_gemma":[0.028980402,0.0002903377,0.00038388127,0.015527304,0.0090944255,0.0049298406,0.004928374,0.0012533505,0.0004431908],"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":[0.00019343606,0.00005321811,0.12397598,0.0005934677,0.000078783465,0.00030270268,0.29618368,0.00029141933,0.00077468605,0.29132077,0.037145946,0.24908592],"study_design_scores_gemma":[0.000017336944,0.000112680915,0.11798349,0.0012329875,0.00009611225,0.00034866147,0.23901321,0.00079266675,0.001005514,0.060950644,0.5783846,0.00006211204],"about_ca_topic_score_codex":0.04863461,"about_ca_topic_score_gemma":0.09904582,"teacher_disagreement_score":0.04863461,"about_ca_system_score_codex":0.007680463,"about_ca_system_score_gemma":0.013335001,"threshold_uncertainty_score":0.09670305},"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":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11920862,0.0031160188,0.0056200624,0.02085548,0.005237727,0.0003026759,0.0069479123,0.0003920864,0.8383194],"genre_scores_gemma":[0.51766205,0.001970511,0.005217144,0.0072413767,0.0010505733,0.00037773242,0.003289258,0.00039035972,0.46280095],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889636,0.0003525286,0.00003888135,0.00021878968,0.00030148952,0.00019188382],"domain_scores_gemma":[0.9986687,0.00016184007,0.00014783579,0.00019046303,0.0003593871,0.00047182126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014290832,0.0003520239,0.00028789218,0.0007170837,0.002795432,0.0024370502,0.00047568628,0.00061460404,0.043922115],"category_scores_gemma":[0.004815199,0.0002795604,0.00017800886,0.0008725488,0.00080136466,0.0016184163,0.0014507399,0.0020434659,0.006580429],"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":[0.00019045721,0.00017406541,0.037820313,0.00031196946,0.00007185034,0.00010878929,0.009640514,0.00021127156,0.0011283846,0.13822657,0.6761662,0.1359496],"study_design_scores_gemma":[0.000008569505,0.000063836655,0.05141718,0.00011340809,0.0000100046245,0.00007540097,0.0044880915,0.00011244401,0.00022311867,0.0045228116,0.93895596,0.000009221633],"about_ca_topic_score_codex":0.01630231,"about_ca_topic_score_gemma":0.051585652,"teacher_disagreement_score":0.043922115,"about_ca_system_score_codex":0.0011544735,"about_ca_system_score_gemma":0.0014725064,"threshold_uncertainty_score":0.14693415},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00092685525,0.000097749005,0.9983107,0.00003899431,0.000043230164,0.0001609331,0.000030985375,0.00007759827,0.0003131024],"genre_scores_gemma":[0.045295518,0.00024348038,0.95147556,0.000121236604,0.000115228264,0.001203354,0.00016762575,0.00005500424,0.0013229878],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97969395,0.014998224,0.00059807865,0.0017856732,0.0025457933,0.00037828923],"domain_scores_gemma":[0.99269074,0.004562992,0.0003644732,0.001076961,0.0011102223,0.0001946168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011989273,0.0011102273,0.001895367,0.002300051,0.0011176899,0.0012415946,0.0024683082,0.00148042,0.005637646],"category_scores_gemma":[0.023777273,0.0007864277,0.0016059971,0.0026553809,0.0012568802,0.0020117287,0.0022873776,0.0019400137,0.0015479575],"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":[0.000556841,0.0002567714,0.005285269,0.0006410045,0.00041643702,0.00017639108,0.00084487285,0.07268939,0.009110954,0.1812985,0.00631591,0.7224077],"study_design_scores_gemma":[0.00033443826,0.00064829586,0.0028843486,0.00018129434,0.00025987253,0.0005561809,0.00015649818,0.80956703,0.0063295844,0.14420778,0.03474053,0.00013418974],"about_ca_topic_score_codex":0.0013984265,"about_ca_topic_score_gemma":0.0014715483,"teacher_disagreement_score":0.011989273,"about_ca_system_score_codex":0.0009860303,"about_ca_system_score_gemma":0.001856853,"threshold_uncertainty_score":0.06340611},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956792,0.00030854656,0.00018172954,0.0013880254,0.000029702174,0.00009754482,0.000050359573,0.000010455759,0.0022544577],"genre_scores_gemma":[0.9968172,0.0003941976,0.00077418034,0.00035105998,0.0000065395893,0.00010779097,0.000048588532,0.000006498104,0.0014940902],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9950545,0.001056069,0.00021888784,0.00030623766,0.0013517344,0.002012544],"domain_scores_gemma":[0.98930025,0.0014436526,0.0010909234,0.00022244015,0.0032017776,0.0047409995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006748028,0.00032624477,0.00066997844,0.00084579695,0.004540403,0.003799273,0.002055471,0.0012790565,0.002763401],"category_scores_gemma":[0.014451085,0.00046710917,0.0004716325,0.001041127,0.0014862069,0.0010902357,0.003037773,0.0019359869,0.00045274897],"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":[0.00021268678,0.0021103043,0.4770915,0.00093522144,0.000046790647,0.0009765586,0.3713926,0.0003100191,0.0023534456,0.0018077004,0.0075122113,0.13525099],"study_design_scores_gemma":[0.000026885464,0.00076221983,0.34688324,0.000820513,0.00004788658,0.00018323341,0.62676775,0.0007572943,0.0016603929,0.00052653824,0.021455858,0.00010825774],"about_ca_topic_score_codex":0.21721686,"about_ca_topic_score_gemma":0.40166387,"teacher_disagreement_score":0.78278315,"about_ca_system_score_codex":0.007029147,"about_ca_system_score_gemma":0.03319129,"threshold_uncertainty_score":0.43190503},"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":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96662986,0.0010776091,0.0005627119,0.004912854,0.00007770288,0.000045989163,0.00012979975,0.000025075991,0.026538396],"genre_scores_gemma":[0.9837712,0.00062492135,0.0002151573,0.00037475245,0.000012776254,0.000024085228,0.000048547263,0.000010017797,0.014918556],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99763596,0.001067996,0.000087692286,0.00020179144,0.0005582238,0.00044831636],"domain_scores_gemma":[0.99503726,0.0011562661,0.00084272673,0.00013194323,0.0012236837,0.0016080777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003276908,0.00027748808,0.00023042058,0.0007472635,0.005236911,0.0045103966,0.00048221913,0.0008560438,0.014432916],"category_scores_gemma":[0.005827008,0.0001800177,0.00023577607,0.0010987839,0.0043060724,0.0027499723,0.0022344622,0.0011879943,0.0011193708],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025509746,0.0001250076,0.09500239,0.00047593666,0.00003411025,0.0009920904,0.8332872,0.0001381933,0.0029105553,0.006163394,0.010341434,0.050274566],"study_design_scores_gemma":[0.00000896969,0.00025795432,0.1311655,0.00031864442,0.000015096641,0.00030468713,0.74390894,0.00014187874,0.00044899524,0.0002914007,0.123082824,0.000055135395],"about_ca_topic_score_codex":0.1856535,"about_ca_topic_score_gemma":0.26356158,"teacher_disagreement_score":0.8143465,"about_ca_system_score_codex":0.008018909,"about_ca_system_score_gemma":0.006976595,"threshold_uncertainty_score":0.36914575},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015385363,0.00043424455,0.9959966,0.0002160848,0.00006628138,0.00037730212,0.0004474002,0.00042898147,0.0004946258],"genre_scores_gemma":[0.062404715,0.0011779083,0.92212194,0.00022950086,0.0003108539,0.0055975514,0.00334463,0.00041958658,0.004393315],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.88448256,0.10091215,0.0029279618,0.006639773,0.0038960618,0.0011415143],"domain_scores_gemma":[0.62697935,0.34278157,0.010527771,0.013748196,0.0050107567,0.00095240003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09557133,0.004442477,0.005807224,0.006535642,0.0027220363,0.005932087,0.01017661,0.004404602,0.021763243],"category_scores_gemma":[0.28737617,0.005242685,0.0067180716,0.008348176,0.0047911727,0.007895801,0.0067422274,0.010906823,0.0053722267],"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":[0.000763471,0.00074626546,0.015389627,0.0015896101,0.0051169647,0.00050583243,0.0018219375,0.21633027,0.00041233885,0.44711077,0.015806628,0.29440638],"study_design_scores_gemma":[0.00047846235,0.00026357,0.003586867,0.00040545163,0.00052830705,0.00023402607,0.0003471731,0.5812701,0.00038826594,0.40114158,0.011175348,0.00018081648],"about_ca_topic_score_codex":0.024013845,"about_ca_topic_score_gemma":0.022205604,"teacher_disagreement_score":0.09557133,"about_ca_system_score_codex":0.004500678,"about_ca_system_score_gemma":0.0073057096,"threshold_uncertainty_score":0.5054356},"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":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015241763,0.0009083189,0.9792021,0.00090221,0.00024068996,0.00033440083,0.0003393842,0.00047068077,0.0023605407],"genre_scores_gemma":[0.305803,0.0015853378,0.6652858,0.0010584685,0.00070786173,0.003248176,0.002714596,0.0002695813,0.019327201],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98369884,0.011657422,0.00056891376,0.0021267442,0.001433044,0.00051518925],"domain_scores_gemma":[0.95671356,0.028569965,0.001169148,0.008684311,0.004373087,0.00048996357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022666454,0.0011226626,0.002282777,0.0032558027,0.0021848215,0.0018664402,0.0033240009,0.0014787447,0.008648756],"category_scores_gemma":[0.078405246,0.00094586186,0.0028390007,0.0036215582,0.0026181964,0.0023184558,0.0026532146,0.0035851267,0.0022085926],"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":[0.0014474783,0.00026303332,0.013407288,0.0007791926,0.000954822,0.0004240631,0.0013440426,0.06288107,0.0041467566,0.35562798,0.02590718,0.5328171],"study_design_scores_gemma":[0.00033000167,0.00044581143,0.008493038,0.00027512334,0.00027659594,0.00037693264,0.00046570634,0.6428284,0.0047046714,0.3087966,0.03290257,0.00010448671],"about_ca_topic_score_codex":0.0096858,"about_ca_topic_score_gemma":0.012559809,"teacher_disagreement_score":0.022666454,"about_ca_system_score_codex":0.001629799,"about_ca_system_score_gemma":0.004468488,"threshold_uncertainty_score":0.11987311},"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049184114,0.0015526708,0.9460279,0.00047503438,0.00010022086,0.00007098663,0.00023239845,0.00019664573,0.0021600977],"genre_scores_gemma":[0.78740484,0.0017227975,0.20692052,0.00028579656,0.00023132387,0.00036755516,0.0007704309,0.00014110678,0.002155642],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9715252,0.019373506,0.0009994947,0.002524518,0.004990872,0.00058634777],"domain_scores_gemma":[0.8450218,0.12391868,0.0069385595,0.014403455,0.009304969,0.00041254313],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036705732,0.0005878519,0.0013806946,0.002104422,0.00053452264,0.0020562245,0.002160105,0.0014623209,0.001310896],"category_scores_gemma":[0.23175864,0.00085161545,0.000971528,0.0022636575,0.0020734014,0.0027844922,0.0023371163,0.0019334789,0.000530254],"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":[0.00034750457,0.00010195503,0.07261148,0.00051292643,0.0012005869,0.0002142668,0.00091597,0.31175593,0.0013780873,0.34534082,0.003423776,0.26219675],"study_design_scores_gemma":[0.00007117543,0.00011490524,0.027103264,0.0003444359,0.00019636919,0.00037179873,0.00027976642,0.6424453,0.0026847436,0.32159024,0.0046447725,0.00015323394],"about_ca_topic_score_codex":0.0022050561,"about_ca_topic_score_gemma":0.001640536,"teacher_disagreement_score":0.036705732,"about_ca_system_score_codex":0.0013366006,"about_ca_system_score_gemma":0.0013323247,"threshold_uncertainty_score":0.19412076},"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":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06730134,0.0034864831,0.53932476,0.0054948223,0.0027850254,0.04473011,0.17439143,0.007302778,0.15518323],"genre_scores_gemma":[0.12304276,0.0032870076,0.47372723,0.0014471697,0.0007972706,0.11149753,0.21262673,0.002749435,0.07082491],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9160166,0.052062113,0.0062929518,0.0038838545,0.0206377,0.0011067786],"domain_scores_gemma":[0.6067029,0.19516821,0.015842868,0.05258394,0.12734629,0.0023556997],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07180206,0.0021670256,0.002471926,0.008215387,0.0028249505,0.003385464,0.004467515,0.0025273834,0.06881249],"category_scores_gemma":[0.29690546,0.0028704118,0.0030699812,0.015882323,0.0012782284,0.005443796,0.0024708821,0.004075023,0.04125414],"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":[0.0007073966,0.002114884,0.0647383,0.0022444644,0.0007666015,0.000101838436,0.0020196422,0.006062793,0.00061620487,0.02700415,0.5115473,0.38207644],"study_design_scores_gemma":[0.0019773552,0.002721835,0.35761768,0.0025429362,0.0015102038,0.0005621693,0.002955715,0.030088324,0.0045264266,0.039522387,0.5553781,0.00059681915],"about_ca_topic_score_codex":0.03493569,"about_ca_topic_score_gemma":0.033948775,"teacher_disagreement_score":0.9281979,"about_ca_system_score_codex":0.0036298956,"about_ca_system_score_gemma":0.015371171,"threshold_uncertainty_score":0.3797301},"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":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.125695,0.013654168,0.090053976,0.07692658,0.00452925,0.00029850134,0.0006238963,0.00041022038,0.68780845],"genre_scores_gemma":[0.8609261,0.010149939,0.021048853,0.0068275947,0.0014612109,0.00033120962,0.0002476828,0.00039550016,0.09861194],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99513865,0.0016608259,0.00018707453,0.0008834597,0.0016094175,0.0005204654],"domain_scores_gemma":[0.9922133,0.0042315186,0.0008870605,0.0006728389,0.0015806868,0.00041449952],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062270877,0.0004338874,0.000428996,0.0017803616,0.0033767892,0.007812025,0.0011762136,0.0019669882,0.02125255],"category_scores_gemma":[0.016409311,0.0005107898,0.00038218824,0.0015188738,0.005893781,0.005534107,0.0025231205,0.0035569142,0.0072604916],"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":[0.00023439867,0.00015685361,0.010832063,0.0008527483,0.00005689742,0.0007735434,0.056731034,0.00087998394,0.00446471,0.61218333,0.052383963,0.26045054],"study_design_scores_gemma":[0.000030699397,0.00008567463,0.010274429,0.0013181528,0.00003983659,0.0005332771,0.023656273,0.0008294598,0.0029528672,0.12320548,0.83699495,0.00007899705],"about_ca_topic_score_codex":0.0052424585,"about_ca_topic_score_gemma":0.006052781,"teacher_disagreement_score":0.9937729,"about_ca_system_score_codex":0.0037551674,"about_ca_system_score_gemma":0.0032451719,"threshold_uncertainty_score":0.07109684},"labels":[],"label_agreement":null},{"id":"W7133121762","doi":"10.1093/jssam/smaf036","title":"Smoothed pseudo-population bootstrap methods with applications to finite population quantiles","year":2025,"lang":"en","type":"article","venue":"Journal of Survey Statistics and Methodology","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Estimator; Resampling; Confidence interval; Bootstrapping (finance); Quantile; Jackknife resampling; Poisson sampling; Population; CDF-based nonparametric confidence interval; Sampling (signal processing)","score_opus":0.4880688058564743,"score_gpt":0.5424089670887016,"score_spread":0.05434016123222729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133121762","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028288863,0.000116117684,0.9964844,0.00005174743,0.00001896853,0.000023731838,0.000020631147,0.0001930827,0.00026245325],"genre_scores_gemma":[0.2742997,0.00049544114,0.72231096,0.00020141815,0.00013528598,0.00057471765,0.0002841214,0.00029307342,0.0014053163],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99418855,0.004428512,0.00014192375,0.00031191783,0.00081614725,0.00011298532],"domain_scores_gemma":[0.96575713,0.02732205,0.0012673304,0.0029322507,0.0024515928,0.00026963008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00960835,0.0005820905,0.0009761308,0.0021012963,0.00047908505,0.0010998846,0.0019677174,0.0009794052,0.004324331],"category_scores_gemma":[0.05820232,0.0005416679,0.0010268253,0.0020219157,0.0014540345,0.0015218533,0.0019063951,0.0020239737,0.00094508636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025370755,0.00013520155,0.004621275,0.00037863688,0.00024154471,0.00035241817,0.00051762164,0.35880193,0.003215226,0.3979915,0.0034019146,0.23008908],"study_design_scores_gemma":[0.000042473443,0.00007740106,0.0011466125,0.000054800483,0.000025261968,0.0000924636,0.00004631059,0.8518042,0.0013362691,0.14078012,0.004567918,0.000026102525],"about_ca_topic_score_codex":0.0015161551,"about_ca_topic_score_gemma":0.0012386687,"teacher_disagreement_score":0.00960835,"about_ca_system_score_codex":0.0006293656,"about_ca_system_score_gemma":0.0009509239,"threshold_uncertainty_score":0.05081439},"labels":[],"label_agreement":null},{"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":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014969765,0.028026706,0.9418899,0.010479824,0.0016672506,0.00027329518,0.001117099,0.0007601545,0.014288747],"genre_scores_gemma":[0.09136524,0.04296245,0.83961004,0.0042720824,0.0075342897,0.003323004,0.0018818236,0.00062009343,0.008430978],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9743119,0.018566227,0.0012185072,0.002228188,0.0034366278,0.00023854467],"domain_scores_gemma":[0.89967054,0.086501606,0.0028657117,0.0071797483,0.003209973,0.0005724358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02941126,0.0019893642,0.0028767488,0.0068857176,0.0013102182,0.0063514193,0.0028896856,0.0033201536,0.010369742],"category_scores_gemma":[0.0729649,0.0009142212,0.0024042295,0.0063731926,0.0072110444,0.00420388,0.0038581186,0.0082747005,0.0029183782],"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":[0.000046795827,0.000056239624,0.001971425,0.0012519625,0.00045231645,0.0001650942,0.000647052,0.016507084,0.00036498348,0.82618904,0.017133474,0.13521463],"study_design_scores_gemma":[0.00002247216,0.000047501755,0.0005592286,0.00037880245,0.000037809485,0.00008083327,0.0001487544,0.016150758,0.00008631771,0.93698883,0.045469183,0.000029514433],"about_ca_topic_score_codex":0.0044926843,"about_ca_topic_score_gemma":0.0025791384,"teacher_disagreement_score":0.02941126,"about_ca_system_score_codex":0.00358181,"about_ca_system_score_gemma":0.005406554,"threshold_uncertainty_score":0.15554345},"labels":[],"label_agreement":null}]}