{"meta":{"query_hash":"9502b421bbb0","filters":{"venue":"AStA Advances in Statistical Analysis"},"cohort_total":12,"direct_labels_cover":0,"predictions_cover":12,"exported":12,"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/9502b421bbb0","api":"https://metacan.xera.ac/api/v1/cohort?venue=AStA+Advances+in+Statistical+Analysis"},"results":[{"id":"W132533186","doi":"10.1007/s10182-018-0325-8","title":"Weak identification in probit models with endogenous covariates","year":2018,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"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; Center for Interuniversity Research and Analysis on Organizations","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec-Société et Culture; Bank of Canada; Alexander von Humboldt-Stiftung","keywords":"Econometrics; Mathematics; Context (archaeology); Probit model; Identification (biology); Covariate; Contrast (vision); Probit; Null hypothesis; Statistics; Instrumental variable; Null (SQL); Endogeneity; Ordered probit; Computer science; Geography","score_opus":0.07067208900857296,"score_gpt":0.3772423559982617,"score_spread":0.30657026698968876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W132533186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052941954,0.00011086367,0.98787314,0.000044411692,0.000033994897,0.0002294527,0.00016619918,0.00003056037,0.006217175],"genre_scores_gemma":[0.5314921,0.00003980463,0.46830025,0.00001617184,0.000019218462,0.000049542145,0.000018411736,0.0000107086935,0.00005373517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978091,0.00024289581,0.0006866658,0.0005046154,0.00036245867,0.00039425798],"domain_scores_gemma":[0.9969476,0.0022239054,0.00017052722,0.00036312017,0.00019674834,0.00009812511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068375625,0.00019547224,0.0005469865,0.00036603995,0.000067352456,0.000056800254,0.00021338832,0.000058893827,0.00047233002],"category_scores_gemma":[0.0015348442,0.00015210576,0.000052571613,0.0018690838,0.00034330538,0.00026742977,0.00004834093,0.00017705004,0.000025718915],"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":[0.000096273376,0.00021364304,0.006162338,0.000052027157,0.00011618008,0.000024252651,0.00032278363,0.0007651893,0.000088837136,0.9705967,0.0000137167945,0.021548092],"study_design_scores_gemma":[0.00033307716,0.00016564554,0.0056026857,0.000038483788,0.00033025068,0.0000034534758,0.0002003618,0.095368035,0.00012522041,0.89752465,0.00008684793,0.00022125118],"about_ca_topic_score_codex":0.00020883816,"about_ca_topic_score_gemma":0.0028651468,"teacher_disagreement_score":0.52619797,"about_ca_system_score_codex":0.00007943529,"about_ca_system_score_gemma":0.00004355966,"threshold_uncertainty_score":0.62026924},"labels":[],"label_agreement":null},{"id":"W2001810418","doi":"10.1007/s10182-008-0082-1","title":"Calculation of the Prokhorov distance by optimal quantization and maximum flow","year":2008,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Advanced Statistical Methods and Models","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":"Université Laval","funders":"","keywords":"Mathematics; Bivariate analysis; Univariate; Simplex; Probability distribution; Quantization (signal processing); Applied mathematics; Metric (unit); Statistical distance; Mathematical optimization; Statistics; Multivariate statistics; Combinatorics","score_opus":0.03538346710639554,"score_gpt":0.38071468493557026,"score_spread":0.3453312178291747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001810418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012323658,0.00061259343,0.98621994,0.00006918814,0.000029916837,0.0001882638,0.00039331682,0.000013529506,0.00014956204],"genre_scores_gemma":[0.46327993,0.00031016796,0.53626525,0.000011161196,0.0000067155243,0.000014082106,0.000023137627,0.000009269449,0.00008028035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99839413,0.00018609471,0.0005276755,0.00032951342,0.00034134884,0.0002212221],"domain_scores_gemma":[0.9981223,0.0012702978,0.00019050344,0.0002489125,0.00009760209,0.00007039177],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023448239,0.00015261577,0.00044600945,0.00007671675,0.000111820584,0.000008543692,0.00011636912,0.000050779876,0.00003874073],"category_scores_gemma":[0.0013732988,0.00010884082,0.000065664746,0.00076662493,0.0003989007,0.00019557665,0.00005532115,0.00013072413,5.03142e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016736088,0.00035854193,0.03904484,0.0002402021,0.00021405864,0.000017026705,0.0007129855,0.031110005,0.00024290114,0.81344247,0.00025680487,0.1141928],"study_design_scores_gemma":[0.0004249372,0.00006534442,0.010285175,0.000038780337,0.000387147,0.000004063273,0.000078510835,0.4298982,0.00017940011,0.55742884,0.00096673844,0.00024284622],"about_ca_topic_score_codex":0.000020954301,"about_ca_topic_score_gemma":0.0001249553,"teacher_disagreement_score":0.45095626,"about_ca_system_score_codex":0.00003490359,"about_ca_system_score_gemma":0.000017930724,"threshold_uncertainty_score":0.44383997},"labels":[],"label_agreement":null},{"id":"W2003792946","doi":"10.1007/s10182-010-0151-0","title":"Absolute continuous bivariate generalized exponential distribution","year":2011,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":46,"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 New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Department of Science and Technology, Ministry of Science and Technology, India","keywords":"Mathematics; Joint probability distribution; Generalized beta distribution; Weibull distribution; Natural exponential family; Exponential distribution; Generalized gamma distribution; Gamma distribution; Applied mathematics; Marginal distribution; Copula (linguistics); Exponential function; Heavy-tailed distribution; Bivariate analysis; Generalized integer gamma distribution; Estimator; Cumulative distribution function; Inverse-chi-squared distribution; Probability density function; Exponential family; Distribution fitting; Statistics; Probability distribution; Mathematical analysis; Econometrics; Random variable","score_opus":0.055716153730191856,"score_gpt":0.36212645921803616,"score_spread":0.3064103054878443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003792946","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005352482,0.00006535455,0.9884058,0.000065951055,0.00006468528,0.0002647226,0.0029867045,0.00009736716,0.0026968848],"genre_scores_gemma":[0.84927666,0.00006850449,0.14862981,0.000044094253,0.00002837073,0.00018086862,0.00160639,0.000014032567,0.00015124414],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979642,0.00014766982,0.0007545413,0.00042604565,0.0003198168,0.00038775033],"domain_scores_gemma":[0.9984919,0.00063419866,0.0002025921,0.0003404747,0.00014949321,0.00018137252],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028224222,0.00020501824,0.00050088816,0.00014938842,0.00012268477,0.000036670746,0.00019969387,0.00007445357,0.0036428538],"category_scores_gemma":[0.001002144,0.00019113088,0.00013330841,0.001262317,0.0002145868,0.00020659821,0.000055642846,0.00015371267,0.0001127444],"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":[0.00005335051,0.00029366545,0.001281419,0.000016948787,0.00013858215,0.000015571437,0.00007707169,0.00004357015,0.000018382487,0.99059415,0.0005059243,0.006961345],"study_design_scores_gemma":[0.000923764,0.00005574423,0.08487754,0.0000143847765,0.0010761386,0.000003354244,0.00011582138,0.040038984,0.000084692256,0.86776066,0.0046297647,0.00041914024],"about_ca_topic_score_codex":0.00013668355,"about_ca_topic_score_gemma":0.00021572676,"teacher_disagreement_score":0.8439242,"about_ca_system_score_codex":0.000085790416,"about_ca_system_score_gemma":0.000024047298,"threshold_uncertainty_score":0.99726796},"labels":[],"label_agreement":null},{"id":"W2005209066","doi":"10.1007/s10182-010-0130-5","title":"Introduction of a new measure for detecting poor fit due to omitted nonlinear terms in SEM","year":2010,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Heteroscedasticity; Homoscedasticity; Measure (data warehouse); Mathematics; Covariance; Nonlinear system; Covariance matrix; Applied mathematics; Linear model; Residual; Statistics; Econometrics; Computer science; Algorithm","score_opus":0.01631907557253821,"score_gpt":0.30903695735933145,"score_spread":0.29271788178679325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005209066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03997904,0.00003180532,0.9587187,0.0009441179,0.00012306515,0.00012115107,0.00002843069,0.000024002917,0.00002966462],"genre_scores_gemma":[0.54819137,0.0000027327376,0.4516356,0.00003861258,0.00008552678,0.000011468856,0.0000064599835,0.000003830606,0.000024407238],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998541,0.000044638276,0.00044283443,0.00047954026,0.00022034359,0.0002716644],"domain_scores_gemma":[0.9990219,0.00030921845,0.0000968415,0.00032677667,0.00012224483,0.00012300645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046022277,0.00012471832,0.00037298797,0.00036925543,0.00003656654,0.000047925732,0.00037436315,0.000058895548,0.000032350505],"category_scores_gemma":[0.001044467,0.00011450558,0.00006419154,0.0017670181,0.00003800719,0.00029444936,0.00007447105,0.00023445209,0.0000039181646],"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":[0.000092790084,0.0001323867,0.005466439,0.000037677033,0.0000735062,0.0000128332895,0.00059299316,0.027894858,0.0038178326,0.02013464,0.00013320595,0.9416108],"study_design_scores_gemma":[0.00038614002,0.00014230316,0.0055758986,0.000021604366,0.000078576784,0.00000407562,0.000051144198,0.96476495,0.0015772129,0.026084647,0.0010770985,0.00023633412],"about_ca_topic_score_codex":0.00023258079,"about_ca_topic_score_gemma":0.0060876003,"teacher_disagreement_score":0.9413745,"about_ca_system_score_codex":0.000026520285,"about_ca_system_score_gemma":0.000053291606,"threshold_uncertainty_score":0.4669402},"labels":[],"label_agreement":null},{"id":"W2008020807","doi":"10.1007/s10182-010-0132-3","title":"Nonlinear structural equation modeling: is partial least squares an alternative?","year":2010,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"LISREL; Structural equation modeling; Latent variable; Mathematics; Partial least squares regression; Statistics; Econometrics","score_opus":0.29481605318908566,"score_gpt":0.5122797312166472,"score_spread":0.2174636780275615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008020807","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38531712,0.000072331975,0.6136181,0.000106073814,0.00030151184,0.00005394808,0.00015139587,0.000019772502,0.00035975437],"genre_scores_gemma":[0.7367756,0.00001976982,0.26290095,0.000063012296,0.00015816843,0.0000060910124,0.000036011894,0.000006873256,0.000033531025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99587715,0.00046514583,0.0010103607,0.0008673198,0.0013628722,0.0004171735],"domain_scores_gemma":[0.9885411,0.009927873,0.00030294748,0.0006403557,0.0003733609,0.00021435095],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0027478125,0.00020228825,0.0005664062,0.00092510507,0.00016861703,0.00026437605,0.0007761618,0.00008104763,0.0020589575],"category_scores_gemma":[0.038494386,0.00014591945,0.0001348699,0.003977259,0.00020441946,0.0008829711,0.00012502674,0.00039664566,0.000037482685],"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":[0.000095889365,0.00008842007,0.33266285,0.000004053438,0.00008811306,0.000019385558,0.0005142754,0.14811563,0.0001180604,0.018851234,0.000022990214,0.4994191],"study_design_scores_gemma":[0.0001845129,0.000070761496,0.01316246,0.000001957935,0.000068835645,0.0000013922906,0.00047016406,0.8208928,0.00003485267,0.1644349,0.0005164992,0.00016083356],"about_ca_topic_score_codex":0.00040935216,"about_ca_topic_score_gemma":0.0012838631,"teacher_disagreement_score":0.6727772,"about_ca_system_score_codex":0.000023001743,"about_ca_system_score_gemma":0.000034481185,"threshold_uncertainty_score":0.99885327},"labels":[],"label_agreement":null},{"id":"W2588733893","doi":"10.1007/s10182-017-0289-0","title":"Empirical phi-divergence test statistics for the difference of means of two populations","year":2017,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Advanced Statistical Methods and Models","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":"McMaster University","funders":"Ministerio de Economía y Competitividad","keywords":"Statistics; Mathematics; Divergence (linguistics); Empirical likelihood; Null hypothesis; Likelihood-ratio test; Statistic; Test statistic; Statistical hypothesis testing; Test (biology); Econometrics; Population; Score test; Likelihood principle; Sample (material); Maximum likelihood; Likelihood function; Quasi-maximum likelihood; Demography; Confidence interval","score_opus":0.22581768633624527,"score_gpt":0.5338017040270089,"score_spread":0.3079840176907636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588733893","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00084520015,0.00015112814,0.99134195,0.00011901514,0.00008919129,0.00030987264,0.006870003,0.000009727214,0.00026391394],"genre_scores_gemma":[0.42500457,0.00011353226,0.5747127,0.000010268502,0.000016574726,0.00003686176,0.000024841804,0.000010327747,0.000070317335],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977923,0.00012097735,0.0009385887,0.00038229823,0.00042791563,0.00033789876],"domain_scores_gemma":[0.97997224,0.018084655,0.000663737,0.0008229641,0.00035242474,0.00010398781],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00056787,0.0002103326,0.0008176622,0.00013010215,0.00029164949,0.000027562182,0.000590761,0.000049863673,0.000138331],"category_scores_gemma":[0.019368276,0.00014687575,0.00014773144,0.00034916413,0.0008317697,0.0001540994,0.00014620423,0.00016725145,8.446094e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005235762,0.00024929908,0.10304495,0.00013197078,0.0001466895,0.000003692842,0.00012635914,0.002657283,0.00005620484,0.8424661,0.000052724612,0.05101236],"study_design_scores_gemma":[0.00035861984,0.00010358765,0.07334632,0.000027854581,0.0009567099,3.883785e-7,0.00006956835,0.13723852,0.00006467891,0.78760785,0.0000812233,0.0001447035],"about_ca_topic_score_codex":0.00017418919,"about_ca_topic_score_gemma":0.0029726394,"teacher_disagreement_score":0.42415938,"about_ca_system_score_codex":0.00003205955,"about_ca_system_score_gemma":0.000043342883,"threshold_uncertainty_score":0.988892},"labels":[],"label_agreement":null},{"id":"W2791805568","doi":"10.1007/s10182-018-0323-x","title":"Expectation–maximization algorithm for system-based lifetime data with unknown system structure","year":2018,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Statistical Distribution Estimation and Applications","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":"McMaster University","funders":"Simons Foundation","keywords":"Component (thermodynamics); Weibull distribution; Expectation–maximization algorithm; Implementation; Computer science; Algorithm; Maximization; Monte Carlo method; Mathematical optimization; Data mining; Mathematics; Maximum likelihood; Statistics","score_opus":0.02817166435814962,"score_gpt":0.36806669300727013,"score_spread":0.3398950286491205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791805568","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015755885,0.000034684213,0.9843244,0.00008558383,0.00005293792,0.0005649762,0.01420837,0.00016079028,0.00041070586],"genre_scores_gemma":[0.42047128,0.0000013612126,0.5741738,0.000022170261,0.00006914798,0.00012209798,0.005096,0.000018167108,0.00002594644],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977704,0.00012378425,0.0006889486,0.0006550819,0.00044172406,0.00032006137],"domain_scores_gemma":[0.99646145,0.0017913445,0.00029210592,0.0007518415,0.0005496661,0.00015357981],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025410712,0.00023630312,0.00051215914,0.00024199199,0.00025143332,0.00008151362,0.00037301838,0.00007836318,0.0002512258],"category_scores_gemma":[0.00078276446,0.00019355917,0.00004962072,0.001633813,0.00027886385,0.0002707424,0.000047341386,0.00009914485,0.0000192835],"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":[0.00006175201,0.00011613206,0.00037890303,0.0002923939,0.0001962159,0.000004721228,0.00004489652,0.00180265,0.0000045002166,0.9755162,0.0004667499,0.021114908],"study_design_scores_gemma":[0.0007605095,0.00009633201,0.0011324353,0.00007744209,0.0009814373,0.0000031285676,0.0004598391,0.9857413,0.00003499887,0.009252041,0.001201807,0.00025871696],"about_ca_topic_score_codex":0.0000222749,"about_ca_topic_score_gemma":0.00036528934,"teacher_disagreement_score":0.98393863,"about_ca_system_score_codex":0.00019374843,"about_ca_system_score_gemma":0.00008944658,"threshold_uncertainty_score":0.7893114},"labels":[],"label_agreement":null},{"id":"W3161027617","doi":"10.1007/s10182-021-00406-8","title":"Quarterback evaluation in the national football league using tracking data","year":2021,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":19,"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":"Football; League; Computer science; Tracking (education); Field (mathematics); Operations research; Engineering; Mathematics; Geography","score_opus":0.18659186370477027,"score_gpt":0.38462930056839645,"score_spread":0.19803743686362618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161027617","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18794881,0.011504896,0.77216536,0.0011800805,0.00035465934,0.00034719703,0.0027815562,0.000014410937,0.023703031],"genre_scores_gemma":[0.99373084,0.00056755095,0.004741849,0.00022119345,0.00006479428,0.0000072315393,0.0006314184,0.000006318445,0.000028787847],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983847,0.000053345895,0.0006776025,0.00047581183,0.000193971,0.00021458429],"domain_scores_gemma":[0.9990625,0.00026098793,0.00018887418,0.00035608388,0.00010258786,0.00002900969],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020718235,0.00010196506,0.0003287377,0.00040489528,0.000064423555,0.0001058213,0.00031222182,0.000038292583,0.0010376024],"category_scores_gemma":[0.0005009934,0.000095995565,0.000056270695,0.0016741519,0.00005223447,0.00053376285,0.000056194134,0.00015528705,0.000024917319],"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":[0.000011131442,0.00020454597,0.54970604,0.000027273427,0.00016258925,0.000030282466,0.00041128983,0.18938151,0.0000024591839,0.24993181,0.00011916339,0.010011902],"study_design_scores_gemma":[0.00020414387,0.00000773152,0.16725305,0.000009585384,0.00007053995,0.0000019469446,0.0002090747,0.7881299,7.648522e-7,0.038419392,0.0055756164,0.0001182497],"about_ca_topic_score_codex":0.00029973796,"about_ca_topic_score_gemma":0.0048182774,"teacher_disagreement_score":0.805782,"about_ca_system_score_codex":0.000116801755,"about_ca_system_score_gemma":0.000062431274,"threshold_uncertainty_score":0.9998756},"labels":[],"label_agreement":null},{"id":"W3202737858","doi":"10.1007/s10182-021-00419-3","title":"A Bayesian nonparametric multi-sample test in any dimension","year":2021,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","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 Toronto","funders":"","keywords":"Mathematics; Dirichlet process; Nonparametric statistics; Prior probability; Dirichlet distribution; Statistics; Multivariate statistics; Dimension (graph theory); Bayesian probability; Multivariate normal distribution; Population; Sample (material); Combinatorics; Mathematical analysis","score_opus":0.013346212943969758,"score_gpt":0.3215683268169546,"score_spread":0.3082221138729848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202737858","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045406245,0.0014102202,0.99735916,0.00021955317,0.00007602454,0.000078939884,0.000066775785,0.00003153622,0.000303746],"genre_scores_gemma":[0.31097287,0.0002198816,0.6885567,0.00014817933,0.000009695222,0.000011972861,0.000020981015,0.00000601352,0.000053736283],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997565,0.00031756025,0.00051711575,0.0008013917,0.00032768745,0.00047127687],"domain_scores_gemma":[0.99593264,0.0031121369,0.0000885736,0.00059714983,0.000101085,0.000168404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005122911,0.00019331863,0.00055061985,0.0006778779,0.000057024183,0.00010142653,0.0003992088,0.000072003495,0.000095133204],"category_scores_gemma":[0.002394889,0.00017788202,0.00010691685,0.0074224635,0.000072141,0.00046693825,0.00023288821,0.00025777635,0.000010191589],"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":[0.000012135082,0.0009161831,0.18455113,0.00004248413,0.00009095355,0.0009170222,0.0003249884,0.0052814516,0.00019431608,0.17685917,0.000035381065,0.6307748],"study_design_scores_gemma":[0.0004668455,0.000049297327,0.0488612,0.00002258176,0.00008055317,0.000005413887,0.000027049515,0.8638,0.00013174475,0.085633636,0.0006365153,0.00028518468],"about_ca_topic_score_codex":0.00020914657,"about_ca_topic_score_gemma":0.002936013,"teacher_disagreement_score":0.85851854,"about_ca_system_score_codex":0.000082024075,"about_ca_system_score_gemma":0.0000738424,"threshold_uncertainty_score":0.7253818},"labels":[],"label_agreement":null},{"id":"W4410908240","doi":"10.1007/s10182-025-00527-4","title":"Using penalized-distance likelihood functions to analyze high-dimensional sparse/non-sparse data","year":2025,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Statistical Methods and Inference","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 Calgary","funders":"","keywords":"Mathematics; Sparse approximation; Sparse matrix; Maximum likelihood; Lasso (programming language); Statistics; Computer science; Pattern recognition (psychology); Artificial intelligence; Algorithm; Gaussian; Physics","score_opus":0.08169404633416365,"score_gpt":0.4307900450660689,"score_spread":0.3490959987319052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410908240","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004141358,0.0002943007,0.9893227,0.00023727158,0.00022137504,0.00026947857,0.003472057,0.000047886613,0.0019935255],"genre_scores_gemma":[0.24638084,0.000044325712,0.75257134,0.00025720222,0.00004877909,0.00003091938,0.0002934076,0.000020029063,0.00035313444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99608564,0.00037333125,0.0010870821,0.001142216,0.0006161423,0.000695599],"domain_scores_gemma":[0.99344563,0.004423361,0.0001971011,0.0013471738,0.00027004737,0.00031670643],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010816896,0.00037331617,0.0010874184,0.0007340346,0.00021699398,0.00010157607,0.00070284435,0.00009903529,0.0016816953],"category_scores_gemma":[0.005472068,0.000335503,0.000118784024,0.0043697255,0.00025636554,0.0003072275,0.0005566875,0.00035682207,0.00006567621],"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":[0.00028894073,0.0006439368,0.018207168,0.00021267268,0.0010470427,0.00011344949,0.000064842025,0.009331205,0.00015263443,0.90100676,0.003907801,0.06502358],"study_design_scores_gemma":[0.00074566936,0.00009328943,0.019260174,0.00026067402,0.002864816,0.0000026291295,0.00024135334,0.35896468,0.000024858942,0.6119826,0.0049205055,0.000638801],"about_ca_topic_score_codex":0.00053417933,"about_ca_topic_score_gemma":0.003138462,"teacher_disagreement_score":0.34963346,"about_ca_system_score_codex":0.00016632331,"about_ca_system_score_gemma":0.00018326925,"threshold_uncertainty_score":0.9999097},"labels":[],"label_agreement":null},{"id":"W4414233165","doi":"10.1007/s10182-025-00539-0","title":"Bayesian analysis of censored measurement error models using finite mixture of heavy-tailed distributions","year":2025,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Statistical Distribution Estimation and Applications","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 Manitoba","funders":"National Natural Science Foundation of China","keywords":"Covariate; Bayesian probability; Markov chain Monte Carlo; Bayesian linear regression; Mixture model; Errors-in-variables models; Observational error; Latent variable; Scale (ratio); Bayesian inference","score_opus":0.06444296842703583,"score_gpt":0.3997372705513714,"score_spread":0.3352943021243356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414233165","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001325778,0.00018142084,0.9884982,0.00014520349,0.00001982245,0.0002308909,0.008952394,0.00002475108,0.0006215422],"genre_scores_gemma":[0.840191,0.00002976249,0.15897086,0.000017509798,0.0000032974158,0.00003728739,0.0007225582,0.000006367855,0.000021379301],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722695,0.00019019762,0.0012919996,0.0004008133,0.00060120644,0.00028881675],"domain_scores_gemma":[0.99656427,0.0017217324,0.00039411476,0.0004932779,0.0007139019,0.00011268196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045214794,0.00021164038,0.001041914,0.0008890724,0.00010404164,0.000017683205,0.00022200926,0.00008824112,0.0004638355],"category_scores_gemma":[0.0025412554,0.00019943387,0.0003294036,0.0077121924,0.00030619762,0.00013773731,0.000056882014,0.00014969357,8.1253927e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004954118,0.00043851222,0.0036052007,0.00011244112,0.0019258389,0.0000014387568,0.000047673057,0.15508355,0.000071924966,0.8373395,0.000059683294,0.0012646767],"study_design_scores_gemma":[0.00024688413,0.0000132691175,0.0069606067,0.000043355227,0.007675095,7.8694946e-8,0.00012391238,0.7214822,0.00011624941,0.26315996,0.0000504916,0.0001278884],"about_ca_topic_score_codex":0.000097642136,"about_ca_topic_score_gemma":0.00080608454,"teacher_disagreement_score":0.8388652,"about_ca_system_score_codex":0.00020216446,"about_ca_system_score_gemma":0.00010276279,"threshold_uncertainty_score":0.8132677},"labels":[],"label_agreement":null},{"id":"W4416215049","doi":"10.1007/s10182-025-00546-1","title":"Margin-closed regime-switching multivariate time series models","year":2025,"lang":"en","type":"article","venue":"AStA Advances in Statistical Analysis","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","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 British Columbia","funders":"","keywords":"Multivariate statistics; Series (stratigraphy); Markov chain; Markov property; Inference; Markov process; Variable-order Markov model; Sequence (biology); Markov model; Latent variable","score_opus":0.014613049848990506,"score_gpt":0.26519732445161653,"score_spread":0.250584274602626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416215049","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012190495,0.0026533916,0.96807724,0.00030503154,0.0001114108,0.00013019258,0.00037742162,0.00004010607,0.01611473],"genre_scores_gemma":[0.9316288,0.00062155654,0.06581767,0.00010696204,0.000025853451,0.00002410762,0.00007010777,0.000014178528,0.0016907316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979323,0.000041299165,0.00091916986,0.0006426207,0.00006463091,0.00039998852],"domain_scores_gemma":[0.9989994,0.00030955675,0.0001970801,0.00037667633,0.00004783518,0.00006946351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005549915,0.00020633903,0.0008067082,0.0006649639,0.00013808343,0.00007665531,0.0002416572,0.00009397846,0.0002960891],"category_scores_gemma":[0.0004443954,0.0002315708,0.00015902844,0.0015495821,0.00007748108,0.0007594046,0.00010147121,0.00023633701,0.00011059799],"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":[0.00009418506,0.000085456064,0.032641232,0.00003911037,0.00019259666,0.000010362935,0.00021612534,0.061674673,0.000007336758,0.89159656,0.000044306456,0.013398058],"study_design_scores_gemma":[0.00022498518,0.000013628679,0.011165964,0.00001663609,0.00005721083,1.2216917e-7,0.000032711872,0.5276993,0.0000030635078,0.45797667,0.0026482583,0.00016146907],"about_ca_topic_score_codex":0.00087948394,"about_ca_topic_score_gemma":0.0005850553,"teacher_disagreement_score":0.91943836,"about_ca_system_score_codex":0.0001182081,"about_ca_system_score_gemma":0.000028005436,"threshold_uncertainty_score":0.9443183},"labels":[],"label_agreement":null}]}