{"meta":{"query_hash":"215245d4a577","filters":{"venue":"Journal of Applied Statistics"},"cohort_total":91,"direct_labels_cover":0,"predictions_cover":91,"exported":91,"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/215245d4a577","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+of+Applied+Statistics"},"results":[{"id":"W1968805547","doi":"10.1080/02664760500168648","title":"Interpretable dimension reduction","year":2005,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Data Analysis with R","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; Acadia University","funders":"University of Waterloo; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Principal component analysis; Linear subspace; Dimensionality reduction; Constraint (computer-aided design); Dimension (graph theory); Mathematics; Homogeneity (statistics); Reduction (mathematics); Mathematical optimization; Computer science; Algorithm; Statistics; Artificial intelligence; Combinatorics","score_opus":0.007379734791390265,"score_gpt":0.24240870830722677,"score_spread":0.23502897351583651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1968805547","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":[0.0022807121,0.00003674617,0.9948702,0.00028994,0.0002690844,0.000031755542,0.0000075744006,0.000014565699,0.002199462],"genre_scores_gemma":[0.40718725,0.0000239271,0.59241873,0.00010804309,0.00014946827,4.2444844e-7,0.0000024911774,0.000004288686,0.00010538954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989526,0.000015889624,0.0004237489,0.000116764466,0.00035569523,0.00013529736],"domain_scores_gemma":[0.9990166,0.00005307823,0.00040641992,0.0002664027,0.00016961794,0.000087919594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037208205,0.00007987432,0.00018085928,0.00014664997,0.000051201154,0.000104148,0.0004707895,0.000028454433,0.000040296905],"category_scores_gemma":[0.000032340457,0.000066493296,0.000034852485,0.00021162032,0.000023827475,0.00040819042,0.000093219365,0.00017217599,0.00005806506],"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":[0.00007956413,0.00020023134,0.000020044694,0.0000131012375,0.00013837634,0.00003872175,0.0013832438,0.0092982035,0.020508854,0.28236663,0.20761795,0.47833505],"study_design_scores_gemma":[0.002600694,0.0007308454,0.0009370469,0.00012518036,0.00039375064,0.0011253335,0.000455098,0.5768302,0.042331792,0.11090702,0.26261732,0.0009457057],"about_ca_topic_score_codex":0.000001443378,"about_ca_topic_score_gemma":0.000001623536,"teacher_disagreement_score":0.567532,"about_ca_system_score_codex":0.00007676418,"about_ca_system_score_gemma":0.000065665685,"threshold_uncertainty_score":0.2711518},"labels":[],"label_agreement":null},{"id":"W1969946313","doi":"10.1080/02664760802192981","title":"Diagnostics of prior-data agreement in applied Bayesian analysis","year":2008,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":62,"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":"Bayesian probability; Prior probability; Computer science; Bayesian hierarchical modeling; Bayesian average; Reliability (semiconductor); Bayesian statistics; Bayesian experimental design; Data mining; Statistics; Bayesian inference; Mathematics; Artificial intelligence","score_opus":0.13993335252795808,"score_gpt":0.4126900095050708,"score_spread":0.2727566569771127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969946313","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":[0.010763728,0.0001209409,0.9857149,0.000036351823,0.0002066342,0.00015140437,0.0005163587,0.0000052530977,0.002484432],"genre_scores_gemma":[0.64932233,0.00020324072,0.35030884,0.000023640285,0.00008989112,0.0000020757554,0.000015135592,0.000011792438,0.000023074484],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9937767,0.000065435524,0.0026533012,0.00043063427,0.002685617,0.0003883254],"domain_scores_gemma":[0.988761,0.0075147515,0.0019111353,0.0009169556,0.00063384767,0.00026228803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002540691,0.0002236558,0.0010796434,0.0009443468,0.00011141041,0.00004952113,0.001639668,0.00008841977,0.00016524455],"category_scores_gemma":[0.007413644,0.00018176963,0.000081863145,0.002199556,0.0002777363,0.00015941271,0.00032560845,0.00044328772,0.00002174628],"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":[0.0019291,0.0021161078,0.07876366,0.0001966139,0.0016961955,0.002190969,0.0074571637,0.12972216,0.001363113,0.19612004,0.024510454,0.5539344],"study_design_scores_gemma":[0.005334874,0.00050524616,0.19133355,0.00010158787,0.0016705679,0.00008939314,0.005215314,0.062142167,0.0023826617,0.7226063,0.00736405,0.0012543198],"about_ca_topic_score_codex":0.000005226344,"about_ca_topic_score_gemma":0.00006595433,"teacher_disagreement_score":0.63855857,"about_ca_system_score_codex":0.000120620585,"about_ca_system_score_gemma":0.0002867333,"threshold_uncertainty_score":0.887536},"labels":[],"label_agreement":null},{"id":"W1972766374","doi":"10.1080/02664763.2011.595399","title":"Applying a marginalized frailty model to competing risks","year":2011,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","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 Guelph; Public Health Agency of Canada; Western University","funders":"","keywords":"Multivariate statistics; Econometrics; Martingale (probability theory); Multivariate analysis; Statistics; Proportional hazards model; Computer science; Breast cancer; Cluster analysis; Actuarial science; Mathematics; Medicine; Economics; Cancer","score_opus":0.1619227687976239,"score_gpt":0.366346027452832,"score_spread":0.2044232586552081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1972766374","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":[0.050796464,0.000043978544,0.75103515,0.00008877236,0.0004776622,0.00088510144,0.00008199917,0.00004862268,0.19654225],"genre_scores_gemma":[0.6494986,0.00008613571,0.34975606,0.00035300196,0.00016621781,0.000029510875,0.0000015973169,0.00001898611,0.000089940295],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976943,0.00009363736,0.0006764731,0.00018032937,0.0009183121,0.00043696293],"domain_scores_gemma":[0.9984473,0.00013940573,0.0006213575,0.00018768723,0.00032748675,0.0002767764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020072598,0.0001658228,0.0003717432,0.00024346322,0.0004336466,0.0000901308,0.0004958611,0.00007516327,0.0001644379],"category_scores_gemma":[0.00013250092,0.00016341347,0.000095580894,0.00035064048,0.00017127172,0.000103058286,0.00007867742,0.00032357936,0.000038805723],"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":[0.00046005356,0.00029198307,0.006086502,0.00007685036,0.00022897603,0.000108393244,0.041266378,0.004483654,0.00018377719,0.8889136,0.01027207,0.0476278],"study_design_scores_gemma":[0.0050850254,0.0005131321,0.05346433,0.00028567328,0.00096220785,0.000015503256,0.05576794,0.01821082,0.00035164607,0.65765923,0.20556475,0.0021197665],"about_ca_topic_score_codex":0.00038000924,"about_ca_topic_score_gemma":0.000323363,"teacher_disagreement_score":0.5987021,"about_ca_system_score_codex":0.0001125458,"about_ca_system_score_gemma":0.00015757253,"threshold_uncertainty_score":0.66638076},"labels":[],"label_agreement":null},{"id":"W1978467022","doi":"10.1080/02664760802443988","title":"Default Bayesian goodness-of-fit tests for the skew-normal model","year":2008,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":23,"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 Arizona; Ryerson University","keywords":"Goodness of fit; Skewness; Statistics; Mathematics; Skew; Bayesian probability; Econometrics; Asymmetry; Kurtosis; Computer science","score_opus":0.15873245974844416,"score_gpt":0.39253831372430315,"score_spread":0.23380585397585898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978467022","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":[0.0011947722,0.000020299327,0.99542487,0.0002578402,0.00006404528,0.00032152786,0.0015387163,0.000014513798,0.0011634289],"genre_scores_gemma":[0.4982252,0.000022615854,0.5014452,0.00008958285,0.0000621188,0.000027023454,0.000019573148,0.000016490943,0.00009220257],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984279,0.000013454299,0.00085054926,0.000100378886,0.00041112615,0.00019657088],"domain_scores_gemma":[0.99576,0.0025744769,0.0007206176,0.00022362336,0.0005969405,0.00012430307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003245502,0.00014081068,0.0003150631,0.000056717905,0.00025583542,0.000018262592,0.00027899235,0.00009330211,0.00007984192],"category_scores_gemma":[0.00095444545,0.00010153019,0.00009109367,0.00016241947,0.00019675275,0.00004792574,0.000025251098,0.00026695876,0.000006963479],"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":[0.00007278782,0.00018983509,0.000014292371,0.000065447275,0.00005312039,0.0000026387704,0.00027894517,0.003190366,0.00021963433,0.94600016,0.04727924,0.0026335416],"study_design_scores_gemma":[0.0009403409,0.000080964994,0.0009748316,0.000018930185,0.00020139113,0.000059049948,0.00015360776,0.2817921,0.0005332706,0.7136062,0.0014910776,0.00014823429],"about_ca_topic_score_codex":0.0000015517546,"about_ca_topic_score_gemma":0.0000028309028,"teacher_disagreement_score":0.49703044,"about_ca_system_score_codex":0.000044942837,"about_ca_system_score_gemma":0.00021432621,"threshold_uncertainty_score":0.41402808},"labels":[],"label_agreement":null},{"id":"W1980895071","doi":"10.1080/02664763.2010.516388","title":"A flexible parametric survival model which allows a bathtub-shaped hazard rate function","year":2011,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":29,"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 Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Weibull distribution; Bathtub; Log-normal distribution; Statistics; Mathematics; Parametric statistics; Hazard; Log-logistic distribution; Distribution (mathematics); Function (biology); Applied mathematics; Econometrics; Distribution fitting; Exponential distribution; Mathematical analysis; Geography","score_opus":0.05949770112114674,"score_gpt":0.29749862229911156,"score_spread":0.2380009211779648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980895071","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":[0.06340094,0.0000805831,0.81749195,0.00008613771,0.0015199382,0.0005152677,0.00008793328,0.00007579797,0.11674147],"genre_scores_gemma":[0.9389525,0.00048657355,0.05961666,0.00018462226,0.0002819177,0.00001376749,0.000006679185,0.000030208348,0.00042708818],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99719375,0.00018937203,0.00079608196,0.00024372521,0.0010766118,0.00050042645],"domain_scores_gemma":[0.9977651,0.00022150048,0.00080125674,0.00023762052,0.0007255785,0.00024890993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031371722,0.0002161167,0.00044088438,0.00047033868,0.00039499518,0.00013197667,0.0004428932,0.00013628005,0.00022085838],"category_scores_gemma":[0.00026265325,0.00020623459,0.00012405324,0.001187687,0.00019042181,0.00022598216,0.000055515266,0.0004149349,0.000056112105],"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":[0.0013455568,0.0007610305,0.0073718377,0.000097091426,0.0006199001,0.0000721125,0.009797711,0.0060951104,0.00018960482,0.94323885,0.014419433,0.015991747],"study_design_scores_gemma":[0.0047445716,0.0010419973,0.14030865,0.000079704434,0.0015269389,0.0000069350676,0.011358899,0.05834878,0.00013505042,0.7509756,0.0299094,0.0015634524],"about_ca_topic_score_codex":0.00022058736,"about_ca_topic_score_gemma":0.0011932034,"teacher_disagreement_score":0.8755515,"about_ca_system_score_codex":0.00013724713,"about_ca_system_score_gemma":0.00036603375,"threshold_uncertainty_score":0.84100026},"labels":[],"label_agreement":null},{"id":"W1983604712","doi":"10.1080/02664760600679619","title":"Two-way analysis of variance for data from a concentrated bipolar Watson distribution","year":2006,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":7,"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":"Simon Fraser University","keywords":"Watson; Variance (accounting); Distribution (mathematics); Statistics; Computer science; Mathematics; Algorithm; Econometrics; Artificial intelligence; Mathematical analysis","score_opus":0.01800048964258992,"score_gpt":0.2616770483557746,"score_spread":0.24367655871318467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1983604712","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":[0.03158925,0.00006728229,0.9513005,0.00002044647,0.00010155612,0.00011244739,0.016499225,0.0000041161634,0.000305199],"genre_scores_gemma":[0.8097698,0.000041691543,0.18623601,0.000028961682,0.00007591566,0.0000018512209,0.0038185795,0.000009018329,0.000018148161],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986926,0.000018380208,0.0005972561,0.00017880094,0.00033099498,0.00018200597],"domain_scores_gemma":[0.99853516,0.0003674843,0.00070732017,0.00025892793,0.00006555791,0.00006554037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036427157,0.00010497746,0.0003352078,0.00003972215,0.00006580611,0.000030363226,0.00031244123,0.000039638493,0.00023428182],"category_scores_gemma":[0.00009584823,0.00009530511,0.000043974393,0.00038333936,0.000100638,0.00007652296,0.000080027916,0.00009393439,0.000005745502],"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":[0.0016463673,0.0014152551,0.06432099,0.00011112506,0.0040000905,0.00010186327,0.0007422959,0.23633185,0.13043691,0.23219404,0.22652704,0.102172166],"study_design_scores_gemma":[0.0025891527,0.00015847474,0.19771019,0.000027597056,0.003803895,0.0000033566346,0.00017404904,0.69330484,0.0027435294,0.05162736,0.047465242,0.00039230575],"about_ca_topic_score_codex":0.001001915,"about_ca_topic_score_gemma":0.0003751353,"teacher_disagreement_score":0.7781806,"about_ca_system_score_codex":0.0000949662,"about_ca_system_score_gemma":0.000028556293,"threshold_uncertainty_score":0.38864297},"labels":[],"label_agreement":null},{"id":"W1984579286","doi":"10.1080/02664763.2012.711814","title":"Spatial modeling using frequentist approach for disease mapping","year":2012,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","cited_by":9,"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 Manitoba","funders":"","keywords":"Frequentist inference; Generalized linear mixed model; Markov chain Monte Carlo; Bayesian probability; Computer science; Econometrics; Spatial econometrics; Statistics; Data mining; Bayesian inference; Machine learning; Mathematics; Artificial intelligence","score_opus":0.11059783449113725,"score_gpt":0.25909455274568427,"score_spread":0.14849671825454702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1984579286","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":[0.011375157,0.0005133973,0.98521525,0.000013359484,0.0003214173,0.00011541253,0.0016271347,0.0000045134034,0.00081438175],"genre_scores_gemma":[0.6779839,0.000036048907,0.3211993,0.000053825956,0.0005859326,0.0000035248574,0.00010676653,0.000016694701,0.000013998763],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869984,0.00000581357,0.00081865134,0.00013215862,0.00006924675,0.00027430643],"domain_scores_gemma":[0.99880606,0.000052242438,0.0007046259,0.00014560552,0.00007490424,0.00021656712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005857065,0.00012273372,0.00039987662,0.00021294881,0.00011790176,0.000064640786,0.00016442558,0.000047514786,0.0000764824],"category_scores_gemma":[0.000078838704,0.00012956098,0.000120195604,0.00011727166,0.000023858838,0.00017283444,0.00002808259,0.0001253062,0.000012146235],"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":[0.0005971458,0.0008932836,0.04270014,0.00063413224,0.0010896696,0.00001538198,0.001995754,0.18542872,0.00040849877,0.74889266,0.0031151795,0.014229422],"study_design_scores_gemma":[0.0005188228,0.000017026025,0.00073589204,0.000008877466,0.00011081437,0.000004970177,0.00014117944,0.9608461,0.000009369393,0.035361577,0.0020397285,0.00020559016],"about_ca_topic_score_codex":0.00010479907,"about_ca_topic_score_gemma":0.0000022492038,"teacher_disagreement_score":0.77541745,"about_ca_system_score_codex":0.00008212769,"about_ca_system_score_gemma":0.000030977542,"threshold_uncertainty_score":0.5283344},"labels":[],"label_agreement":null},{"id":"W1989860334","doi":"10.1080/0266476022000030075","title":"An extension of the Dirichlet prior for the analysis of longitudinal multinomial data","year":2003,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","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 British Columbia","funders":"","keywords":"Multinomial distribution; Dirichlet distribution; Multinomial probit; Bayesian probability; Computer science; Econometrics; Prior probability; Longitudinal data; Statistics; Mathematics; Multinomial logistic regression; Data mining","score_opus":0.12119000676231616,"score_gpt":0.4159998562650252,"score_spread":0.29480984950270905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1989860334","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":[0.009179504,0.000027425582,0.9889182,0.00003035006,0.00015459725,0.00023884214,0.0013516971,0.000002081843,0.000097312644],"genre_scores_gemma":[0.3425006,0.000014121559,0.65740967,0.000016685643,0.000038369053,0.0000018084173,0.0000053211497,0.000009403996,0.000004027396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981999,0.00012838426,0.0009278751,0.00015602153,0.0004318248,0.00015603633],"domain_scores_gemma":[0.9907822,0.006581824,0.0012851561,0.0008041226,0.00048293214,0.000063756524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019166002,0.00012636704,0.00058159925,0.00009209628,0.00010854701,0.00002242926,0.00067149167,0.000055626275,0.000064450585],"category_scores_gemma":[0.0044665593,0.000065736494,0.00011393652,0.00037216715,0.00019482596,0.000043225726,0.00006542279,0.00019064077,1.930422e-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":[0.0003219789,0.00036395522,0.0009588394,0.00013017333,0.0009309807,0.0000034091743,0.00036497132,0.00020041915,0.002737517,0.94742703,0.00257415,0.043986555],"study_design_scores_gemma":[0.0016784196,0.00039529448,0.06764036,0.000077121855,0.010585872,0.00001994387,0.0007676641,0.0750307,0.0040115514,0.83868456,0.0008396326,0.00026890144],"about_ca_topic_score_codex":0.0000061682426,"about_ca_topic_score_gemma":0.000021742537,"teacher_disagreement_score":0.3333211,"about_ca_system_score_codex":0.000019287694,"about_ca_system_score_gemma":0.00013316165,"threshold_uncertainty_score":0.53472114},"labels":[],"label_agreement":null},{"id":"W1992107314","doi":"10.1080/02664763.2012.692545","title":"Biostatistics: a computing approach","year":2012,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","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":"Carleton University","funders":"","keywords":"Biostatistics; Computer science; Data mining; Econometrics; Data science; Mathematics; Medicine","score_opus":0.058661597922472,"score_gpt":0.2880189262616139,"score_spread":0.2293573283391419,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992107314","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":[0.0059968983,0.00011149027,0.9671052,0.000039692663,0.0009182779,0.000094654075,0.00004302275,0.000022994438,0.025667738],"genre_scores_gemma":[0.81241196,0.00001336391,0.1839252,0.0005881677,0.002965778,7.784724e-7,0.000047513997,0.000023438079,0.000023812818],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99862933,0.000004225793,0.00054048374,0.00009878152,0.00039164204,0.00033555858],"domain_scores_gemma":[0.9986496,0.00011040626,0.00073922396,0.00014250413,0.00032602527,0.00003225968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00060002925,0.00015855163,0.00027132014,0.00021390783,0.000119794386,0.00018316919,0.00030280507,0.000056199908,0.0001711094],"category_scores_gemma":[0.00015913718,0.00013064321,0.00003799758,0.00032213077,0.00007877923,0.00054886716,0.000116041134,0.000240379,0.00016754112],"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":[0.00011848652,0.00038812388,0.004154734,0.00040618534,0.00007505009,0.00001351332,0.00024142014,0.0003362187,0.00044000024,0.81159276,0.10399545,0.07823808],"study_design_scores_gemma":[0.0025356899,0.00007118356,0.035855684,0.00023681491,0.0010122558,0.00030422807,0.0037935684,0.054440465,0.00072801905,0.08041546,0.8187397,0.0018669439],"about_ca_topic_score_codex":0.00001018261,"about_ca_topic_score_gemma":8.746941e-7,"teacher_disagreement_score":0.806415,"about_ca_system_score_codex":0.000026372136,"about_ca_system_score_gemma":0.000026946862,"threshold_uncertainty_score":0.53274757},"labels":[],"label_agreement":null},{"id":"W1992842452","doi":"10.1080/02664763.2012.694257","title":"The Oxford handbook of quantitative asset management","year":2012,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"GDG Environnement","funders":"","keywords":"Asset management; Asset (computer security); Computer science; Econometrics; Mathematics; Economics; Finance","score_opus":0.02784343026381192,"score_gpt":0.2466945333010758,"score_spread":0.21885110303726388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992842452","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":[0.014763204,0.005719717,0.8628857,0.0001165504,0.001387765,0.0003364554,0.0003564058,0.000006022161,0.11442818],"genre_scores_gemma":[0.8728107,0.008410539,0.1179544,0.00012364976,0.00016901155,0.000009795941,0.0000054387783,0.000021230135,0.0004952254],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998773,0.0000065810364,0.00082881,0.00007055805,0.000086626314,0.0002344703],"domain_scores_gemma":[0.9985014,0.00012482684,0.0011060127,0.00015081327,0.00006628791,0.00005061038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009815069,0.000092863826,0.00029854444,0.00011447703,0.00010792729,0.000028535675,0.00021547578,0.000031460077,0.000031943826],"category_scores_gemma":[0.000041207688,0.00007569903,0.00006629912,0.00012404606,0.000072142146,0.000097397395,0.000043296317,0.00012881121,0.000055831322],"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":[0.000095671756,0.00007560597,0.0030749694,0.00003712501,0.00012501358,0.0000030195213,0.00041849865,0.00006042031,0.0000049062946,0.97671425,0.009648884,0.009741621],"study_design_scores_gemma":[0.0009940185,0.00022989744,0.063799605,0.000044021956,0.000057992824,0.0000035187866,0.0010201712,0.00022504367,0.00017206314,0.3483466,0.58488435,0.000222741],"about_ca_topic_score_codex":0.0000036612773,"about_ca_topic_score_gemma":0.0000029704856,"teacher_disagreement_score":0.8580475,"about_ca_system_score_codex":0.00005246882,"about_ca_system_score_gemma":0.000009633853,"threshold_uncertainty_score":0.30869168},"labels":[],"label_agreement":null},{"id":"W1995233261","doi":"10.1080/02664760050173300","title":"Unequal probability sampling in fixed area plots of stem volume with and without prior inclusion probabilities","year":2000,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Forest ecology and management","field":"Environmental Science","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":"Canadian Sport Centre Pacific; Natural Resources Canada","funders":"","keywords":"Statistics; Sampling (signal processing); Mathematics; Stratified sampling; Sample size determination; Sampling design; Poisson sampling; Cluster sampling; Consistency (knowledge bases); Sampling bias; Population; Systematic sampling; Mean squared error; Econometrics; Slice sampling; Importance sampling; Monte Carlo method; Computer science; Demography","score_opus":0.01480942598056659,"score_gpt":0.2243010419601518,"score_spread":0.2094916159795852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995233261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985939,0.000009239961,0.012476047,0.00003728744,0.000017849161,0.00033682608,0.000014892297,0.0000046190858,0.0011641936],"genre_scores_gemma":[0.92924255,0.000014997373,0.07058515,0.000035984427,0.000006702683,0.000006467465,0.0000012423643,0.000007001219,0.00009992231],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989726,0.000030586754,0.00043312207,0.00013808311,0.00026959396,0.00015604522],"domain_scores_gemma":[0.99949825,0.00007744395,0.00024380203,0.00010551144,0.000017281733,0.000057709996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054851937,0.0001011516,0.00024634768,0.000036475096,0.00009328875,0.000009148769,0.00011754743,0.00004543725,0.00036505243],"category_scores_gemma":[0.000015641986,0.000076509656,0.0000125252545,0.00009475558,0.00029729522,0.00008100225,0.00016148602,0.00015076039,0.0000043886616],"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":[0.004046416,0.0011118186,0.71656966,0.0005003378,0.000092752416,0.00003714725,0.01399743,0.14413337,0.0006205784,0.022344124,0.00062555354,0.09592081],"study_design_scores_gemma":[0.0028189064,0.0014914644,0.84977657,0.0001289924,0.000092241,0.000022380415,0.0008113191,0.0060133385,0.00019230212,0.13628358,0.0020487371,0.00032017202],"about_ca_topic_score_codex":0.000030504485,"about_ca_topic_score_gemma":0.00041292096,"teacher_disagreement_score":0.13812003,"about_ca_system_score_codex":0.00012976615,"about_ca_system_score_gemma":0.000029008015,"threshold_uncertainty_score":0.3997068},"labels":[],"label_agreement":null},{"id":"W2001217603","doi":"10.1080/02664760050120588","title":"Detecting excessive similarity in answers on multiple choice exams","year":2000,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":72,"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":"","keywords":"Cheating; False accusation; Bonferroni correction; Simple (philosophy); Computer science; Econometrics; Similarity (geometry); Statistics; Mathematics; Artificial intelligence; Psychology; Social psychology; Epistemology","score_opus":0.022900217674808723,"score_gpt":0.30883947224276775,"score_spread":0.28593925456795904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001217603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89599353,0.00004765583,0.008348178,0.00066245865,0.00045926363,0.00023721857,0.000082368424,0.000021095662,0.09414823],"genre_scores_gemma":[0.9918231,0.00020249112,0.006787441,0.00053066213,0.00045210574,0.0000014193283,0.000001866547,0.000008354255,0.00019256119],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985365,0.00012811701,0.00042327377,0.00011064019,0.0005213401,0.00028008205],"domain_scores_gemma":[0.9963887,0.0030457927,0.00028381345,0.00006451561,0.00009147761,0.00012573687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001496302,0.00009904635,0.00021877419,0.000093154886,0.00026071197,0.000045068457,0.00025518006,0.0003198166,0.0004984227],"category_scores_gemma":[0.002053487,0.00009284901,0.00003519063,0.0002018591,0.00013277333,0.00010676421,0.000008537924,0.0018071702,0.00002304492],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012014601,0.00042609207,0.019449841,0.000057504214,0.000097374155,0.0003213067,0.0971502,0.009136831,0.00062780984,0.05062998,0.01837601,0.8025256],"study_design_scores_gemma":[0.00764833,0.00092133245,0.09757487,0.00060326356,0.0001975556,0.000037807815,0.066175714,0.007829263,0.0034195948,0.17810552,0.6357927,0.0016940715],"about_ca_topic_score_codex":0.0007999705,"about_ca_topic_score_gemma":0.001893631,"teacher_disagreement_score":0.8008315,"about_ca_system_score_codex":0.00017383407,"about_ca_system_score_gemma":0.00017813152,"threshold_uncertainty_score":0.78513557},"labels":[],"label_agreement":null},{"id":"W2002579858","doi":"10.1080/02664763.2011.580336","title":"A spatial random-effects model for interzone flows: commuting in Northern Ireland","year":2011,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Urban Transport and Accessibility","field":"Social Sciences","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":"Queen's University","funders":"","keywords":"Econometrics; Variable (mathematics); Estimation; Geography; Latent variable; Mathematics; Statistics; Computer science; Economics","score_opus":0.03238235178081022,"score_gpt":0.29100531848409006,"score_spread":0.25862296670327983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002579858","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":[0.3661979,0.000023957467,0.6313067,0.000016554988,0.00014523478,0.00025874557,0.000025596853,0.000006115986,0.0020191947],"genre_scores_gemma":[0.94467777,0.000012193035,0.055086706,0.00003652314,0.00013893342,0.000007927893,0.0000037516857,0.000010261888,0.000025953912],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989242,0.000037563623,0.0004940828,0.00009104078,0.00023339578,0.00021974696],"domain_scores_gemma":[0.9989998,0.00036456998,0.00032536694,0.00007591245,0.00014220647,0.00009217311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000995154,0.000090877606,0.00029563459,0.00006917153,0.00013832365,0.000026932843,0.00022438851,0.00006939856,0.000019980753],"category_scores_gemma":[0.00015234205,0.000078046134,0.00006098901,0.000079337704,0.000097800286,0.00008646766,0.000011856419,0.00021299359,0.0000014189563],"study_design_candidate":"theoretical_or_conceptual","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":[0.011844149,0.0017817143,0.4669981,0.00058113964,0.00028881512,0.00017121415,0.3336055,0.0029698438,0.00066542224,0.03078319,0.0012343766,0.14907657],"study_design_scores_gemma":[0.032774962,0.00082014716,0.10380826,0.0004750583,0.0006049738,0.000003853429,0.009303196,0.28411365,0.0007561757,0.56516874,0.0009960461,0.0011749458],"about_ca_topic_score_codex":0.00050717406,"about_ca_topic_score_gemma":0.047935955,"teacher_disagreement_score":0.5784798,"about_ca_system_score_codex":0.00007273238,"about_ca_system_score_gemma":0.00017960319,"threshold_uncertainty_score":0.9694367},"labels":[],"label_agreement":null},{"id":"W2007805548","doi":"10.1080/0266476032000075976","title":"Impact evaluation of job training programmes: Selection bias in multilevel models","year":2003,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":20,"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":"Regione Lombardia; Memorial University of Newfoundland","keywords":"Selection (genetic algorithm); Multilevel model; Computer science; Selection bias; Observational study; Propensity score matching; Set (abstract data type); Hierarchical database model; Random effects model; Sample (material); Sample size determination; Statistics; Econometrics; Machine learning; Data mining; Mathematics; Meta-analysis","score_opus":0.47239335593781373,"score_gpt":0.4972340829281534,"score_spread":0.02484072699033968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007805548","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":[0.18841039,0.000017615921,0.80971664,0.0000022469776,0.000031091502,0.00034746577,0.000020942369,0.000017260898,0.0014363526],"genre_scores_gemma":[0.57177025,0.0000111223335,0.42817262,0.0000032365072,0.000012710344,0.000010756978,0.0000014193629,0.000015014109,0.0000028728225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979603,0.000125605,0.00090240897,0.00010352944,0.0006941315,0.00021398765],"domain_scores_gemma":[0.9974146,0.0006059438,0.0009706573,0.000109539265,0.00083074416,0.000068528956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028832525,0.00015200366,0.00040961942,0.00026245907,0.0000263691,0.000017766588,0.00009707956,0.000094575786,0.000042750795],"category_scores_gemma":[0.0017796428,0.00012934032,0.00005573319,0.00024349432,0.00004460928,0.00015953605,0.000008027752,0.00032039086,4.894156e-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":[0.00022845977,0.000591312,0.0007777693,0.00015967974,0.00015549628,0.00000901916,0.0073890095,0.061356675,0.00722804,0.7213435,0.0006932118,0.20006779],"study_design_scores_gemma":[0.0009265413,0.00027004708,0.0005012873,0.00008589641,0.000101339865,0.000029191264,0.0007050096,0.06442361,0.0035570657,0.9292655,0.000011033098,0.00012348167],"about_ca_topic_score_codex":0.000006076107,"about_ca_topic_score_gemma":0.000025748162,"teacher_disagreement_score":0.38335988,"about_ca_system_score_codex":0.00033195675,"about_ca_system_score_gemma":0.00045939197,"threshold_uncertainty_score":0.52743447},"labels":[],"label_agreement":null},{"id":"W2009166315","doi":"10.1080/02664760902914482","title":"Inference on <i>C</i> <sub>pk</sub> for autocorrelated data in the presence of random measurement errors","year":2009,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","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 Windsor","keywords":"Autocorrelation; Estimator; Autoregressive model; Observational error; Statistics; Econometrics; Sampling (signal processing); Mathematics; Computer science","score_opus":0.1962317579989197,"score_gpt":0.4289423317052731,"score_spread":0.23271057370635342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009166315","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":[0.0064984662,0.00006250562,0.99166304,0.00024982914,0.00028453625,0.000575648,0.00025934228,0.00000833259,0.0003983097],"genre_scores_gemma":[0.93024725,0.00003413224,0.06945691,0.00014803557,0.00008434905,0.000009146962,0.0000050932604,0.000012054729,0.000003052147],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99447966,0.00013998746,0.0016811687,0.00032316364,0.0030820586,0.00029398134],"domain_scores_gemma":[0.986826,0.0099322805,0.0013395537,0.0007223075,0.0010735542,0.00010632949],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0070910393,0.00018418039,0.00054736313,0.00021159709,0.00008859129,0.00009636605,0.0019244415,0.00006935784,0.000004358579],"category_scores_gemma":[0.024259027,0.000113888884,0.0000478805,0.00057340553,0.0001309601,0.00023704932,0.00007897399,0.0004910904,0.000004590363],"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":[0.005535192,0.0010742996,0.00030677358,0.000092520844,0.0000836936,0.00012000957,0.0031284161,0.080001,0.021201324,0.12253184,0.020349931,0.745575],"study_design_scores_gemma":[0.005443759,0.0011831684,0.0061690602,0.0002578189,0.00010774784,0.000016755164,0.001231372,0.04443654,0.008324411,0.93040544,0.002086904,0.00033703138],"about_ca_topic_score_codex":0.0000013760547,"about_ca_topic_score_gemma":0.000011147095,"teacher_disagreement_score":0.92374873,"about_ca_system_score_codex":0.00007325424,"about_ca_system_score_gemma":0.00025534982,"threshold_uncertainty_score":0.98396003},"labels":[],"label_agreement":null},{"id":"W2010794591","doi":"10.1080/02664760701592992","title":"A Stylometric Analysis of King Alfred's Literary Works","year":2007,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Authorship Attribution and Profiling","field":"Computer Science","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":"Actua; Simon Fraser University; University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of Newcastle Australia","keywords":"Computer science; Perspective (graphical); Subject (documents); Stylometry; Simple (philosophy); Key (lock); Bayesian probability; Artificial intelligence; Linguistics; Natural language processing; Epistemology; Philosophy; Library science","score_opus":0.021858001564333224,"score_gpt":0.29520584941709904,"score_spread":0.27334784785276584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010794591","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":[0.011985632,0.00030871815,0.98655343,0.00003322439,0.00020202315,0.00003982848,0.000027409942,0.000011523535,0.0008382369],"genre_scores_gemma":[0.63236165,0.000024654646,0.36746937,0.000079769175,0.000044736295,1.6629909e-7,0.00000504669,0.0000035110788,0.000011116764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982909,0.000030693067,0.0008149072,0.000120560064,0.00052531436,0.00021765547],"domain_scores_gemma":[0.9976934,0.00075410283,0.00087461225,0.00021112624,0.00032438233,0.00014238514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019890086,0.000098140146,0.0003741047,0.0014679879,0.00005734545,0.00008313448,0.00049154076,0.00007126104,0.000032640266],"category_scores_gemma":[0.00014786731,0.00008735045,0.00011536843,0.004034811,0.00003305316,0.00016026142,0.00007547838,0.00030309442,0.0000028942834],"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":[0.00015039575,0.00015926978,0.0059043188,0.000042767235,0.0010792343,0.00016108762,0.0032418699,0.003430412,0.001156049,0.45201433,0.00065793144,0.53200233],"study_design_scores_gemma":[0.004105846,0.0010681801,0.3588534,0.00036316997,0.003829852,0.0001598437,0.0013004135,0.3682013,0.020085096,0.22996396,0.010453541,0.0016153919],"about_ca_topic_score_codex":0.0000027540514,"about_ca_topic_score_gemma":0.0000033949452,"teacher_disagreement_score":0.620376,"about_ca_system_score_codex":0.000056085173,"about_ca_system_score_gemma":0.00007704354,"threshold_uncertainty_score":0.35620478},"labels":[],"label_agreement":null},{"id":"W2012214625","doi":"10.1080/02664761003692449","title":"Bayesian–frequentist hybrid model with application to the analysis of gene copy number changes","year":2011,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","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":"Western University","funders":"National Center for Research Resources; National Institutes of Health","keywords":"Frequentist inference; Bayesian probability; Computer science; Comparative genomic hybridization; Data mining; Bayesian inference; Artificial intelligence; Machine learning; Genome; Biology; Genetics; Gene","score_opus":0.009908883366534903,"score_gpt":0.22534686292090342,"score_spread":0.21543797955436852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012214625","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":[0.12368779,0.000020883945,0.87470067,0.000042085987,0.000021293765,0.00009725698,0.00039151026,0.0000013149782,0.0010371815],"genre_scores_gemma":[0.871362,0.000039128885,0.12824348,0.00011706263,0.00005956214,0.000010795701,0.00007376711,0.0000099014305,0.000084305786],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993596,0.000012278604,0.00027046888,0.00010304639,0.00014801878,0.00010657749],"domain_scores_gemma":[0.99915683,0.000009739624,0.0003336586,0.00021253285,0.0002299047,0.00005732715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015245586,0.000090283334,0.0001838854,0.00005765582,0.000050475766,0.000011034735,0.00018247664,0.000031172887,0.00003427789],"category_scores_gemma":[0.0000065878753,0.00006226376,0.00004443694,0.00013934866,0.00004341692,0.000002073304,0.000024787643,0.00005305526,0.0000024159926],"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":[0.0037275879,0.0011389141,0.020525804,0.00018935095,0.012440652,0.000041116356,0.009051619,0.30454296,0.49251482,0.112381496,0.02306557,0.020380117],"study_design_scores_gemma":[0.0019237074,0.0012683502,0.01809895,0.000023512664,0.005911534,0.00020822919,0.0020057622,0.033222813,0.9184365,0.008012445,0.010007725,0.0008804668],"about_ca_topic_score_codex":0.000020097003,"about_ca_topic_score_gemma":0.00011442604,"teacher_disagreement_score":0.7476742,"about_ca_system_score_codex":0.000013367088,"about_ca_system_score_gemma":0.00006834242,"threshold_uncertainty_score":0.25390422},"labels":[],"label_agreement":null},{"id":"W2018100203","doi":"10.1080/02664760120074951","title":"Economic design of X charts with variable parameters: The Markov chain approach","year":2001,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":88,"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; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Control chart; Control limits; Markov chain; Statistics; Variable (mathematics); Sampling (signal processing); Statistical process control; Sample size determination; Mathematics; Exponential distribution; Interval (graph theory); Limit (mathematics); Computer science; Mathematical optimization; Process (computing)","score_opus":0.08370642413956754,"score_gpt":0.3382596461692194,"score_spread":0.25455322202965186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2018100203","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":[0.0018072218,0.000039097104,0.99473184,0.000057150002,0.00019080445,0.00020963264,0.000069016,0.0000056334725,0.0028895831],"genre_scores_gemma":[0.28572991,0.000034607307,0.71391886,0.000043609634,0.000112916714,0.0000066344146,0.0000010604525,0.000017487298,0.00013491129],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971337,0.00011460392,0.0011520431,0.00024357036,0.0010629748,0.00029314327],"domain_scores_gemma":[0.9926122,0.0051189554,0.0013613657,0.00037102913,0.0003905076,0.00014598394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029725502,0.00017931384,0.00051783776,0.00015938477,0.00013290091,0.0001315198,0.0007782918,0.00005487773,0.00009090981],"category_scores_gemma":[0.0010139972,0.00009082697,0.000037093017,0.0003529763,0.000269903,0.0001819491,0.000060311733,0.0003317413,0.000016764056],"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":[0.003442043,0.00027082697,0.00080324145,0.000048944614,0.00022620069,0.00011171713,0.0015389301,0.66335934,0.0004086709,0.1713114,0.008765557,0.14971313],"study_design_scores_gemma":[0.00186369,0.0010132046,0.0008549075,0.000057986956,0.00016360435,0.00037146214,0.003511464,0.1203596,0.0007029043,0.86597186,0.004697857,0.0004314632],"about_ca_topic_score_codex":0.0000033614788,"about_ca_topic_score_gemma":0.0000011610861,"teacher_disagreement_score":0.6946605,"about_ca_system_score_codex":0.000086948516,"about_ca_system_score_gemma":0.00022861427,"threshold_uncertainty_score":0.37038165},"labels":[],"label_agreement":null},{"id":"W2026793228","doi":"10.1080/02664763.2010.545374","title":"A segmented regime-switching model with its application to stock market indices","year":2011,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; University of Otago","keywords":"Econometrics; Stock market; Stock market index; Volatility (finance); Stock (firearms); Markov chain; Index (typography); Economics; Computer science; Mathematics; Statistics; Geography","score_opus":0.02894789656705783,"score_gpt":0.22642639733573133,"score_spread":0.19747850076867351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026793228","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":[0.058578104,0.000036793146,0.9043494,0.000046199046,0.000056131666,0.0002696083,0.00026500673,0.000008886525,0.036389906],"genre_scores_gemma":[0.821602,0.000031287058,0.17790599,0.00014608279,0.000038245573,0.000013487242,0.0000055186547,0.000022736003,0.00023463627],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987396,0.0000076149,0.0007426949,0.00021512594,0.00009205663,0.0002029015],"domain_scores_gemma":[0.9984275,0.000052639698,0.0010240114,0.0002201343,0.000116101925,0.00015959864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080558844,0.00014495832,0.00036609118,0.00022516458,0.00007572198,0.000038785536,0.00024743294,0.00006379204,0.00014703056],"category_scores_gemma":[0.00004463422,0.00013934124,0.00003680748,0.00018657726,0.000016607264,0.00011019865,0.000041532676,0.00022852515,0.000015712423],"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":[0.004183515,0.00087583077,0.049742438,0.0003668719,0.00059439085,0.000033936612,0.0077947164,0.0039020986,0.00039230473,0.8933178,0.009869967,0.028926123],"study_design_scores_gemma":[0.0008856134,0.00026084098,0.015807703,0.00002445545,0.000036396803,0.000011206909,0.0001305974,0.8591834,0.000039930317,0.12135052,0.0019529433,0.0003164088],"about_ca_topic_score_codex":0.000018004363,"about_ca_topic_score_gemma":0.000028633081,"teacher_disagreement_score":0.8552813,"about_ca_system_score_codex":0.00009197179,"about_ca_system_score_gemma":0.00004733325,"threshold_uncertainty_score":0.56821704},"labels":[],"label_agreement":null},{"id":"W2028104463","doi":"10.1080/0266476042000285503","title":"Monitoring Process Mean and Variability with One Non-central Chi-square Chart","year":2004,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":71,"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 New Brunswick","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"EWMA chart; Control chart; Chart; Statistics; Statistic; X-bar chart; Process (computing); Statistical process control; Mathematics; Control limits; Computer science","score_opus":0.05249982508359512,"score_gpt":0.3654536126362057,"score_spread":0.31295378755261055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028104463","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":[0.18336006,0.000030145096,0.8156129,0.00008239873,0.00027178295,0.00017162682,0.00006585978,0.0000131849765,0.00039201527],"genre_scores_gemma":[0.7083018,0.00002196434,0.29132462,0.000014761183,0.00030150282,0.000004268653,6.572711e-7,0.000019429506,0.000011023233],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99605566,0.00003508193,0.001072651,0.00039691146,0.0019934997,0.00044620896],"domain_scores_gemma":[0.9966263,0.00087216933,0.000836768,0.00027966767,0.0009530777,0.00043197707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001376533,0.00024046905,0.00058518484,0.00015555415,0.00022593405,0.00022741788,0.00045844837,0.000075933625,0.000020717504],"category_scores_gemma":[0.0009421955,0.00017527334,0.00003266648,0.0004610938,0.00030039158,0.0003652327,0.00006681461,0.0005415178,0.000008735338],"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":[0.005410284,0.002224898,0.085782684,0.0010367241,0.0005593388,0.000811223,0.03068251,0.12071582,0.004141383,0.1717191,0.0002625001,0.57665354],"study_design_scores_gemma":[0.0035114714,0.000829104,0.061487228,0.00034600528,0.00015365137,0.00014277836,0.0048601106,0.0011050303,0.009436501,0.91739607,0.00013915512,0.00059290935],"about_ca_topic_score_codex":0.0000024449678,"about_ca_topic_score_gemma":0.0000040948016,"teacher_disagreement_score":0.74567693,"about_ca_system_score_codex":0.00016791407,"about_ca_system_score_gemma":0.0003050741,"threshold_uncertainty_score":0.7147439},"labels":[],"label_agreement":null},{"id":"W2037011349","doi":"10.1080/02664763.2014.960372","title":"A multiple imputation approach to nonlinear mixed-effects models with covariate measurement errors and missing values","year":2014,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"National Natural Science Foundation of China","keywords":"Covariate; Imputation (statistics); Missing data; Markov chain Monte Carlo; Statistics; Computer science; Gibbs sampling; Econometrics; Observational error; Markov chain; Monte Carlo method; Mathematics; Bayesian probability","score_opus":0.07023764708469796,"score_gpt":0.3212560569575242,"score_spread":0.2510184098728262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037011349","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":[0.0021698528,0.000011479077,0.9966149,0.000036292084,0.00007912918,0.0003086564,0.000030791973,0.000023145702,0.0007257971],"genre_scores_gemma":[0.22556624,0.0000032662906,0.7742311,0.00007646129,0.00007826849,0.000007130003,0.0000016925478,0.00003417522,0.0000016736781],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981844,0.00013733526,0.0005542426,0.00019595586,0.0006908065,0.00023729389],"domain_scores_gemma":[0.99696165,0.0017326238,0.00044786502,0.00014501896,0.00046004888,0.00025280597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015572145,0.00020466956,0.0004892526,0.000114161405,0.000093530834,0.0000911345,0.000118028714,0.00006283369,0.0000013353463],"category_scores_gemma":[0.0017201455,0.00014936307,0.000026935155,0.000129387,0.0000663427,0.00006611352,0.000031735242,0.00022503918,9.1331003e-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":[0.00035050945,0.00023000823,0.000024579582,0.00048704672,0.00010706859,0.000009433326,0.0013497957,0.0016783582,0.00097546156,0.8876958,0.00047845932,0.10661348],"study_design_scores_gemma":[0.0009453648,0.00036136442,0.0003087207,0.00012621225,0.00016580556,0.000026999482,0.0001262724,0.24467385,0.0005373166,0.752526,0.000033889923,0.00016824823],"about_ca_topic_score_codex":0.0000049152036,"about_ca_topic_score_gemma":0.0000027855938,"teacher_disagreement_score":0.24299549,"about_ca_system_score_codex":0.00006758167,"about_ca_system_score_gemma":0.00007870889,"threshold_uncertainty_score":0.6090849},"labels":[],"label_agreement":null},{"id":"W2039859119","doi":"10.1080/0266476032000076056","title":"Exact prediction intervals for exponential distributions based on doubly Type-II censored samples","year":2003,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Distribution Estimation and Applications","field":"Mathematics","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Order statistic; Mathematics; Exponential function; Statistics; Statistic; Inference; Type (biology); Exponential distribution; Applied mathematics; Exponential type; Sample size determination; Sample (material); Sufficient statistic; Computer science; Mathematical analysis","score_opus":0.07057935865896448,"score_gpt":0.3541304357021198,"score_spread":0.2835510770431553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039859119","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":[0.0016039677,0.0000035015453,0.98712236,0.00017021573,0.000282834,0.00042112888,0.00852744,0.00003625073,0.0018323328],"genre_scores_gemma":[0.62536097,0.0000044612143,0.37388602,0.00007674748,0.000087528744,0.000038914404,0.00048068026,0.000020237025,0.00004441811],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99831575,0.00005006551,0.0008487008,0.00016659852,0.00038659413,0.00023229592],"domain_scores_gemma":[0.99685186,0.0015396819,0.00057094457,0.00021563009,0.00064654055,0.00017534864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048498603,0.00017848186,0.00032099985,0.0001078476,0.00031335047,0.000054101827,0.00013849516,0.00009094504,0.0004902562],"category_scores_gemma":[0.0026181021,0.00015984195,0.000102115206,0.00021049597,0.000088147586,0.000049268707,0.000011281182,0.00020033077,0.000014891502],"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":[0.00022109093,0.0004612228,0.0000075281378,0.000049814913,0.000042410087,0.0000014045168,0.00005835035,0.00048559878,0.0006445332,0.9390568,0.057864394,0.0011068425],"study_design_scores_gemma":[0.004069266,0.00095682195,0.0015000657,0.00009901269,0.00044468857,0.000022254977,0.00021387328,0.024395265,0.005810369,0.9286411,0.033478193,0.00036910936],"about_ca_topic_score_codex":5.8036665e-7,"about_ca_topic_score_gemma":0.0000010078495,"teacher_disagreement_score":0.623757,"about_ca_system_score_codex":0.00014985295,"about_ca_system_score_gemma":0.00016277307,"threshold_uncertainty_score":0.65181655},"labels":[],"label_agreement":null},{"id":"W2047584164","doi":"10.1080/02664763.2011.632404","title":"Two-step and likelihood methods for HIV viral dynamic models with covariate measurement errors and missing data","year":2011,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","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":"University of British Columbia; York University","funders":"","keywords":"Covariate; Missing data; Autocorrelation; Statistics; Econometrics; Computer science; Standard error; Mathematics","score_opus":0.09824906713412437,"score_gpt":0.3427253060192883,"score_spread":0.24447623888516393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047584164","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":[0.00005226765,0.00033134123,0.99877113,0.000110124325,0.00010736735,0.00020503302,0.00005054721,0.000016855613,0.000355307],"genre_scores_gemma":[0.021170342,0.00005672181,0.97857034,0.00013827089,0.000030287329,0.000003231248,0.0000025628428,0.000024407711,0.0000038482362],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858886,0.00010638945,0.00044040708,0.0003129789,0.00029583863,0.00025552767],"domain_scores_gemma":[0.99850714,0.00018155204,0.00044462318,0.00041533416,0.00024877637,0.00020259482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029508579,0.00018223145,0.00036959664,0.000097146,0.00010293989,0.00012578035,0.0005397526,0.000049928054,7.983296e-7],"category_scores_gemma":[0.00004656301,0.00013620593,0.000018957066,0.000080092344,0.00007040819,0.00035438803,0.00020432254,0.0002027952,9.731255e-8],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020143375,0.000052752308,0.0000026312723,0.000061618885,0.00011345807,0.00001470017,0.001287966,0.0000468576,0.0012583603,0.42784712,0.00017935841,0.5689337],"study_design_scores_gemma":[0.000998392,0.00016167917,0.000034681063,0.00003285126,0.00011033689,0.000075046,0.000034122368,0.5216031,0.0001746453,0.47650638,0.00013704516,0.00013171448],"about_ca_topic_score_codex":0.0000062343534,"about_ca_topic_score_gemma":0.000008652536,"teacher_disagreement_score":0.568802,"about_ca_system_score_codex":0.00003646992,"about_ca_system_score_gemma":0.00018154604,"threshold_uncertainty_score":0.5554316},"labels":[],"label_agreement":null},{"id":"W2052304942","doi":"10.1080/02664760903406488","title":"Optimal design of accelerated degradation tests based on Wiener process models","year":2010,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Reliability and Maintenance Optimization","field":"Engineering","cited_by":170,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Quantile; Wiener process; Estimator; Mathematics; Robustness (evolution); Delta method; Statistics; Random variable; Sensitivity (control systems); Mathematical optimization; Range (aeronautics); Computer science; Applied mathematics; Engineering","score_opus":0.019967688203337306,"score_gpt":0.2430872403094555,"score_spread":0.2231195521061182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052304942","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":[0.03264637,0.0000026854468,0.96632046,0.000012370025,0.0001495516,0.00013361624,0.000025634283,0.00001846915,0.00069084513],"genre_scores_gemma":[0.6292545,0.000011256859,0.3706644,0.000014570431,0.000025217061,0.0000031930856,0.000008902558,0.000014075951,0.000003875934],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919546,0.000008826665,0.00038362367,0.00006588592,0.00023229426,0.00011388598],"domain_scores_gemma":[0.99915713,0.00013710595,0.00018906513,0.000101479505,0.00036012603,0.000055077002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026048048,0.000100840254,0.0001763645,0.00010026705,0.000024478137,0.00002215596,0.00010752031,0.00007681938,0.000024112443],"category_scores_gemma":[0.000086201864,0.00008661397,0.000019109651,0.00014425811,0.000033572876,0.00012235391,0.000003172528,0.00026078688,0.0000011915355],"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":[0.00013324639,0.000058106525,0.0000048142006,0.000055475513,0.000011240654,0.0000020044733,0.00008927995,0.9813689,0.012937359,0.0027795406,0.00054290576,0.0020171439],"study_design_scores_gemma":[0.00045387662,0.000111540794,0.0000661834,0.000023436902,0.000023164703,0.0000025938778,0.00002469524,0.9789407,0.016077155,0.0041711805,0.000019617342,0.00008580455],"about_ca_topic_score_codex":5.438292e-7,"about_ca_topic_score_gemma":9.84637e-7,"teacher_disagreement_score":0.59660816,"about_ca_system_score_codex":0.000028185168,"about_ca_system_score_gemma":0.00008592665,"threshold_uncertainty_score":0.3532015},"labels":[],"label_agreement":null},{"id":"W2059933233","doi":"10.1080/02664763.2014.962490","title":"Application of skew-normal distribution for detecting differential expression to microRNA data","year":2014,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","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":"McMaster University; Pharma Medica Research (Canada)","funders":"","keywords":"Outlier; Statistic; Statistics; Skewness; Normal distribution; Mathematics; Normality; Context (archaeology); Skew; Skew normal distribution; Wald test; Identification (biology); Test statistic; Statistical hypothesis testing; Computer science; Biology","score_opus":0.010821660928917624,"score_gpt":0.2710627005506191,"score_spread":0.2602410396217015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059933233","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":[0.2286102,0.000016714132,0.7703748,0.000012400447,0.00006948695,0.00016502084,0.0007364716,0.0000017817306,0.000013161975],"genre_scores_gemma":[0.8808296,0.0000051269617,0.117457055,0.000018298962,0.00034410445,0.000006542685,0.0013226585,0.000013145836,0.0000035032244],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991379,0.000020360105,0.00041279112,0.00016069213,0.00014880877,0.00011949391],"domain_scores_gemma":[0.9988233,0.00004613805,0.0005102331,0.0003178225,0.0002215498,0.00008097615],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002711521,0.000091586735,0.00015197668,0.000032295236,0.000053581647,0.000014139005,0.00026014852,0.0001018818,0.0000034769025],"category_scores_gemma":[0.00021400467,0.00008685424,0.00003606136,0.000043371012,0.000024325318,0.0000048076445,0.00011411693,0.000073509334,8.8774334e-7],"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":[0.0004437854,0.000046798745,0.00008311612,0.000057558107,0.000022971586,8.397844e-8,0.000016232081,0.00026450472,0.96972096,0.0006352685,0.0028781798,0.02583052],"study_design_scores_gemma":[0.0008826319,0.00022542436,0.003654511,0.000024855648,0.000085198415,0.0000057489838,0.000022368778,0.0051553617,0.9736385,0.0011417642,0.015030146,0.00013351368],"about_ca_topic_score_codex":0.0000012849197,"about_ca_topic_score_gemma":0.0000022502627,"teacher_disagreement_score":0.6529177,"about_ca_system_score_codex":0.000018343486,"about_ca_system_score_gemma":0.00004150801,"threshold_uncertainty_score":0.3541813},"labels":[],"label_agreement":null},{"id":"W2063301308","doi":"10.1080/02664760802124455","title":"Statistical inference for start-up demonstration tests with rejection of units upon observing<i>d</i>failures","year":2008,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods in Clinical Trials","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":"McMaster University","funders":"Chinese University of Hong Kong; University of Hong Kong","keywords":"Inference; Estimator; Statistical inference; Likelihood function; Computer science; Bayesian probability; Statistics; Bayesian inference; Maximum likelihood; Expectation–maximization algorithm; Mathematics; Sample (material); Econometrics; Artificial intelligence","score_opus":0.4423127721272717,"score_gpt":0.48979964912010265,"score_spread":0.04748687699283094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063301308","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":[0.028973684,0.000012487558,0.96877635,0.00005723766,0.00036267107,0.000561097,0.00093774876,0.000023543562,0.00029518298],"genre_scores_gemma":[0.27911782,0.000051267765,0.7205358,0.000031484018,0.00017723853,0.0000147100955,0.000010984896,0.00003556344,0.00002511396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9963699,0.00023885479,0.0019828896,0.00024493545,0.0008390332,0.00032440058],"domain_scores_gemma":[0.9474825,0.048539326,0.0017670748,0.00028357882,0.0017137275,0.00021377091],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019493944,0.0002688427,0.0009840882,0.00014914564,0.00015162832,0.000030032157,0.00026983547,0.00017905829,0.00007294675],"category_scores_gemma":[0.048974473,0.00021199272,0.00006206309,0.00037243386,0.00033505473,0.00010192151,0.000037652844,0.000465807,0.0000022719075],"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":[0.003911419,0.00045437284,0.00080534583,0.0007397482,0.00028491355,0.00006399924,0.00069572974,0.0003933906,0.0028226196,0.9599333,0.01035032,0.019544845],"study_design_scores_gemma":[0.0031910092,0.0023451755,0.0031245209,0.00021172002,0.00045683797,0.000098268734,0.00026528517,0.0017201417,0.004451612,0.9833026,0.0005237523,0.00030911184],"about_ca_topic_score_codex":0.000008866031,"about_ca_topic_score_gemma":0.000049238042,"teacher_disagreement_score":0.25014415,"about_ca_system_score_codex":0.000086212756,"about_ca_system_score_gemma":0.0006458579,"threshold_uncertainty_score":0.9590364},"labels":[],"label_agreement":null},{"id":"W2064981318","doi":"10.1080/02664763.2012.740620","title":"Heterogeneity of variance and biased hypothesis tests","year":2012,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","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":"Carleton University","funders":"","keywords":"Type I and type II errors; Statistics; Mathematics; Variance (accounting); Sample size determination; Statistical power; Normal distribution; Analysis of variance; F-test of equality of variances; Statistical hypothesis testing; Econometrics; Test statistic","score_opus":0.039078554075293384,"score_gpt":0.29527450327084737,"score_spread":0.256195949195554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064981318","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":[0.006928801,0.0001036491,0.9925241,0.000035651596,0.000085058105,0.000065367945,0.000049947266,0.000021792965,0.00018564412],"genre_scores_gemma":[0.4705177,0.0000320815,0.5293628,0.000051837975,0.000027690263,0.0000010018642,2.1129058e-7,0.0000053507306,0.0000013354286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99886423,0.000029167853,0.0004874269,0.00010726342,0.00029937096,0.00021252735],"domain_scores_gemma":[0.9980628,0.0008806351,0.00047682284,0.00023051583,0.00018354307,0.00016572147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004471132,0.00011258007,0.00028717326,0.00008638368,0.00003992299,0.00002449869,0.00034026167,0.000046285644,0.0000031412137],"category_scores_gemma":[0.0003702187,0.00009771986,0.00002505633,0.00013079365,0.00008729269,0.00019387319,0.00009559237,0.00015088748,0.0000016285163],"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":[0.00006653461,0.00022918392,0.00065529835,0.00008179069,0.000051700285,0.000017765478,0.0004042097,0.0003442123,0.01302999,0.8288926,0.0011207028,0.15510602],"study_design_scores_gemma":[0.00085902424,0.0004574656,0.018820124,0.000085243686,0.00008752255,0.00016279817,0.000024330382,0.02902747,0.042162817,0.9070001,0.00087832764,0.00043476745],"about_ca_topic_score_codex":0.0000012752798,"about_ca_topic_score_gemma":6.3463506e-7,"teacher_disagreement_score":0.4635889,"about_ca_system_score_codex":0.000029518562,"about_ca_system_score_gemma":0.00004460154,"threshold_uncertainty_score":0.39849},"labels":[],"label_agreement":null},{"id":"W2065171914","doi":"10.1080/02664760701234967","title":"Sample-based Maximum Likelihood Estimation of the Autologistic Model","year":2007,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Stochastic processes and statistical mechanics","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":"Natural Resources Canada; Canadian Forest Service","funders":"","keywords":"Statistics; Mathematics; Sample size determination; Markov chain Monte Carlo; Sample variance; Sampling (signal processing); Monte Carlo method; Estimation theory; Variance (accounting); Computer science","score_opus":0.03630332767794559,"score_gpt":0.31901511875813093,"score_spread":0.28271179108018535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2065171914","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":[0.0015911132,0.000015359677,0.9970599,0.00006552751,0.00023284883,0.00019437999,0.00034388585,0.000014235096,0.00048277876],"genre_scores_gemma":[0.44912064,0.0000017522226,0.5507539,0.00006901788,0.000030787574,0.0000014390837,0.0000026082,0.000015946602,0.0000039288],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977451,0.000018357117,0.0011072514,0.00012286793,0.00069939124,0.00030706328],"domain_scores_gemma":[0.99405533,0.0039142244,0.0011936168,0.00025868436,0.00044789442,0.00013023456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010439273,0.00018100596,0.00044140324,0.000102831706,0.000093359304,0.000021095735,0.00036280707,0.00011144312,0.000029797477],"category_scores_gemma":[0.0047658044,0.0001237347,0.000088105975,0.00022862696,0.00012260229,0.000030266157,0.0000472949,0.00033848835,0.0000022702495],"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":[0.0001927767,0.00018064925,0.000005933105,0.00028033974,0.000039699924,0.000007893833,0.00018097372,0.0155827245,0.0002616248,0.9564533,0.0010950315,0.025719022],"study_design_scores_gemma":[0.00045604075,0.000109791516,0.000046399102,0.000049426857,0.00014458015,0.000010416064,0.00005623182,0.37207997,0.0008741801,0.62607676,0.000013528773,0.00008265142],"about_ca_topic_score_codex":0.0000024718581,"about_ca_topic_score_gemma":0.000007018953,"teacher_disagreement_score":0.44752955,"about_ca_system_score_codex":0.00008873895,"about_ca_system_score_gemma":0.00035438608,"threshold_uncertainty_score":0.57054573},"labels":[],"label_agreement":null},{"id":"W2067267828","doi":"10.1080/02664760500449170","title":"A note comparing component-slope, Scheffé and Cox parameterizations of the linear mixture experiment model","year":2006,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":15,"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":"Pacific Northwest National Laboratory; Simon Fraser University","keywords":"Component (thermodynamics); Mixture model; Linear model; Statistics; Mathematics; Thermodynamics; Physics","score_opus":0.08472300885455115,"score_gpt":0.39775683772838866,"score_spread":0.3130338288738375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067267828","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":[0.13498057,0.00012639268,0.86260283,0.00006387981,0.00015436207,0.00017194147,0.000070458096,0.000004266217,0.0018253153],"genre_scores_gemma":[0.5176285,0.000004756095,0.48223576,0.000043619457,0.00002881052,0.0000016791222,0.0000013740392,0.000008116012,0.00004741001],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972794,0.00013940867,0.0011213471,0.00017723154,0.001119687,0.00016292819],"domain_scores_gemma":[0.99740154,0.00086674915,0.0010073712,0.00029167783,0.0003419906,0.000090691545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011771474,0.00015101767,0.00046280696,0.0001314694,0.00014393147,0.00010469049,0.00048385913,0.00006374852,0.000024304834],"category_scores_gemma":[0.0003028196,0.000096616124,0.00007270403,0.00032342668,0.00025423817,0.00009117627,0.00016409658,0.00024149336,0.000003329843],"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":[0.00038702154,0.00036375935,0.0008082284,0.000019074681,0.000041564177,0.000009426383,0.001580731,0.25983083,0.6480241,0.08096479,0.004179008,0.003791498],"study_design_scores_gemma":[0.0013371065,0.00015199145,0.0034441797,0.00003952465,0.00007091792,0.0000395326,0.0006268672,0.80750406,0.12851457,0.057082456,0.00096057064,0.00022824726],"about_ca_topic_score_codex":0.000008833971,"about_ca_topic_score_gemma":0.0000027026474,"teacher_disagreement_score":0.5476732,"about_ca_system_score_codex":0.000045233846,"about_ca_system_score_gemma":0.000099973506,"threshold_uncertainty_score":0.39398912},"labels":[],"label_agreement":null},{"id":"W2074553505","doi":"10.1080/02664760903186049","title":"Clustering probability distributions","year":2010,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":57,"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 Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Joint probability distribution; Probability distribution; Computer science; Mathematics; Probability density function; Algorithm; Statistical physics; Data mining; Statistics; Physics","score_opus":0.01810154605205502,"score_gpt":0.29800518970734263,"score_spread":0.27990364365528764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074553505","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":[0.0036603962,0.0000040238165,0.9947535,0.00018407122,0.0004735366,0.000091281894,0.000038775797,0.000026103471,0.0007683356],"genre_scores_gemma":[0.21529275,0.0000039667534,0.7845392,0.000018131654,0.00011339309,0.0000030175556,0.0000015301542,0.0000059783965,0.000022041437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987537,0.000016282116,0.00039654877,0.00014554989,0.00043621598,0.00025168207],"domain_scores_gemma":[0.9986377,0.00023594484,0.00023654984,0.0003641839,0.00035133748,0.00017429233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054068916,0.000094185976,0.00017059372,0.00007590694,0.00012129843,0.00012418083,0.0007747958,0.000048241265,0.000017696866],"category_scores_gemma":[0.00025560876,0.000082695566,0.00003453574,0.00022514515,0.000094889,0.0001900746,0.00027045808,0.00066265697,0.000013412783],"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":[0.00006610142,0.00027254806,0.00009429708,0.00008764456,0.000051874333,0.00014281474,0.00063331047,0.0051670135,0.029385434,0.5154784,0.002041152,0.44657946],"study_design_scores_gemma":[0.0014488646,0.00036019625,0.005233863,0.000028536615,0.000023007766,0.0005918498,0.00006089952,0.37384287,0.0080415495,0.5925037,0.017365452,0.0004991783],"about_ca_topic_score_codex":0.0000013773886,"about_ca_topic_score_gemma":0.0000100289035,"teacher_disagreement_score":0.4460803,"about_ca_system_score_codex":0.000067708104,"about_ca_system_score_gemma":0.00016501236,"threshold_uncertainty_score":0.33722273},"labels":[],"label_agreement":null},{"id":"W2074581004","doi":"10.1080/02664760701235279","title":"Describing the Dynamics of Attention to TV Commercials: A Hierarchical Bayes Analysis of the Time to Zap an Ad","year":2007,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bayes' theorem; Computer science; Dynamics (music); Bayesian probability; Statistics; Econometrics; Artificial intelligence; Mathematics; Psychology","score_opus":0.030774668382366675,"score_gpt":0.2712812290075166,"score_spread":0.24050656062514994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074581004","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78257257,0.000009622668,0.21490696,0.00065866736,0.00013269956,0.00021276122,0.00005448943,0.0000060732655,0.0014461732],"genre_scores_gemma":[0.99179894,0.0000020765344,0.0075001614,0.00053153577,0.00009897808,0.0000010285164,0.000013633076,0.0000132326395,0.000040425184],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99857956,0.00002404967,0.0006860542,0.00009802018,0.00043966994,0.00017262078],"domain_scores_gemma":[0.99844307,0.00033913003,0.0006198043,0.00022173859,0.00034113554,0.000035137957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017742538,0.0001090011,0.0003408839,0.00044741444,0.00013388474,0.00007516774,0.00037975254,0.000037455527,0.0001872149],"category_scores_gemma":[0.00022512116,0.0000710103,0.00012545238,0.0011777891,0.000056167915,0.00010312118,0.0001413197,0.00019589793,0.0000055947658],"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":[0.0014679317,0.0005086638,0.07683318,0.00014267459,0.0010625321,0.000018356848,0.0015994306,0.0036152876,0.023123402,0.035597518,0.0044012372,0.8516298],"study_design_scores_gemma":[0.00058441336,0.00007716008,0.9491955,0.00015304286,0.0050694803,0.000004061538,0.0017584199,0.037888147,0.000155365,0.0025481808,0.0022636396,0.00030256528],"about_ca_topic_score_codex":0.00010340189,"about_ca_topic_score_gemma":0.0007925231,"teacher_disagreement_score":0.8723623,"about_ca_system_score_codex":0.0000391688,"about_ca_system_score_gemma":0.000029417606,"threshold_uncertainty_score":0.28957158},"labels":[],"label_agreement":null},{"id":"W2077523965","doi":"10.1080/02664763.2010.491861","title":"A modified bootstrap procedure for cluster sampling variance estimation of species richness","year":2011,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Census and Population Estimation","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Forest Service","funders":"","keywords":"Species richness; Estimator; Statistics; Mathematics; Variance (accounting); Resampling; Cluster sampling; Sampling (signal processing); Econometrics; Computer science; Ecology; Population; Biology","score_opus":0.15004602367404446,"score_gpt":0.35373574263334123,"score_spread":0.20368971895929677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077523965","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":[0.03008225,0.000008302325,0.96804726,0.000022241788,0.0001389641,0.000326693,0.00012118375,0.000010024889,0.0012430934],"genre_scores_gemma":[0.49424323,0.0000031641193,0.5056223,0.000013156124,0.000056136178,0.000005218822,0.000010523367,0.000012074383,0.000034190292],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987232,0.000011701864,0.0008028015,0.00008374996,0.00025264468,0.00012590786],"domain_scores_gemma":[0.9978538,0.00042007174,0.0011605414,0.00011306636,0.00040369522,0.000048806745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043670528,0.000115111245,0.00030341832,0.000103342056,0.00006110923,0.000015882546,0.000107368876,0.00007120357,0.000034056244],"category_scores_gemma":[0.00039955307,0.00010054456,0.000053014577,0.00009738312,0.000035893117,0.00009116995,0.000011427427,0.000106890126,8.7128524e-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":[0.0005195168,0.00018687802,0.00016932948,0.0007802837,0.00006506239,8.9044875e-7,0.0028934286,0.016073957,0.000416912,0.9730423,0.0018739314,0.0039774873],"study_design_scores_gemma":[0.001209229,0.00014911266,0.0064013964,0.00011446358,0.00019901719,0.000020618727,0.00018983148,0.11161165,0.0012276312,0.8785549,0.00016147256,0.0001607161],"about_ca_topic_score_codex":0.0000011995044,"about_ca_topic_score_gemma":0.000003123777,"teacher_disagreement_score":0.46416098,"about_ca_system_score_codex":0.00003724564,"about_ca_system_score_gemma":0.000073017036,"threshold_uncertainty_score":0.41000882},"labels":[],"label_agreement":null},{"id":"W2086120770","doi":"10.1080/02664760120011563","title":"Prior distribution assessment for a multivariate normal distribution: An experimental study","year":2001,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":18,"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":"Kuwait University; Global Institute for Water Security, University of Saskatchewan","keywords":"Multivariate normal distribution; Statistics; Variance (accounting); Multivariate statistics; Distribution (mathematics); Normal distribution; Mathematics; Conjugate prior; Econometrics; Prior probability; Computer science; Bayesian probability","score_opus":0.05948208554205539,"score_gpt":0.4262112367468744,"score_spread":0.36672915120481897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086120770","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":[0.036525257,0.000006537402,0.9604684,0.000026288242,0.00024951083,0.00063134695,0.0019029495,0.00001864835,0.00017103918],"genre_scores_gemma":[0.41620624,0.000002808347,0.58344644,0.000012271146,0.00017756855,0.000032954173,0.000098413315,0.000014663884,0.000008601192],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99797046,0.00011364148,0.00091159286,0.00019995759,0.0004943799,0.0003099578],"domain_scores_gemma":[0.9973507,0.0011850408,0.0006462136,0.00020489385,0.00039259047,0.00022056501],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010656206,0.00021317392,0.00047595365,0.000036455418,0.00022754571,0.00010755575,0.00021585845,0.00007245406,0.00012615445],"category_scores_gemma":[0.0005085843,0.00017716833,0.000067664456,0.00012709164,0.00006757973,0.00012485514,0.000043061682,0.00026178738,0.000002050043],"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":[0.0008940136,0.0040777763,0.00040424825,0.00004568701,0.000109420456,0.00008409088,0.00060495554,0.000007526443,0.0009640416,0.95125926,0.002092986,0.039455973],"study_design_scores_gemma":[0.008323772,0.006800118,0.021924056,0.00006207989,0.0005757501,0.00015139105,0.0056333137,0.011254151,0.0017719294,0.93981886,0.0030116546,0.0006729515],"about_ca_topic_score_codex":0.0000050458266,"about_ca_topic_score_gemma":0.0000036416761,"teacher_disagreement_score":0.379681,"about_ca_system_score_codex":0.00023067078,"about_ca_system_score_gemma":0.00014339827,"threshold_uncertainty_score":0.7224715},"labels":[],"label_agreement":null},{"id":"W2088787243","doi":"10.1080/02664763.2013.780156","title":"A generalized bivariate Bernoulli model with covariate dependence","year":2013,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Distribution Estimation and Applications","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":"Western University","funders":"","keywords":"Covariate; Bernoulli's principle; Bivariate analysis; Mathematics; Statistics; Econometrics; Applied mathematics; Physics","score_opus":0.06531214407639342,"score_gpt":0.3309955742985418,"score_spread":0.2656834302221484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088787243","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":[0.0056167813,0.0000049198375,0.99088156,0.00031014194,0.000037597212,0.00030896082,0.0004022924,0.00003111531,0.0024066577],"genre_scores_gemma":[0.3107874,0.000011033635,0.6887222,0.00017793014,0.00003960478,0.000035758825,0.000023587027,0.00002132135,0.00018117444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983293,0.000025767447,0.00073484675,0.00014875148,0.00052013836,0.00024119855],"domain_scores_gemma":[0.9976743,0.0005127869,0.0006758221,0.00022232765,0.0006878199,0.00022695964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025328295,0.00018080973,0.00035386873,0.00008092468,0.00012452182,0.00010232135,0.00023341404,0.00006920799,0.0006040799],"category_scores_gemma":[0.0002654835,0.00013594117,0.000041264342,0.00019885144,0.00009924528,0.00011277524,0.000028597977,0.00025449175,0.00011034825],"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":[0.00006065186,0.0001381396,0.000006024755,0.00003155631,0.00006206257,0.000006948063,0.00012844025,0.0030793787,0.0007863458,0.97464263,0.01960232,0.0014554979],"study_design_scores_gemma":[0.0010528233,0.00006315506,0.00035728526,0.000020697053,0.00012727203,0.000041641073,0.000058683887,0.17675848,0.00024602513,0.82088476,0.00021749764,0.00017165262],"about_ca_topic_score_codex":0.000010306613,"about_ca_topic_score_gemma":0.000003856316,"teacher_disagreement_score":0.30517063,"about_ca_system_score_codex":0.00007124432,"about_ca_system_score_gemma":0.00018443381,"threshold_uncertainty_score":0.6614252},"labels":[],"label_agreement":null},{"id":"W2089608879","doi":"10.1080/02664760701590376","title":"Estimation of the Length Distribution of Marine Populations in the Gaussian-multinomial Setting using the Method of Moments","year":2007,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Marine and fisheries research","field":"Environmental Science","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":"University of Alberta","funders":"Háskóli Íslands; Icelandic Centre for Research; University of Washington","keywords":"Estimator; Multinomial distribution; Mathematics; Statistics; Minimum-variance unbiased estimator; Covariance; Covariance matrix; Estimation of covariance matrices; Gaussian; Applied mathematics","score_opus":0.03537306179584561,"score_gpt":0.346556136312434,"score_spread":0.3111830745165884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089608879","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":[0.39176303,0.0000011870893,0.60384345,0.00011292899,0.000047333946,0.00020998134,0.0000629037,6.173243e-7,0.003958586],"genre_scores_gemma":[0.9070047,0.0000032680687,0.0929434,0.000009914664,0.000017198972,6.275644e-7,0.000008372819,0.0000032443754,0.000009251694],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987239,0.00008124997,0.0005495139,0.000048389866,0.00048593973,0.00011096664],"domain_scores_gemma":[0.99888,0.0003364382,0.0006066849,0.00012996471,0.00002888861,0.000017974293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018363703,0.000053230913,0.00012310385,0.000025095389,0.00007587999,0.000008040261,0.00023315515,0.000027461734,0.000096453936],"category_scores_gemma":[0.00020830335,0.000028133329,0.000031825053,0.0002606752,0.00013489301,0.000046955418,0.00012317639,0.0001932143,1.9131544e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043778965,0.00038471504,0.25555503,0.00010095561,0.000051181152,0.000005674825,0.003769593,0.19434184,0.010649927,0.01895319,0.00057722157,0.5151729],"study_design_scores_gemma":[0.00060968904,0.00008273516,0.8081163,0.000017548718,0.000060620703,0.000017072096,0.0015181539,0.17702691,0.0033778728,0.008761484,0.00034232318,0.00006924181],"about_ca_topic_score_codex":0.00034944498,"about_ca_topic_score_gemma":0.00007908686,"teacher_disagreement_score":0.55256134,"about_ca_system_score_codex":0.00008621609,"about_ca_system_score_gemma":0.000022291148,"threshold_uncertainty_score":0.11472438},"labels":[],"label_agreement":null},{"id":"W2091280909","doi":"10.1080/02664760903301127","title":"Bayesian and likelihood inference for cure rates based on defective inverse Gaussian regression models","year":2010,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":44,"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":"Gibbs sampling; Bayesian probability; Statistics; Bayesian inference; Econometrics; Bayesian linear regression; Mathematics; Inference; Regression; Biostatistics; Mixture model; Computer science; Artificial intelligence; Medicine","score_opus":0.06860073087418259,"score_gpt":0.4269199345563927,"score_spread":0.35831920368221015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091280909","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":[0.010460563,0.000015141839,0.9857051,0.00014254397,0.0003742512,0.00029369805,0.00012981569,0.000007841176,0.0028710924],"genre_scores_gemma":[0.47852457,0.000006428171,0.5211922,0.00017525052,0.00006205484,0.000006506622,0.0000018852031,0.000012785773,0.000018311157],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976749,0.00012976365,0.0007198938,0.0002997674,0.0009330348,0.00024267423],"domain_scores_gemma":[0.99351025,0.0045978157,0.0007968126,0.0002859896,0.000505593,0.00030355257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026535036,0.00020949122,0.00043318758,0.0003152258,0.00017072797,0.00022652205,0.00037713183,0.0001391181,0.00009024874],"category_scores_gemma":[0.0020510408,0.00013802593,0.000076445605,0.00025395476,0.00016641726,0.00022658156,0.00005153085,0.0005008054,0.000007247213],"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":[0.0078109587,0.0010266464,0.0017674862,0.00008925852,0.00012093179,0.00011927248,0.0050735218,0.02633001,0.22524528,0.3401343,0.04442031,0.34786204],"study_design_scores_gemma":[0.001337075,0.00073170057,0.00047493205,0.000041706066,0.00003258339,0.000010202738,0.00066578924,0.43014455,0.01475296,0.5510386,0.00057792914,0.00019193406],"about_ca_topic_score_codex":0.0000024042715,"about_ca_topic_score_gemma":0.000012908858,"teacher_disagreement_score":0.468064,"about_ca_system_score_codex":0.00003816578,"about_ca_system_score_gemma":0.0002272291,"threshold_uncertainty_score":0.56285346},"labels":[],"label_agreement":null},{"id":"W2104999300","doi":"10.1080/02664763.2013.800035","title":"Estimating the proportion of true null hypotheses using the pattern of observed<i>p</i>-values","year":2013,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":11,"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 Guelph","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Hong Kong Baptist University; St. Jude Children's Research Hospital; National Institutes of Health; National Science Foundation","keywords":"Statistics; Mathematics; Null (SQL); Null hypothesis; Econometrics; Computer science; Data mining","score_opus":0.5316892023117963,"score_gpt":0.5023413434252647,"score_spread":0.029347858886531575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104999300","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":[0.19539781,0.000025954037,0.8033739,0.000085027925,0.0003777645,0.0004949743,0.00010175205,0.0000065954773,0.00013623701],"genre_scores_gemma":[0.38297814,0.000006772501,0.6167631,0.000044016506,0.00017123326,0.0000050561184,3.9735664e-7,0.000023715596,0.0000075108505],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99596465,0.0004233707,0.0024516436,0.0001301375,0.0008095727,0.00022062953],"domain_scores_gemma":[0.9602627,0.034665912,0.0037514518,0.00042367505,0.0008322871,0.00006397035],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004182937,0.00018742315,0.00080139044,0.000053794676,0.00010516022,0.00004545948,0.00050741417,0.00009482396,0.00017633091],"category_scores_gemma":[0.027997766,0.00009633484,0.00014313625,0.00017617398,0.00045557716,0.00006397265,0.000089709065,0.00042933243,0.000003497953],"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":[0.00067672366,0.0018668844,0.0031248294,0.0036494643,0.0017930595,0.000029482144,0.009295838,0.00830686,0.05872825,0.31995097,0.013078056,0.5794996],"study_design_scores_gemma":[0.00055357546,0.00020011277,0.0014842772,0.000230576,0.0004047385,0.00001805529,0.00081027887,0.016819196,0.009889883,0.9694615,0.000012320362,0.00011547602],"about_ca_topic_score_codex":0.00003058258,"about_ca_topic_score_gemma":0.0000017616279,"teacher_disagreement_score":0.64951056,"about_ca_system_score_codex":0.00004221626,"about_ca_system_score_gemma":0.00012394208,"threshold_uncertainty_score":0.9801898},"labels":[],"label_agreement":null},{"id":"W2109280416","doi":"10.1080/02664760802443962","title":"Nonlinear voxel-based modelling of the haemodynamic response in fMRI","year":2008,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":3,"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":"Medical Research Council","keywords":"Voxel; Convolution (computer science); Kernel (algebra); Parametric statistics; Mathematics; Nonlinear system; Curve fitting; Artificial intelligence; Computer science; Algorithm; Statistics; Physics","score_opus":0.035654251873052004,"score_gpt":0.3027550393782124,"score_spread":0.2671007875051604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109280416","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":[0.20634688,0.000020849568,0.7929187,0.0002741175,0.00001765542,0.0001731524,0.000046408244,0.0000057705256,0.00019647756],"genre_scores_gemma":[0.5431989,0.000045183053,0.45659786,0.00009291973,0.000022502354,0.0000029880127,0.000002514235,0.000010039223,0.000027073567],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905443,0.000017199154,0.0004978001,0.000072606905,0.0002485605,0.000109377244],"domain_scores_gemma":[0.99899685,0.00020872464,0.00036715763,0.0002043394,0.00016802605,0.00005491304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002535595,0.00008123484,0.00025642017,0.00010486364,0.000047330712,0.0000019065836,0.000114399416,0.000051068786,0.0000076088445],"category_scores_gemma":[0.000056218105,0.00005747535,0.00005663294,0.00020996017,0.00011543532,0.00001578155,0.000015587686,0.00031072405,9.869314e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008813748,0.0010852696,0.00081745494,0.0001252183,0.00003167903,0.00020648731,0.0007717423,0.9243837,0.04216888,0.015692007,0.0017124122,0.004191393],"study_design_scores_gemma":[0.0035705804,0.000657753,0.0053091645,0.00028660052,0.00012762935,0.00029092643,0.00019352534,0.9340965,0.03198559,0.019529236,0.003741909,0.00021056677],"about_ca_topic_score_codex":0.0000032618254,"about_ca_topic_score_gemma":0.0000016966608,"teacher_disagreement_score":0.33685204,"about_ca_system_score_codex":0.0000791846,"about_ca_system_score_gemma":0.00029485245,"threshold_uncertainty_score":0.23437767},"labels":[],"label_agreement":null},{"id":"W2112912314","doi":"10.1080/02664763.2013.789098","title":"Multivariate models for correlated count data","year":2013,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Methods and Models","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":"Carleton University; University of British Columbia","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Overdispersion; Count data; Poisson distribution; Multivariate statistics; Statistics; Negative binomial distribution; Mathematics; Zero-inflated model; Poisson regression; Econometrics; Population; Demography","score_opus":0.2020919523255862,"score_gpt":0.4319513065614795,"score_spread":0.22985935423589332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112912314","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":[0.0002046286,0.000027116215,0.9962214,0.000064523476,0.00028581798,0.00056865596,0.0015571953,0.000018889557,0.0010517761],"genre_scores_gemma":[0.02434921,0.000033281245,0.97508097,0.000121380064,0.00014081862,0.00002121208,0.000052152984,0.000049983464,0.0001510147],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981175,0.000036929847,0.00094976724,0.00021889794,0.00036700154,0.0003099035],"domain_scores_gemma":[0.9943149,0.0035949629,0.0007643151,0.00046119737,0.00066882983,0.00019579704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008139829,0.00019575864,0.000534724,0.00006906482,0.00009382674,0.000058773818,0.0004764585,0.00010105914,0.00009260073],"category_scores_gemma":[0.0013510416,0.00015357253,0.00004408355,0.00007685804,0.000069171685,0.0002642405,0.00010739331,0.0003039329,0.000010922976],"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":[0.00016214502,0.00014391851,4.9450244e-7,0.00010014005,0.000112888425,0.000008228017,0.0002376479,0.0024026432,0.0006434317,0.9181662,0.04196116,0.03606111],"study_design_scores_gemma":[0.00084437244,0.00008399447,0.000005715564,0.000022535776,0.000114434115,0.000010334559,0.0000885486,0.35582307,0.000045004977,0.6416265,0.001214681,0.000120839235],"about_ca_topic_score_codex":0.000007632652,"about_ca_topic_score_gemma":0.0000021472647,"teacher_disagreement_score":0.3534204,"about_ca_system_score_codex":0.000056869445,"about_ca_system_score_gemma":0.00010782725,"threshold_uncertainty_score":0.62625057},"labels":[],"label_agreement":null},{"id":"W2113104757","doi":"10.1080/02664763.2012.740627","title":"Contrasting the Gini and Zenga indices of economic inequality","year":2012,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Income, Poverty, and Inequality","field":"Social Sciences","cited_by":44,"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":"","keywords":"Index (typography); Econometrics; Inequality; Economics; Gini coefficient; Economic inequality; Sample (material); Contrast (vision); Statistics; Confidence interval; Population; Demographic economics; Mathematics; Demography; Sociology; Computer science","score_opus":0.042298010096055265,"score_gpt":0.33582545082759435,"score_spread":0.2935274407315391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113104757","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95242697,0.00031500307,0.012819357,0.0003316106,0.0008607162,0.00016500399,0.00017150064,0.0000073280294,0.03290253],"genre_scores_gemma":[0.9954262,0.00014249184,0.0036388745,0.00014050877,0.000624366,6.909529e-7,0.000001047162,0.000004973983,0.000020848707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99881697,0.00014867197,0.0005229002,0.00004854444,0.0002544136,0.00020847442],"domain_scores_gemma":[0.99782854,0.0011082137,0.0007953837,0.00007059174,0.00008781362,0.000109452565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038008667,0.00006904631,0.0002369772,0.000034613306,0.0002431667,0.000036601527,0.00016122509,0.000053000826,0.00007033479],"category_scores_gemma":[0.00035402592,0.00004802739,0.000029422952,0.000046146517,0.00029252406,0.00013971739,0.000027810425,0.0001954559,0.0000031625698],"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":[0.00007812597,0.000068005524,0.039410662,0.00004583997,0.000066153334,8.651416e-7,0.032794442,0.000014780941,0.00013224273,0.91410816,0.002415793,0.010864915],"study_design_scores_gemma":[0.0033589797,0.0004400643,0.5177548,0.00010755948,0.0004968281,0.000021077794,0.1107101,0.00049747573,0.001405306,0.2536126,0.1107898,0.0008054222],"about_ca_topic_score_codex":0.00024929948,"about_ca_topic_score_gemma":0.00014720437,"teacher_disagreement_score":0.6604956,"about_ca_system_score_codex":0.000063751904,"about_ca_system_score_gemma":0.0001518166,"threshold_uncertainty_score":0.19585},"labels":[],"label_agreement":null},{"id":"W2117179243","doi":"10.1080/02664760903521476","title":"Bayesian parametric accelerated failure time spatial model and its application to prostate cancer","year":2010,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Cancer Institute; McGill University","keywords":"Prostate cancer; Bayesian probability; Parametric statistics; Accelerated failure time model; Semiparametric model; Computer science; Parametric model; Statistics; Econometrics; Mathematics; Cancer; Proportional hazards model; Medicine; Internal medicine","score_opus":0.026308004376340482,"score_gpt":0.3414047602150342,"score_spread":0.3150967558386937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117179243","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":[0.017744103,0.000009574636,0.9806358,0.00024562603,0.0000907285,0.0004757241,0.00045919046,0.000020083817,0.0003191522],"genre_scores_gemma":[0.3352056,0.0000163394,0.6644659,0.00009205975,0.00011497684,0.000028817605,0.000004240178,0.00002712085,0.000044926157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983596,0.000032546664,0.00069090613,0.00022480144,0.0004099075,0.00028218795],"domain_scores_gemma":[0.997668,0.0007874648,0.0005174771,0.00017742481,0.00051263924,0.00033694148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051408546,0.00021601257,0.00046237194,0.00020817143,0.00009973626,0.000094577474,0.0002114107,0.00013190915,0.00015830877],"category_scores_gemma":[0.00089559826,0.00017926903,0.000029570645,0.00035007647,0.00005137371,0.00007119118,0.000053232856,0.0005553876,0.000017667266],"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":[0.00035008296,0.00019315376,0.00009523889,0.00019266961,0.00008703628,0.000019356563,0.0006790355,0.000681246,0.06834362,0.70233166,0.006473115,0.22055382],"study_design_scores_gemma":[0.0006041562,0.00013716766,0.00040030418,0.000029121356,0.00013000752,0.000022210366,0.00002727399,0.295887,0.002306847,0.6997849,0.00039849302,0.0002725553],"about_ca_topic_score_codex":0.000009733188,"about_ca_topic_score_gemma":0.00005035054,"teacher_disagreement_score":0.31746152,"about_ca_system_score_codex":0.000039640323,"about_ca_system_score_gemma":0.00017640862,"threshold_uncertainty_score":0.73103786},"labels":[],"label_agreement":null},{"id":"W2147583488","doi":"10.1080/02664761003758976","title":"Classification with discrete and continuous variables via general mixed-data models","year":2011,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":23,"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 Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Categorical variable; Extension (predicate logic); Ordinal data; Linear discriminant analysis; Continuous variable; Ordinal regression; Generalized linear mixed model; Discriminant function analysis; Mathematics; Data mining; Statistics; Pattern recognition (psychology); Artificial intelligence; Machine learning","score_opus":0.16432620844668666,"score_gpt":0.3663746482197034,"score_spread":0.20204843977301673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147583488","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":[0.0020627435,0.00003283244,0.99402124,0.000016575968,0.00007714477,0.0001648021,0.00042956794,0.000013831601,0.003181237],"genre_scores_gemma":[0.15344203,0.00006877485,0.84627426,0.00003278004,0.000078313904,0.000004105959,0.000017121447,0.000032216267,0.000050417017],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99856305,0.000056392528,0.00061285275,0.00022757686,0.00031570587,0.00022444873],"domain_scores_gemma":[0.9977272,0.00064485194,0.0008369384,0.0003774227,0.00023653169,0.00017703576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063910114,0.00018454307,0.0004551691,0.000062490726,0.00008075452,0.000033205284,0.0002695929,0.00007162322,0.000019094712],"category_scores_gemma":[0.00022710998,0.00013152476,0.00001688115,0.000070121525,0.00015076155,0.00019974094,0.0000843311,0.00025069516,5.248674e-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":[0.00032469886,0.00008947638,0.000016703236,0.00006354489,0.00008894752,0.00003401374,0.00040156752,0.000085845786,0.0004437544,0.9662549,0.0010928797,0.031103674],"study_design_scores_gemma":[0.00065937807,0.0002099348,0.00017261882,0.00003021669,0.00023689124,0.00007133332,0.00020389538,0.077457964,0.0001364782,0.9204775,0.0001678814,0.00017587429],"about_ca_topic_score_codex":0.000006402781,"about_ca_topic_score_gemma":0.000008829481,"teacher_disagreement_score":0.15137929,"about_ca_system_score_codex":0.000024538811,"about_ca_system_score_gemma":0.000056003766,"threshold_uncertainty_score":0.5363424},"labels":[],"label_agreement":null},{"id":"W2228863754","doi":"10.1080/02664763.2015.1094454","title":"Exact confidence intervals for randomized response strategies","year":2015,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Survey Sampling and Estimation Techniques","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Saskatchewan","keywords":"Exact statistics; Confidence interval; Statistics; Randomized response; Test statistic; Coverage probability; Statistical hypothesis testing; Confidence distribution; Mathematics; CDF-based nonparametric confidence interval; Likelihood-ratio test; p-value; Statistic; Test (biology); Inference; Computer science; Artificial intelligence","score_opus":0.14001051688027102,"score_gpt":0.41346491575438765,"score_spread":0.2734543988741166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2228863754","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008464328,0.000033060634,0.9897316,0.00008777877,0.00018641393,0.00037568336,0.00006578889,0.00004534248,0.001010005],"genre_scores_gemma":[0.32590693,0.000012841733,0.6738443,0.000043994005,0.00007230019,0.000022767008,0.0000035441103,0.000018437298,0.00007493151],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99837095,0.00020847301,0.000869785,0.00008347651,0.00032395552,0.00014337264],"domain_scores_gemma":[0.9878076,0.010278399,0.0008575267,0.00014638768,0.0007929803,0.00011711346],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008893905,0.00012818379,0.0006261105,0.00012623791,0.00004061293,0.00010419505,0.00018066469,0.00006612363,0.000020216594],"category_scores_gemma":[0.009905287,0.0000985028,0.00009413867,0.00006447177,0.00010844158,0.00010012079,0.000017323278,0.00015201756,0.000004089178],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.142824,0.000093751376,0.0000022732468,0.00012192213,0.00013665411,0.000011936991,0.003184122,0.00019745427,0.00049735914,0.777411,0.073131055,0.0023885],"study_design_scores_gemma":[0.022250174,0.00022370226,0.000006956566,0.00006910215,0.00009597602,0.000026334565,0.0012440704,0.0014910139,0.0017410957,0.9719862,0.000750377,0.00011499839],"about_ca_topic_score_codex":0.000004163296,"about_ca_topic_score_gemma":0.0000021037301,"teacher_disagreement_score":0.3174426,"about_ca_system_score_codex":0.000058094058,"about_ca_system_score_gemma":0.00034050582,"threshold_uncertainty_score":0.9984347},"labels":[],"label_agreement":null},{"id":"W2346012900","doi":"10.1080/02664763.2016.1174194","title":"<i>L</i><sup>1</sup>-distance and classification problem by Bayesian method","year":2016,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":37,"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 Lethbridge","keywords":"Bayesian probability; Relation (database); MATLAB; Mathematics; Computer science; Econometrics; Statistics; Probability density function; Algorithm; Data mining","score_opus":0.04986414214939088,"score_gpt":0.3765667825173506,"score_spread":0.3267026403679597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2346012900","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":[0.0001094534,0.00007918056,0.99633616,0.00035088233,0.00003899742,0.0002078826,0.0005170348,0.000019655763,0.0023407794],"genre_scores_gemma":[0.023126403,0.00024529555,0.97600657,0.00010278483,0.00008825498,0.000011715294,0.0000034489758,0.000042704265,0.00037279946],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99807936,0.00011443758,0.00086476264,0.00024279868,0.00040934983,0.00028926786],"domain_scores_gemma":[0.995443,0.00311417,0.00072595,0.0002120168,0.0002627882,0.00024209936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00104256,0.00021403375,0.0004911408,0.00006967484,0.00009529531,0.000038771857,0.00016927625,0.00010043087,0.00004893377],"category_scores_gemma":[0.00069053017,0.00014088149,0.000041227027,0.000099361205,0.00013585291,0.00012263023,0.000034052624,0.00023174116,0.0000039762813],"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":[0.00013121517,0.00007170533,0.000008404154,0.000082926366,0.00004002039,0.000008863943,0.00020776642,0.000025052015,0.0053181355,0.73524255,0.016711686,0.24215166],"study_design_scores_gemma":[0.0009790268,0.00014336128,0.000013771535,0.0000944099,0.00010072784,0.000038863345,0.00016336018,0.006476348,0.00075195386,0.9748897,0.016138067,0.00021043584],"about_ca_topic_score_codex":5.35308e-7,"about_ca_topic_score_gemma":9.703649e-7,"teacher_disagreement_score":0.24194123,"about_ca_system_score_codex":0.00008468221,"about_ca_system_score_gemma":0.000065499,"threshold_uncertainty_score":0.574498},"labels":[],"label_agreement":null},{"id":"W2410096635","doi":"10.1080/02664763.2016.1193846","title":"An approach to measure distance between compositional diet estimates containing essential zeros","year":2016,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":20,"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 New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Compositional data; Measure (data warehouse); Statistics; Statistic; Property (philosophy); Mathematics; Distance measures; Coherence (philosophical gambling strategy); Econometrics; Computer science; Data mining; Artificial intelligence","score_opus":0.01989767148608147,"score_gpt":0.254926559314041,"score_spread":0.23502888782795955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2410096635","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":[0.003058402,0.000008680812,0.9933227,0.0004855518,0.000093246235,0.00007663351,0.00008728542,0.000024858924,0.0028426584],"genre_scores_gemma":[0.6064639,9.0582233e-7,0.39329922,0.000056892655,0.00015287506,0.00000257158,0.000007320592,0.0000026221421,0.000013695326],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986374,0.00002595471,0.00042328966,0.00021793658,0.00044617194,0.00024925583],"domain_scores_gemma":[0.9985794,0.0002962557,0.0003272222,0.00022882572,0.0003402748,0.0002280274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004461552,0.00014339265,0.00028098625,0.000050556657,0.00013805593,0.000111366564,0.00068160385,0.00005725935,0.00001046253],"category_scores_gemma":[0.00009509578,0.00010212134,0.000036063626,0.00012132503,0.0000677845,0.00017221531,0.0000837552,0.00015396737,0.000007128424],"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":[0.0007481311,0.0004367007,0.0042556147,0.000116147115,0.0002347133,0.00009881613,0.0018518902,0.0058851894,0.09400342,0.83311874,0.007221355,0.05202932],"study_design_scores_gemma":[0.010066772,0.0045661116,0.083591945,0.0009302042,0.00041881044,0.00048354507,0.0009899805,0.04681809,0.084620245,0.7305201,0.033694074,0.0033000826],"about_ca_topic_score_codex":8.206254e-7,"about_ca_topic_score_gemma":2.3204773e-7,"teacher_disagreement_score":0.6034055,"about_ca_system_score_codex":0.000045713452,"about_ca_system_score_gemma":0.00008695664,"threshold_uncertainty_score":0.41643873},"labels":[],"label_agreement":null},{"id":"W2528587226","doi":"10.1080/02664763.2016.1238054","title":"A likelihood-based approach for multivariate one-sided tests with missing data","year":2016,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods in Clinical Trials","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 British Columbia","funders":"","keywords":"Multivariate statistics; Missing data; Multivariate analysis; Anesthesiology; Statistics; Medicine; Library science; Computer science; Mathematics","score_opus":0.5821130806050215,"score_gpt":0.5298083091860011,"score_spread":0.05230477141902046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2528587226","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":[0.00020521333,0.000008981115,0.9957931,0.00032063198,0.0001759015,0.000699827,0.0021767844,0.00003303496,0.00058651174],"genre_scores_gemma":[0.017100872,0.00000637465,0.9820429,0.0001873961,0.0005070269,0.000021649235,0.00001536239,0.00008996609,0.000028425853],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99641573,0.00022728303,0.0016948575,0.00042633832,0.00076515385,0.0004706337],"domain_scores_gemma":[0.9130518,0.083538264,0.0016705178,0.00084052235,0.0005782749,0.00032065008],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0048781456,0.0002968408,0.0010818343,0.000123056,0.00011055925,0.00008031427,0.0008142213,0.00016666386,0.00006239256],"category_scores_gemma":[0.07227664,0.00017485945,0.00008032642,0.00016824035,0.00023429068,0.000100520134,0.00011306145,0.0003229693,0.0000042613],"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":[0.011329493,0.003234556,0.00014287097,0.0014803137,0.0013458354,0.00010278807,0.00024510568,0.00011776863,0.021131467,0.46126267,0.032897204,0.46670994],"study_design_scores_gemma":[0.008390291,0.0006699043,0.0001471917,0.00045400957,0.0007643743,0.000016520835,0.00004571081,0.0074202907,0.0022175615,0.9789718,0.0005422816,0.00036005714],"about_ca_topic_score_codex":0.0000017189519,"about_ca_topic_score_gemma":0.0000022777267,"teacher_disagreement_score":0.51770914,"about_ca_system_score_codex":0.00009550479,"about_ca_system_score_gemma":0.00047139195,"threshold_uncertainty_score":0.935538},"labels":[],"label_agreement":null},{"id":"W2567192494","doi":"10.1080/02664763.2016.1268106","title":"A functional data approach to model score difference process in professional basketball games","year":2016,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":30,"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":"National Natural Science Foundation of China","keywords":"Basketball; Realization (probability); Process (computing); Computer science; Momentum (technical analysis); Econometrics; Statistics; Mathematics; Economics","score_opus":0.09927779556843992,"score_gpt":0.2682724620487213,"score_spread":0.16899466648028139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2567192494","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":[0.16111448,0.00009676836,0.83201253,0.00033244447,0.00040100503,0.00017782522,0.0015494141,0.000005477626,0.0043100337],"genre_scores_gemma":[0.97793466,0.0000979067,0.020376524,0.00023594138,0.00014707269,0.000008738426,0.000035057623,0.000017058414,0.0011470454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855274,0.0000028709567,0.0008137544,0.00027315598,0.0001365187,0.00022095969],"domain_scores_gemma":[0.99887705,0.000059299564,0.00055133144,0.0002893666,0.000097410775,0.00012551696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006007318,0.00013073166,0.00036590823,0.0002528601,0.0000445608,0.000035244248,0.00044997578,0.000060904807,0.00012807049],"category_scores_gemma":[0.000081290316,0.000095251926,0.00002640163,0.00017359896,0.000041196752,0.00015343542,0.00009578824,0.00018589925,0.000034249962],"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":[0.0005093227,0.0008434362,0.075044565,0.0001712079,0.000094618044,0.000013626781,0.0010742224,0.045187738,0.00010097777,0.82729626,0.040205672,0.009458344],"study_design_scores_gemma":[0.002174364,0.00010562866,0.21019647,0.00017777225,0.000021606638,0.0000218231,0.00018572377,0.530835,0.000029643292,0.24966286,0.006039114,0.000550004],"about_ca_topic_score_codex":0.0000036666752,"about_ca_topic_score_gemma":0.0000072815833,"teacher_disagreement_score":0.81682014,"about_ca_system_score_codex":0.000072574236,"about_ca_system_score_gemma":0.00014988988,"threshold_uncertainty_score":0.3884261},"labels":[],"label_agreement":null},{"id":"W2886082462","doi":"10.1080/02664763.2018.1510475","title":"Detection of a change-point in variance by a weighted sum of powers of variances test","year":2018,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Variance (accounting); Statistics; Mathematics; Value (mathematics); Point (geometry); Test (biology); One-way analysis of variance; Sample size determination; Sequence (biology); Analysis of variance","score_opus":0.06539002197327509,"score_gpt":0.3386058483489105,"score_spread":0.2732158263756354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886082462","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":[0.019504637,0.000047442558,0.9782774,0.00002372403,0.00017849698,0.00018172548,0.00049419835,0.0000035416758,0.0012888628],"genre_scores_gemma":[0.53107363,0.000042554766,0.46880132,0.00001307485,0.00004945349,0.000002926863,8.1074245e-7,0.000009844833,0.000006372013],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980986,0.000067109686,0.0011794637,0.000111252455,0.0003741947,0.00016936354],"domain_scores_gemma":[0.9951124,0.0025059062,0.0015826141,0.00016256845,0.00056856585,0.00006792222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009191017,0.00013151488,0.000621444,0.00015238572,0.000019806404,0.0000063399943,0.00018012049,0.000087187706,0.00010012538],"category_scores_gemma":[0.0019934797,0.00011017999,0.00004182583,0.0003253052,0.00026170965,0.000050469193,0.000028529688,0.00019735558,9.994808e-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":[0.0010902925,0.0013519478,0.0006880899,0.0011600825,0.00017314343,0.000017258692,0.0037920186,0.000002638466,0.26453492,0.6559629,0.0017807011,0.06944602],"study_design_scores_gemma":[0.0015285986,0.0021680885,0.0034990564,0.00043333627,0.00014842351,0.00001564072,0.0005036661,0.0040469463,0.13828942,0.8489214,0.00024617816,0.00019919328],"about_ca_topic_score_codex":0.000040466923,"about_ca_topic_score_gemma":0.000026993019,"teacher_disagreement_score":0.51156896,"about_ca_system_score_codex":0.00003890646,"about_ca_system_score_gemma":0.000080225844,"threshold_uncertainty_score":0.44930097},"labels":[],"label_agreement":null},{"id":"W2889750398","doi":"10.1080/02664763.2018.1517145","title":"Bayesian growth curve model useful for high-dimensional longitudinal data","year":2018,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Michael's Hospital; McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Test statistic; Computer science; Inference; Monotone polygon; Curse of dimensionality; Null hypothesis; Statistical hypothesis testing; Bayesian probability; Statistic; Singularity; Null (SQL); Mathematics; Sample size determination; Statistics; Data mining; Artificial intelligence","score_opus":0.04115864328533659,"score_gpt":0.30809958014203026,"score_spread":0.2669409368566937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889750398","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":[0.017432665,0.000050135906,0.98116535,0.00014081626,0.00026451694,0.00010628088,0.0005786542,0.0000027958954,0.00025877487],"genre_scores_gemma":[0.75618327,0.00003456949,0.24243864,0.00020018307,0.0006819134,0.0000042467314,0.00033201143,0.000016933056,0.00010821329],"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990597,0.000011880702,0.00033386284,0.00022967017,0.00021403491,0.00015089138],"domain_scores_gemma":[0.99874157,0.000020048798,0.00032461638,0.0003439369,0.00046925436,0.00010058219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002713078,0.00011081678,0.00014771103,0.000049338698,0.00009069901,0.000024590658,0.00034430847,0.00008420122,0.000022551638],"category_scores_gemma":[0.00008467609,0.00009569072,0.000029235918,0.000050743147,0.00008335745,0.0000060547477,0.00010099972,0.00008216699,0.000003266067],"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":[0.0017363606,0.00019958698,0.00033185244,0.00004775958,0.00017270156,0.000003545075,0.000064027336,0.00088387297,0.35211286,0.02414187,0.61253107,0.00777453],"study_design_scores_gemma":[0.009381996,0.0033862996,0.0070947446,0.00010175943,0.0005862658,0.00014042252,0.0002300778,0.19264899,0.5530159,0.13063934,0.10138591,0.001388324],"about_ca_topic_score_codex":0.000001182544,"about_ca_topic_score_gemma":0.000007985314,"teacher_disagreement_score":0.73875064,"about_ca_system_score_codex":0.000015688405,"about_ca_system_score_gemma":0.00022804279,"threshold_uncertainty_score":0.39021543},"labels":[],"label_agreement":null},{"id":"W2896915321","doi":"10.1080/02664763.2021.1957789","title":"A new GEE method to account for heteroscedasticity using asymmetric least-square regressions","year":2021,"lang":"en","type":"preprint","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal; McGill University; Jewish General Hospital","funders":"","keywords":"Heteroscedasticity; Estimator; Mathematics; Generalized estimating equation; Estimating equations; Statistics; Asymptotic distribution; Inference; Econometrics; Covariance matrix; Applied mathematics; Computer science","score_opus":0.13253678431776542,"score_gpt":0.45245195313507025,"score_spread":0.31991516881730486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896915321","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":[0.00025800668,0.000083167135,0.9953561,0.000100223944,0.0011305095,0.0008601642,0.0019396967,0.00002395891,0.00024819994],"genre_scores_gemma":[0.0022461766,0.000023163333,0.99645746,0.00020897563,0.0008555656,0.000028931416,0.000025029549,0.00011146762,0.000043226155],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9957234,0.00023999005,0.0018983706,0.00056616176,0.000991359,0.00058066857],"domain_scores_gemma":[0.98724794,0.008046606,0.0020119792,0.0005827372,0.0014185066,0.00069222983],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017384714,0.00058262964,0.0018034541,0.0005502889,0.0001846988,0.00038981836,0.00066883623,0.00045655412,0.00016450215],"category_scores_gemma":[0.008406849,0.00050505955,0.00033529263,0.000483657,0.000046241734,0.000056501904,0.0005934762,0.0014030646,0.0000030723536],"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":[0.0007093149,0.00043130922,0.000022664564,0.00286186,0.0006676993,0.0001893284,0.0012161852,0.0028111192,0.0020978337,0.56836987,0.029037494,0.39158532],"study_design_scores_gemma":[0.00091073994,0.00028877676,0.00015115454,0.0013788259,0.0011776953,0.00009158082,0.000397661,0.015676115,0.0014238366,0.9771347,0.00071820285,0.0006506796],"about_ca_topic_score_codex":0.000034662866,"about_ca_topic_score_gemma":0.000014211301,"teacher_disagreement_score":0.40876487,"about_ca_system_score_codex":0.00039677086,"about_ca_system_score_gemma":0.0015347956,"threshold_uncertainty_score":0.99994576},"labels":[],"label_agreement":null},{"id":"W2902854630","doi":"10.1080/02664763.2018.1552668","title":"Testing homogeneity in a heteroscedastic contaminated normal mixture","year":2018,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods in Clinical Trials","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":"York University; University of Waterloo; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Homogeneity (statistics); Heteroscedasticity; Statistics; Mixture model; Inference; Mathematics; Normal distribution; Test statistic; Type I and type II errors; Statistical hypothesis testing; Computer science; Artificial intelligence","score_opus":0.32812212445169364,"score_gpt":0.49402816850563375,"score_spread":0.1659060440539401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902854630","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":[0.12694773,0.000012053079,0.8681828,0.000036851256,0.00085550995,0.000308778,0.00023990915,0.000027416047,0.0033889867],"genre_scores_gemma":[0.36866558,0.0000027311808,0.63072246,0.00010534753,0.00045711346,0.000003510764,7.1668484e-7,0.000027313126,0.000015227073],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966173,0.00028548908,0.0018994478,0.00022259864,0.0005606222,0.000414513],"domain_scores_gemma":[0.96371144,0.033916548,0.0011783842,0.00026008455,0.0007187843,0.00021476569],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0033072028,0.00023948238,0.00090007926,0.00017632966,0.00008121806,0.000049047765,0.00035708284,0.00019517493,0.00017621212],"category_scores_gemma":[0.069230266,0.0002020256,0.00007131761,0.00043608606,0.00032953784,0.00005296305,0.00008951318,0.0006993002,0.000023956143],"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":[0.00510833,0.0027211981,0.009717839,0.0011696838,0.00063921546,0.0018036494,0.0025375164,0.00010120057,0.0491621,0.64544594,0.025898658,0.2556947],"study_design_scores_gemma":[0.002702474,0.0010125788,0.011116995,0.00020213198,0.00018047709,0.00009369913,0.0001042301,0.0014751409,0.0036218825,0.9789909,0.00020125737,0.00029824805],"about_ca_topic_score_codex":0.0000049349765,"about_ca_topic_score_gemma":0.000022688318,"teacher_disagreement_score":0.33354497,"about_ca_system_score_codex":0.00011182096,"about_ca_system_score_gemma":0.00016015022,"threshold_uncertainty_score":0.93861},"labels":[],"label_agreement":null},{"id":"W2964293100","doi":"10.1080/02664763.2018.1536878","title":"Is it even rainier in<i>North</i>Vancouver? A non-parametric rank-based test for semicontinuous longitudinal data","year":2018,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Parametric statistics; Rank (graph theory); Computer science; Longitudinal data; Random effects model; Statistics; Mathematics; Algorithm; Econometrics; Data mining; Medicine","score_opus":0.15126136075443297,"score_gpt":0.3990622772537438,"score_spread":0.24780091649931085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964293100","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":[0.007952787,0.000017984847,0.9870917,0.00009688065,0.00046807213,0.0004754005,0.0026016056,0.0000103613675,0.0012852162],"genre_scores_gemma":[0.244264,0.000013577152,0.7547924,0.00042673032,0.00036860976,0.000012684314,0.00001968542,0.000038693743,0.00006360291],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972039,0.00004533487,0.0013523978,0.00036180555,0.00056888285,0.00046772],"domain_scores_gemma":[0.9872176,0.010192809,0.001003286,0.00064068596,0.0007409886,0.0002045984],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016299528,0.00028318935,0.0008090406,0.00031211314,0.00010298736,0.00007452276,0.0007579852,0.00012634993,0.00023432566],"category_scores_gemma":[0.009330317,0.00024127192,0.00007429525,0.0006154912,0.0002016361,0.00009118326,0.00011608354,0.00042316868,0.000016408481],"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":[0.001439818,0.0011755226,0.008099078,0.0006450791,0.00022478498,0.00014300588,0.0011231828,0.000033292636,0.00038547243,0.015436099,0.9064736,0.06482108],"study_design_scores_gemma":[0.015335433,0.0041616894,0.017893469,0.000576371,0.0012044111,0.000080395344,0.0008493898,0.16719979,0.0020562995,0.7439838,0.045031376,0.0016275916],"about_ca_topic_score_codex":0.000012184128,"about_ca_topic_score_gemma":0.00031573852,"teacher_disagreement_score":0.8614422,"about_ca_system_score_codex":0.00010209277,"about_ca_system_score_gemma":0.00042378504,"threshold_uncertainty_score":0.9990145},"labels":[],"label_agreement":null},{"id":"W2967275303","doi":"10.1080/02664763.2019.1652254","title":"EM-test for homogeneity in a two-sample problem with a mixture structure","year":2019,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Distribution Estimation and Applications","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":"York University","funders":"","keywords":"Homogeneity (statistics); Statistics; Sample size determination; Mathematics; Null hypothesis; Sample (material); Computer science; Chemistry; Chromatography","score_opus":0.020846216808293388,"score_gpt":0.3290732872956579,"score_spread":0.3082270704873645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967275303","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":[0.02902308,0.000005392846,0.9642989,0.00012871846,0.00003428496,0.0007276237,0.005422834,0.0000136531235,0.0003454979],"genre_scores_gemma":[0.45581797,0.000001455076,0.5439118,0.00007706918,0.00003638903,0.000020602723,0.00009291037,0.000016408694,0.000025390687],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99872905,0.00001412523,0.0005885236,0.00015053665,0.00030444266,0.0002133472],"domain_scores_gemma":[0.9959273,0.0029110534,0.0005056543,0.0001742169,0.0003726796,0.00010909839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021794897,0.00015774147,0.000359213,0.00008688754,0.000056645855,0.000047822745,0.0001632324,0.000056033874,0.00022424037],"category_scores_gemma":[0.0006857735,0.0001216056,0.000037718535,0.00023283805,0.00004291208,0.00004706117,0.000016001884,0.00025341482,0.000007557422],"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":[0.00017417419,0.00022755055,0.000577496,0.000203302,0.000034301174,0.0000039564698,0.00029533697,0.00050565734,0.00082555914,0.9888079,0.006095417,0.0022493503],"study_design_scores_gemma":[0.0032765013,0.00025712495,0.0027175406,0.00006847623,0.000104003964,0.000038194707,0.00035713316,0.0067766206,0.0006038615,0.98344624,0.0021186462,0.0002356312],"about_ca_topic_score_codex":0.000003240028,"about_ca_topic_score_gemma":0.000107386535,"teacher_disagreement_score":0.4267949,"about_ca_system_score_codex":0.000087873384,"about_ca_system_score_gemma":0.00015214707,"threshold_uncertainty_score":0.49589324},"labels":[],"label_agreement":null},{"id":"W2991264399","doi":"10.1080/02664763.2019.1695759","title":"Robust signed-rank estimation and variable selection for semi-parametric additive partial linear models","year":2019,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nonparametric statistics; Additive model; Outlier; Estimator; Covariate; Mathematics; Parametric statistics; Model selection; Smoothing; Parametric model; Spline (mechanical); Robustness (evolution); Leverage (statistics); Semiparametric model; Smoothing spline; Smoothness; Econometrics; Mathematical optimization; Statistics; Spline interpolation","score_opus":0.06985366722994428,"score_gpt":0.357185286224967,"score_spread":0.2873316189950227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991264399","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":[0.0013823819,0.000018484921,0.99667215,0.0000147442215,0.00016989256,0.00054979976,0.00048680574,0.000017842303,0.0006878809],"genre_scores_gemma":[0.060166463,0.00002455168,0.93942666,0.000043847278,0.00014857491,0.000020639183,0.000019968256,0.00003748491,0.00011183171],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848014,0.000047997084,0.0006811615,0.00020582005,0.00032247382,0.00026239574],"domain_scores_gemma":[0.9948071,0.0038513725,0.0006304114,0.00010554065,0.0004661657,0.00013941019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076743827,0.00018532376,0.00050299946,0.0001504155,0.00009891769,0.000041613355,0.00008517971,0.000119477685,0.00005307259],"category_scores_gemma":[0.0011217663,0.0001639885,0.000043953292,0.00021652972,0.000043586457,0.00018898648,0.000022994798,0.00026819797,0.0000030425683],"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":[0.0004107082,0.00009243993,0.0000018613904,0.00017353149,0.000068747715,0.00000138818,0.00015207371,0.18819124,0.0005125205,0.7892727,0.0014186738,0.01970411],"study_design_scores_gemma":[0.0006866329,0.00025911772,0.0000017092677,0.000023953196,0.0001120649,0.000011282746,0.00004703677,0.49945047,0.00037667318,0.49874556,0.00018626482,0.00009923496],"about_ca_topic_score_codex":0.0000019507233,"about_ca_topic_score_gemma":8.477413e-7,"teacher_disagreement_score":0.3112592,"about_ca_system_score_codex":0.00008254959,"about_ca_system_score_gemma":0.00010947439,"threshold_uncertainty_score":0.6687257},"labels":[],"label_agreement":null},{"id":"W2992485813","doi":"10.1080/02664763.2021.1911966","title":"Confounding adjustment methods for multi-level treatment comparisons under lack of positivity and unknown model specification","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"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":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Université Laval","keywords":"Covariate; Estimator; Observational study; Context (archaeology); Specification; Confounding; Matching (statistics); Variance (accounting); Propensity score matching","score_opus":0.6386904553834739,"score_gpt":0.5704813769769004,"score_spread":0.06820907840657353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2992485813","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":[0.0017960095,0.00010400932,0.9971441,0.000053665066,0.000051192124,0.00030055753,0.0002519497,0.000013429598,0.00028509658],"genre_scores_gemma":[0.055501755,0.00025251115,0.9440225,0.000032648386,0.00003167101,0.000016012273,0.000015532454,0.000020894173,0.000106478175],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99887884,0.00005651694,0.0006385508,0.00013096648,0.00015105591,0.00014405343],"domain_scores_gemma":[0.9971383,0.0013983244,0.0007419564,0.00016292119,0.0004782935,0.00008017684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045887366,0.00015157711,0.0005128953,0.000066595196,0.000055333247,0.000019808818,0.000067472865,0.00006713826,0.000008265273],"category_scores_gemma":[0.00020527815,0.00013186959,0.00005455872,0.000064680964,0.000076310156,0.00005488545,0.000028913639,0.000118635966,2.1909722e-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":[0.000094927374,0.00041253938,0.0000065489858,0.000099132725,0.00013071213,0.0000020528473,0.00039924833,0.00086071325,0.039383594,0.92862886,0.0005285514,0.029453136],"study_design_scores_gemma":[0.0013769043,0.00025533032,0.00025043977,0.00006321583,0.00033710516,0.000018053046,0.00056223024,0.08824231,0.11205124,0.796358,0.0003212281,0.00016394557],"about_ca_topic_score_codex":0.0000013457395,"about_ca_topic_score_gemma":0.000013331956,"teacher_disagreement_score":0.13227084,"about_ca_system_score_codex":0.00023795872,"about_ca_system_score_gemma":0.00016026325,"threshold_uncertainty_score":0.5377486},"labels":[],"label_agreement":null},{"id":"W3043881144","doi":"10.1080/02664763.2020.1795819","title":"Identifying key factors in momentum in basketball games","year":2020,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","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 Prince Edward Island; University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Basketball; Operationalization; Momentum (technical analysis); Attendance; Key (lock); Salary; Econometrics; Computer science; Field (mathematics); Statistic; Mathematics; Statistics; Economics; Physics; Computer security; Geography; Financial economics","score_opus":0.05086614624785881,"score_gpt":0.2377608578415713,"score_spread":0.1868947115937125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3043881144","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94684184,0.00046412682,0.044433482,0.00041990087,0.0003911522,0.000120767814,0.00021618111,0.000005487399,0.0071070762],"genre_scores_gemma":[0.9955551,0.0004167705,0.0036682296,0.00021405613,0.000080833546,9.4091115e-7,0.000006712712,0.000013917647,0.000043460404],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998629,0.000002771587,0.0009784065,0.00013557998,0.00006700161,0.0001872712],"domain_scores_gemma":[0.99915045,0.000043853477,0.00060991355,0.00007554693,0.00002388075,0.00009637759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003483358,0.000104536826,0.00041200395,0.00026290314,0.000019160301,0.000056361117,0.00016821202,0.000047009857,0.00031233445],"category_scores_gemma":[0.000052050764,0.000109519475,0.00004425995,0.0002561781,0.000020646368,0.00010725134,0.000027645754,0.0002800541,0.00003316188],"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":[0.00012825557,0.00017086326,0.57686305,0.00015323279,0.00006927673,0.00016168693,0.009226625,0.012656638,0.00010602418,0.39396673,0.0053206957,0.001176899],"study_design_scores_gemma":[0.0031234617,0.00026587647,0.7429738,0.000090330395,0.000021637208,0.0000061013156,0.0025112252,0.07178582,0.00026286943,0.12101375,0.057246894,0.00069823663],"about_ca_topic_score_codex":0.000046046993,"about_ca_topic_score_gemma":0.000040170427,"teacher_disagreement_score":0.27295297,"about_ca_system_score_codex":0.00008629985,"about_ca_system_score_gemma":0.000027918242,"threshold_uncertainty_score":0.44660744},"labels":[],"label_agreement":null},{"id":"W3048846794","doi":"10.1080/02664763.2022.2034760","title":"Sensitivity analysis of error-contaminated time series data under autoregressive models with the application of COVID-19 data","year":2022,"lang":"en","type":"preprint","venue":"Journal of Applied Statistics","topic":"COVID-19 epidemiological studies","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":true,"ca_institutions":"Western University; University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Autoregressive model; Observational error; Sensitivity (control systems); Time series; Series (stratigraphy); Statistics; Estimation; Coronavirus disease 2019 (COVID-19); Computer science; Errors-in-variables models; Autoregressive integrated moving average; Econometrics; Mathematics; Engineering","score_opus":0.3084389534572723,"score_gpt":0.45031641575627324,"score_spread":0.14187746229900094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048846794","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":[0.003939797,0.00012694279,0.96511716,0.0014106169,0.00004239433,0.0006851615,0.028499767,0.0000249723,0.00015320031],"genre_scores_gemma":[0.6815176,0.00035379684,0.3114349,0.00059057923,0.00011235717,0.000047419053,0.0057729282,0.00007710005,0.00009332114],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956702,0.00063000154,0.0016638957,0.00067193917,0.0011055047,0.00025846975],"domain_scores_gemma":[0.97763413,0.011976882,0.006519115,0.0031000238,0.0006314891,0.00013837867],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.005660867,0.0004156282,0.0022718867,0.00028479347,0.00020400052,0.00002891537,0.0021591245,0.00020013822,0.0000935535],"category_scores_gemma":[0.0035122675,0.00026160784,0.00014008649,0.0005779379,0.0006373061,0.00012165991,0.005180678,0.0010721694,6.7342904e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014722488,0.00055448216,0.00045441624,0.0014598307,0.015081127,0.000080352416,0.0023055167,0.7957372,0.00020770585,0.15091366,0.03071919,0.0010142738],"study_design_scores_gemma":[0.0006827104,0.00020475923,0.0021682621,0.00006691041,0.014991175,0.000017122917,0.0027223136,0.6468575,0.00002718105,0.33021832,0.0015849149,0.00045882977],"about_ca_topic_score_codex":0.00035909383,"about_ca_topic_score_gemma":0.0008332205,"teacher_disagreement_score":0.6775778,"about_ca_system_score_codex":0.0003637233,"about_ca_system_score_gemma":0.00090303214,"threshold_uncertainty_score":0.9999836},"labels":[],"label_agreement":null},{"id":"W3093066829","doi":"10.1080/02664763.2020.1833183","title":"The GLM framework of the Lee–Carter model: a multi-country study","year":2020,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":10,"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":"Universiti Malaya","keywords":"Deviance (statistics); Negative binomial distribution; Generalized linear model; Statistics; Poisson distribution; Econometrics; Mathematics; Count data; Poisson regression; Binomial distribution; Statistical model; Deviance information criterion; Demography; Sociology; Population; Bayesian probability; Bayesian inference","score_opus":0.028181942462116884,"score_gpt":0.31734128641478293,"score_spread":0.28915934395266607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093066829","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":[0.2795272,0.00042079328,0.6939648,0.004966202,0.0024918667,0.0029159903,0.00036745003,0.00005892679,0.015286808],"genre_scores_gemma":[0.9800279,0.00016043261,0.01883401,0.0006462084,0.00026996067,0.0000069024068,3.6942947e-7,0.000015203799,0.00003898323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99766874,0.00015546665,0.00062611874,0.00012795751,0.0011634651,0.00025826943],"domain_scores_gemma":[0.9983202,0.00035120087,0.00071402354,0.00024364608,0.00026395702,0.000106972795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012664108,0.00012579131,0.0002654406,0.000033213626,0.00057241274,0.00011439717,0.0007989598,0.00006480395,0.000014436381],"category_scores_gemma":[0.00028640157,0.000075630844,0.00010189612,0.00039808432,0.00039807527,0.000059122784,0.00009826493,0.00049249444,0.0000041601133],"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":[0.0004666773,0.0010939615,0.045476094,0.0000909991,0.00089366443,0.000043693188,0.13595186,0.01715708,0.00006580898,0.7526524,0.03224838,0.013859365],"study_design_scores_gemma":[0.0061877193,0.0011126732,0.24683377,0.00018338322,0.001983581,0.0000037524135,0.24917275,0.05512542,0.000098793054,0.34487957,0.093131416,0.0012871523],"about_ca_topic_score_codex":0.00006344697,"about_ca_topic_score_gemma":0.00044283178,"teacher_disagreement_score":0.7005007,"about_ca_system_score_codex":0.000047762973,"about_ca_system_score_gemma":0.0001710804,"threshold_uncertainty_score":0.4402594},"labels":[],"label_agreement":null},{"id":"W3113121140","doi":"10.1080/02664763.2020.1856352","title":"Ultrahigh-dimensional sufficient dimension reduction for censored data with measurement error in covariates","year":2020,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Inference","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":"Western University","funders":"","keywords":"Covariate; Dimensionality reduction; Computer science; Observational error; Dimension (graph theory); Sufficient dimension reduction; Statistics; Subspace topology; Feature (linguistics); Reduction (mathematics); Standard error; Data mining; Mathematics; Artificial intelligence","score_opus":0.17343395960140334,"score_gpt":0.3608302552843572,"score_spread":0.18739629568295385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113121140","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":[0.015306706,0.000024549285,0.9829044,0.00051904254,0.00018298153,0.0004114842,0.0005561287,0.000011813897,0.00008291636],"genre_scores_gemma":[0.27260685,0.000004990044,0.7271579,0.00009130094,0.000088044006,0.0000048174757,0.000024419072,0.000019564102,0.0000020910563],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978964,0.00006395223,0.0007899273,0.00025363377,0.00076935114,0.00022676957],"domain_scores_gemma":[0.9974663,0.0009904674,0.00056006794,0.00022615271,0.0005869387,0.00017003175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012449422,0.00017077956,0.0004477947,0.00006904296,0.000064079155,0.000031396743,0.0002444778,0.000057505025,0.00004161814],"category_scores_gemma":[0.002185902,0.00012393668,0.0000246116,0.00017097943,0.00007048745,0.000054377346,0.000052267387,0.0002626941,0.0000023387895],"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":[0.0048436513,0.0008132943,0.00004127486,0.00044201824,0.0001988577,0.00006138431,0.0016938554,0.0030020354,0.035972275,0.9110031,0.03403165,0.007896615],"study_design_scores_gemma":[0.011677461,0.004815718,0.0023319721,0.00065952307,0.0010294251,0.00016417573,0.0026581113,0.18466303,0.015489529,0.7727548,0.0026491915,0.0011070749],"about_ca_topic_score_codex":0.0000039583406,"about_ca_topic_score_gemma":0.0000051162374,"teacher_disagreement_score":0.25730017,"about_ca_system_score_codex":0.000087228305,"about_ca_system_score_gemma":0.00021013596,"threshold_uncertainty_score":0.5053991},"labels":[],"label_agreement":null},{"id":"W3118534316","doi":"10.1080/02664763.2020.1870669","title":"Adaptive kernel scaling support vector machine with application to a prostate cancer image study","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Health Research","keywords":"Support vector machine; Computer science; Interpretability; Pattern recognition (psychology); Artificial intelligence; Kernel (algebra); Feature vector; Classifier (UML); Relevance vector machine; Radial basis function kernel; Scaling; Kernel method; Machine learning; Data mining; Mathematics","score_opus":0.01173480914352574,"score_gpt":0.2853612597932442,"score_spread":0.27362645064971847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118534316","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":[0.0018516278,0.000015844895,0.9966555,0.00035478765,0.000065647546,0.00047414354,0.00025464632,0.000052379623,0.00027541493],"genre_scores_gemma":[0.38448778,0.000016817517,0.6150858,0.00021069741,0.000045483448,0.00007085072,0.00001431176,0.000014965909,0.000053333824],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9984019,0.000037293015,0.0005051582,0.00030338773,0.00054810056,0.00020417634],"domain_scores_gemma":[0.9979719,0.00008578059,0.00052830164,0.00045394409,0.00081056065,0.0001495371],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037577839,0.00015280921,0.00027716093,0.000115375304,0.00008454232,0.00016218258,0.00052577496,0.000028257866,0.000015788763],"category_scores_gemma":[0.00003888639,0.00012747878,0.000020591382,0.00050622225,0.00003316056,0.00023079984,0.00014107347,0.00024370031,0.000014780232],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019166699,0.0037676094,0.0048519694,0.00020976042,0.00076816586,0.0015358164,0.026276194,0.0048351292,0.12076609,0.28037122,0.036767848,0.51793355],"study_design_scores_gemma":[0.018370416,0.01244904,0.19155839,0.0006409946,0.0011423158,0.0013462903,0.012662598,0.2898826,0.34686777,0.07018207,0.049494516,0.0054030037],"about_ca_topic_score_codex":0.000017236802,"about_ca_topic_score_gemma":0.000041405943,"teacher_disagreement_score":0.5125305,"about_ca_system_score_codex":0.00015611648,"about_ca_system_score_gemma":0.0004066577,"threshold_uncertainty_score":0.51984334},"labels":[],"label_agreement":null},{"id":"W3133223479","doi":"10.1080/02664763.2021.1887102","title":"Negligible interaction test for continuous predictors","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods in Clinical Trials","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":"York University; McMaster University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Null hypothesis; Interaction; Equivalence (formal languages); Econometrics; Null (SQL); Psychology; Test (biology); Statistics; Mathematics; Computer science; Data mining","score_opus":0.3108828984686719,"score_gpt":0.5234423770236948,"score_spread":0.21255947855502288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133223479","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":[0.0022973064,0.000021067004,0.9916658,0.00014381047,0.0015395514,0.00027535128,0.00068619876,0.000022272983,0.003348655],"genre_scores_gemma":[0.020967012,0.00005026047,0.97765297,0.0001583663,0.00083796086,0.0000132609775,0.0000056293597,0.000041196523,0.00027335263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99751776,0.00010797257,0.0015354416,0.00017991773,0.00041533506,0.00024359104],"domain_scores_gemma":[0.92153,0.076108806,0.0010794012,0.00021490408,0.0008981255,0.000168785],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0016946737,0.00016370021,0.00076997036,0.0000732418,0.000068136906,0.00007374762,0.00017785678,0.00013086463,0.0002539843],"category_scores_gemma":[0.10111865,0.00014120292,0.00014308596,0.00015116204,0.00007875454,0.0000515093,0.0000450516,0.00038854603,0.000009048028],"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":[0.0007837556,0.00092983263,0.00026939285,0.00043512104,0.00037871415,0.00015866249,0.0002935723,0.000038030194,0.005496537,0.7664307,0.17275959,0.052026127],"study_design_scores_gemma":[0.0017347488,0.0004459617,0.00011792108,0.00008459774,0.00035515122,0.0000661122,0.0003458898,0.00036944944,0.00902899,0.97557515,0.011724606,0.00015143766],"about_ca_topic_score_codex":4.2828307e-7,"about_ca_topic_score_gemma":0.0000020629273,"teacher_disagreement_score":0.20914447,"about_ca_system_score_codex":0.000080747195,"about_ca_system_score_gemma":0.00021196358,"threshold_uncertainty_score":0.906453},"labels":[],"label_agreement":null},{"id":"W3189285760","doi":"10.1080/02664763.2021.1962261","title":"Likelihood ratio test for genetic association study with case–control data under Probit model","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","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":"University of Waterloo","funders":"Higher Education Discipline Innovation Project; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Likelihood-ratio test; Statistics; Probit model; Probit; Score test; Econometrics; Logistic regression; Multinomial probit; Logit; Multivariate probit model; Mathematics","score_opus":0.01974508177449127,"score_gpt":0.28413637639978745,"score_spread":0.2643912946252962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3189285760","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":[0.12283088,0.000110222514,0.8750583,0.0002127122,0.000068404566,0.00036752142,0.0012716067,0.0000025782358,0.00007779217],"genre_scores_gemma":[0.7584127,0.000039744555,0.24066836,0.00027910993,0.00022375977,0.00001851682,0.000177587,0.000020697425,0.0001595079],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987297,0.00006551799,0.0005278164,0.0002550315,0.00018267632,0.00023922721],"domain_scores_gemma":[0.99790543,0.0002922988,0.0006632136,0.00035122855,0.0007057233,0.00008209443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007320143,0.00013564828,0.0002996802,0.000029762969,0.00011523359,0.000037492424,0.0001765207,0.00012153085,0.0000063687457],"category_scores_gemma":[0.0006819211,0.000116846015,0.000036018726,0.00006595365,0.000017622508,0.000004131794,0.000060521026,0.00012874292,0.0000012228344],"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":[0.0016266108,0.0053236806,0.19270319,0.00017880056,0.0067693405,0.000796853,0.0009438195,0.49816307,0.10318408,0.0020613961,0.17130435,0.016944807],"study_design_scores_gemma":[0.05308753,0.018902337,0.19526497,0.00007493942,0.010286241,0.0037140911,0.01592075,0.64130914,0.0061467164,0.042766243,0.009443273,0.0030837583],"about_ca_topic_score_codex":0.0000027755234,"about_ca_topic_score_gemma":0.00026072832,"teacher_disagreement_score":0.63558185,"about_ca_system_score_codex":0.000060996415,"about_ca_system_score_gemma":0.00055745384,"threshold_uncertainty_score":0.4764842},"labels":[],"label_agreement":null},{"id":"W3206708024","doi":"10.1080/02664763.2021.1987400","title":"A novel group VIF regression for group variable selection with application to multiple change-point detection","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Group selection; Group (periodic table); Feature selection; Variance inflation factor; Computer science; Data set; Variable (mathematics); Selection (genetic algorithm); Set (abstract data type); Linear regression; Mathematics; Algorithm; Data mining; Artificial intelligence; Machine learning","score_opus":0.06313427155823831,"score_gpt":0.3346291392769928,"score_spread":0.2714948677187545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206708024","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":[0.0013289794,0.000011237453,0.99736774,0.000051502484,0.00019503155,0.00061173405,0.00016053303,0.000022922746,0.00025032097],"genre_scores_gemma":[0.09371587,0.000005521012,0.90550584,0.00013950349,0.00034964216,0.00019958432,0.000015831974,0.000037334514,0.00003085145],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985402,0.00004217596,0.00056808983,0.00024186245,0.00035974305,0.00024789438],"domain_scores_gemma":[0.9970374,0.0013960601,0.00055501045,0.0001702168,0.0006711555,0.00017016595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069503824,0.00018139288,0.00037777,0.00010679761,0.00015176211,0.00005879882,0.000101493286,0.000100629244,0.000032670927],"category_scores_gemma":[0.0009795298,0.00014208323,0.000039986433,0.0003763623,0.000025207934,0.00006877083,0.00003091254,0.00023759219,0.0000027894023],"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":[0.0010699707,0.00049863866,0.000031043055,0.00026667785,0.00008331703,0.000005587318,0.0005714919,0.000049615268,0.17195003,0.64135706,0.0008165405,0.18330002],"study_design_scores_gemma":[0.005504068,0.003283424,0.0029509533,0.000532194,0.0006164295,0.00039433897,0.0012944764,0.052853934,0.030693363,0.88980687,0.011277569,0.00079237437],"about_ca_topic_score_codex":0.00001844644,"about_ca_topic_score_gemma":0.000099495155,"teacher_disagreement_score":0.2484498,"about_ca_system_score_codex":0.00013936449,"about_ca_system_score_gemma":0.00006431702,"threshold_uncertainty_score":0.5793986},"labels":[],"label_agreement":null},{"id":"W3207567276","doi":"10.1080/02664763.2024.2317312","title":"Multiple observers ranked set samples for shrinkage estimators","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Fuzzy Systems and Optimization","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":"Memorial University of Newfoundland","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"RSS; Statistics; Collinearity; Estimator; Linear regression; Data set; Mathematics; Regression analysis; Lasso (programming language); Computer science; Shrinkage; Multicollinearity; Logistic regression; Data mining","score_opus":0.06952640954494788,"score_gpt":0.3267111903633924,"score_spread":0.25718478081844454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207567276","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":[0.010692216,0.00012536744,0.98656654,0.000059930975,0.00075365294,0.00036710154,0.0010310417,0.00004661721,0.00035751154],"genre_scores_gemma":[0.30664107,0.00002404965,0.6928484,0.000026039148,0.00025289622,0.000011920864,0.000041171654,0.00004700555,0.00010743108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99873763,0.000016529117,0.00066109345,0.000120632845,0.00028582427,0.00017828355],"domain_scores_gemma":[0.99749666,0.0017831458,0.00029892783,0.00012492237,0.00020358681,0.00009274674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054988964,0.00014497033,0.00033774183,0.00011759868,0.000074500385,0.00013024647,0.00013562519,0.00007732854,0.00003577033],"category_scores_gemma":[0.0005510051,0.00011808359,0.0000972414,0.00012225797,0.000030383842,0.00008972365,0.0000173727,0.0001541441,0.0000053953936],"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":[0.0002988292,0.00010110023,0.00016380682,0.0025150978,0.0005077493,0.00008169273,0.0029371704,0.008287435,0.0006989632,0.7555169,0.22336577,0.005525492],"study_design_scores_gemma":[0.0036778606,0.00039937455,0.000325332,0.00061445043,0.00070889574,0.00010825259,0.0018190343,0.26330513,0.0012161424,0.6745221,0.052676056,0.00062736846],"about_ca_topic_score_codex":0.000004038074,"about_ca_topic_score_gemma":0.000011501182,"teacher_disagreement_score":0.29594886,"about_ca_system_score_codex":0.00007868319,"about_ca_system_score_gemma":0.00011401248,"threshold_uncertainty_score":0.4815309},"labels":[],"label_agreement":null},{"id":"W4200286052","doi":"10.1080/02664763.2021.2017413","title":"Pearson's goodness-of-fit tests for sparse distributions","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Tianjin University; National Key Research and Development Program of China; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Pearson's chi-squared test; Mathematics; Goodness of fit; Statistics; Chi-square test; Categorical variable; Test statistic; Statistic; Pearson product-moment correlation coefficient; Mean squared error; Statistical hypothesis testing","score_opus":0.19727193181187358,"score_gpt":0.4524682452303399,"score_spread":0.2551963134184663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200286052","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":[0.0015815892,0.000065109445,0.99448025,0.000086446424,0.00022035089,0.00016124023,0.0026740637,0.000008393151,0.00072257203],"genre_scores_gemma":[0.0612294,0.00004983267,0.9383489,0.00003172018,0.00013391848,0.000009005449,0.00002557951,0.000027158778,0.00014450046],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984446,0.000038958966,0.00081628584,0.00014206301,0.00031477664,0.00024331146],"domain_scores_gemma":[0.994494,0.0035758493,0.0006830179,0.00021158587,0.00087702856,0.00015851526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004991951,0.00014862188,0.0005477009,0.00004912041,0.00008348422,0.000022877131,0.00014141083,0.00007326403,0.00006121681],"category_scores_gemma":[0.0034962315,0.00013202189,0.00010663395,0.00014731969,0.000092844304,0.000047413865,0.000041437303,0.00022178612,0.0000016936659],"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":[0.0001037233,0.00027326998,0.000008485311,0.00022538738,0.00007803626,0.000047861387,0.00013688226,0.00012304098,0.0027277337,0.97225684,0.00778048,0.016238246],"study_design_scores_gemma":[0.00087317673,0.0001517798,0.0000888535,0.00006155213,0.00023926339,0.000049108192,0.0002467631,0.0010683968,0.004589102,0.9868712,0.00561549,0.00014535076],"about_ca_topic_score_codex":4.1276581e-7,"about_ca_topic_score_gemma":0.0000038000912,"teacher_disagreement_score":0.05964781,"about_ca_system_score_codex":0.000053009902,"about_ca_system_score_gemma":0.00023497704,"threshold_uncertainty_score":0.53836966},"labels":[],"label_agreement":null},{"id":"W4210655835","doi":"10.1080/02664763.2022.2031125","title":"The Kendall interaction filter for variable interaction screening in high dimensional classification problems","year":2022,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":8,"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 du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Université du Québec à Montréal","keywords":"Categorical variable; Computer science; Measure (data warehouse); Monotonic function; Variable (mathematics); Identification (biology); Interaction; Filter (signal processing); Machine learning; Artificial intelligence; Data mining; Mathematics","score_opus":0.12165883727174664,"score_gpt":0.3661828880895972,"score_spread":0.24452405081785056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210655835","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":[0.004658144,0.000008809678,0.9934138,0.00022794653,0.0006903021,0.00030410077,0.00017589546,0.000007155306,0.0005138288],"genre_scores_gemma":[0.2350524,0.000007668151,0.7645523,0.000081558894,0.000110212815,0.00006997175,0.000021988862,0.000018778816,0.000085140084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99840647,0.0001275818,0.0007838852,0.00012631461,0.00037230464,0.00018347111],"domain_scores_gemma":[0.9935303,0.005288386,0.00077967864,0.00012142964,0.00023191748,0.000048297286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016622341,0.000107822154,0.00022435449,0.000103187995,0.0002920005,0.00006514912,0.00016473189,0.0000331375,0.00017979028],"category_scores_gemma":[0.001069541,0.00008147155,0.000036581474,0.00014537273,0.000033839577,0.00007245551,0.000058327016,0.0005217219,0.0000012396625],"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":[0.0007395141,0.00016841646,0.00004527219,0.000053189655,0.000050212082,0.0000030579567,0.00029795425,0.0054304535,0.0015738882,0.93057555,0.012031786,0.049030714],"study_design_scores_gemma":[0.00082737923,0.0003049298,0.0007388714,0.00004515611,0.000053990167,0.000033543936,0.00083066936,0.12854138,0.000116442396,0.8541637,0.014223817,0.000120085606],"about_ca_topic_score_codex":0.000010765553,"about_ca_topic_score_gemma":0.000007723375,"teacher_disagreement_score":0.23039427,"about_ca_system_score_codex":0.0001539528,"about_ca_system_score_gemma":0.000077384946,"threshold_uncertainty_score":0.33223137},"labels":[],"label_agreement":null},{"id":"W4214628116","doi":"10.1080/02664763.2022.2041566","title":"Logarithmic confidence estimation of a ratio of binomial proportions for dependent populations","year":2022,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","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 Regina","funders":"Kazan Federal University; Kasetsart University","keywords":"Confidence interval; Statistics; Mathematics; Estimator; Coverage probability; Binomial proportion confidence interval; Logarithm; Ratio estimator; Interval estimation; Tolerance interval; Monte Carlo method; Sample size determination; Negative binomial distribution; Bias of an estimator; Poisson distribution; Minimum-variance unbiased estimator","score_opus":0.1423891164881695,"score_gpt":0.43763149706737403,"score_spread":0.29524238057920454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214628116","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":[0.004967132,0.000017528979,0.99111485,0.000043132557,0.0003817213,0.00032110457,0.002988641,0.000003932275,0.00016192479],"genre_scores_gemma":[0.59588766,0.0000011799789,0.4039716,0.000005656568,0.000035358455,0.0000230528,0.00002246796,0.0000066604607,0.000046365334],"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99642015,0.000052932046,0.0017556183,0.00016014955,0.0014725354,0.00013860484],"domain_scores_gemma":[0.9938725,0.0023785853,0.0024104423,0.00018727056,0.0010744281,0.00007676228],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013747938,0.00009489988,0.0003926037,0.00029886808,0.000224387,0.00003113457,0.00039672374,0.000028247508,0.00035282466],"category_scores_gemma":[0.004745679,0.00008442642,0.00006346948,0.00037851275,0.00012418827,0.00014482421,0.00008229065,0.00021144879,0.0000017312062],"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":[0.0004186934,0.00018943801,0.00015269617,0.000050428716,0.000029601568,0.000008312694,0.0006928561,0.5006995,0.0024225062,0.4548705,0.0037160448,0.03674943],"study_design_scores_gemma":[0.0008115061,0.00045358812,0.0010602698,0.000015617126,0.000079584264,0.000039227543,0.0018860941,0.10349905,0.0021236413,0.88954866,0.00036611845,0.00011662766],"about_ca_topic_score_codex":0.000004993522,"about_ca_topic_score_gemma":0.000007717367,"teacher_disagreement_score":0.5909205,"about_ca_system_score_codex":0.00011681567,"about_ca_system_score_gemma":0.0003858924,"threshold_uncertainty_score":0.56813633},"labels":[],"label_agreement":null},{"id":"W4224928706","doi":"10.1080/02664763.2022.2064440","title":"Bayesian Markov Chain Monte Carlo for reparameterized Stochastic volatility models using Asian FX rates <b>during Covid-19</b>","year":2022,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","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":"Imperial College London; McGill University","keywords":"Markov chain Monte Carlo; Stochastic volatility; Bayesian probability; Volatility (finance); Autocorrelation; Monte Carlo method; Econometrics; Markov chain; Mathematics; Approximate Bayesian computation; Coronavirus disease 2019 (COVID-19); Statistical physics; Applied mathematics; Computer science; Statistics; Physics; Artificial intelligence; Medicine","score_opus":0.0606067351453571,"score_gpt":0.2838054273426945,"score_spread":0.22319869219733737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224928706","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":[0.21882214,0.00025695274,0.77775604,0.000092335235,0.00035193286,0.00043531516,0.0021562483,0.00001603916,0.00011299102],"genre_scores_gemma":[0.86133504,0.000016103715,0.13826384,0.00013212877,0.00011078662,0.00003544621,0.000016237593,0.000047283345,0.00004314812],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727046,0.00004060495,0.0016726142,0.0004096204,0.00016181947,0.00044489765],"domain_scores_gemma":[0.99745154,0.000306906,0.001534566,0.0003171377,0.00011642418,0.00027339492],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019227271,0.00025100695,0.0008543122,0.0003711233,0.0007464009,0.000090320034,0.00033347943,0.00008944873,0.00009629456],"category_scores_gemma":[0.00060014933,0.0003098282,0.0002044577,0.0002550537,0.0000664632,0.00017848203,0.00012199691,0.0004717862,9.110596e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002320657,0.00018564524,0.0008676947,0.00024447078,0.00013682198,0.000025820867,0.0036433714,0.9215432,0.0001701524,0.069357395,0.000385508,0.0011192586],"study_design_scores_gemma":[0.0013738102,0.00012688882,0.00018080401,0.000007666667,0.000034082852,0.000018575567,0.00045272603,0.7580457,0.000007838986,0.23920746,0.00031129346,0.0002331925],"about_ca_topic_score_codex":0.00016440247,"about_ca_topic_score_gemma":0.000027509152,"teacher_disagreement_score":0.6425129,"about_ca_system_score_codex":0.00064800965,"about_ca_system_score_gemma":0.00027798433,"threshold_uncertainty_score":0.9999354},"labels":[],"label_agreement":null},{"id":"W4232213304","doi":"10.1080/02664763.2016.1264701","title":"Editorial","year":2017,"lang":"en","type":"editorial","venue":"Journal of Applied Statistics","topic":"","field":"","cited_by":2,"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":"Specialized Research Fund for the Doctoral Program of Higher Education of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Fonds De La Recherche Scientifique - FNRS; Deutsche Forschungsgemeinschaft","keywords":"Computer science; Statistics; Mathematics","score_opus":0.009989680985973942,"score_gpt":0.30116442590020437,"score_spread":0.29117474491423045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232213304","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[6.58005e-7,0.000065223336,0.0044219843,0.0000049850423,0.9716226,0.00018288988,0.013006475,0.000029028302,0.010666147],"genre_scores_gemma":[0.000013173142,0.00019344864,0.021850662,0.000004348577,0.97639936,0.0000052880737,0.00051693735,0.00034564032,0.00067111524],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9920261,0.000062272906,0.0016850367,0.0003431663,0.0053042863,0.0005791398],"domain_scores_gemma":[0.9849801,0.002366554,0.007919387,0.0008773573,0.0034509725,0.0004055988],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0021383623,0.0006438772,0.0016241309,0.0004123407,0.00030807065,0.0005646908,0.0019384276,0.0017720181,0.00015337457],"category_scores_gemma":[0.0069625364,0.00058682327,0.00024167722,0.00008466054,0.00030793756,0.00016161823,0.0001881503,0.0046362593,0.0014876672],"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":[0.0014637328,0.00011243227,2.903297e-7,0.00012495331,0.00040484127,0.00016609687,0.00010591909,0.000035014382,0.00013621515,0.0011402093,0.995117,0.0011932935],"study_design_scores_gemma":[0.002480394,0.0002930143,0.0000015751671,0.00014142536,0.00074963603,0.000007891251,0.000020901252,0.0000083674595,0.000024856625,0.0136355,0.98210984,0.0005266061],"about_ca_topic_score_codex":0.000010563475,"about_ca_topic_score_gemma":0.000019677862,"teacher_disagreement_score":0.017428678,"about_ca_system_score_codex":0.0006258529,"about_ca_system_score_gemma":0.004003877,"threshold_uncertainty_score":0.99965835},"labels":[],"label_agreement":null},{"id":"W4284990586","doi":"10.1080/02664763.2022.2097204","title":"A flexible test for early-stage studies with multiple endpoints","year":2022,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Behavioral and Psychological Studies","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; Institute of Aging; University of Kansas Medical Center; National Institutes of Health; National Center for Advancing Translational Sciences; University of Kansas","keywords":"Null hypothesis; Parametric statistics; Statistical hypothesis testing; Computer science; Statistics; Test (biology); Type I and type II errors; Null (SQL); Econometrics; Sample size determination; Mathematics; Machine learning; Data mining","score_opus":0.21459634131199407,"score_gpt":0.38375300150811786,"score_spread":0.1691566601961238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284990586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85196525,0.002285298,0.113194875,0.001009917,0.0036114766,0.0020591165,0.006636936,0.00013071435,0.019106412],"genre_scores_gemma":[0.9596238,0.000041418272,0.036019213,0.00040427674,0.00018629339,0.00019685233,0.000009942545,0.000028850793,0.0034893432],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987323,0.00003316112,0.00045510274,0.00018514584,0.00030499988,0.00028928154],"domain_scores_gemma":[0.9981019,0.0010233516,0.00047180813,0.00013700135,0.00018387043,0.00008206866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038772234,0.00016145808,0.00040456012,0.00007273717,0.00034875813,0.000017546245,0.00020983124,0.000033719993,0.0006387029],"category_scores_gemma":[0.00007695865,0.000111328605,0.00006160008,0.00015974374,0.00013002896,0.000022712375,0.00007518844,0.0003630452,0.00001672207],"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":[0.02154708,0.0067403684,0.115211345,0.00022260398,0.0029483011,0.0015567767,0.035930622,0.00077714975,0.002174966,0.11819257,0.5671868,0.12751147],"study_design_scores_gemma":[0.018722748,0.023053838,0.25550374,0.000046564233,0.00086895697,0.00035459394,0.054065287,0.00003209291,0.0006229099,0.038948137,0.6065523,0.0012288082],"about_ca_topic_score_codex":0.000009129054,"about_ca_topic_score_gemma":0.000011179076,"teacher_disagreement_score":0.1402924,"about_ca_system_score_codex":0.00006435546,"about_ca_system_score_gemma":0.000021495636,"threshold_uncertainty_score":0.6993349},"labels":[],"label_agreement":null},{"id":"W4307243917","doi":"10.1080/02664763.2022.2138838","title":"A two-stage latent factor regression method to model the common and unique effects of multiple highly correlated exposure variables","year":2022,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Air Quality and Health Impacts","field":"Environmental Science","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":"University of Saskatchewan; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Dalhousie University; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Multicollinearity; Variance inflation factor; Statistics; Latent variable; Econometrics; Regression analysis; Collinearity; Variance (accounting); Regression; Mathematics; Regression diagnostic; Factor analysis; Linear regression; Latent variable model; Estimator; Factor regression model; Principal component analysis; Proper linear model; Polynomial regression","score_opus":0.028183303826129203,"score_gpt":0.3158498331322785,"score_spread":0.2876665293061493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307243917","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":[0.3200418,0.00004389745,0.67843205,0.0004682016,0.00010877305,0.0004451423,0.0002812244,0.000007618744,0.0001712822],"genre_scores_gemma":[0.78549886,0.000025074005,0.21349114,0.0008690073,0.0000101862715,0.0000074646723,0.000003975594,0.000011189488,0.00008311192],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985251,0.00025243722,0.00046319666,0.00011143045,0.00046011302,0.00018772011],"domain_scores_gemma":[0.99806035,0.0010648759,0.00052345794,0.0001438026,0.000018534742,0.00018899288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009979579,0.00011403701,0.00028024,0.000039823884,0.0002612232,0.000013630464,0.0001941484,0.000041554977,0.00009190812],"category_scores_gemma":[0.000100488316,0.000075818854,0.00002388395,0.00014635167,0.000058012396,0.000045108824,0.00022081353,0.0004267403,0.000001694909],"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":[0.0014688536,0.00036500287,0.0047720536,0.00024794252,0.00006513879,0.00005859015,0.014420711,0.8850866,0.035805568,0.019330874,0.012557622,0.025821023],"study_design_scores_gemma":[0.005471063,0.0030084313,0.06357304,0.00017699903,0.00020590035,0.00007546152,0.0016493526,0.875343,0.013391192,0.029858755,0.0066927844,0.0005539884],"about_ca_topic_score_codex":0.00018274003,"about_ca_topic_score_gemma":0.000037081933,"teacher_disagreement_score":0.46545705,"about_ca_system_score_codex":0.0001540413,"about_ca_system_score_gemma":0.000050532748,"threshold_uncertainty_score":0.30918032},"labels":[],"label_agreement":null},{"id":"W4319072054","doi":"10.1080/02664763.2023.2172143","title":"Bayesian adaptive selection of basis functions for functional data representation","year":2023,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Functional data analysis; Basis (linear algebra); Computer science; Basis function; Bayesian probability; Representation (politics); Context (archaeology); Selection (genetic algorithm); Mathematics; Machine learning; Artificial intelligence","score_opus":0.2690950358091204,"score_gpt":0.41425535177611555,"score_spread":0.14516031596699513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319072054","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":[0.0008322163,0.0000033588763,0.9959489,0.000063574975,0.00033703295,0.0002043178,0.001746925,0.000019879088,0.0008437611],"genre_scores_gemma":[0.08881535,0.000016318372,0.91055775,0.00001997423,0.000265152,0.0000138947535,0.00012948782,0.000022077757,0.00016001161],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99851596,0.00005285189,0.00071529805,0.00016694536,0.00039217758,0.00015679229],"domain_scores_gemma":[0.99410146,0.004315176,0.00066539284,0.00021736477,0.0006241196,0.00007648502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009303807,0.000105906074,0.0003162134,0.00018905959,0.00010138626,0.000019701652,0.0001657909,0.000062052786,0.00017945832],"category_scores_gemma":[0.00284813,0.000094237206,0.000049043956,0.0004285659,0.000061639395,0.000083338666,0.000049729995,0.0001653325,0.0000061896603],"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":[0.00078835647,0.00015548588,0.00021164872,0.00015015014,0.0002544223,0.000003527807,0.0001955759,0.00061676744,0.002069515,0.7072476,0.22333829,0.064968646],"study_design_scores_gemma":[0.00081783417,0.00039466878,0.0035119173,0.000035094876,0.00032440023,0.000014448373,0.00079884956,0.10625645,0.0010654649,0.885662,0.0009887877,0.00013008079],"about_ca_topic_score_codex":0.000004198605,"about_ca_topic_score_gemma":0.000009110917,"teacher_disagreement_score":0.22234951,"about_ca_system_score_codex":0.000041311836,"about_ca_system_score_gemma":0.00015080353,"threshold_uncertainty_score":0.38428816},"labels":[],"label_agreement":null},{"id":"W4383533098","doi":"10.1080/02664763.2023.2232127","title":"Family of bivariate distributions on the unit square: theoretical properties and applications","year":2023,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Advanced Statistical Methods and Models","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":"McMaster University","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação de Apoio à Pesquisa do Distrito Federal; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Bivariate analysis; Quantile; Mathematics; Marginal distribution; Statistics; Preprint; Monte Carlo method; Bivariate data; Independence (probability theory); Unit square; Unit (ring theory); Applied mathematics; Combinatorics; Random variable; Computer science","score_opus":0.14446447072446472,"score_gpt":0.3823033967727893,"score_spread":0.23783892604832457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383533098","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":[0.004924862,0.00001915885,0.992236,0.00031948442,0.000038954713,0.00029258052,0.0007122676,0.000017148493,0.001439508],"genre_scores_gemma":[0.62256587,0.00014797153,0.37701797,0.00007303477,0.00007966647,0.00004142945,0.000008803536,0.000023741222,0.000041472573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877846,0.00007579958,0.0005504148,0.000104081555,0.000317207,0.00017405055],"domain_scores_gemma":[0.99553806,0.003603507,0.00032579122,0.00019795491,0.00024567335,0.00008900466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007849693,0.00012076913,0.0002943581,0.00007101097,0.00014970174,0.000023012153,0.0001591149,0.00004959005,0.000020796666],"category_scores_gemma":[0.0010026934,0.00007069566,0.00003713609,0.00025351465,0.00044437006,0.000022270073,0.00005292709,0.0002698486,0.000006110935],"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":[0.00007960946,0.000071778995,0.0000027840492,0.00007315532,0.000039369203,0.0000035872815,0.0001670801,0.00008695622,0.0013678164,0.98846114,0.0011502579,0.008496489],"study_design_scores_gemma":[0.0002420627,0.00013212189,0.00019583729,0.00004419713,0.00009168888,0.000005372905,0.00046523495,0.0021414568,0.00065504713,0.9947569,0.0011887164,0.0000813895],"about_ca_topic_score_codex":6.834227e-7,"about_ca_topic_score_gemma":3.6330576e-7,"teacher_disagreement_score":0.61764103,"about_ca_system_score_codex":0.000017069262,"about_ca_system_score_gemma":0.00005976784,"threshold_uncertainty_score":0.28828856},"labels":[],"label_agreement":null},{"id":"W4386742233","doi":"10.1080/02664763.2023.2258301","title":"The spike-and-slab lasso and scalable algorithm to accommodate multinomial outcomes in variable selection problems","year":2023,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":1,"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 Institutes of Health Research; National Institutes of Health; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Novartis Pharmaceuticals Corporation; University of Southern California; Biogen; Eli Lilly and Company; Bristol-Myers Squibb; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Meso Scale Diagnostics; National Institute on Aging; Alzheimer's Association","keywords":"Categorical variable; Prior probability; Multinomial distribution; Lasso (programming language); Computer science; Bayesian probability; Model selection; Algorithm; Multinomial probit; Variable (mathematics); Generalization; Econometrics; Mathematical optimization; Mathematics; Multinomial logistic regression; Machine learning; Artificial intelligence","score_opus":0.030928941227488013,"score_gpt":0.3379198239562676,"score_spread":0.30699088272877956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386742233","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":[0.0057669426,0.000008575506,0.992947,0.00025112292,0.00016469571,0.0002715334,0.00013492469,0.000018814817,0.00043639255],"genre_scores_gemma":[0.0086793015,0.00006511741,0.990983,0.000057969562,0.00006569009,0.00001631832,0.0000018168153,0.000020608071,0.000110175235],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985963,0.00007172455,0.0006160231,0.00014502417,0.00027083297,0.00030008084],"domain_scores_gemma":[0.99586797,0.0034995254,0.0002645228,0.00010079046,0.00013569817,0.0001315124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015362526,0.00014471766,0.0003915976,0.00013076003,0.00016733624,0.00014461647,0.00013197944,0.000068189845,0.000014221221],"category_scores_gemma":[0.0011961705,0.00009736004,0.000017200811,0.00034229274,0.00006348984,0.00005235601,0.000091109374,0.00032285013,0.0000075148796],"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":[0.000069430636,0.000061719154,0.0011318651,0.00007825746,0.000047322625,0.000013487721,0.00032916517,0.0000426771,0.0005108908,0.8145903,0.0035215842,0.17960331],"study_design_scores_gemma":[0.0007489448,0.00015940565,0.007846428,0.000046376426,0.000045298882,0.000020767602,0.00015830362,0.020006837,0.00013743347,0.96912533,0.0015653013,0.0001395968],"about_ca_topic_score_codex":0.000021858425,"about_ca_topic_score_gemma":0.000041646494,"teacher_disagreement_score":0.1794637,"about_ca_system_score_codex":0.000050353763,"about_ca_system_score_gemma":0.00006670174,"threshold_uncertainty_score":0.39702272},"labels":[],"label_agreement":null},{"id":"W4386996496","doi":"10.1080/02664763.2023.2260572","title":"Estimating the prevalence of osteoporosis using ranked-based methodologies and Manitoba's population-based BMD registry","year":2023,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Bone health and osteoporosis research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Medicine; Osteoporosis; Statistics; Population; Demography; Environmental health; Mathematics; Internal medicine","score_opus":0.10055409936087145,"score_gpt":0.400756879025482,"score_spread":0.30020277966461056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386996496","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9278527,0.00020755552,0.07051366,0.00061556813,0.00016251637,0.00042651824,0.00014680598,0.000022392918,0.000052286538],"genre_scores_gemma":[0.5895952,0.000036263664,0.41010332,0.00014330137,0.00007941255,0.0000041451462,0.000011438999,0.000015070372,0.00001182776],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981089,0.0001221901,0.0007422884,0.00013247483,0.00064197107,0.00025217273],"domain_scores_gemma":[0.99610776,0.0024438377,0.0007359279,0.0002315165,0.00034050134,0.00014047927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020305559,0.00012228634,0.00040737094,0.00018871961,0.0001695076,0.000026164034,0.0001289825,0.000082398576,0.000022131415],"category_scores_gemma":[0.001657996,0.00008412786,0.00005321616,0.0003383919,0.00016542054,0.000031086416,0.00003194467,0.00037556788,0.0000012953473],"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":[0.011533403,0.00054982235,0.46399593,0.059841488,0.0006024509,0.0005634409,0.0029859876,0.1818505,0.06439735,0.003145654,0.009252142,0.20128183],"study_design_scores_gemma":[0.0036577797,0.0007362403,0.7085412,0.0009059089,0.00060162257,0.00008999082,0.0016055729,0.27530152,0.004121099,0.004160832,0.000068905174,0.00020930155],"about_ca_topic_score_codex":0.00012897971,"about_ca_topic_score_gemma":0.000017249746,"teacher_disagreement_score":0.33958966,"about_ca_system_score_codex":0.0000811331,"about_ca_system_score_gemma":0.00048589823,"threshold_uncertainty_score":0.34306347},"labels":[],"label_agreement":null},{"id":"W4387972453","doi":"10.1080/02664763.2023.2272223","title":"Improving the Hosmer-Lemeshow goodness-of-fit test in large models with replicated Bernoulli trials","year":2023,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":33,"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; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Goodness of fit; Covariate; Logistic regression; Statistics; Type I and type II errors; Bernoulli trial; Bernoulli's principle; Mathematics; Test (biology); Sample size determination; Computer science; Econometrics; Biology","score_opus":0.1822081850794053,"score_gpt":0.27385853381424047,"score_spread":0.09165034873483516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387972453","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79612404,0.00028202438,0.19707942,0.0004187593,0.0002316777,0.0005682041,0.0016615074,0.00001532829,0.003619008],"genre_scores_gemma":[0.99210685,0.0003222577,0.0072421054,0.00006802294,0.000064062755,0.000013730819,0.000027547398,0.000023630204,0.00013180474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99819195,0.000016985334,0.0013559927,0.00016678167,0.000068824935,0.0001994502],"domain_scores_gemma":[0.99741054,0.0005165433,0.0017916224,0.0002115994,0.000023574736,0.00004612791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032613212,0.000113910886,0.00056879356,0.0001799789,0.000056879326,0.00003100832,0.00019871356,0.000060231,0.000090945454],"category_scores_gemma":[0.00022755595,0.000089900845,0.00005882582,0.00022869972,0.000051749954,0.00011594975,0.000043495744,0.00019643312,0.00005339211],"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":[0.00041671278,0.0006091524,0.16303523,0.00015994819,0.00035066143,0.000028734588,0.0031727029,0.09276188,0.0010826093,0.7207752,0.005979276,0.0116279],"study_design_scores_gemma":[0.008581895,0.0007842275,0.3180537,0.00008957295,0.00015931082,0.000022872935,0.0033638848,0.29589435,0.0011192404,0.3683899,0.0028030644,0.0007379689],"about_ca_topic_score_codex":0.000036352892,"about_ca_topic_score_gemma":0.00002244375,"teacher_disagreement_score":0.35238528,"about_ca_system_score_codex":0.000107397034,"about_ca_system_score_gemma":0.00003580225,"threshold_uncertainty_score":0.36660498},"labels":[],"label_agreement":null},{"id":"W4388421561","doi":"10.1080/02664763.2023.2277669","title":"A computationally efficient sequential regression imputation algorithm for multilevel data","year":2023,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","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 Waterloo","funders":"","keywords":"Imputation (statistics); Computer science; Missing data; Computation; Singleton; Algorithm; Regression; Data mining; Statistics; Machine learning; Mathematics","score_opus":0.13883124269288116,"score_gpt":0.43675601875730574,"score_spread":0.2979247760644246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388421561","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":[0.0004042864,0.0000059454287,0.9955241,0.000063984204,0.00041517557,0.00030803547,0.0031504189,0.000034818804,0.000093239934],"genre_scores_gemma":[0.004790681,0.0000091868005,0.9944917,0.00004135823,0.00029846738,0.000009110208,0.00030353176,0.000031100404,0.00002488834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980636,0.000059012833,0.00082927017,0.00021856216,0.0005823939,0.00024714385],"domain_scores_gemma":[0.99388176,0.004523717,0.0007220452,0.00023527881,0.00051230687,0.00012490533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014060655,0.00016046413,0.0003743865,0.00017575544,0.00013525697,0.00006828343,0.00036083374,0.00007692549,0.00003326651],"category_scores_gemma":[0.0015720646,0.00012700526,0.0000486423,0.00020693452,0.00006862834,0.000051362407,0.000120616554,0.0001936301,0.000013435307],"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":[0.00009161524,0.00010199773,0.0000013709281,0.00011634793,0.00006386835,0.000035015368,0.00029811737,0.00056499784,0.00035497514,0.38252053,0.025500927,0.5903503],"study_design_scores_gemma":[0.00068575615,0.0000720767,0.0001637904,0.000045996585,0.000072675764,0.000014140457,0.000088189634,0.50138247,0.0000859217,0.49700913,0.00028905898,0.00009082249],"about_ca_topic_score_codex":0.000001149729,"about_ca_topic_score_gemma":6.609689e-7,"teacher_disagreement_score":0.59025943,"about_ca_system_score_codex":0.000054551754,"about_ca_system_score_gemma":0.00020755494,"threshold_uncertainty_score":0.51791245},"labels":[],"label_agreement":null},{"id":"W4391681347","doi":"10.1080/02664763.2024.2313459","title":"Estimating effects of time-varying exposures on mortality risk","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Health Systems, Economic Evaluations, Quality of Life","field":"Economics, Econometrics and Finance","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":"St. Paul's Hospital; Simon Fraser University","funders":"National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Statistics; Econometrics; Mathematics; Environmental science","score_opus":0.1425939188732576,"score_gpt":0.4118796880386475,"score_spread":0.26928576916538993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391681347","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":[0.32079598,0.0023491941,0.6649561,0.0007274585,0.0024662993,0.0005720997,0.0012508656,0.00004374755,0.006838281],"genre_scores_gemma":[0.7918858,0.000105848034,0.20646186,0.0006715498,0.0007121825,0.000012424154,0.000014350944,0.000046620346,0.000089365545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953202,0.00011643078,0.003943135,0.0002365089,0.00016253251,0.00022117709],"domain_scores_gemma":[0.99230087,0.0037963325,0.0034566023,0.000243802,0.000072756775,0.0001296622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009080761,0.00015854255,0.00094599754,0.00032458777,0.000092251175,0.000079636135,0.0001921498,0.0000911851,0.00013903467],"category_scores_gemma":[0.0035502,0.00017742165,0.00011113257,0.00014239359,0.000057092206,0.00014591885,0.000025328158,0.0003559587,0.0004238965],"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":[0.00010914434,0.00033980538,0.010921099,0.0073235086,0.0011847148,0.000071057024,0.006744592,0.035965916,0.00020686409,0.8433161,0.08766661,0.0061505926],"study_design_scores_gemma":[0.0018656518,0.0008856064,0.026580669,0.0015142664,0.00019491975,0.000027630413,0.00028787303,0.27744833,0.0005762555,0.6850926,0.0048199515,0.000706219],"about_ca_topic_score_codex":0.000064215455,"about_ca_topic_score_gemma":0.0000030252877,"teacher_disagreement_score":0.47108984,"about_ca_system_score_codex":0.0002370846,"about_ca_system_score_gemma":0.00013971061,"threshold_uncertainty_score":0.7235045},"labels":[],"label_agreement":null},{"id":"W4397013935","doi":"10.1080/02664763.2024.2355551","title":"Z-residual diagnostic tool for assessing covariate functional form in shared frailty models","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Inference","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":"Dalhousie University; University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Residual; Computer science; Data mining; Statistics; Econometrics; Mathematics; Machine learning; Algorithm","score_opus":0.20880257825316087,"score_gpt":0.404266068349312,"score_spread":0.19546349009615113,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397013935","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":[0.0049916245,0.0000621468,0.99220896,0.000089945344,0.00054425333,0.00027416798,0.0008552152,0.000021926375,0.0009517431],"genre_scores_gemma":[0.17812026,0.000022619872,0.8213496,0.00007646307,0.00030312708,0.000031127238,0.000020412268,0.000034139273,0.000042215597],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99808276,0.00004187919,0.0009633383,0.00018883504,0.00043033043,0.0002928532],"domain_scores_gemma":[0.98210883,0.01715495,0.00027033925,0.0001184959,0.0002555653,0.00009182398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012421751,0.00018547788,0.00044461727,0.00017791569,0.00007209553,0.000246221,0.00014552468,0.00010888792,0.00018633119],"category_scores_gemma":[0.0045227986,0.00015296231,0.00006937767,0.00017169738,0.000054174732,0.00020736508,0.00003762643,0.00041762282,0.0000058628466],"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":[0.00011612222,0.000093455004,0.000019800884,0.00035848058,0.000068364316,0.000069250505,0.0003260867,0.0007386047,0.0002564595,0.9504952,0.013415378,0.034042805],"study_design_scores_gemma":[0.00066666474,0.000104386185,0.0010843186,0.00022704146,0.00012802106,0.000025697025,0.00009424981,0.07660409,0.00009997326,0.9203956,0.00039876142,0.0001711616],"about_ca_topic_score_codex":0.0000027183448,"about_ca_topic_score_gemma":0.0000050379817,"teacher_disagreement_score":0.17312862,"about_ca_system_score_codex":0.00013570553,"about_ca_system_score_gemma":0.00034314854,"threshold_uncertainty_score":0.6237622},"labels":[],"label_agreement":null},{"id":"W4398174693","doi":"10.1080/02664763.2024.2352759","title":"Iterative smoothing for change-point regression function estimation","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Fire effects on ecosystems","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Canadian Statistical Sciences Institute; Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Institute for Catastrophic Loss Reduction","keywords":"Smoothing; Outlier; Computer science; Robustness (evolution); Change detection; Data mining; Algorithm; Artificial intelligence; Computer vision","score_opus":0.015737665287759765,"score_gpt":0.27174935554534324,"score_spread":0.25601169025758347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398174693","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":[0.012432184,0.000081956925,0.98474,0.0001657188,0.0011731507,0.00039891337,0.000053465257,0.000024540626,0.0009300469],"genre_scores_gemma":[0.88350725,0.00001044254,0.11591728,0.00011275393,0.00030422775,0.000031018135,0.000015276373,0.00002226885,0.000079485784],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991096,0.000022068101,0.00032706582,0.00012420554,0.00028998562,0.00012704797],"domain_scores_gemma":[0.99929667,0.00031975913,0.00022828726,0.00007149647,0.000022605716,0.00006116557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058383564,0.00010288472,0.00015237322,0.0000637959,0.00008169875,0.000094014,0.00007382703,0.00004950883,0.00014757442],"category_scores_gemma":[0.00007145623,0.00007692258,0.00003871704,0.000113116876,0.000027685126,0.0002859138,0.000024064835,0.00015550976,0.00008128787],"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":[0.00056791125,0.00007829506,0.00008223057,0.00046044524,0.0000783001,0.000055018398,0.0057919184,0.004376226,0.017471876,0.015227543,0.08246258,0.87334764],"study_design_scores_gemma":[0.00063810515,0.0009784066,0.0016713926,0.0004887221,0.0001380429,0.000060993607,0.00021539662,0.9269551,0.0025944945,0.038026802,0.027986031,0.0002465101],"about_ca_topic_score_codex":0.0000080984555,"about_ca_topic_score_gemma":0.000009306088,"teacher_disagreement_score":0.9225789,"about_ca_system_score_codex":0.00023578948,"about_ca_system_score_gemma":0.000013035297,"threshold_uncertainty_score":0.3136812},"labels":[],"label_agreement":null},{"id":"W4399243542","doi":"10.1080/02664763.2024.2360590","title":"Bayesian modeling framework for optimizing pre-hospital stroke triage decisions","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Acute Ischemic Stroke Management","field":"Medicine","cited_by":2,"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":"National Institute of Neurological Disorders and Stroke; National Institutes of Health","keywords":"Triage; Bayesian probability; Stroke (engine); Computer science; Emergency medicine; Medicine; Artificial intelligence","score_opus":0.021925721050042285,"score_gpt":0.31793197808769735,"score_spread":0.29600625703765504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399243542","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":[0.00378159,0.00037492768,0.99129397,0.0005300218,0.00082085683,0.0005520687,0.00023720661,0.000037637026,0.002371714],"genre_scores_gemma":[0.3201503,0.00016061506,0.67864096,0.00013520714,0.000633362,0.000014225647,0.000015697145,0.000044328655,0.00020531786],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981974,0.000007248194,0.0007813188,0.00020752278,0.00052188843,0.00028463683],"domain_scores_gemma":[0.99819076,0.0009798456,0.00021691834,0.00022023782,0.00018883949,0.00020341176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004607325,0.00018725263,0.00045374676,0.00024178613,0.00007435149,0.000101420745,0.00016529801,0.00011866552,0.000064934364],"category_scores_gemma":[0.00060489296,0.00015527151,0.00017523285,0.00014620501,0.000031545187,0.000065594126,0.000060742612,0.00058135646,0.0000072689495],"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":[0.0043410156,0.00071932125,0.000053041458,0.0011398828,0.0036387902,0.0015117188,0.005132332,0.078274526,0.004346857,0.3058631,0.36032516,0.23465426],"study_design_scores_gemma":[0.0028651974,0.0011349655,0.00001951838,0.0012015654,0.0018305106,0.00009929039,0.0021116303,0.9141578,0.0009448715,0.0509327,0.024350706,0.0003512111],"about_ca_topic_score_codex":7.1183166e-7,"about_ca_topic_score_gemma":2.0125597e-7,"teacher_disagreement_score":0.8358833,"about_ca_system_score_codex":0.00016770684,"about_ca_system_score_gemma":0.00017768434,"threshold_uncertainty_score":0.63317883},"labels":[],"label_agreement":null},{"id":"W4399774164","doi":"10.1080/02664763.2024.2351467","title":"Identifying waves of COVID-19 mortality using skew normal curves","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"COVID-19 epidemiological studies","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":true,"ca_institutions":"Centre for Global Health Research; St. Michael's Hospital; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Skew; Coronavirus disease 2019 (COVID-19); Demography; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Econometrics; Statistics; Geography; Mathematics; Medicine; Computer science; Telecommunications; Internal medicine; Outbreak; Sociology; Virology","score_opus":0.41372363974161586,"score_gpt":0.5089745621759725,"score_spread":0.09525092243435662,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399774164","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":[0.047810998,0.002344604,0.948001,0.00041211044,0.00037665575,0.00020411357,0.00029566634,0.000042995613,0.0005118123],"genre_scores_gemma":[0.5841999,0.0018974615,0.41240296,0.001054244,0.0003420107,0.0000044169064,0.000006656284,0.000041629544,0.000050728864],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.997384,0.0001207504,0.0014246175,0.00019026811,0.0006084303,0.00027192946],"domain_scores_gemma":[0.9923765,0.006208659,0.0008319228,0.00019373407,0.00019122731,0.00019793684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027627987,0.00020505945,0.00079615327,0.00013842715,0.00011883189,0.00004378642,0.00025467033,0.00011391315,0.00017258518],"category_scores_gemma":[0.006613872,0.00015537582,0.00016837522,0.0002641622,0.00021049469,0.00009434931,0.00015800363,0.0005438929,0.000004553807],"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":[0.00017188657,0.00030552162,0.0034414255,0.022673003,0.001530992,0.0006185288,0.0030818367,0.0013395456,0.0038828438,0.8731995,0.08646879,0.0032861154],"study_design_scores_gemma":[0.00034850894,0.000100691075,0.0021648384,0.00065824593,0.0007430306,0.00006019471,0.00046201903,0.0031327761,0.00040930667,0.9881847,0.0034833413,0.00025237433],"about_ca_topic_score_codex":0.00005109028,"about_ca_topic_score_gemma":0.000026193979,"teacher_disagreement_score":0.5363889,"about_ca_system_score_codex":0.0002430332,"about_ca_system_score_gemma":0.00035866335,"threshold_uncertainty_score":0.79179007},"labels":[],"label_agreement":null},{"id":"W4401219420","doi":"10.1080/02664763.2024.2383286","title":"Mixtures of logistic normal multinomial regression models for microbiome data","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","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":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Microbiome; Cluster analysis; Logistic regression; Computer science; Multinomial logistic regression; Mixture model; Covariate; Regression; Statistics; Data mining; Artificial intelligence; Biology; Machine learning; Mathematics; Bioinformatics","score_opus":0.045773993847910026,"score_gpt":0.3420589211448471,"score_spread":0.29628492729693706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401219420","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":[0.051864445,0.0021569347,0.9391988,0.00007926282,0.0007395343,0.00027549747,0.0054286146,0.0000055872147,0.00025135375],"genre_scores_gemma":[0.8482587,0.0003446064,0.15008475,0.000060979804,0.00044834183,0.0000015802185,0.0006997763,0.000023066224,0.00007820903],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99906075,0.000014055476,0.00047540033,0.00018322392,0.00009365509,0.00017290602],"domain_scores_gemma":[0.9992106,0.00006699175,0.00025477697,0.00025351104,0.00014526944,0.00006883395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032341265,0.00011883442,0.00023337467,0.00007301827,0.000041651234,0.000024753559,0.00031092222,0.00012030884,0.000008330533],"category_scores_gemma":[0.000049420043,0.0000925601,0.00005312006,0.000046732486,0.000073678915,0.000005620513,0.00011139265,0.00013005978,0.0000013532555],"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":[0.0005405336,0.00006394998,0.000004915204,0.00042508516,0.00008676581,0.000009436071,0.000092622686,0.00051618397,0.93211746,0.0025370305,0.05824362,0.0053623943],"study_design_scores_gemma":[0.007145135,0.0032570034,0.00045701116,0.0008203789,0.0009812256,0.00047086165,0.0005995174,0.049357884,0.7134497,0.020348212,0.20190877,0.0012042809],"about_ca_topic_score_codex":0.00000430141,"about_ca_topic_score_gemma":0.0000090007425,"teacher_disagreement_score":0.7963942,"about_ca_system_score_codex":0.00001533821,"about_ca_system_score_gemma":0.00028616487,"threshold_uncertainty_score":0.37744913},"labels":[],"label_agreement":null},{"id":"W4402456274","doi":"10.1080/02664763.2024.2401470","title":"Bayesian inference for Laplace distribution based on complete and censored samples with illustrations","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Distribution Estimation and Applications","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":"McMaster University","funders":"Young Scientists Fund; Government of Jiangsu Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Inference; Bayesian probability; Bayesian inference; Laplace distribution; Econometrics; Statistics; Laplace transform; Mathematics; Statistical inference; Laplace's method; Distribution (mathematics); Bayesian linear regression; Computer science; Applied mathematics; Artificial intelligence; Exponential distribution","score_opus":0.06054244856844389,"score_gpt":0.3517124401438856,"score_spread":0.2911699915754417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402456274","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":[0.00026220604,0.0000076250008,0.9866517,0.0006507195,0.00004740673,0.00031255427,0.011663269,0.00003559778,0.0003689306],"genre_scores_gemma":[0.6182199,0.000006230322,0.38109735,0.00006625662,0.000045482433,0.00003027148,0.00049758516,0.000013658347,0.000023249491],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989954,0.000018380459,0.0004307902,0.00014472478,0.00026345803,0.00014719668],"domain_scores_gemma":[0.9963462,0.002932926,0.00019494398,0.00011483137,0.00028591295,0.00012523093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017808238,0.00013669087,0.000216745,0.00006532627,0.00015603456,0.0001308111,0.000075285076,0.00004915228,0.000062241685],"category_scores_gemma":[0.0005493298,0.000106648535,0.000030698076,0.00016774931,0.0001329254,0.000046543937,0.000006687748,0.00016965173,0.0000041655344],"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":[0.00011655297,0.00007721038,0.0000061192504,0.00016012692,0.000028279817,0.0000037580523,0.000054282482,0.0006503817,0.000098830744,0.9807187,0.014861458,0.003224308],"study_design_scores_gemma":[0.0009628528,0.00039700235,0.0011214409,0.00017757583,0.00022697543,0.000019572515,0.00015795637,0.4162755,0.00015447385,0.5663684,0.013921236,0.0002170066],"about_ca_topic_score_codex":9.94793e-7,"about_ca_topic_score_gemma":0.0000064352394,"teacher_disagreement_score":0.6179577,"about_ca_system_score_codex":0.000071246344,"about_ca_system_score_gemma":0.00015254834,"threshold_uncertainty_score":0.4349001},"labels":[],"label_agreement":null},{"id":"W4403764486","doi":"10.1080/02664763.2024.2418473","title":"Evaluating the median <i>p</i> -value method for assessing the statistical significance of tests when using multiple imputation","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Clinical Evaluative Sciences; Sunnybrook Hospital; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Statistics; Mathematics; Wilcoxon signed-rank test; Test statistic; Statistical significance; Statistic; Statistical hypothesis testing; Logistic regression; Student's t-test; p-value; F-test; Type I and type II errors; Pearson's chi-squared test; Linear regression; Pooling; Nominal level; Imputation (statistics); Missing data; Mann–Whitney U test; Computer science; Artificial intelligence","score_opus":0.15242597773040908,"score_gpt":0.5050042235663473,"score_spread":0.3525782458359382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403764486","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":[0.0008742948,0.000074961186,0.99691683,0.00030979846,0.0004594193,0.0006064738,0.0006199327,0.000015437221,0.00012283467],"genre_scores_gemma":[0.07756226,0.0000065572253,0.9219395,0.0000900611,0.00032083792,0.00002329032,0.0000064347614,0.000045012777,0.000006063278],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969193,0.0004733445,0.001287121,0.0002207804,0.0007920646,0.00030743884],"domain_scores_gemma":[0.9383285,0.060011867,0.00081761,0.00022390243,0.00052370125,0.000094416],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0061154217,0.00021705283,0.0005150457,0.0000906363,0.00023939845,0.0002412564,0.00034097405,0.000085745625,0.000037792735],"category_scores_gemma":[0.010865469,0.00012241189,0.00009774875,0.00023682628,0.00024044704,0.00009955942,0.000047951435,0.00049356604,0.0000010564621],"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":[0.0000729252,0.000044215547,0.00001347288,0.000466994,0.00010897072,0.0000107467995,0.0013301863,0.0007686965,0.009293893,0.71250886,0.0013186283,0.27406242],"study_design_scores_gemma":[0.00022286743,0.00012778798,0.00007048162,0.00012442262,0.00033980198,0.000027234204,0.0004021252,0.43345448,0.00065428944,0.56441927,0.0000712,0.00008601364],"about_ca_topic_score_codex":0.000018711306,"about_ca_topic_score_gemma":0.0000061516134,"teacher_disagreement_score":0.4326858,"about_ca_system_score_codex":0.00010457248,"about_ca_system_score_gemma":0.00059526507,"threshold_uncertainty_score":0.99746644},"labels":[],"label_agreement":null},{"id":"W4404762088","doi":"10.1080/02664763.2024.2433567","title":"Tests of covariate effects under finite Gaussian mixture regression models","year":2024,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Bat Biology and Ecology Studies","field":"Agricultural and Biological Sciences","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":"University of British Columbia; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Covariate; Statistics; Regression; Cluster analysis; Regression analysis; Population; Statistical hypothesis testing; Mixture model; Type I and type II errors; Econometrics; Statistical power; Mathematics; Computer science; Medicine","score_opus":0.023407624683698114,"score_gpt":0.2588780555190716,"score_spread":0.2354704308353735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404762088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9534415,0.0051678307,0.026562892,0.0042500696,0.0026811166,0.00045018826,0.00061705045,0.00007558274,0.0067537827],"genre_scores_gemma":[0.99515253,0.00033438826,0.0040337667,0.00018422931,0.00018129869,0.0000020138277,0.000013735342,0.0000010697323,0.000096935684],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992756,0.000037386948,0.000303603,0.0001108012,0.00011840854,0.00015420209],"domain_scores_gemma":[0.99836326,0.0012900252,0.00019229595,0.000027280128,0.00007472107,0.00005244215],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024971258,0.00011032413,0.00027277545,0.00002082208,0.00009464205,0.000016052065,0.00012338268,0.00014517765,0.000055462027],"category_scores_gemma":[0.000052044885,0.0000359723,0.00005489001,0.00014558864,0.00010629011,0.00004455741,0.00004044837,0.0002550622,0.000008954809],"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":[0.0010559743,0.00048599453,0.0014833938,0.0005239168,0.0010762458,0.00048526822,0.0014117243,0.0024279335,0.34328535,0.3849481,0.0737402,0.18907592],"study_design_scores_gemma":[0.000842805,0.0023466733,0.15015273,0.0005999582,0.00046527124,0.00011794376,0.0006946714,0.0035173353,0.0071328664,0.8237466,0.009851744,0.0005313924],"about_ca_topic_score_codex":0.0000037088937,"about_ca_topic_score_gemma":0.000050914863,"teacher_disagreement_score":0.43879852,"about_ca_system_score_codex":0.000015248976,"about_ca_system_score_gemma":0.000017806615,"threshold_uncertainty_score":0.14669079},"labels":[],"label_agreement":null},{"id":"W4406887934","doi":"10.1080/02664763.2025.2457011","title":"Penalized functional regression using R package PFLR","year":2025,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Inference","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":"York University; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Discovery Eye Foundation","keywords":"R package; Statistics; Regression; Regression analysis; Computer science; Mathematics; Econometrics","score_opus":0.1246479271484594,"score_gpt":0.40539007199199856,"score_spread":0.28074214484353915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406887934","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":[0.0071403706,0.000040333394,0.98309636,0.000056118293,0.0005092729,0.00009471714,0.00007728159,0.0000113964725,0.008974144],"genre_scores_gemma":[0.060309984,0.000022136526,0.9390487,0.00016593799,0.0001414448,0.0000018240462,0.000003010015,0.000015566538,0.0002914115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99841267,0.00007862825,0.0007649649,0.00012518068,0.00042434165,0.0001942123],"domain_scores_gemma":[0.9964854,0.002312169,0.0005504582,0.00017152997,0.00037945405,0.00010095914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007269603,0.00015695415,0.00043955012,0.00015432277,0.00012145047,0.00004963412,0.00015277317,0.00008528403,0.0004971021],"category_scores_gemma":[0.0018251836,0.000115276016,0.00006642108,0.0002054763,0.000088286055,0.0000377654,0.000052839307,0.00034811156,0.0000062473773],"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":[0.00030388648,0.000104093495,0.00006489171,0.00012469658,0.00007930649,0.00003376063,0.00008313479,0.00002780167,0.0057900976,0.93997526,0.035421204,0.017991863],"study_design_scores_gemma":[0.00093566586,0.000059872575,0.0005275391,0.00018444985,0.00017785102,0.000025194953,0.00014869789,0.002408704,0.0018997947,0.9915677,0.0019414647,0.00012307306],"about_ca_topic_score_codex":0.0000022723827,"about_ca_topic_score_gemma":0.0000010350697,"teacher_disagreement_score":0.053169616,"about_ca_system_score_codex":0.00009136959,"about_ca_system_score_gemma":0.00023978298,"threshold_uncertainty_score":0.5442919},"labels":[],"label_agreement":null},{"id":"W4408655878","doi":"10.1080/02664763.2025.2481458","title":"Zero-inflated Poisson mixed model for longitudinal count data with informative dropouts","year":2025,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","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":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Count data; Zero-inflated model; Zero (linguistics); Statistics; Poisson distribution; Mathematics; Poisson regression; Overdispersion; Longitudinal data; Mixed model; Quasi-likelihood; Econometrics; Computer science; Medicine; Data mining; Population","score_opus":0.0772638870620557,"score_gpt":0.3879022313273999,"score_spread":0.3106383442653442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408655878","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":[0.00046687972,0.000012847226,0.9953356,0.00010147324,0.00014019423,0.00037827427,0.001886569,0.00001854054,0.0016596555],"genre_scores_gemma":[0.06670809,0.000017545855,0.9329397,0.000107021,0.0000408539,0.000010482241,0.000056542594,0.000021907788,0.00009784735],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9980441,0.00003158218,0.0009753865,0.00020133865,0.0004430499,0.0003045464],"domain_scores_gemma":[0.99527514,0.0025776767,0.0008150883,0.00044788222,0.0007571879,0.0001270528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009701449,0.00023833732,0.0006244467,0.00015539685,0.00013625383,0.00010339996,0.0005317104,0.00010026244,0.000020088177],"category_scores_gemma":[0.0012556502,0.0001727334,0.000037623955,0.0002162459,0.00013505481,0.00017077074,0.00011544166,0.00035353377,0.000002545031],"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":[0.00089307834,0.00011167816,0.00003841573,0.00032567806,0.00025073037,0.000015605505,0.00039045524,0.00021635208,0.00005256267,0.94868845,0.034245476,0.014771512],"study_design_scores_gemma":[0.0013025688,0.00018392265,0.00016861915,0.00015106928,0.00033812606,0.000013868869,0.0001523927,0.2556623,0.0001715181,0.74133587,0.0003580687,0.00016168214],"about_ca_topic_score_codex":0.0000027836331,"about_ca_topic_score_gemma":0.0000147977735,"teacher_disagreement_score":0.25544596,"about_ca_system_score_codex":0.00010137231,"about_ca_system_score_gemma":0.00048227303,"threshold_uncertainty_score":0.70438635},"labels":[],"label_agreement":null},{"id":"W4411538707","doi":"10.1080/02664763.2025.2520337","title":"A gradient boosting decision tree based estimation method for the mixture cure model","year":2025,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Epoxy Resin Curing Processes","field":"Engineering","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":"Queen's University","funders":"National Social Science Fund of China; Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Decision tree; Boosting (machine learning); Computer science; Gradient boosting; Artificial intelligence; Machine learning; Decision tree model; Tree (set theory); Statistics; Pattern recognition (psychology); Mathematics; Econometrics; Random forest","score_opus":0.013072253230806498,"score_gpt":0.30235673940852925,"score_spread":0.28928448617772273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411538707","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":[0.00032643243,0.00035910707,0.9981922,0.00012790872,0.00024814197,0.00018992703,0.000052260897,0.000031546908,0.00047245965],"genre_scores_gemma":[0.102616884,0.000040288323,0.8971427,0.00008441051,0.00005240494,0.000014157312,0.00000429962,0.000021481002,0.000023396555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913025,0.000007187824,0.0004181297,0.000079681806,0.00021691358,0.00014785399],"domain_scores_gemma":[0.9974156,0.0020736041,0.00015899053,0.00012844114,0.00018349009,0.000039888168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045416717,0.00012574799,0.0001987727,0.000114602844,0.000110454814,0.00006153248,0.00019690416,0.00006389225,0.0000024871845],"category_scores_gemma":[0.00036691027,0.000090471876,0.000049529954,0.00016472554,0.000015681844,0.00004205302,0.000013655254,0.00024342583,5.789864e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007373575,0.000012621428,0.0000029598625,0.00022904687,0.000043541168,0.0000016250273,0.00011835934,0.8565199,0.0005138249,0.009039039,0.011558356,0.12188702],"study_design_scores_gemma":[0.0004904241,0.000022040607,0.000055811895,0.00012915065,0.00013859269,0.0000032590349,0.00003398337,0.9295783,0.0025004651,0.06557065,0.0013996988,0.00007760402],"about_ca_topic_score_codex":4.4802437e-7,"about_ca_topic_score_gemma":0.000006279063,"teacher_disagreement_score":0.12180942,"about_ca_system_score_codex":0.00007527008,"about_ca_system_score_gemma":0.000095892625,"threshold_uncertainty_score":0.36893362},"labels":[],"label_agreement":null},{"id":"W4411932830","doi":"10.1080/02664763.2025.2525880","title":"A constrained robust Markov regime-switching model for long-term risk evaluation","year":2025,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Term (time); Markov chain; Computer science; Mathematics; Econometrics; Statistics","score_opus":0.0506153612571772,"score_gpt":0.2849498678545155,"score_spread":0.2343345065973383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411932830","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":[0.05958083,0.0004197729,0.9363313,0.00008724489,0.0003231757,0.0003679807,0.00047822244,0.0000075427297,0.0024039503],"genre_scores_gemma":[0.77789897,0.0002129175,0.22156082,0.00007799598,0.000092519884,0.000014066771,0.000018883124,0.000014749486,0.000109071334],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983328,0.000011935119,0.0011383669,0.00021073734,0.00009011483,0.00021607037],"domain_scores_gemma":[0.998077,0.00025360656,0.0011416051,0.00017790096,0.00028964388,0.00006029496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022654617,0.00014162366,0.00046351182,0.0002745239,0.00017336277,0.00007581413,0.0001772435,0.00010865062,0.00002528243],"category_scores_gemma":[0.00064975565,0.00015875524,0.00011191958,0.00013892801,0.000033887194,0.00010563501,0.000025820318,0.0002860494,0.0000045965867],"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":[0.0006293385,0.0001599467,0.012499505,0.00019570364,0.0002097937,0.0000027915007,0.0009954668,0.23953848,0.00004298342,0.6363594,0.0029014703,0.106465116],"study_design_scores_gemma":[0.0011263916,0.00003359811,0.0038444235,0.000031406376,0.00007313706,0.0000010940375,0.00003054595,0.68417335,0.000008819456,0.31049064,0.000084854306,0.00010177181],"about_ca_topic_score_codex":0.000010079884,"about_ca_topic_score_gemma":0.000030535677,"teacher_disagreement_score":0.71831816,"about_ca_system_score_codex":0.00019873111,"about_ca_system_score_gemma":0.00023499414,"threshold_uncertainty_score":0.64738506},"labels":[],"label_agreement":null},{"id":"W4414911999","doi":"10.1080/02664763.2025.2567987","title":"Joint survival and longitudinal modelling for combined cohort data","year":2025,"lang":"en","type":"article","venue":"Journal of Applied Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Joint (building); Cohort; Longitudinal data; Survival analysis; Cohort study; Proportional hazards model","score_opus":0.25192330949239683,"score_gpt":0.4043214594719593,"score_spread":0.15239814997956247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414911999","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":[0.0024650404,0.00003596889,0.99432474,0.00009092845,0.00030127153,0.00024751516,0.0006023262,0.0000082552415,0.0019239695],"genre_scores_gemma":[0.06511023,0.00007013499,0.9346025,0.000037795046,0.000078113495,0.0000048095562,0.000016862425,0.000014233935,0.00006529863],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986014,0.000034454384,0.0007368911,0.00018783117,0.00025206126,0.00018735975],"domain_scores_gemma":[0.9955253,0.0033978543,0.00036505348,0.00029810355,0.00032000884,0.000093707335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015693789,0.00013844653,0.0005285771,0.00008579997,0.00009611099,0.00006468982,0.00025316974,0.000059807553,0.000020975855],"category_scores_gemma":[0.0015172076,0.00011501006,0.000027439499,0.00008690733,0.000089872316,0.0000428907,0.00012813596,0.00022229704,5.924706e-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":[0.00022312037,0.00007716284,0.00026764724,0.0002364178,0.00014884416,0.0000068612126,0.000035951438,0.000092743176,0.0000821755,0.9813827,0.009137098,0.008309227],"study_design_scores_gemma":[0.0008968124,0.00012291445,0.0008216446,0.00006771856,0.0003074878,0.0000054435545,0.000090385736,0.108808115,0.00010331476,0.88808465,0.0005806885,0.00011081055],"about_ca_topic_score_codex":0.0000034988418,"about_ca_topic_score_gemma":0.0000029581859,"teacher_disagreement_score":0.10871538,"about_ca_system_score_codex":0.000029545841,"about_ca_system_score_gemma":0.00012648256,"threshold_uncertainty_score":0.46899742},"labels":[],"label_agreement":null}]}