{"meta":{"query_hash":"d5798dda5751","filters":{"venue":"The Annals of Applied Statistics"},"cohort_total":71,"direct_labels_cover":0,"predictions_cover":71,"exported":71,"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/d5798dda5751","api":"https://metacan.xera.ac/api/v1/cohort?venue=The+Annals+of+Applied+Statistics"},"results":[{"id":"W1965857117","doi":"10.1214/08-aoas199","title":"$\\mathcal{G}$-SELC: Optimization by sequential elimination of level combinations using genetic algorithms and Gaussian processes","year":2009,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Georgia Research Foundation; Acadia University; University of Georgia; Pfizer; National Science Foundation","keywords":"Gaussian process; Set (abstract data type); Process (computing); Gaussian; Data set; Genetic algorithm","score_opus":0.10767218017510702,"score_gpt":0.36841160371865145,"score_spread":0.2607394235435444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965857117","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":[0.004325229,0.00009022461,0.9939224,0.0010159059,0.000030801384,0.00020988511,0.00021516894,0.000019343901,0.00017102211],"genre_scores_gemma":[0.4385985,0.00005603028,0.5611499,0.0001462485,0.00001105881,0.0000024688238,0.000027743117,0.000004898705,0.0000031207217],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989036,0.00006877038,0.0003518756,0.00019462523,0.00035035194,0.00013079846],"domain_scores_gemma":[0.9987714,0.0003112005,0.00031224272,0.00017802096,0.00037876068,0.00004833255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002811195,0.00011287372,0.00017339156,0.00007605503,0.00010462972,0.00006089291,0.00032729853,0.00003454248,0.0000024096043],"category_scores_gemma":[0.00011763966,0.00009995749,0.00001673602,0.00041242258,0.00010844651,0.00015097266,0.000073666546,0.00006381168,4.6439877e-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":[0.00002136303,0.00016598587,0.0000026640164,0.00008933841,0.000025105148,8.4513846e-7,0.0013687424,0.571112,0.0020387708,0.36411262,0.00030539228,0.060757183],"study_design_scores_gemma":[0.00020180037,0.000087071356,0.0012477742,0.000014043108,0.000017790864,0.0000029518508,0.000037994218,0.85846263,0.0082022,0.13161288,0.000014874921,0.00009795339],"about_ca_topic_score_codex":0.000009684961,"about_ca_topic_score_gemma":6.1092186e-7,"teacher_disagreement_score":0.43427327,"about_ca_system_score_codex":0.000009400029,"about_ca_system_score_gemma":0.00013127793,"threshold_uncertainty_score":0.4076148},"labels":[],"label_agreement":null},{"id":"W1970646576","doi":"10.1214/14-aoas727","title":"Effect of breastfeeding on gastrointestinal infection in infants: A targeted maximum likelihood approach for clustered longitudinal data","year":2014,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Breastfeeding; Confounding; Breastfeeding promotion; Context (archaeology); Estimation; Duration (music); Intervention (counseling); Random effects model; Breast feeding","score_opus":0.10728965630770694,"score_gpt":0.3946682202134613,"score_spread":0.2873785639057544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1970646576","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":[0.010134474,0.000004269722,0.9865514,0.000041872332,0.00004140917,0.00073299254,0.0011319848,0.000022046906,0.0013395671],"genre_scores_gemma":[0.3952544,0.0000049686814,0.60449475,0.00002530918,0.00005663879,0.00004296166,0.00009801546,0.000021736274,0.0000012468396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806327,0.00024223489,0.0006641105,0.00034397087,0.0003149966,0.0003714472],"domain_scores_gemma":[0.9909316,0.007686737,0.0004669139,0.00067435554,0.00016950464,0.00007091898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034841087,0.00023912232,0.00061253447,0.00012305641,0.000066809196,0.00002324948,0.0004361695,0.00006136534,0.000017307731],"category_scores_gemma":[0.005100156,0.00016881026,0.000047359244,0.00022663319,0.00017576784,0.000045469482,0.00016247538,0.00023340806,0.0000018288551],"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":[0.0037944806,0.0005378001,0.0020190259,0.0026853452,0.00009460497,0.0000016545665,0.00022614519,0.00010474704,0.0012812223,0.69399244,0.0029881834,0.29227436],"study_design_scores_gemma":[0.0015308409,0.00222639,0.011306307,0.00030663298,0.00012992689,0.00001241163,0.000022864395,0.10424931,0.0039977594,0.87597036,0.000016991016,0.00023021456],"about_ca_topic_score_codex":0.00005714077,"about_ca_topic_score_gemma":0.0000146361635,"teacher_disagreement_score":0.38511992,"about_ca_system_score_codex":0.000012122943,"about_ca_system_score_gemma":0.000033914595,"threshold_uncertainty_score":0.6883883},"labels":[],"label_agreement":null},{"id":"W1971541813","doi":"10.1214/10-aoas442","title":"Forecasting emergency medical service call arrival rates","year":2011,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":123,"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":"Computer science; Queueing theory; Context (archaeology); Exponential smoothing; Smoothing; Covariate; Econometrics; Mathematics; Machine learning; Geography","score_opus":0.5015733237736453,"score_gpt":0.4569802608908218,"score_spread":0.0445930628828235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971541813","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":[0.1511375,0.00009534632,0.670685,0.004761314,0.00036109105,0.00095490017,0.00083357294,0.0002243564,0.17094693],"genre_scores_gemma":[0.9273255,0.00005901998,0.07139488,0.0007973851,0.00009388626,0.000045094584,0.000014837794,0.000020688403,0.00024872148],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973445,0.000053625725,0.0008742545,0.00028237136,0.0011531181,0.00029210703],"domain_scores_gemma":[0.9970898,0.000919985,0.00046997808,0.00069200684,0.0006791198,0.00014910195],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028783914,0.00014443499,0.00025727914,0.000075691256,0.00020795074,0.000025884372,0.0014540278,0.00008143521,0.0017131552],"category_scores_gemma":[0.0014766692,0.00008965704,0.000056928413,0.0006778354,0.00018443003,0.000043711618,0.00028381962,0.0001960883,0.00013790173],"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":[0.00012445338,0.00017553147,0.0004597702,0.00002893434,0.000043744578,0.0000066394614,0.0037841925,0.00005717115,0.0002761819,0.67456317,0.20457941,0.11590078],"study_design_scores_gemma":[0.00009838709,0.000066613204,0.0018018878,0.000015286527,0.000016469585,0.00000707596,0.00042398798,0.035858136,0.0042249807,0.9490374,0.008280511,0.0001693013],"about_ca_topic_score_codex":0.00016232066,"about_ca_topic_score_gemma":0.00013693838,"teacher_disagreement_score":0.77618796,"about_ca_system_score_codex":0.0000034511577,"about_ca_system_score_gemma":0.000075728516,"threshold_uncertainty_score":0.9991994},"labels":[],"label_agreement":null},{"id":"W1987751717","doi":"10.1214/10-aoas342","title":"A nonlinear mixed effects directional model for the estimation of the rotation axes of the human ankle","year":2010,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Rotation (mathematics); Orientation (vector space); Nonlinear system; Measure (data warehouse); Monte Carlo method; Linear model; Sample (material); Data set","score_opus":0.07298192094243762,"score_gpt":0.35242304500087684,"score_spread":0.27944112405843924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987751717","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":[0.3006868,0.000009434496,0.6962429,0.0005625513,0.00014482945,0.0011368021,0.00074709184,0.00001138558,0.00045817468],"genre_scores_gemma":[0.87069607,0.0000033822732,0.12899727,0.00008122008,0.00003898646,0.00007046414,0.000014334947,0.000011122391,0.000087139655],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99909186,0.000049689337,0.0003698748,0.00009488985,0.00028438744,0.0001092953],"domain_scores_gemma":[0.9962417,0.0025565822,0.00052948884,0.00043235137,0.00022535767,0.000014524592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069799076,0.00009943788,0.00018287353,0.000020625144,0.00027718485,0.000011376913,0.00035867578,0.00006162787,0.000013683672],"category_scores_gemma":[0.0008403938,0.000042601427,0.00009410662,0.00015991984,0.00023374347,0.000018874376,0.0000753298,0.00016384595,6.174221e-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":[0.000036841153,0.00020755765,0.000031107254,0.00015918487,0.00006594579,1.9707429e-8,0.00045991337,0.010719783,0.025211558,0.9556474,0.0041567795,0.0033039139],"study_design_scores_gemma":[0.00023150336,0.000033224296,0.0046527246,0.000018728877,0.000102390804,3.9881752e-7,0.000055939785,0.38600564,0.05889736,0.54990447,0.00004445055,0.0000531428],"about_ca_topic_score_codex":0.000017866209,"about_ca_topic_score_gemma":0.00003198137,"teacher_disagreement_score":0.5700093,"about_ca_system_score_codex":0.0000036709698,"about_ca_system_score_gemma":0.000035504116,"threshold_uncertainty_score":0.21319099},"labels":[],"label_agreement":null},{"id":"W2012397316","doi":"10.1214/14-aoas774","title":"Evaluating epoetin dosing strategies using observational longitudinal data","year":2014,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Medicine; Observational study; Dosing; Regimen; Kidney disease; Intensive care medicine; Proportional hazards model; Dialysis; Anemia; Marginal structural model; Randomized controlled trial; Hemodialysis; Epoetin alfa; Clinical trial; Survival analysis; Internal medicine","score_opus":0.9581370777790906,"score_gpt":0.6916552922079258,"score_spread":0.26648178557116486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012397316","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":[0.03000422,0.000019661791,0.96567297,0.00027943472,0.00020650272,0.00038879164,0.0009834107,0.000045589783,0.0023993936],"genre_scores_gemma":[0.13263103,0.000012399143,0.8666702,0.00022543648,0.0003597032,0.000008474837,0.000040456576,0.000038404425,0.000013926286],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.996226,0.0006658548,0.0013543256,0.00045343212,0.00090662425,0.00039374945],"domain_scores_gemma":[0.9303155,0.06679905,0.0009416576,0.0014049702,0.00044540231,0.00009342547],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012395255,0.0002409413,0.00066205615,0.000047415517,0.00024097854,0.00010949243,0.001010298,0.000103742364,0.00017984414],"category_scores_gemma":[0.053885277,0.00018089442,0.00005303343,0.00023564506,0.00045741972,0.00010469655,0.00047518656,0.00031350905,0.000012436393],"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":[0.00016631848,0.00008470025,0.000051756906,0.0001834142,0.00009474265,0.0000010516203,0.0001285697,0.0010632176,0.0015790467,0.9683631,0.0022263557,0.026057713],"study_design_scores_gemma":[0.00034211442,0.00008420849,0.0010439053,0.0000704619,0.00016366248,0.00000195439,0.00015338299,0.11406103,0.0007326079,0.88304126,0.00012422429,0.00018121205],"about_ca_topic_score_codex":0.0000247145,"about_ca_topic_score_gemma":0.0000070146825,"teacher_disagreement_score":0.11299781,"about_ca_system_score_codex":0.000013144046,"about_ca_system_score_gemma":0.00018131034,"threshold_uncertainty_score":0.9540843},"labels":[],"label_agreement":null},{"id":"W2028703934","doi":"10.1214/14-aoas747","title":"Imputation of truncated p-values for meta-analysis methods and its genomic application","year":2014,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; University of Toronto","funders":"National Institute of Mental Health","keywords":"Inference; Imputation (statistics); False discovery rate; Raw data; Genomics; Statistical power; Multiple comparisons problem","score_opus":0.10692720296288404,"score_gpt":0.41959529675988433,"score_spread":0.3126680937970003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028703934","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":[0.028147506,0.00058719446,0.97038424,0.00016498058,0.0000101085725,0.0002973368,0.00020626836,0.000003486545,0.00019885458],"genre_scores_gemma":[0.94109136,0.00016250038,0.058077376,0.0001499346,0.00002346587,0.0001492869,0.0002750372,0.000009568595,0.0000614688],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99932075,0.00007577088,0.00026642176,0.00018137341,0.0000773416,0.000078346224],"domain_scores_gemma":[0.9990771,0.000098391785,0.0003235346,0.0002543311,0.00022052217,0.000026130798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072678726,0.00008267395,0.00026839183,0.0000500378,0.000044365745,0.000006018849,0.00011528699,0.000053014952,0.0000065370928],"category_scores_gemma":[0.000067127505,0.00005945823,0.000112772854,0.0001213016,0.000051668354,0.0000012880093,0.000028530416,0.00002229829,4.1564832e-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":[0.00012133308,0.000020915717,0.0000033947224,0.00003930375,0.0039211195,2.105056e-9,0.00010440343,0.001896572,0.9524307,0.025931394,0.00070902513,0.014821793],"study_design_scores_gemma":[0.00020506521,0.00010942034,0.0011179947,4.491032e-7,0.009029138,1.3016734e-7,0.00007434287,0.024003906,0.93492156,0.025733009,0.004706781,0.00009819301],"about_ca_topic_score_codex":0.0000037358059,"about_ca_topic_score_gemma":0.0000024258038,"teacher_disagreement_score":0.91294384,"about_ca_system_score_codex":0.0000014057383,"about_ca_system_score_gemma":0.000017380558,"threshold_uncertainty_score":0.24246362},"labels":[],"label_agreement":null},{"id":"W2042759248","doi":"10.1214/14-aoas804","title":"A two-step approach to model precipitation extremes in California based on max-stable and marginal point processes","year":2015,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Hydrology and Drought Analysis","field":"Environmental Science","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":"Environment and Climate Change Canada","funders":"","keywords":"Maxima; Extreme value theory; Pairwise comparison; Statistics; Univariate; Mathematics; Block (permutation group theory); Maxima and minima; Generalized extreme value distribution; Confidence interval; Point estimation; Precipitation; Econometrics; Multivariate statistics; Meteorology; Geography; Combinatorics; Mathematical analysis","score_opus":0.05744828277066105,"score_gpt":0.28995323345361307,"score_spread":0.23250495068295202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042759248","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":[0.19749129,0.000035054407,0.73520637,0.0010957053,0.000010839455,0.00056654273,0.0003349759,0.000021143862,0.0652381],"genre_scores_gemma":[0.92395157,0.0000072979306,0.07496198,0.0008915359,0.00000628065,0.000042912332,0.00003617234,0.000007997091,0.00009423086],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999119,0.000037625305,0.00019041466,0.00020526817,0.00025680262,0.00019092475],"domain_scores_gemma":[0.99952143,0.00011415209,0.00007650258,0.00017326018,0.000025289546,0.00008936185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005973579,0.00010650135,0.00016371191,0.000051865685,0.000052519434,0.000013377188,0.00014006661,0.000034275603,0.00003083819],"category_scores_gemma":[0.00008973229,0.00007850732,0.000010820909,0.000263421,0.00012902213,0.000041682964,0.000057273068,0.000079740144,0.000052136118],"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":[0.00051025936,0.00018801066,0.0011886361,0.00003147264,0.000009372154,0.0000010529989,0.0015621688,0.9849266,0.00015434773,0.0046416707,0.0052930187,0.0014933973],"study_design_scores_gemma":[0.00039856328,0.00008581413,0.0010051348,0.000006021686,0.000023166127,4.63292e-7,0.00030970704,0.95950145,0.00044448455,0.037798144,0.00030870785,0.0001183674],"about_ca_topic_score_codex":0.00013362303,"about_ca_topic_score_gemma":0.00024812,"teacher_disagreement_score":0.7264603,"about_ca_system_score_codex":0.000020166388,"about_ca_system_score_gemma":0.00003300597,"threshold_uncertainty_score":0.32014358},"labels":[],"label_agreement":null},{"id":"W2043089632","doi":"10.1214/12-aoas537","title":"A model for sequential evolution of ligands by exponential enrichment (SELEX) data","year":2012,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced biosensing and bioanalysis techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Systematic evolution of ligands by exponential enrichment; Oligonucleotide; Computational biology; Biology; DNA; Computer science; Genetics; RNA","score_opus":0.08406956993041677,"score_gpt":0.3643286796780921,"score_spread":0.2802591097476754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043089632","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":[0.07452681,0.00035865663,0.92129856,0.000058789683,0.000028885193,0.00021563575,0.0033995253,0.000008691252,0.00010446374],"genre_scores_gemma":[0.9525377,0.00022528779,0.04548425,0.00007076227,0.00011000714,0.000009978644,0.0014725128,0.00001198796,0.00007749532],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992111,0.000011800881,0.0002644035,0.00016911894,0.00014307821,0.00020051969],"domain_scores_gemma":[0.99907374,0.000022101853,0.00022473342,0.00050916057,0.00013067135,0.000039606737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040283176,0.00010630927,0.00016049267,0.000022203516,0.000053482072,0.0000047641042,0.00026533328,0.000075161224,7.1854146e-7],"category_scores_gemma":[0.000039169532,0.00008041185,0.000044715,0.00005216403,0.00012788508,0.0000040110085,0.00015525329,0.00003866043,2.5787128e-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":[0.00027449487,0.00012311403,0.000012456323,0.00002714012,0.00010445401,2.1037799e-8,0.000046288158,0.00009397882,0.9600891,0.0046035885,0.03218699,0.0024383627],"study_design_scores_gemma":[0.00019156831,0.00010554194,0.000017702378,0.000004732598,0.00009853804,5.622188e-7,0.00005448904,0.014785488,0.9789835,0.003274856,0.0023706465,0.000112352296],"about_ca_topic_score_codex":0.000007791053,"about_ca_topic_score_gemma":0.0000044091685,"teacher_disagreement_score":0.8780109,"about_ca_system_score_codex":0.0000050348744,"about_ca_system_score_gemma":0.000036612622,"threshold_uncertainty_score":0.32791004},"labels":[],"label_agreement":null},{"id":"W2057931901","doi":"10.1214/13-aoas684","title":"Beta regression for time series analysis of bounded data, with application to Canada Google® Flu Trends","year":2014,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":64,"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":"Bounded function; Autoregressive model; Mathematics; Econometrics; Statistics; Autoregressive integrated moving average; Regression analysis; Time series; Computer science","score_opus":0.11027838743097933,"score_gpt":0.42605134573024833,"score_spread":0.315772958299269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2057931901","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":[0.0031327591,0.000016836177,0.98916507,0.00070948654,0.000033649994,0.00024612152,0.005546974,0.0000119691,0.0011371175],"genre_scores_gemma":[0.75150925,0.000006294769,0.24685141,0.00021611417,0.000059353897,0.000052036583,0.0005470035,0.00002348016,0.000735034],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99722385,0.000053120948,0.00073949393,0.00048235533,0.0012371799,0.0002639812],"domain_scores_gemma":[0.99355096,0.0034653002,0.0006522527,0.0014444381,0.00075796293,0.00012906428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014521332,0.0001724518,0.000616824,0.00022067373,0.00018046556,0.000048022845,0.0012737424,0.00003164459,0.000032082375],"category_scores_gemma":[0.0010971685,0.000103816965,0.00003160731,0.0015720358,0.00019741437,0.00008947631,0.00020067573,0.00007725266,0.000004691998],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016895042,0.000087479166,0.0002206128,0.00006814502,0.00053260144,0.0000010050408,0.0006066966,0.030118803,0.0018003022,0.22132924,0.030270774,0.71327484],"study_design_scores_gemma":[0.0010180115,0.00081974507,0.014721364,0.00006472851,0.0016554658,0.0000016475984,0.0012822764,0.33321583,0.025142696,0.45159653,0.16953793,0.0009437572],"about_ca_topic_score_codex":0.0038878135,"about_ca_topic_score_gemma":0.040536877,"teacher_disagreement_score":0.7483765,"about_ca_system_score_codex":0.00001958248,"about_ca_system_score_gemma":0.00015230391,"threshold_uncertainty_score":0.97697085},"labels":[],"label_agreement":null},{"id":"W2068388041","doi":"10.1214/09-aoas318","title":"Modeling hourly ozone concentration fields","year":2010,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Economic and Environmental Valuation","field":"Economics, Econometrics and Finance","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; University of British Columbia","funders":"","keywords":"Bayesian probability; Kriging; Computer science; Kalman filter; Computation; Point process; Algorithm; Machine learning; Mathematics; Statistics; Artificial intelligence","score_opus":0.1730773880426103,"score_gpt":0.2705241227258004,"score_spread":0.0974467346831901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2068388041","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":[0.77489036,0.000061781866,0.20604652,0.00045052086,0.00017433,0.00013517772,0.0003207845,0.000009523138,0.01791102],"genre_scores_gemma":[0.9943441,0.00015548618,0.0048641143,0.00040820998,0.00006892159,0.000008932244,0.000052011274,0.000009699512,0.00008852578],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9993614,0.0000031333166,0.00035761812,0.00012713787,0.00002626432,0.0001244257],"domain_scores_gemma":[0.9995408,0.000042813022,0.00017010445,0.0002038089,0.000012591604,0.000029857692],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039627857,0.00006869735,0.00014751624,0.000019824865,0.00006665874,0.000018645991,0.00012727264,0.00005664368,0.00036658812],"category_scores_gemma":[0.000025268115,0.00006715176,0.000026172227,0.000032254502,0.00006197507,0.000051310257,0.000022348346,0.00012964719,0.0002047376],"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":[0.000015104781,0.000030352494,0.0011591705,0.000007843259,0.000020433406,1.0972565e-7,0.00049072097,0.013586614,0.000392537,0.9812187,0.0010686874,0.002009752],"study_design_scores_gemma":[0.00033620486,0.000047624082,0.011619181,0.0000026635712,0.000008428744,6.047677e-7,0.0001381005,0.33108082,0.0015352954,0.653794,0.0012488508,0.0001882266],"about_ca_topic_score_codex":0.000087892935,"about_ca_topic_score_gemma":0.00003178801,"teacher_disagreement_score":0.32742468,"about_ca_system_score_codex":0.000005903149,"about_ca_system_score_gemma":0.0000068018335,"threshold_uncertainty_score":0.4013883},"labels":[],"label_agreement":null},{"id":"W2070512361","doi":"10.1214/12-aoas566","title":"Dating medieval English charters","year":2012,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":15,"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 Toronto","funders":"","keywords":"Documentation; History; Politics; Genealogy; Phrase; Variation (astronomy); Classics; Law; Computer science; Political science; Natural language processing","score_opus":0.05168577421080451,"score_gpt":0.30302702096211015,"score_spread":0.25134124675130565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070512361","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":[0.007043059,0.00010879026,0.97565734,0.00021566979,0.00071031816,0.00007834029,0.000023528528,0.00007644908,0.016086515],"genre_scores_gemma":[0.84284973,0.000023346292,0.1564765,0.00031680058,0.00027508623,0.00000469702,0.000005458146,0.00000628173,0.000042071784],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99927646,0.000021151789,0.00017668972,0.00009580652,0.00019478728,0.0002350934],"domain_scores_gemma":[0.9992718,0.00014613557,0.00014890402,0.00024513117,0.00013485213,0.00005317029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056297996,0.00007340916,0.00010182227,0.0000319052,0.000121370795,0.000048358033,0.0003672772,0.000023663139,0.000010899686],"category_scores_gemma":[0.00007764272,0.000053182594,0.000016233478,0.00012541024,0.00010250128,0.00018142007,0.000081992745,0.00009826367,0.00001617562],"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":[0.000013022777,0.000042716023,0.00006138364,0.000053288884,0.00002772007,3.7890382e-7,0.01103449,0.000031928823,0.0011686608,0.39845484,0.010490772,0.5786208],"study_design_scores_gemma":[0.0021433025,0.0003506182,0.008610364,0.0002248303,0.00016340298,0.00008269973,0.008542078,0.15258567,0.35675514,0.41876328,0.04972476,0.0020538687],"about_ca_topic_score_codex":0.0000023384655,"about_ca_topic_score_gemma":2.3986468e-7,"teacher_disagreement_score":0.8358067,"about_ca_system_score_codex":0.0000029587152,"about_ca_system_score_gemma":0.000032719112,"threshold_uncertainty_score":0.21687232},"labels":[],"label_agreement":null},{"id":"W2076514995","doi":"10.1214/12-aoas584","title":"Robust VIF regression with application to variable selection in large data sets","year":2013,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Outlier; Robustness (evolution); Feature selection; Computer science; Estimator; Regression; Robust regression; Lasso (programming language); Covariate; Regression analysis; Variance (accounting); Variance inflation factor; Econometrics; Artificial intelligence; Machine learning; Statistics; Mathematics; Multicollinearity; Economics","score_opus":0.20471608224767654,"score_gpt":0.4366883251623959,"score_spread":0.23197224291471938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076514995","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":[0.0014105843,0.0000087395565,0.9952713,0.0002452426,0.000013524318,0.0009509813,0.00066912005,0.000030775784,0.0013996819],"genre_scores_gemma":[0.08274702,0.000014564707,0.9165591,0.00029143976,0.000025810721,0.00015191606,0.00009663204,0.000030891133,0.00008262488],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985922,0.00006877191,0.00039070513,0.00033396276,0.00028732096,0.00032706888],"domain_scores_gemma":[0.9978463,0.0010198025,0.00021421377,0.0006266607,0.00020183832,0.00009119402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008861735,0.00016394406,0.00030226077,0.00006191762,0.00009659199,0.000023957044,0.00038462997,0.00006123923,0.00006978209],"category_scores_gemma":[0.00040945841,0.00010492926,0.000008420686,0.00034961206,0.00004919334,0.00009904345,0.00017032873,0.00018506168,0.000016179883],"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":[0.00017288423,0.00019084777,0.000016313925,0.00011864169,0.000022143346,6.22886e-7,0.0003153549,0.0040304186,0.0021550725,0.9487077,0.014768914,0.029501073],"study_design_scores_gemma":[0.00028546277,0.00008084995,0.0002857696,0.000051422154,0.000022786571,0.0000013192437,0.0001485184,0.1509293,0.00079046615,0.84639215,0.00086403714,0.00014790743],"about_ca_topic_score_codex":0.00007270177,"about_ca_topic_score_gemma":0.000087254775,"teacher_disagreement_score":0.14689888,"about_ca_system_score_codex":0.000015062419,"about_ca_system_score_gemma":0.000041793217,"threshold_uncertainty_score":0.4278891},"labels":[],"label_agreement":null},{"id":"W2088906176","doi":"10.1214/13-aoas626","title":"Travel time estimation for ambulances using Bayesian data augmentation","year":2013,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":109,"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":"Global Positioning System; Bayesian probability; Computer science; Estimation; Path (computing); Data mining; Statistics; Mathematics; Artificial intelligence; Engineering","score_opus":0.14421433261847197,"score_gpt":0.3997035024737231,"score_spread":0.25548916985525116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2088906176","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":[0.0055915504,0.000013698191,0.99077,0.00061158434,0.000048694365,0.0005370291,0.00066443457,0.000024064977,0.0017389827],"genre_scores_gemma":[0.6595069,0.000043041404,0.33837464,0.00021842314,0.00007354158,0.00002477561,0.0015763034,0.00001144703,0.00017088179],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929726,0.000028521426,0.00021648941,0.00011536606,0.00020769061,0.00013464439],"domain_scores_gemma":[0.99918735,0.0002686128,0.00019163993,0.00016224568,0.00015578217,0.000034388097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047188162,0.00005922241,0.00009775727,0.00003156291,0.0002988578,0.000054644406,0.00022038064,0.000034699922,0.00009942732],"category_scores_gemma":[0.00007312853,0.00005035216,0.000011124159,0.00011113088,0.00011965517,0.00017657378,0.0000067886135,0.000030519295,0.000012548504],"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":[0.00024027226,0.00016246657,0.00020564787,0.00018925795,0.00014694367,4.2302372e-7,0.042808946,0.26439172,0.0035710821,0.48754805,0.064049125,0.13668609],"study_design_scores_gemma":[0.0002808029,0.000029163322,0.004817868,0.00002046753,0.00005928511,9.2086225e-8,0.003049316,0.9244984,0.0006221131,0.06597679,0.00050564145,0.00014007793],"about_ca_topic_score_codex":0.0005746029,"about_ca_topic_score_gemma":0.00006144228,"teacher_disagreement_score":0.66010666,"about_ca_system_score_codex":0.000006523734,"about_ca_system_score_gemma":0.000071360875,"threshold_uncertainty_score":0.22986028},"labels":[],"label_agreement":null},{"id":"W2098683668","doi":"10.1214/08-aoas222","title":"Handbook for the GREAT08 Challenge: An image analysis competition for cosmological lensing","year":2009,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Galaxies: Formation, Evolution, Phenomena","field":"Physics and Astronomy","cited_by":121,"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 Victoria; University of British Columbia","funders":"Science and Technology Facilities Council; European Commission; National Aeronautics and Space Administration; University College London; California Institute of Technology; Jet Propulsion Laboratory","keywords":"Weak gravitational lensing; Dark energy; Dark matter; Galaxy; Inference; Strong gravitational lensing; Cosmology; Gravitational lens; Physics; Data science; Astrophysics; Computer science; Theoretical physics; Astronomy; Artificial intelligence; Redshift","score_opus":0.05355674815407757,"score_gpt":0.3134809803572959,"score_spread":0.2599242322032183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098683668","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":[0.12294714,0.0000633166,0.873706,0.0008255875,0.000030925898,0.00081493723,0.0010472416,0.000023580213,0.0005412739],"genre_scores_gemma":[0.9794814,0.000016027108,0.01958898,0.0000405308,0.00016022801,0.00005978037,0.0006012557,0.000009407924,0.000042368367],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991442,0.00002654872,0.00030645824,0.00014731668,0.00014237248,0.00023309056],"domain_scores_gemma":[0.99872154,0.00039639676,0.00024501057,0.00029787957,0.00029801638,0.000041174826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039500586,0.00013431114,0.0002448763,0.000047930793,0.0004044752,0.000047703248,0.00020245812,0.00002648744,0.000052434007],"category_scores_gemma":[0.000011450931,0.00008716427,0.000109181296,0.00013193408,0.00014058176,0.000073352916,0.000015866779,0.00006925328,0.000003947202],"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":[0.00020123807,0.00017312216,0.0017776848,0.000017366992,0.0003687229,4.0369468e-9,0.0014781101,0.0009068912,0.00023085182,0.9880268,0.0023617118,0.004457522],"study_design_scores_gemma":[0.0005521878,0.00031387078,0.25428972,0.0000061641445,0.00050514744,1.6313287e-7,0.0009796417,0.031836756,0.0007917721,0.7098748,0.000674189,0.00017557727],"about_ca_topic_score_codex":0.000017238664,"about_ca_topic_score_gemma":0.000008681221,"teacher_disagreement_score":0.8565343,"about_ca_system_score_codex":0.000009614756,"about_ca_system_score_gemma":0.0000253283,"threshold_uncertainty_score":0.3554456},"labels":[],"label_agreement":null},{"id":"W2107904222","doi":"10.1214/10-aoas398l","title":"Discussion of: A statistical analysis of multiple temperature proxies: Are reconstructions of surface temperatures over the last 1000 years reliable?","year":2011,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Tree-ring climate responses","field":"Earth and Planetary 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","funders":"","keywords":"Proxy (statistics); Autocorrelation; Statistical analysis; Paleoclimatology; Econometrics; History; Geology; Psychology; Statistics; Mathematics; Climate change; Oceanography","score_opus":0.03359346518537585,"score_gpt":0.2685703369750909,"score_spread":0.23497687178971507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107904222","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":[0.98592275,0.0001148531,0.00020482915,0.000049472135,0.000055221375,0.00022831213,0.012940906,0.0000103074135,0.00047332878],"genre_scores_gemma":[0.99036276,0.00018030411,0.009233731,0.000020457264,0.000009724415,0.0000013608748,0.00014288606,0.0000063312186,0.000042449232],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986317,0.000110488065,0.00051684584,0.00017733016,0.000364705,0.00019892337],"domain_scores_gemma":[0.9976903,0.0011631055,0.0004953952,0.00042754176,0.00016915318,0.00005448573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004492565,0.00014190283,0.00045453574,0.00012349448,0.00009326403,0.00001328099,0.00032107756,0.00006976709,0.0006006976],"category_scores_gemma":[0.00018562555,0.00007043437,0.000081852224,0.0006698745,0.00067083916,0.000041718413,0.000029298712,0.00017645345,0.000003760423],"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":[0.0031081873,0.00032625676,0.9138372,0.000523927,0.002124317,0.000010597465,0.009690369,0.03154078,0.008426641,0.01812486,0.006545685,0.0057412065],"study_design_scores_gemma":[0.0001530407,0.0001069894,0.98906016,0.000049623486,0.00030890392,0.0000014427826,0.0020558694,0.0015898343,0.004860011,0.0016086422,0.000104380604,0.000101102836],"about_ca_topic_score_codex":0.0008625427,"about_ca_topic_score_gemma":0.0021263612,"teacher_disagreement_score":0.07522299,"about_ca_system_score_codex":0.00000167258,"about_ca_system_score_gemma":0.000074080184,"threshold_uncertainty_score":0.65772176},"labels":[],"label_agreement":null},{"id":"W2126292488","doi":"10.1214/09-aoas285","title":"BART: Bayesian additive regression trees","year":2010,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1515,"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":"Division of Mathematical Sciences; Natural Sciences and Engineering Research Council of Canada; Isaac Newton Institute for Mathematical Sciences; National Science Foundation","keywords":"Frequentist inference; Bayesian probability; Nonparametric regression; Bayesian inference; Bayesian linear regression; Markov chain Monte Carlo; Boosting (machine learning); Feature selection; Inference; Bayesian average","score_opus":0.13013747162264705,"score_gpt":0.41145148035021956,"score_spread":0.2813140087275725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126292488","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":[0.009303468,0.000012867774,0.9365047,0.0005446177,0.00023675813,0.00038328423,0.0020003037,0.00006195454,0.050952002],"genre_scores_gemma":[0.43728957,0.000035615056,0.56205493,0.00026619088,0.00011876237,0.000024967223,0.000018862813,0.000026099146,0.0001649899],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987293,0.00006922084,0.0004029951,0.00019183266,0.00033074638,0.00027590638],"domain_scores_gemma":[0.99466676,0.0042385967,0.0002659683,0.0005020593,0.00021819075,0.00010840171],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007018677,0.00017981976,0.0003304221,0.000042009335,0.00013381345,0.00002477123,0.00032719702,0.00009040145,0.0009160514],"category_scores_gemma":[0.0020674586,0.00010942678,0.00004479791,0.00012861117,0.00036830266,0.000021601856,0.00008145787,0.00036873785,0.000032977303],"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":[0.00006777944,0.000063767795,0.000005429509,0.000027640728,0.000022950442,0.0000024858934,0.00042826924,6.1376943e-7,0.003474567,0.87283474,0.03185389,0.09121789],"study_design_scores_gemma":[0.00015238319,0.00007675122,0.0011329798,0.000027194183,0.000033296852,0.0000018275091,0.00017981089,0.0010462016,0.016558804,0.97736824,0.0032784822,0.00014404679],"about_ca_topic_score_codex":0.000010004628,"about_ca_topic_score_gemma":0.00003545016,"teacher_disagreement_score":0.4279861,"about_ca_system_score_codex":0.0000027320048,"about_ca_system_score_gemma":0.00004554183,"threshold_uncertainty_score":0.99999726},"labels":[],"label_agreement":null},{"id":"W2148429219","doi":"10.1214/10-aoas378","title":"Detecting multiple authorship of United States Supreme Court legal decisions using function words","year":2011,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Authorship Attribution and Profiling","field":"Computer Science","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 Toronto","funders":"","keywords":"Supreme court; Style (visual arts); Function (biology); Legal writing; Writing style; Statistical analysis","score_opus":0.24488643153322526,"score_gpt":0.347889792177648,"score_spread":0.10300336064442273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148429219","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":[0.13760938,0.00003082987,0.861544,0.00006308993,0.00015630468,0.0001529222,0.00010980975,0.000052912634,0.00028075866],"genre_scores_gemma":[0.8363841,0.000017004237,0.16338657,0.00013527858,0.000021107064,0.0000035632788,0.000026832837,0.000011014315,0.000014517586],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848187,0.00013525083,0.00051256904,0.00021144445,0.00035520643,0.00030367306],"domain_scores_gemma":[0.9975441,0.0010745646,0.00041555593,0.00046742935,0.00040323593,0.00009510239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015973838,0.0001464091,0.000225333,0.0001780299,0.00023979071,0.000037812377,0.0005782854,0.00007915979,0.000025697876],"category_scores_gemma":[0.0004497444,0.00011767514,0.000049226594,0.00071807444,0.00013791898,0.00012343204,0.00018661121,0.00024111365,0.0000071926747],"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":[0.0006720368,0.0001814138,0.0006507174,0.00006238949,0.00016417578,0.0000056413287,0.016538598,0.009733577,0.008798529,0.9210965,0.00060052145,0.041495893],"study_design_scores_gemma":[0.0004153797,0.00021560125,0.0036292481,0.00006710214,0.000071547445,0.00000518637,0.0014762902,0.6351608,0.098200835,0.25957826,0.0008729588,0.00030680082],"about_ca_topic_score_codex":0.0002269908,"about_ca_topic_score_gemma":0.000027162205,"teacher_disagreement_score":0.69877476,"about_ca_system_score_codex":0.000010424179,"about_ca_system_score_gemma":0.00007469267,"threshold_uncertainty_score":0.4798653},"labels":[],"label_agreement":null},{"id":"W2492804687","doi":"10.1214/16-aoas909","title":"A Bayesian graphical model for genome-wide association studies (GWAS)","year":2016,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; York University; University of Toronto","funders":"National Cancer Institute","keywords":"Genome-wide association study; Computer science; Bayesian probability; Genetic association; Graphical model; Single-nucleotide polymorphism; Computational biology; Data mining; Machine learning; Artificial intelligence; Biology; Genetics","score_opus":0.0591072333190735,"score_gpt":0.3411212849881219,"score_spread":0.28201405166904836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492804687","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":[0.07723756,0.00027221005,0.9144621,0.006464248,0.0000547447,0.0003255907,0.0008462415,0.000007761311,0.0003295313],"genre_scores_gemma":[0.9752475,0.0015094872,0.020264508,0.0019289305,0.00010284046,0.000085563166,0.000075905016,0.000016560849,0.00076871424],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990865,0.00004432602,0.00030939392,0.00018830458,0.00010768737,0.00026376627],"domain_scores_gemma":[0.9982867,0.00083932077,0.00028368452,0.00023314117,0.00031732483,0.000039814146],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080457045,0.000110055415,0.00022401549,0.000023781527,0.00010122601,0.0000041965254,0.00015747816,0.000121369136,0.000003444628],"category_scores_gemma":[0.0018416956,0.00006762816,0.00007277091,0.000045118046,0.000098076016,0.0000011254646,0.00006282305,0.00003808992,0.000003016398],"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":[0.0011926111,0.00035311264,0.026951984,0.00018534705,0.0034041498,7.4020585e-7,0.0015507797,0.01535481,0.14620782,0.11233127,0.6693136,0.023153745],"study_design_scores_gemma":[0.0022019933,0.00074798,0.04437144,0.000024358887,0.0002864987,8.964428e-7,0.0004887376,0.01553028,0.014359679,0.88807094,0.03320287,0.0007143494],"about_ca_topic_score_codex":0.0000014766456,"about_ca_topic_score_gemma":0.000022691927,"teacher_disagreement_score":0.89800996,"about_ca_system_score_codex":0.000013172863,"about_ca_system_score_gemma":0.00004848178,"threshold_uncertainty_score":0.27577963},"labels":[],"label_agreement":null},{"id":"W2569003638","doi":"10.1214/16-aoas964","title":"Inferring rooted population trees using asymmetric neighbor joining","year":2016,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","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","funders":"","keywords":"Population; Artificial intelligence; Computer science; Mathematics; Geography; Demography; Sociology","score_opus":0.06098441619541242,"score_gpt":0.31021719994415936,"score_spread":0.24923278374874694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569003638","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":[0.8947126,0.000069681904,0.1036632,0.000099328434,0.00007973333,0.00011395627,0.0002208235,0.000007981338,0.0010326665],"genre_scores_gemma":[0.9920478,0.000049552484,0.0074874638,0.00016962388,0.0000860347,0.0000010723201,0.000076838194,0.000010329252,0.0000713282],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99935436,0.000024629535,0.00019085848,0.00013985904,0.00014453822,0.00014573177],"domain_scores_gemma":[0.9994473,0.000039629496,0.00016608764,0.00021537075,0.00009422017,0.000037378148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013811409,0.0000959712,0.00011306266,0.000056441168,0.000096486794,0.000012119391,0.00013418669,0.00007381602,0.000023875768],"category_scores_gemma":[0.00008373743,0.000063612446,0.000032852022,0.00012271457,0.000048857044,0.0000028257518,0.00007736439,0.00003573926,0.000003549667],"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":[0.0005661028,0.00006184719,0.033769626,0.000059365546,0.00028627092,0.0000020855805,0.00039304316,0.012687838,0.6884413,0.056893017,0.00472395,0.20211555],"study_design_scores_gemma":[0.0015003347,0.00026493677,0.69801503,0.000057885358,0.00013548371,0.000007640064,0.00023862369,0.0016452906,0.2576973,0.029960645,0.009864996,0.00061182847],"about_ca_topic_score_codex":0.000035470035,"about_ca_topic_score_gemma":0.000019371791,"teacher_disagreement_score":0.66424537,"about_ca_system_score_codex":0.0000038768517,"about_ca_system_score_gemma":0.000019629448,"threshold_uncertainty_score":0.25940403},"labels":[],"label_agreement":null},{"id":"W2602208471","doi":"10.1214/18-aoas1162","title":"Exact spike train inference via $\\ell_{0}$ optimization","year":2018,"lang":"en","type":"preprint","venue":"The Annals of Applied Statistics","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Python (programming language); Computer science; TRACE (psycholinguistics); Inference; Software; Optimization problem; Spike (software development); Convex optimization; Measure (data warehouse); Algorithm; Mathematical optimization; Regular polygon; Mathematics; Artificial intelligence; Programming language","score_opus":0.10499761598033654,"score_gpt":0.3403495868487135,"score_spread":0.235351970868377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602208471","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":[0.016887238,0.000014742908,0.97027963,0.0005657828,0.0007851507,0.00083130866,0.0015810052,0.00008837552,0.008966781],"genre_scores_gemma":[0.9820464,0.00062928785,0.014630293,0.0018409587,0.00025762396,0.00004881907,0.00021575553,0.00005709242,0.00027372994],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980721,0.00010175467,0.000508605,0.00053119595,0.0004705434,0.00031583747],"domain_scores_gemma":[0.9977005,0.0007059727,0.00062917144,0.0006979559,0.00018952054,0.00007686457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043306116,0.0003054341,0.00036037402,0.00009801225,0.00017128223,0.00009523723,0.000659725,0.0001795906,0.00018791154],"category_scores_gemma":[0.00042496237,0.00023467322,0.00007342583,0.0001946258,0.00040214206,0.00003990231,0.00043456937,0.00047504393,0.000048146972],"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":[0.0006820332,0.0003701025,0.000009640927,0.00062203786,0.000071498085,0.000016831016,0.0012377066,0.62960756,0.08964818,0.19842932,0.016290348,0.06301475],"study_design_scores_gemma":[0.00021139848,0.0002096027,0.00021184162,0.00006565473,0.000054403685,0.0000031443087,0.000022637269,0.6234893,0.051099073,0.32319808,0.00097490405,0.0004599519],"about_ca_topic_score_codex":0.000026033975,"about_ca_topic_score_gemma":0.0000070481665,"teacher_disagreement_score":0.9651592,"about_ca_system_score_codex":0.000015725798,"about_ca_system_score_gemma":0.000093807495,"threshold_uncertainty_score":0.9569696},"labels":[],"label_agreement":null},{"id":"W2605027696","doi":"10.1214/16-aoas1002","title":"Electricity price dependence in New York State zones: A robust detrended correlation approach","year":2017,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Electric Power System Optimization","field":"Engineering","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":"HEC Montréal","funders":"","keywords":"Econometrics; Electricity; Detrended fluctuation analysis; Grid; Estimator; Electricity price; Computer science; Economics; Statistics; Mathematics","score_opus":0.0574632283859776,"score_gpt":0.26386248696745934,"score_spread":0.20639925858148173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605027696","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":[0.0032700603,0.00022170467,0.9817686,0.000021574633,0.00011291089,0.00039376435,0.000039157454,0.00007581488,0.014096388],"genre_scores_gemma":[0.94782096,0.00020499184,0.051577132,0.000018678456,0.000039918777,0.000018513003,0.000031253334,0.000035604215,0.00025292076],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998769,0.000029357008,0.00040379833,0.00017918077,0.0002902815,0.00032838914],"domain_scores_gemma":[0.99886656,0.00017446729,0.00028258428,0.00053807977,0.00007245247,0.000065837114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004519231,0.00017146532,0.00025464693,0.00011568837,0.00012850111,0.000077333476,0.0004799227,0.00007659463,0.0000071604577],"category_scores_gemma":[0.0001306881,0.00015414247,0.000022304,0.00029305424,0.00004285192,0.000104726096,0.000035941917,0.00023911102,0.000012201267],"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":[0.000073992545,0.000041712374,0.00022692533,0.000112838425,0.000046260124,0.0000015449696,0.0011105892,0.96198416,0.00020975739,0.018528149,0.004021719,0.013642329],"study_design_scores_gemma":[0.00042484538,0.00003712566,0.0069632563,0.000029551726,0.00001988436,0.0000032617675,0.000050085026,0.98187983,0.0014942354,0.00871611,0.00014933705,0.00023248965],"about_ca_topic_score_codex":0.00020375715,"about_ca_topic_score_gemma":0.0001418633,"teacher_disagreement_score":0.94455093,"about_ca_system_score_codex":0.000043309992,"about_ca_system_score_gemma":0.00008814939,"threshold_uncertainty_score":0.6285747},"labels":[],"label_agreement":null},{"id":"W2761069967","doi":"10.1214/17-aoas1044","title":"Latent class modeling using matrix covariates with application to identifying early placebo responders based on EEG signals","year":2017,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Mental Health Research Topics","field":"Psychology","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 Alberta","funders":"National Institute of Mental Health","keywords":"Covariate; Latent class model; Latent variable; Statistics; Placebo; Missing data; Bayesian probability; Matrix decomposition; Artificial intelligence; Computer science; Econometrics; Psychology; Mathematics; Medicine","score_opus":0.25930561809344677,"score_gpt":0.49458103777685225,"score_spread":0.23527541968340548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2761069967","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":[0.24500991,0.000018287597,0.74911296,0.0011235472,0.00008360347,0.0014736939,0.00024824665,0.0000289269,0.0029008023],"genre_scores_gemma":[0.9697488,0.0000068711174,0.029156376,0.00065915345,0.000052249954,0.000120020246,0.000022488915,0.000043449843,0.00019059949],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99795896,0.00013676415,0.0004230661,0.00035731235,0.0006170873,0.00050682254],"domain_scores_gemma":[0.9976426,0.00047781077,0.00038811023,0.0010989272,0.00021230495,0.00018027356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015408423,0.0001867,0.00027440966,0.00015334263,0.00059292384,0.00012824466,0.0006298753,0.00008801395,0.00008271269],"category_scores_gemma":[0.00008667043,0.0001450271,0.000030270698,0.00012188527,0.00013855696,0.000049368376,0.00009929218,0.00028413456,0.000116893614],"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":[0.023203082,0.000434749,0.00059395883,0.0004903491,0.00025685786,0.000036154415,0.0049717897,0.525338,0.014069405,0.41085654,0.0023458854,0.017403249],"study_design_scores_gemma":[0.0023137205,0.0008169188,0.007692899,0.00022171723,0.0000746496,0.0000024656358,0.0009152523,0.9538374,0.0031596085,0.030146057,0.00036898424,0.0004503194],"about_ca_topic_score_codex":0.000764442,"about_ca_topic_score_gemma":0.000045206907,"teacher_disagreement_score":0.7247389,"about_ca_system_score_codex":0.000053096763,"about_ca_system_score_gemma":0.00010612095,"threshold_uncertainty_score":0.59140337},"labels":[],"label_agreement":null},{"id":"W2767505813","doi":"10.1214/21-aoas1471","title":"Improving exoplanet detection power: Multivariate Gaussian process models for stellar activity","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Astrophysics Division; Pennsylvania Space Grant Consortium; Natural Sciences and Engineering Research Council of Canada; European Commission; National Aeronautics and Space Administration; University of Pennsylvania; Simons Foundation Autism Research Initiative; Pennsylvania State University; Simons Foundation; Institute for Computational and Data Sciences, Pennsylvania State University; Division of Mathematical Sciences; National Science Foundation","keywords":"Exoplanet; Radial velocity; Physics; Planet; Astrophysics; Astronomy; Astron; Gaussian process; Gaussian; Stars","score_opus":0.05106795244628423,"score_gpt":0.325273856738226,"score_spread":0.2742059042919418,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767505813","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":[0.25022984,0.00017497469,0.7337,0.000108876004,0.00008098932,0.0004855993,0.004407696,0.00012003883,0.010691998],"genre_scores_gemma":[0.9976347,0.00001586091,0.0018226232,0.00007655605,0.000041708343,0.00012213469,0.00007425691,0.000030021252,0.00018213438],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99888295,0.000014434563,0.00024545318,0.0002526723,0.00030979663,0.0002947194],"domain_scores_gemma":[0.9988648,0.00032593153,0.00036025833,0.0003101082,0.00008621602,0.00005265048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002851996,0.00016442456,0.00026679764,0.000071782924,0.00039950426,0.000024903737,0.000316632,0.000053785596,0.00030374303],"category_scores_gemma":[0.000051866467,0.00014182425,0.000055694494,0.00029255226,0.00006343035,0.000044332966,0.00008906421,0.0002524073,0.0000014085649],"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":[0.0030563793,0.00060476956,0.000014696493,0.0009940441,0.00059920416,0.0000049805744,0.0025792837,0.049721412,0.88203526,0.017993815,0.0011172723,0.041278873],"study_design_scores_gemma":[0.0005378397,0.00012514585,0.00002164116,0.0000029793528,0.00018551531,0.0000044304024,0.0019194251,0.09982383,0.8625377,0.034193706,0.00039395,0.0002538324],"about_ca_topic_score_codex":0.000086510896,"about_ca_topic_score_gemma":0.00000718726,"teacher_disagreement_score":0.7474049,"about_ca_system_score_codex":0.000033044955,"about_ca_system_score_gemma":0.000060190312,"threshold_uncertainty_score":0.5783425},"labels":[],"label_agreement":null},{"id":"W2789596487","doi":"10.1214/17-aoas1108","title":"Simultaneous modelling of movement, measurement error, and observer dependence in mark-recapture distance sampling: An application to Arctic bird surveys","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Estimator; Distance sampling; Mark and recapture; Observer (physics); Statistics; Abundance estimation; Sampling (signal processing); Observational error; Computer science; Abundance (ecology); Mathematics; Econometrics; Ecology; Biology; Computer vision","score_opus":0.10828061340485357,"score_gpt":0.3023662759143145,"score_spread":0.1940856625094609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789596487","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":[0.4848453,0.000011667287,0.51454824,0.00013813979,0.000015265834,0.00029342005,0.0000352347,0.00000753373,0.00010521095],"genre_scores_gemma":[0.9839863,0.000024037763,0.015317086,0.0006005944,0.000013166504,0.000028070335,0.0000075268094,0.000011619765,0.000011562062],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9988681,0.00008589479,0.0003073154,0.00024595327,0.00031111576,0.00018162838],"domain_scores_gemma":[0.9991731,0.00021797241,0.0001781112,0.00028662826,0.00008779893,0.000056385004],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014992068,0.00010747701,0.00015155843,0.000023641196,0.000079433536,0.00000813731,0.00022336267,0.00005180954,0.000035449735],"category_scores_gemma":[0.000092672,0.000092960705,0.000009977656,0.00019099191,0.00022526208,0.000055682205,0.000076735814,0.0000841878,0.0000156686],"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":[0.0007073272,0.00042708564,0.2475734,0.00011480855,0.000045099798,0.0000017558508,0.0038647905,0.68143237,0.013407999,0.0147728175,0.000250561,0.037401985],"study_design_scores_gemma":[0.00028561786,0.00023958407,0.7120999,0.000033832148,0.000022243788,4.471486e-7,0.00027362097,0.21158203,0.002386665,0.072660595,0.00018039627,0.00023502277],"about_ca_topic_score_codex":0.00094495533,"about_ca_topic_score_gemma":0.008534394,"teacher_disagreement_score":0.49923113,"about_ca_system_score_codex":0.000035368856,"about_ca_system_score_gemma":0.0000144910055,"threshold_uncertainty_score":0.47623923},"labels":[],"label_agreement":null},{"id":"W2790880830","doi":"10.1214/17-aoas1092","title":"Automated threshold selection for extreme value analysis via ordered goodness-of-fit tests with adjustment for false discovery rate","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Hydrology and Drought Analysis","field":"Environmental Science","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Generalized Pareto distribution; Goodness of fit; False discovery rate; Statistics; Extreme value theory; Sample size determination; Mathematics; Selection (genetic algorithm); Multiple comparisons problem; Threshold limit value; Computer science; Model selection; Artificial intelligence","score_opus":0.05727779193429081,"score_gpt":0.3207032615150507,"score_spread":0.26342546958075985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790880830","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":[0.29614368,0.000020926731,0.7018404,0.00019230766,0.000031285526,0.0007131261,0.0004823867,0.00004735539,0.00052854023],"genre_scores_gemma":[0.97783875,0.0000166986,0.021438371,0.00023197902,0.000037729496,0.000107129556,0.000112858026,0.000017068365,0.00019940424],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880326,0.000035306115,0.0003666413,0.00029259932,0.00021075581,0.00029143432],"domain_scores_gemma":[0.99885064,0.00033368837,0.00036396674,0.00031268343,0.00008908597,0.000049923994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056472607,0.000172326,0.0003927139,0.00007709506,0.00019986767,0.000015046709,0.00023270094,0.00007125011,0.0001307671],"category_scores_gemma":[0.000039458722,0.00011578584,0.000100716934,0.000764271,0.00044470115,0.000084275714,0.00005282109,0.000052357307,0.000011747374],"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":[0.009142936,0.0017002585,0.020653578,0.0002668282,0.009292597,0.000002040365,0.0031529348,0.75834596,0.09443482,0.059703685,0.032135032,0.011169313],"study_design_scores_gemma":[0.0008586931,0.00087596435,0.028147826,0.0000079633155,0.0024787688,7.848966e-7,0.000095303156,0.88891435,0.032816947,0.045059584,0.0004613322,0.00028249825],"about_ca_topic_score_codex":0.00018418985,"about_ca_topic_score_gemma":0.0012466068,"teacher_disagreement_score":0.6816951,"about_ca_system_score_codex":0.000020896194,"about_ca_system_score_gemma":0.000022595334,"threshold_uncertainty_score":0.47216097},"labels":[],"label_agreement":null},{"id":"W2884750441","doi":"10.1214/18-aoas1160sf","title":"When should modes of inference disagree? Some simple but challenging examples","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Frequentist inference; Fiducial inference; Inference; Bayes' theorem; Computer science; Simple (philosophy); Bayesian inference; Statistical inference; Artificial intelligence; Machine learning; Predictive inference; Econometrics; Bayesian probability; Mathematics; Epistemology; Statistics; Philosophy","score_opus":0.20253955059033146,"score_gpt":0.36163241960983933,"score_spread":0.15909286901950787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884750441","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":[0.01584931,0.00009459157,0.9814124,0.000528627,0.000043861502,0.00010789041,0.00017131085,0.000052922518,0.0017390877],"genre_scores_gemma":[0.9320842,0.00014302119,0.06729458,0.00035450028,0.00007450771,0.0000075118733,0.000009514114,0.000010525431,0.000021630465],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9986288,0.00003657332,0.00039474264,0.00025831335,0.00036445435,0.00031712253],"domain_scores_gemma":[0.99825,0.00047057436,0.00023589839,0.0007174834,0.00025083884,0.000075170465],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046086055,0.00016359965,0.00027870337,0.00006142143,0.00013336266,0.00005157742,0.0011404471,0.00005912687,0.000021790967],"category_scores_gemma":[0.00006886381,0.00012262187,0.000029737006,0.00012583354,0.00036838467,0.00014055579,0.0003219028,0.00013736583,0.000017983317],"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":[0.000017787384,0.000040040024,0.000012769963,0.00003833204,0.000023176812,5.713977e-7,0.0018394471,0.000864953,0.0042085866,0.9540402,0.0009571902,0.03795691],"study_design_scores_gemma":[0.00009179841,0.0001237631,0.00023699,0.000026225505,0.000009766789,6.3156784e-7,0.00017035085,0.18734686,0.0249234,0.7866876,0.00022673667,0.00015587527],"about_ca_topic_score_codex":0.00013110008,"about_ca_topic_score_gemma":0.000018926667,"teacher_disagreement_score":0.9162349,"about_ca_system_score_codex":0.0000048434267,"about_ca_system_score_gemma":0.00007152157,"threshold_uncertainty_score":0.5000375},"labels":[],"label_agreement":null},{"id":"W2890389585","doi":"10.1214/17-aoas1130","title":"Estimating and comparing cancer progression risks under varying surveillance protocols","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":13,"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 Toronto","funders":"National Cancer Institute; National Institutes of Health; Prostate Cancer Canada; Genomic Health; Canary Foundation; U.S. Department of Defense","keywords":"Prostate cancer; Schema (genetic algorithms); Medicine; Cancer; Computer science; Econometrics; Machine learning; Internal medicine; Mathematics","score_opus":0.47324418958584247,"score_gpt":0.5406745580878244,"score_spread":0.06743036850198192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890389585","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":[0.04003439,0.000028583305,0.9522151,0.00015307861,0.00006595905,0.003062055,0.00013608587,0.000048962804,0.0042557996],"genre_scores_gemma":[0.4431845,0.000007948051,0.55597407,0.00009208451,0.00009981825,0.0006130416,0.000001968363,0.000017826882,0.000008747019],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99871916,0.00009017757,0.00042301774,0.00021004362,0.0002765334,0.00028107196],"domain_scores_gemma":[0.99737036,0.0016580069,0.0003573379,0.00028694494,0.0002556273,0.00007174162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009856386,0.00016082305,0.00035975428,0.000027736574,0.00023149655,0.000049714537,0.00019617015,0.000048704867,0.00006274658],"category_scores_gemma":[0.00069210277,0.00010805754,0.000016472692,0.00012344924,0.0004393143,0.000024088904,0.00013503322,0.00016465916,0.0000039789047],"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":[0.00020762272,0.0000783419,0.0013512742,0.0005027173,0.000059544156,0.0000010480384,0.0010363082,0.00011959421,0.0011233147,0.86229616,0.0017794983,0.13144454],"study_design_scores_gemma":[0.00028660058,0.0001223278,0.0057546934,0.000255469,0.000019675472,0.0000014282705,0.000062486004,0.09000044,0.0038288112,0.8994012,0.00009203212,0.00017487518],"about_ca_topic_score_codex":0.000047796922,"about_ca_topic_score_gemma":0.000018510067,"teacher_disagreement_score":0.4031501,"about_ca_system_score_codex":0.00000768563,"about_ca_system_score_gemma":0.000041129006,"threshold_uncertainty_score":0.44064584},"labels":[],"label_agreement":null},{"id":"W2890985400","doi":"10.1214/18-aoas1138","title":"A frequency-calibrated Bayesian search for new particles","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Gaussian Processes and Bayesian Inference","field":"Computer Science","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"False discovery rate; Computer science; Inference; Bayesian probability; Bayesian inference; Statistical inference; Data mining; Bayesian hierarchical modeling; Nuisance parameter; Function (biology); Machine learning; Artificial intelligence; Statistics; Mathematics","score_opus":0.08347519627341762,"score_gpt":0.33547479827747323,"score_spread":0.2519996020040556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890985400","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":[0.0015605785,0.000026196885,0.9928924,0.0028252366,0.0000561592,0.00024529983,0.0000703577,0.00005499309,0.0022687782],"genre_scores_gemma":[0.64211184,0.000015183596,0.35709462,0.0005891349,0.00009207091,0.000012169558,0.0000041178396,0.000009515906,0.00007133642],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998852,0.00002136451,0.0002817403,0.00024227533,0.00023493903,0.0003676676],"domain_scores_gemma":[0.9987335,0.00023894304,0.00012051933,0.000504339,0.00027345202,0.00012923454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003210875,0.00012311542,0.00016993086,0.00004341239,0.00016893941,0.0001323567,0.0009951331,0.000042995296,0.00005081603],"category_scores_gemma":[0.000039577804,0.00008668608,0.000030239698,0.00037630045,0.00022464448,0.000115605406,0.000124771,0.00007758745,0.000039324343],"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":[0.00002834492,0.000027769698,0.000027795226,0.00004054858,0.000020558253,8.5180955e-7,0.00099832,0.000011793888,0.0024452507,0.9373116,0.011564365,0.0475228],"study_design_scores_gemma":[0.00021726251,0.00022009229,0.00057001685,0.000016502821,0.0000085057645,0.0000016822463,0.000053592586,0.037546948,0.11525399,0.8452438,0.0007274527,0.0001401612],"about_ca_topic_score_codex":0.000049319075,"about_ca_topic_score_gemma":0.000019500976,"teacher_disagreement_score":0.64055127,"about_ca_system_score_codex":0.0000043151767,"about_ca_system_score_gemma":0.00030086414,"threshold_uncertainty_score":0.35349557},"labels":[],"label_agreement":null},{"id":"W2891725784","doi":"10.1214/17-aoas1119","title":"Topological data analysis of single-trial electroencephalographic signals","year":2018,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Topological and Geometric Data Analysis","field":"Computer Science","cited_by":93,"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 of Biomedical Imaging and Bioengineering; King Abdullah University of Science and Technology; McMaster University; University of Wisconsin-Madison; Emory University; National Institutes of Health; National Science Foundation","keywords":"Electroencephalography; Pattern recognition (psychology); Computer science; Resampling; Neurophysiology; Artificial intelligence; Speech recognition; Neuroscience; Psychology","score_opus":0.16827890641685442,"score_gpt":0.3625785741721692,"score_spread":0.1942996677553148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891725784","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":[0.03463269,0.000103014245,0.9616544,0.0006322789,0.000066464905,0.00016616922,0.0010048219,0.000035675755,0.0017044783],"genre_scores_gemma":[0.96052414,0.00011042862,0.03863885,0.0004542279,0.00007412501,0.000004218691,0.00017147517,0.0000032101352,0.000019324305],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99797887,0.00010510168,0.00058874657,0.00046696706,0.00052023405,0.00034009363],"domain_scores_gemma":[0.9963341,0.0009834708,0.00044211204,0.001863021,0.00029769412,0.00007963047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001188821,0.0001455097,0.00056900235,0.0005031321,0.000116145726,0.000049641025,0.0034098162,0.00006995512,0.00020723119],"category_scores_gemma":[0.00041818107,0.00008853448,0.000122251,0.005667158,0.00084640173,0.00010379904,0.00088231603,0.00011072348,0.000012089827],"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":[0.00126203,0.0005938684,0.000110349465,0.000008388785,0.0020375177,0.0000043642804,0.00019930226,0.00018833394,0.002419479,0.9519293,0.0056797294,0.03556736],"study_design_scores_gemma":[0.004089332,0.005247654,0.011972507,0.00000958598,0.0033765587,0.0000025543595,0.00019764855,0.08542255,0.015595133,0.8667529,0.006571977,0.0007615638],"about_ca_topic_score_codex":0.000072828494,"about_ca_topic_score_gemma":0.00004973857,"teacher_disagreement_score":0.92589146,"about_ca_system_score_codex":0.0000031243248,"about_ca_system_score_gemma":0.000032703785,"threshold_uncertainty_score":0.6336344},"labels":[],"label_agreement":null},{"id":"W2949319659","doi":"10.1214/19-aoas1248","title":"Correction to: Statistical modeling and analysis of trace element concentrations in forensic glass evidence","year":2019,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Forensic and Genetic Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council","keywords":"TRACE (psycholinguistics); Forensic science; Computer science; Statistical analysis; Statistics; Data science; Archaeology; Mathematics; History; Philosophy; Linguistics","score_opus":0.05227684764868486,"score_gpt":0.3627472880181723,"score_spread":0.31047044036948745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949319659","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":[0.7119067,0.00015149114,0.28710264,0.000099659024,0.00004121295,0.0002534539,0.00018511961,0.0000010701951,0.00025868355],"genre_scores_gemma":[0.99288386,0.00033109824,0.0065339003,0.000077016855,0.000009962916,0.000009527555,0.000080623984,0.000005105545,0.00006892168],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992087,0.000032939675,0.00026054485,0.000169246,0.00018065618,0.00014794337],"domain_scores_gemma":[0.9993726,0.00016389959,0.00006342929,0.00021093502,0.00014569848,0.000043459975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003584143,0.000069010646,0.00017665203,0.000061575694,0.000021656098,0.000007800755,0.00009029542,0.00003045421,0.000019592686],"category_scores_gemma":[0.0001393661,0.00005580446,0.00002253775,0.0002132897,0.00009391182,0.0000016035118,0.000052664505,0.000056626195,0.0000016872643],"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":[0.0017263483,0.00017785082,0.013366307,0.00015937498,0.0008911007,0.0000015028464,0.0016380725,0.55473334,0.2926183,0.06612284,0.011077648,0.057487313],"study_design_scores_gemma":[0.00038457644,0.0006938464,0.036842924,0.000047699126,0.00019473501,7.490707e-7,0.00092021184,0.88217604,0.07515202,0.0031410449,0.00026189067,0.0001842861],"about_ca_topic_score_codex":0.00009690461,"about_ca_topic_score_gemma":0.00028586164,"teacher_disagreement_score":0.32744268,"about_ca_system_score_codex":0.0000041093,"about_ca_system_score_gemma":0.00005563964,"threshold_uncertainty_score":0.22756398},"labels":[],"label_agreement":null},{"id":"W2951194651","doi":"10.1214/18-aoas1236","title":"Early diagnosis of neurological disease using peak degeneration ages of multiple biomarkers","year":2019,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and 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":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Genentech; National Institute of Neurological Disorders and Stroke; IXICO; National Institute of General Medical Sciences; H. Lundbeck A/S; Servier; Eisai; Northern California Institute for Research and Education; Pfizer; Biogen; BioClinica; F. Hoffmann-La Roche; University of Southern California; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Bristol-Myers Squibb; National Institute on Aging; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Biomarker; Disease; Medicine; Pathology; Biology","score_opus":0.21261294380341322,"score_gpt":0.3913457883170323,"score_spread":0.1787328445136191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951194651","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":[0.85179675,0.000032556065,0.14657468,0.000051429008,0.000045390716,0.00032089718,0.0009341808,0.000008610244,0.00023553125],"genre_scores_gemma":[0.7636896,0.00003423147,0.23617645,0.000050177692,0.000013369422,0.000010144447,0.000009185155,0.000011990896,0.0000049111522],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987332,0.00012863647,0.0005170078,0.00015888242,0.0002941367,0.00016812795],"domain_scores_gemma":[0.9946973,0.0042515085,0.00041822862,0.00035042467,0.0002128006,0.00006977092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004969571,0.00012802704,0.00035922372,0.000046962727,0.000035345936,0.00000871261,0.00020460015,0.000048469738,0.00010795256],"category_scores_gemma":[0.0017510897,0.000089543304,0.000056491088,0.00013190377,0.00022846718,0.000021138563,0.000075080876,0.00008254494,0.0000030586134],"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":[0.000827944,0.00039961428,0.018863872,0.0006641192,0.00012788427,0.000002983919,0.00049140555,0.0005231547,0.018195305,0.94323033,0.0009148252,0.015758567],"study_design_scores_gemma":[0.00054798706,0.00046772632,0.12859166,0.0000805153,0.00019693813,4.202213e-7,0.00009531393,0.043062914,0.042313714,0.7843756,0.00003670985,0.00023051073],"about_ca_topic_score_codex":0.000034867284,"about_ca_topic_score_gemma":0.0000021849826,"teacher_disagreement_score":0.15885472,"about_ca_system_score_codex":0.000002789791,"about_ca_system_score_gemma":0.000032337743,"threshold_uncertainty_score":0.365147},"labels":[],"label_agreement":null},{"id":"W2959430680","doi":"10.1214/21-aoas1457","title":"Markov-switching state space models for uncovering musical interpretation","year":2021,"lang":"en","type":"preprint","venue":"The Annals of Applied Statistics","topic":"Music and Audio Processing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Interpretation (philosophy); Musical; Performing arts; Computer science; Active listening; Space (punctuation); Cognitive psychology; Subject (documents); Improvisation; Psychology; Linguistics; Cognitive science; Communication; Visual arts; Art; World Wide Web","score_opus":0.06173092111457535,"score_gpt":0.31619146310697216,"score_spread":0.2544605419923968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2959430680","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":[0.006365477,0.00014009644,0.9901484,0.00090165896,0.00037274964,0.00041487682,0.00016133417,0.00006092902,0.0014344723],"genre_scores_gemma":[0.572364,0.0000939142,0.42634994,0.0009647662,0.000073687865,0.00004742165,0.000045404344,0.00002334058,0.00003755555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813926,0.000046702993,0.00052085496,0.0005398025,0.0004096893,0.00034369694],"domain_scores_gemma":[0.99764663,0.0005542323,0.0006111523,0.0007563279,0.00036052658,0.00007112547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076880853,0.00027724382,0.00046139886,0.000074204065,0.00015663118,0.00044279723,0.0010628386,0.00010264088,0.0000041602502],"category_scores_gemma":[0.000089150344,0.00023334681,0.00010781595,0.00014228188,0.000062668434,0.00017174886,0.0013167466,0.0004335803,0.0000012799431],"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":[0.00013275273,0.00006297318,5.652778e-7,0.0012360252,0.0001626338,0.0000069775906,0.017275045,0.39460292,0.0012017397,0.17276908,0.0036020628,0.40894723],"study_design_scores_gemma":[0.00009477159,0.000015987682,0.000012582352,0.00017716359,0.00001916465,8.419925e-7,0.000108764085,0.5927353,0.002216699,0.40431222,0.00012809115,0.0001784406],"about_ca_topic_score_codex":0.000032108685,"about_ca_topic_score_gemma":0.000014340953,"teacher_disagreement_score":0.5659985,"about_ca_system_score_codex":0.00002374805,"about_ca_system_score_gemma":0.00031982237,"threshold_uncertainty_score":0.95156074},"labels":[],"label_agreement":null},{"id":"W2962800545","doi":"10.1214/16-aoas993","title":"A continuous-time stochastic block model for basketball networks","year":2017,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University; University of Waterloo; Royal Bank of Canada","funders":"","keywords":"Basketball; Analytics; Computer science; Stochastic block model; Data science; Offensive; Block (permutation group theory); Cluster analysis; Machine learning; Artificial intelligence; Operations research; Engineering; Geography; Mathematics","score_opus":0.09067351114725328,"score_gpt":0.28776109313606096,"score_spread":0.1970875819888077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962800545","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":[0.010292166,0.00022284259,0.9735798,0.0005877569,0.00014579722,0.00047053405,0.0023888065,0.000015729938,0.012296524],"genre_scores_gemma":[0.9932975,0.00015830349,0.0036253037,0.0004195497,0.00013107187,0.000033082444,0.000037466914,0.000028903487,0.0022687998],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989059,0.0000014826823,0.0005156162,0.0002220445,0.000045089106,0.00030987733],"domain_scores_gemma":[0.9981932,0.000112120826,0.000832207,0.0007012487,0.00009871164,0.00006253421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066761544,0.00014501002,0.0004328253,0.00004756976,0.00035540736,0.0001062671,0.0005381711,0.00006722803,0.00007502492],"category_scores_gemma":[0.00008166794,0.00012981165,0.000082962644,0.00002938996,0.00016654938,0.00005105825,0.0000798601,0.00010397524,0.000055961562],"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":[0.000105723455,0.000046536665,0.00011220737,0.000025007448,0.000084779786,3.8843254e-7,0.000211497,0.30908197,0.0000046988453,0.6732333,0.0158649,0.001229031],"study_design_scores_gemma":[0.00027812793,0.000037971597,0.0009420338,0.000007614571,0.00001537243,3.123354e-7,0.00000937253,0.8553733,0.000009100733,0.14066039,0.0025187475,0.00014764028],"about_ca_topic_score_codex":0.00004084063,"about_ca_topic_score_gemma":0.000012342798,"teacher_disagreement_score":0.98300534,"about_ca_system_score_codex":0.0000070102597,"about_ca_system_score_gemma":0.00002061155,"threshold_uncertainty_score":0.52935654},"labels":[],"label_agreement":null},{"id":"W2983854231","doi":"10.1214/21-aoas1565","title":"Measurement error correction in particle tracking microrheology","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Streptococcal Infections and Treatments","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 Alberta; University of Waterloo","funders":"","keywords":"Microrheology; Estimator; Range (aeronautics); Computer science; Power law; Bandwidth (computing); Viscoelasticity; Algorithm; Statistical physics; Physics; Acoustics; Mathematics; Statistics; Engineering; Telecommunications; Aerospace engineering","score_opus":0.15190217414061702,"score_gpt":0.36921828068977763,"score_spread":0.21731610654916061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983854231","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":[0.9877898,0.00015447305,0.00635075,0.00085867464,0.00030046864,0.0007542303,0.00006530346,0.000028466206,0.0036978314],"genre_scores_gemma":[0.9991224,0.00001319586,0.0003224687,0.0003023871,0.000015032806,0.00012137137,0.000011650543,0.000007893532,0.00008361192],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99933434,0.00003676634,0.00020002335,0.00010050792,0.00018821144,0.00014017151],"domain_scores_gemma":[0.9996148,0.000059918075,0.000077749006,0.00014332769,0.00007633308,0.000027874015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003361041,0.00006162694,0.00014171643,0.00004146626,0.00010802322,0.0000032480275,0.000039192833,0.000014494973,0.00021553725],"category_scores_gemma":[0.00003966924,0.000048353577,0.000025236786,0.00017406943,0.000052663345,0.000008098456,0.000031883457,0.00013039312,0.0000070778656],"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":[0.0074288524,0.009086649,0.20282109,0.00024724548,0.0012834487,0.0001804825,0.008898854,0.021940527,0.12283101,0.14029959,0.04534609,0.43963617],"study_design_scores_gemma":[0.0062301583,0.0026379814,0.7846357,0.000068465364,0.00037024784,0.00011541738,0.0044354172,0.014676165,0.15098532,0.025519727,0.009950837,0.000374545],"about_ca_topic_score_codex":0.000106238236,"about_ca_topic_score_gemma":0.00005335788,"teacher_disagreement_score":0.58181465,"about_ca_system_score_codex":0.00004818111,"about_ca_system_score_gemma":0.000041663006,"threshold_uncertainty_score":0.23599818},"labels":[],"label_agreement":null},{"id":"W2990428857","doi":"10.1214/19-aoas1274","title":"Joint model of accelerated failure time and mechanistic nonlinear model for censored covariates, with application in HIV/AIDS","year":2019,"lang":"en","type":"article","venue":"The Annals 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":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; City University of New York; National Science Foundation","keywords":"Covariate; Proportional hazards model; Accelerated failure time model; Econometrics; Inference; Statistics; Survival analysis; Computer science; Outcome (game theory); Mathematics; Artificial intelligence","score_opus":0.08529347782029319,"score_gpt":0.3467134122240529,"score_spread":0.2614199344037597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990428857","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":[0.0068373038,0.0000041800126,0.9885118,0.000091786715,0.0000044957383,0.0010762108,0.0031671978,0.000016633354,0.00029037934],"genre_scores_gemma":[0.17498985,0.000009672599,0.8247065,0.000055107314,0.0000070272354,0.000059868355,0.00007489569,0.000029227258,0.00006785704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870163,0.00003564607,0.0005444715,0.0002524461,0.00022805887,0.00023774778],"domain_scores_gemma":[0.99782753,0.0010775374,0.00035906915,0.00036287488,0.00031767465,0.00005528749],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006101011,0.0001917118,0.0005506563,0.0000709527,0.00003793245,0.00001730118,0.00017955324,0.00008924532,0.000017104705],"category_scores_gemma":[0.0002237782,0.00013461932,0.000024488234,0.00015500127,0.00011819407,0.000029043062,0.000051046387,0.00013220999,0.000004316734],"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":[0.0004255228,0.00010823006,0.0000040184946,0.0003670369,0.000038099923,1.9711376e-7,0.0004034229,0.006696357,0.02198725,0.96787906,0.0002189044,0.0018719188],"study_design_scores_gemma":[0.00038296636,0.00008666236,0.000008432045,0.0000290115,0.000035369147,3.5048637e-7,0.00003879576,0.5098462,0.0033969989,0.4860878,0.000001866097,0.00008552257],"about_ca_topic_score_codex":0.000009003549,"about_ca_topic_score_gemma":0.0000098353585,"teacher_disagreement_score":0.50314987,"about_ca_system_score_codex":0.00000937952,"about_ca_system_score_gemma":0.00008660583,"threshold_uncertainty_score":0.54896164},"labels":[],"label_agreement":null},{"id":"W2990681736","doi":"10.1214/19-aoas1269","title":"Robust elastic net estimators for variable selection and identification of proteomic biomarkers","year":2019,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"University of British Columbia; Genome Canada","keywords":"Estimator; Outlier; Robustness (evolution); Feature selection; Computer science; Robust statistics; Robust regression; Elastic net regularization; Lasso (programming language); Mathematics; Statistics; Artificial intelligence; Biology","score_opus":0.12250591961529245,"score_gpt":0.3935837860991451,"score_spread":0.2710778664838527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990681736","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":[0.02427754,0.000011841619,0.97370976,0.000034792538,0.000052037572,0.0010997033,0.0005727901,0.000016107,0.00022542682],"genre_scores_gemma":[0.19574542,0.000012433146,0.80405384,0.000017103906,0.00001207554,0.000054619548,0.000017255656,0.000021829177,0.00006540704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893045,0.000038426922,0.0005013347,0.00018961879,0.00015903283,0.00018112981],"domain_scores_gemma":[0.9971091,0.0019696348,0.00044344482,0.00020990353,0.00022671458,0.000041177205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086712575,0.00012223865,0.00030040572,0.000051133968,0.000064263906,0.00001333377,0.00010924463,0.00005580644,0.000017591761],"category_scores_gemma":[0.000730666,0.00009506667,0.000023302398,0.00012989233,0.00010157296,0.00003910473,0.000029523759,0.0000705399,0.0000017796575],"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":[0.0002701027,0.000052185107,0.0000140424645,0.00068562076,0.00007406486,4.3713925e-8,0.00013660369,0.0043198303,0.033621456,0.9560997,0.0006038911,0.004122489],"study_design_scores_gemma":[0.00028285763,0.00011422507,0.00017154175,0.00002858722,0.00007669203,8.95147e-7,0.0000599734,0.14209963,0.016597826,0.8404275,0.000048086495,0.00009219443],"about_ca_topic_score_codex":0.000006752826,"about_ca_topic_score_gemma":0.0000012993603,"teacher_disagreement_score":0.17146787,"about_ca_system_score_codex":0.00000803827,"about_ca_system_score_gemma":0.000040308085,"threshold_uncertainty_score":0.38767064},"labels":[],"label_agreement":null},{"id":"W3018701121","doi":"10.1214/20-aoas1348","title":"Markov decision processes with dynamic transition probabilities: An analysis of shooting strategies in basketball","year":2020,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Basketball; Transition (genetics); Markov chain; Computer science; Machine learning; History; Chemistry","score_opus":0.051517805710940424,"score_gpt":0.2760733188156001,"score_spread":0.22455551310465968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3018701121","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":[0.81337297,0.00014129153,0.18363713,0.00026081456,0.00000770827,0.00018661811,0.0009838883,0.00000808101,0.0014014958],"genre_scores_gemma":[0.99370676,0.00036902467,0.0056157596,0.00018591862,0.00000884256,0.000007877792,0.000090940724,0.000011093259,0.000003805524],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989456,0.000004960335,0.0006165774,0.00021339685,0.000072529496,0.0001469526],"domain_scores_gemma":[0.99913305,0.00014412738,0.00038703877,0.00019378195,0.000101722035,0.000040270003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041349456,0.00010787836,0.00044099134,0.00017219703,0.0000348981,0.000033040113,0.00018273802,0.000034559947,0.000113524475],"category_scores_gemma":[0.00004099346,0.000087230655,0.00003649567,0.0008216609,0.00009456602,0.00011708873,0.0000134321335,0.00007872879,0.0000016856234],"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":[0.0007694686,0.00021633446,0.007874197,0.0008729061,0.00040295525,0.0000027797257,0.017645955,0.6682478,0.000031894404,0.30046976,0.00005814095,0.0034078127],"study_design_scores_gemma":[0.0003554625,0.0003448754,0.059978124,0.000049463273,0.00011860635,2.2103174e-7,0.004876274,0.861473,0.000095232695,0.072334774,0.00013189993,0.00024201488],"about_ca_topic_score_codex":0.00017916737,"about_ca_topic_score_gemma":0.001048846,"teacher_disagreement_score":0.22813497,"about_ca_system_score_codex":0.000008865011,"about_ca_system_score_gemma":0.00006025638,"threshold_uncertainty_score":0.3557163},"labels":[],"label_agreement":null},{"id":"W3021847850","doi":"10.1214/21-aoas1526","title":"Permutation tests under a rotating sampling plan with clustered data","year":2022,"lang":"en","type":"article","venue":"The Annals 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":"University of British Columbia","funders":"","keywords":"Permutation (music); Sampling (signal processing); Resampling; Statistics; Parametric statistics; Inference; Econometrics; Sampling distribution; Computer science; Mathematics; Artificial intelligence","score_opus":0.12410127655508822,"score_gpt":0.3257595050175824,"score_spread":0.20165822846249415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3021847850","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":[0.5487289,0.0000162247,0.43527108,0.0015497154,0.00009219505,0.0010038717,0.0011142334,0.00005393726,0.012169863],"genre_scores_gemma":[0.9815085,0.0000036514343,0.017197609,0.00094728055,0.000008239468,0.000035147074,0.00022023369,0.000009558759,0.00006979111],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99924767,0.00003184881,0.00014431591,0.00017953973,0.00023918397,0.00015746168],"domain_scores_gemma":[0.9992835,0.00019218029,0.0001377722,0.00035821268,0.000005316526,0.000023026338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044960633,0.00006992635,0.00008639797,0.000015245349,0.00032516904,0.000010863269,0.00042019744,0.000010421699,0.0006330819],"category_scores_gemma":[0.000017329983,0.00005289144,0.0000056735526,0.00011246137,0.00013793416,0.00004049337,0.00070326554,0.000105827065,0.000027601553],"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":[0.00020695648,0.00011885317,0.0014108679,0.000023127403,0.00006436541,0.000006403521,0.002051482,0.8558905,0.00027841155,0.114951976,0.015235661,0.009761369],"study_design_scores_gemma":[0.0014184903,0.0007591925,0.43131742,0.000014053249,0.00017357827,0.000019820363,0.009242653,0.18457377,0.00023035172,0.36024648,0.011387313,0.000616883],"about_ca_topic_score_codex":0.00006726577,"about_ca_topic_score_gemma":0.00022834237,"teacher_disagreement_score":0.67131674,"about_ca_system_score_codex":0.000014727859,"about_ca_system_score_gemma":0.0000106766,"threshold_uncertainty_score":0.69318026},"labels":[],"label_agreement":null},{"id":"W3037512058","doi":"10.1214/20-aoas1331","title":"Focused model selection for linear mixed models with an application to whale ecology","year":2020,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Norges Forskningsråd","keywords":"Whaling; Generalized linear mixed model; Model selection; Mixed model; Estimator; Linear model; Selection (genetic algorithm); Computer science; Whale; Information Criteria; Ecology; Econometrics; Mathematics; Statistics; Artificial intelligence; Machine learning; Biology","score_opus":0.19487171623464805,"score_gpt":0.40556105054850106,"score_spread":0.210689334313853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037512058","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":[0.0028907855,0.0000015520367,0.994058,0.0009541905,0.000010488673,0.0010442709,0.0006659249,0.000053431304,0.00032135934],"genre_scores_gemma":[0.20058045,0.000003682585,0.7982055,0.00086158194,0.00005561069,0.00022809258,0.000026380892,0.000031182833,0.0000075434427],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988687,0.000048963946,0.00035345886,0.0002803299,0.00019524933,0.0002533093],"domain_scores_gemma":[0.99816614,0.0008783569,0.00019498654,0.0002485243,0.0003536749,0.00015831027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038002804,0.00016060295,0.0003375256,0.000032964508,0.0001098465,0.000018582767,0.0002444773,0.000070901595,0.000009309274],"category_scores_gemma":[0.00028789075,0.000116147356,0.000025205954,0.00019505553,0.00007694692,0.00004491927,0.00003462644,0.00011376311,0.000005215308],"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":[0.0007017859,0.0000889631,0.0000015077935,0.000119344455,0.00003273709,1.4221447e-7,0.0008430343,0.014558118,0.0014355473,0.9583472,0.002712067,0.02115958],"study_design_scores_gemma":[0.00018354227,0.00041356208,0.000009065523,0.0000033937197,0.0000349932,2.6287097e-7,0.000053410367,0.48686644,0.0032912644,0.5090256,0.000034528603,0.00008394889],"about_ca_topic_score_codex":0.000007655241,"about_ca_topic_score_gemma":0.00004289983,"teacher_disagreement_score":0.4723083,"about_ca_system_score_codex":0.0000088662155,"about_ca_system_score_gemma":0.00007518889,"threshold_uncertainty_score":0.47363517},"labels":[],"label_agreement":null},{"id":"W3106574156","doi":"10.1214/23-aoas1737","title":"Predictive inference for travel time on transportation networks","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Traffic Prediction and Management Techniques","field":"Engineering","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":"HEC Montréal; University of Toronto","funders":"","keywords":"Computer science; Predictive inference; Population; Global Positioning System; Inference; Statistical inference; Statistics; Data mining; Mathematics; Artificial intelligence; Bayesian inference","score_opus":0.03528464756629771,"score_gpt":0.2870721727432698,"score_spread":0.25178752517697206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3106574156","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":[0.0013620162,0.000005381627,0.9920417,0.000060286216,0.00006328236,0.00039869855,0.0008077271,0.0011502388,0.0041106828],"genre_scores_gemma":[0.9974543,0.00025158256,0.0016762932,0.000101095575,0.000034745295,0.00011098235,0.00029442477,0.000018344164,0.00005823629],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995435,0.000003756898,0.00015305555,0.00007198766,0.000098225995,0.00012948176],"domain_scores_gemma":[0.9996169,0.00018627012,0.000031735453,0.00010945844,0.000033698205,0.000021921047],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014552641,0.00007764095,0.00009922742,0.00005384228,0.000035597626,0.000007154521,0.00009915861,0.000035536632,0.0000061891733],"category_scores_gemma":[0.000008357213,0.00006536374,0.00002147226,0.00013059661,0.000031845502,0.000016847902,0.0000024842668,0.00006427361,0.000013268447],"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":[0.00010340741,0.000017554086,0.0000011766471,0.00006770998,0.0000738593,5.077471e-7,0.0005283413,0.47903815,0.0005552925,0.17140284,0.31023794,0.037973206],"study_design_scores_gemma":[0.00018794273,0.00012426177,0.0048530665,0.000018861323,0.000029376737,2.705402e-8,0.000094029645,0.9758671,0.0034051624,0.013045319,0.0022750436,0.00009980017],"about_ca_topic_score_codex":8.9060154e-7,"about_ca_topic_score_gemma":0.0000019982906,"teacher_disagreement_score":0.99609226,"about_ca_system_score_codex":0.0000038404833,"about_ca_system_score_gemma":0.000004068309,"threshold_uncertainty_score":0.2665456},"labels":[],"label_agreement":null},{"id":"W3168647111","doi":"10.1214/22-aoas1726","title":"Evaluating the use of generalized dynamic weighted ordinary least squares for individualized HIV treatment strategies","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Agence Nationale de la Recherche","keywords":"Categorical variable; Estimator; Ordinary least squares; Human immunodeficiency virus (HIV); Mathematics; Population; Mathematical optimization; Robustness (evolution); Computer science; Medicine; Statistics; Econometrics; Algorithm; Immunology","score_opus":0.6063138857192424,"score_gpt":0.5398848109691714,"score_spread":0.06642907475007098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168647111","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":[0.2584332,0.00006336772,0.73300606,0.0006746544,0.000051486655,0.0027306478,0.0043538683,0.00034744773,0.00033928722],"genre_scores_gemma":[0.3423781,0.00040893466,0.65547156,0.000091143214,0.00003508144,0.0006953121,0.00043135366,0.00008149737,0.00040701914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982267,0.00014764172,0.00067522627,0.00021315478,0.00039757925,0.00033967485],"domain_scores_gemma":[0.99343157,0.0049599237,0.0006287247,0.00063111266,0.0003125535,0.00003613507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008456055,0.00025865278,0.0005128207,0.00010365302,0.0001868291,0.00004860372,0.00035921164,0.000074087846,0.00003256438],"category_scores_gemma":[0.0004216852,0.0001495634,0.00009924773,0.00032208383,0.00030504767,0.000083270934,0.000108425724,0.00010156575,0.00000476788],"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":[0.000588895,0.00012774931,0.000003103391,0.00020537872,0.000269064,0.0000015354753,0.002267179,0.002369026,0.010364819,0.94649875,0.007348758,0.029955754],"study_design_scores_gemma":[0.00065194094,0.00059579144,0.00006460872,0.000048295016,0.00017528053,9.764441e-7,0.0012171259,0.040148005,0.016048694,0.94013786,0.00074528164,0.00016616542],"about_ca_topic_score_codex":0.000031790576,"about_ca_topic_score_gemma":0.000030326608,"teacher_disagreement_score":0.08394491,"about_ca_system_score_codex":0.000026381913,"about_ca_system_score_gemma":0.00012672764,"threshold_uncertainty_score":0.60990185},"labels":[],"label_agreement":null},{"id":"W3174385715","doi":"10.1214/21-aoas1570","title":"Estimation of the marginal effect of antidepressants on body mass index under confounding and endogenous covariate-driven monitoring times","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Covariate; Endogeneity; Confounding; Statistics; Body mass index; Propensity score matching; Marginal structural model; Econometrics; Selection bias; Index (typography); Medicine; Computer science; Mathematics; Internal medicine","score_opus":0.17584202781014677,"score_gpt":0.41534126538013316,"score_spread":0.2394992375699864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174385715","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":[0.7394337,0.00004247969,0.25655898,0.000047685546,0.00010407305,0.001120252,0.0005312348,0.000057837828,0.0021037802],"genre_scores_gemma":[0.9842955,0.000033853958,0.015562146,0.000012983464,0.000011959605,0.00004183122,0.0000059497615,0.000022490247,0.000013273141],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99875426,0.00014688916,0.00037257688,0.00012937229,0.00043235035,0.0001645237],"domain_scores_gemma":[0.99680704,0.002164672,0.0005786813,0.0003552394,0.00007218526,0.000022187107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006953872,0.0001460667,0.0003517733,0.00006250304,0.00015791511,0.000009622526,0.0002847149,0.000035488923,0.000023437435],"category_scores_gemma":[0.00021515627,0.000099657904,0.00003355506,0.00013273295,0.00019560009,0.000029801931,0.00018082737,0.00021636234,3.7669207e-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":[0.0006867533,0.00011376923,0.0014723543,0.00054493156,0.00019518043,0.00000320046,0.00079008023,0.037950113,0.0952588,0.85745484,0.00022526878,0.005304724],"study_design_scores_gemma":[0.00036851416,0.0003874432,0.002414512,0.0000937156,0.00009510558,0.000004658931,0.00025717125,0.00963583,0.44123885,0.5453765,0.0000065110835,0.00012122341],"about_ca_topic_score_codex":0.000021664317,"about_ca_topic_score_gemma":4.5187562e-7,"teacher_disagreement_score":0.34598005,"about_ca_system_score_codex":0.000021884438,"about_ca_system_score_gemma":0.00003142979,"threshold_uncertainty_score":0.40639314},"labels":[],"label_agreement":null},{"id":"W3181775732","doi":"10.1214/20-aoas1423","title":"A compositional model to assess expression changes from single-cell RNA-seq data","year":2021,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","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":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Science Foundation; National Institutes of Health; National Cancer Institute; National Institute of Dental and Craniofacial Research; University of Wisconsin-Madison","keywords":"Cluster analysis; Bayesian probability; Expression (computer science); Mixture model; Computer science; Prior probability; Hierarchical clustering; Posterior probability; Probability distribution; Computational biology; Mathematics; Data mining; Artificial intelligence; Statistics; Biology","score_opus":0.21491683278284487,"score_gpt":0.3373738237349338,"score_spread":0.12245699095208892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181775732","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":[0.3341382,0.00035946388,0.65107733,0.0008173263,0.00012633279,0.0001977992,0.010307221,0.000012809832,0.0029635031],"genre_scores_gemma":[0.8782606,0.00020423823,0.11304054,0.0022373162,0.00020748765,0.0000111816635,0.005829296,0.000030000017,0.0001793246],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990107,0.000035555073,0.00020143938,0.00034586695,0.00021693052,0.00018954348],"domain_scores_gemma":[0.9988419,0.00007122169,0.00009194018,0.00073608366,0.0001754654,0.000083393126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013251306,0.00014295081,0.00017734851,0.000017276292,0.000085896165,0.000033492754,0.00047293276,0.000086028485,0.000026411723],"category_scores_gemma":[0.000031515017,0.00012196835,0.00002731068,0.000060022314,0.000066425746,0.0000027604735,0.0003184963,0.000086923086,0.000006065211],"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":[0.00022544999,0.00021454335,0.000006627343,0.000021840182,0.00003376698,0.0000027045264,0.00012069638,0.001921194,0.9785481,0.00069268316,0.016261159,0.0019512434],"study_design_scores_gemma":[0.00028988623,0.0000815328,0.00003912231,0.000019486124,0.000028122255,8.6265385e-7,0.00008186162,0.005373984,0.9867226,0.0031365387,0.0040660216,0.00015999992],"about_ca_topic_score_codex":0.000018696617,"about_ca_topic_score_gemma":0.000066846645,"teacher_disagreement_score":0.5441224,"about_ca_system_score_codex":0.0000035125238,"about_ca_system_score_gemma":0.000087270106,"threshold_uncertainty_score":0.4973725},"labels":[],"label_agreement":null},{"id":"W3191733181","doi":"10.1214/21-aoas1501","title":"The ASA president’s task force statement on statistical significance and replicability","year":2021,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Task force; Statement (logic); Task (project management); Statistical analysis; Statistics; Computer science; Econometrics; Natural language processing; Mathematics; Political science; Law; Management; Economics","score_opus":0.5158428041741353,"score_gpt":0.5546070747217429,"score_spread":0.03876427054760756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191733181","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":[0.011356819,0.00017529243,0.96797323,0.005667308,0.00037971724,0.0019437192,0.005576773,0.00008641865,0.0068407287],"genre_scores_gemma":[0.18610907,0.0009365461,0.8101794,0.0014905841,0.00019465594,0.00023886444,0.000024251567,0.0000757114,0.0007508836],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9953939,0.0009812603,0.0015855256,0.000621802,0.00088643667,0.00053108315],"domain_scores_gemma":[0.8735695,0.12391846,0.0005614384,0.0013569982,0.0004141421,0.00017947296],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0066540404,0.00029111234,0.0007043376,0.00002070479,0.00037172934,0.00011155499,0.00046640157,0.000105157786,0.00014429659],"category_scores_gemma":[0.05931144,0.00017731966,0.00007224241,0.00018885879,0.0011372487,0.000023588424,0.00028463968,0.0004574249,0.00001908618],"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":[0.0006102726,0.00020423938,0.000014912231,0.00018435014,0.00013760234,0.000012530055,0.00024071686,0.00001912398,0.00046803715,0.9313173,0.038859095,0.027931785],"study_design_scores_gemma":[0.00046382847,0.0002302706,0.0016106653,0.00003591525,0.00010925178,0.0000020438272,0.00038576117,0.00044011284,0.008744556,0.9844792,0.0033013776,0.00019704516],"about_ca_topic_score_codex":0.000015997744,"about_ca_topic_score_gemma":0.000025311198,"teacher_disagreement_score":0.17475225,"about_ca_system_score_codex":0.00002943506,"about_ca_system_score_gemma":0.0001794265,"threshold_uncertainty_score":0.9486124},"labels":[],"label_agreement":null},{"id":"W4220666549","doi":"10.1214/21-aoas1499","title":"Bayesian adjustment for preferential testing in estimating infection fatality rates, as motivated by the COVID-19 pandemic","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"COVID-19 epidemiological studies","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":"University of British Columbia","funders":"Institute of Genetics; Canadian Institutes of Health Research; European Commission","keywords":"Coronavirus disease 2019 (COVID-19); Bayesian probability; Pandemic; Statistics; Case fatality rate; Econometrics; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Identifiability; Demography; 2019-20 coronavirus outbreak; Population; Statistical hypothesis testing; Mathematics; Geography; Actuarial science; Medicine; Economics; Virology; Sociology; Outbreak","score_opus":0.5179263313108267,"score_gpt":0.4970631588051286,"score_spread":0.02086317250569808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220666549","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":[0.15347464,0.0001215066,0.8395098,0.0019402937,0.00014004312,0.00257493,0.0017584343,0.00015189365,0.00032847215],"genre_scores_gemma":[0.9684618,0.000029327202,0.02766902,0.0027193436,0.000064420274,0.00084689056,0.00014686144,0.00002708332,0.00003522371],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9978384,0.00041258085,0.00075051805,0.0003009513,0.00032620883,0.00037134046],"domain_scores_gemma":[0.98054224,0.018348616,0.0006166311,0.00032583994,0.000099016914,0.00006765116],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003620915,0.00021093569,0.0004313167,0.000040208688,0.0006807205,0.000018113202,0.0003221796,0.00005054754,0.00007235591],"category_scores_gemma":[0.016857365,0.00013495579,0.000055882898,0.0003194343,0.0001777535,0.000022080047,0.00039221343,0.00035775575,0.0000014530782],"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":[0.002023069,0.0016693692,0.027834171,0.0025324782,0.00078185345,0.0000051488405,0.010397368,0.20358093,0.0035067725,0.44750452,0.2412989,0.058865402],"study_design_scores_gemma":[0.0007311207,0.00026180834,0.0030165457,0.0000147024275,0.00008235206,0.0000036365598,0.0005219591,0.06160468,0.0002247085,0.93078035,0.0025474923,0.00021064238],"about_ca_topic_score_codex":0.0013841816,"about_ca_topic_score_gemma":0.00016052501,"teacher_disagreement_score":0.8149872,"about_ca_system_score_codex":0.0001716923,"about_ca_system_score_gemma":0.000112851216,"threshold_uncertainty_score":0.9914241},"labels":[],"label_agreement":null},{"id":"W4221109862","doi":"10.1214/21-aoas1518","title":"Accounting for drop-out using inverse probability censoring weights in longitudinal clustered data with informative cluster size","year":2022,"lang":"en","type":"article","venue":"The Annals 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 Toronto","funders":"","keywords":"Censoring (clinical trials); Statistics; Inverse probability; Inference; Generalized estimating equation; Mathematics; Random effects model; Estimating equations; Marginal structural model; Econometrics; Causal inference; Computer science; Medicine; Estimator; Artificial intelligence; Meta-analysis","score_opus":0.16111533411320592,"score_gpt":0.35644827601533313,"score_spread":0.19533294190212722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221109862","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":[0.021621328,0.000010136175,0.9764931,0.00023467239,0.00008046503,0.00079468964,0.0003932223,0.000020995894,0.0003513717],"genre_scores_gemma":[0.22009861,0.0000031890152,0.7793494,0.00043471163,0.000028925764,0.00004111768,0.000021913433,0.0000112596035,0.000010903577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833834,0.0001228082,0.00045372656,0.00036346464,0.00036687806,0.00035477878],"domain_scores_gemma":[0.99753344,0.0009100044,0.00038646854,0.00097640173,0.00014689502,0.0000468142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002188983,0.00017072368,0.0002996118,0.00006954012,0.00030899388,0.00008107564,0.0013538988,0.00003043965,0.0000052805754],"category_scores_gemma":[0.00011341988,0.00012392133,0.000025663912,0.0002947747,0.0001112007,0.0003766797,0.0013324751,0.00025860983,7.572377e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017622787,0.0003700943,0.00045119948,0.0007444011,0.0002184071,0.000014653446,0.044143707,0.024287157,0.0005661051,0.8649769,0.0024775658,0.059987567],"study_design_scores_gemma":[0.0007216842,0.0000972458,0.00048311386,0.000025569912,0.000022657832,0.0000061939186,0.00025878742,0.77558166,0.00033723796,0.2216986,0.0005537302,0.00021350574],"about_ca_topic_score_codex":0.00003195826,"about_ca_topic_score_gemma":0.00007212636,"teacher_disagreement_score":0.7512945,"about_ca_system_score_codex":0.000040062474,"about_ca_system_score_gemma":0.00015371596,"threshold_uncertainty_score":0.5053365},"labels":[],"label_agreement":null},{"id":"W4287780226","doi":"10.1214/22-aoas1701","title":"The scalable birth–death MCMC algorithm for mixed graphical model learning with application to genomic data integration","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","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 Toronto; York University; Lunenfeld-Tanenbaum Research Institute; University of New Brunswick","funders":"National Center for Advancing Translational Sciences; National Cancer Institute","keywords":"Subtyping; Lasso (programming language); Computer science; Inference; Scalability; Biological data; Feature selection; Computational biology; Data mining; Machine learning; Artificial intelligence; Bioinformatics; Biology","score_opus":0.062091907064135005,"score_gpt":0.33707138606872744,"score_spread":0.2749794790045924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287780226","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":[0.016168114,0.000047106703,0.98189086,0.00074570463,0.00002682425,0.00051080465,0.0004318695,0.00001804407,0.00016066244],"genre_scores_gemma":[0.9283915,0.0008390281,0.065635614,0.0003568783,0.00014522173,0.00053789397,0.00312945,0.000045968896,0.0009184314],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917454,0.000025601292,0.0001894131,0.0002814026,0.00014902023,0.0001800233],"domain_scores_gemma":[0.99897784,0.000065580265,0.00012722255,0.0006205107,0.00016057499,0.000048247075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051074754,0.00010033992,0.000093964576,0.00003528685,0.00025517595,0.000032693526,0.00043237608,0.000054240463,7.7772364e-7],"category_scores_gemma":[0.000049708204,0.00006142817,0.000019203986,0.00018373183,0.00006799491,0.0000028081624,0.00013818823,0.00007600213,0.000006496711],"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":[0.0004914891,0.000035895213,0.000014685637,0.000020340643,0.00006428049,7.5185035e-8,0.0001607853,0.024686981,0.5278847,0.032206066,0.044385552,0.37004915],"study_design_scores_gemma":[0.0003651809,0.00021969306,0.00069756975,0.000008869251,0.000029745812,5.9497916e-7,0.0005387677,0.79845315,0.10427778,0.013473628,0.08175438,0.00018065465],"about_ca_topic_score_codex":0.0000058482174,"about_ca_topic_score_gemma":0.000023448018,"teacher_disagreement_score":0.91625524,"about_ca_system_score_codex":0.0000041163594,"about_ca_system_score_gemma":0.00006867328,"threshold_uncertainty_score":0.25049677},"labels":[],"label_agreement":null},{"id":"W4297333613","doi":"10.1214/22-aoas1600","title":"Bayesian hierarchical random-effects meta-analysis and design of phase I clinical trials","year":2022,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Cancer Institute","keywords":"Meta-analysis; Random effects model; Computer science; Bayesian probability; Parametric statistics; Clinical study design; Statistics; Clinical trial; Data mining; Artificial intelligence; Mathematics; Medicine","score_opus":0.8487982915840147,"score_gpt":0.6507765650971692,"score_spread":0.19802172648684546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297333613","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":[0.0005404325,0.00022199508,0.9931199,0.00052334595,0.00013046135,0.002052602,0.0030990867,0.000027868928,0.00028430484],"genre_scores_gemma":[0.1327813,0.00017256154,0.8659258,0.0005824588,0.00009444062,0.0003348166,0.000014346949,0.000042626514,0.00005167913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97383726,0.019141141,0.0048631025,0.0005736763,0.0011702421,0.0004146061],"domain_scores_gemma":[0.58672816,0.41003245,0.0020356309,0.00082668924,0.000184106,0.00019297682],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.08113342,0.00032990563,0.005871309,0.00021641643,0.00021350342,0.000025648935,0.00064381794,0.0001334861,0.0011976423],"category_scores_gemma":[0.14842562,0.00021133371,0.0013435851,0.0007714313,0.00092078623,0.00001884968,0.00038404512,0.00071768905,0.0000020043035],"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":[0.011269355,0.0021357422,0.000006429858,0.00033221723,0.1243932,0.000023065564,0.0004913687,0.0006351654,0.0005221032,0.8004571,0.0104572475,0.04927695],"study_design_scores_gemma":[0.0040500886,0.00088625704,0.000018853747,0.0000025124696,0.11489191,0.000001305729,0.00006219816,0.007649299,0.0015580802,0.87058365,0.00011077578,0.00018504856],"about_ca_topic_score_codex":0.000008131169,"about_ca_topic_score_gemma":0.0000011579832,"teacher_disagreement_score":0.3908913,"about_ca_system_score_codex":0.000007691122,"about_ca_system_score_gemma":0.00011318978,"threshold_uncertainty_score":0.9997154},"labels":[],"label_agreement":null},{"id":"W4320169867","doi":"10.1214/22-aoas1639","title":"Modeling panels of extremes","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Financial Risk and Volatility Modeling","field":"Economics, Econometrics and Finance","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":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation HEC; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Pooling; Extreme value theory; Inference; Computer science; Regression; Econometrics; Statistics; Regression analysis; Data mining; Mathematics; Machine learning; Artificial intelligence","score_opus":0.23901888810594185,"score_gpt":0.3158408307269341,"score_spread":0.07682194262099223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320169867","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":[0.5314291,0.00043710443,0.45774966,0.0002779812,0.00012185857,0.00020040602,0.0014852696,0.000040793526,0.00825783],"genre_scores_gemma":[0.995268,0.000811002,0.0036791803,0.0000632428,0.00003522013,0.0000070306232,0.000024774834,0.000015468659,0.0000961069],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989488,0.000005187586,0.0006292064,0.00015840019,0.000054747157,0.0002036444],"domain_scores_gemma":[0.99925065,0.00012859244,0.00022764599,0.00029554893,0.000070418806,0.000027121481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007718411,0.000088729954,0.00032341087,0.0001135411,0.000065138534,0.000009215589,0.00021942642,0.000047568476,0.000036394973],"category_scores_gemma":[0.00012396516,0.00008324947,0.000055331708,0.00027321538,0.000067494126,0.000031369604,0.00006266982,0.00008525779,0.00009236911],"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":[0.000041866304,0.00002500496,0.00021909155,0.00006512694,0.000025962427,3.9678673e-7,0.0014622862,0.06069091,0.00014238166,0.9310403,0.0007406198,0.0055460385],"study_design_scores_gemma":[0.000077547316,0.00001604815,0.00090834365,0.0000070121714,0.0000030994076,5.290249e-8,0.0001391057,0.4944863,0.00037878475,0.50348604,0.00043107898,0.00006658998],"about_ca_topic_score_codex":0.00017375882,"about_ca_topic_score_gemma":0.000007060684,"teacher_disagreement_score":0.46383888,"about_ca_system_score_codex":0.0000039742663,"about_ca_system_score_gemma":0.000016389238,"threshold_uncertainty_score":0.33948147},"labels":[],"label_agreement":null},{"id":"W4320176121","doi":"10.1214/22-aoas1624","title":"Regularized fingerprinting in detection and attribution of climate change with weight matrix optimizing the efficiency in scaling factor estimation","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Spatial and Panel Data Analysis","field":"Economics, Econometrics and Finance","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":"Environment and Climate Change Canada","funders":"National Science Foundation","keywords":"Covariance matrix; Mathematics; Statistics; Estimator; Matrix (chemical analysis); Linear regression; Covariance; Estimation of covariance matrices; Applied mathematics","score_opus":0.08214424114205639,"score_gpt":0.2889005372703241,"score_spread":0.20675629612826774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320176121","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":[0.85071945,0.00012935665,0.14812905,0.00021915542,0.000024010205,0.00023357343,0.00045348695,0.000010262836,0.00008167923],"genre_scores_gemma":[0.9951596,0.0007242318,0.0040177885,0.0000137742445,0.000012557871,0.000019746933,0.00004367665,0.0000070365045,0.0000015448587],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992248,0.00001588172,0.00041616967,0.00013837869,0.00004740004,0.00015738401],"domain_scores_gemma":[0.99928224,0.00017493937,0.00036056218,0.00014515084,0.000024825942,0.0000122940455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008758586,0.000072503244,0.00023038861,0.00021072746,0.00007285165,0.000020026077,0.00009354992,0.000035039466,0.000007398913],"category_scores_gemma":[0.00005529671,0.000053234104,0.00001762203,0.00062162784,0.00006488594,0.000056919787,0.000048148904,0.00008306721,0.0000054979078],"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":[0.0010356385,0.00020752792,0.074112445,0.0009175556,0.00017285149,0.000006916475,0.019377336,0.07830653,0.0029293576,0.6205073,0.000014758846,0.20241176],"study_design_scores_gemma":[0.000397054,0.000039112638,0.2392238,0.000059165846,0.000013314949,4.474534e-7,0.00029367825,0.7373252,0.001462793,0.021052508,0.000017670707,0.000115248695],"about_ca_topic_score_codex":0.00035506254,"about_ca_topic_score_gemma":0.000109052395,"teacher_disagreement_score":0.6590187,"about_ca_system_score_codex":0.000009994878,"about_ca_system_score_gemma":0.000003976501,"threshold_uncertainty_score":0.21708237},"labels":[],"label_agreement":null},{"id":"W4367598633","doi":"10.1214/22-aoas1656","title":"Robust joint modelling of left-censored longitudinal data and survival data with application to HIV vaccine studies","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and 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 British Columbia","funders":"National Institute of Allergy and Infectious Diseases","keywords":"Outlier; Estimator; Inference; Multivariate statistics; Longitudinal data; Computer science; Statistics; Human immunodeficiency virus (HIV); Longitudinal study; Data mining; Econometrics; Mathematics; Artificial intelligence; Medicine; Immunology","score_opus":0.6228817504563653,"score_gpt":0.4455431750804737,"score_spread":0.1773385753758916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367598633","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":[0.010177807,0.000064572254,0.98279333,0.00049524935,0.000023541359,0.0004227338,0.0057919286,0.00003382897,0.0001970036],"genre_scores_gemma":[0.17785399,0.00058819505,0.8210512,0.000044141336,0.000046624897,0.0000138128335,0.0003416579,0.000030974148,0.000029435125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998313,0.000061582105,0.00055905693,0.00043159872,0.00038805607,0.0002466909],"domain_scores_gemma":[0.9949387,0.002691912,0.00028398325,0.0016687572,0.0003398318,0.00007685446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018534043,0.00018018976,0.0005598362,0.0000703855,0.000094101786,0.000018766812,0.00071682135,0.000034539502,0.000009750765],"category_scores_gemma":[0.0010656769,0.000119260105,0.000009377341,0.00027779475,0.00015931224,0.00004708563,0.0009462761,0.00012178309,0.000007017228],"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":[0.0005046861,0.00012907338,0.00020516467,0.0009607365,0.00040820386,0.0000042216757,0.0015327897,0.010581255,0.00051213073,0.93956876,0.025184497,0.02040847],"study_design_scores_gemma":[0.00037970464,0.00013859858,0.001516015,0.00011170077,0.00020912397,0.0000021450116,0.0014798829,0.5156298,0.00070755923,0.4793577,0.00024089868,0.0002268679],"about_ca_topic_score_codex":0.000025454654,"about_ca_topic_score_gemma":0.000042400647,"teacher_disagreement_score":0.5050486,"about_ca_system_score_codex":0.000004531132,"about_ca_system_score_gemma":0.00003557109,"threshold_uncertainty_score":0.48632857},"labels":[],"label_agreement":null},{"id":"W4367598648","doi":"10.1214/22-aoas1675","title":"Mixed-frequency extreme value regression: Estimating the effect of mesoscale convective systems on extreme rainfall intensity","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Hydrology and Drought Analysis","field":"Environmental Science","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":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Fondation HEC","keywords":"Extreme value theory; Flash flood; Mesoscale meteorology; Generalized extreme value distribution; Maxima; Environmental science; Climatology; Intensity (physics); Covariate; Statistics; Mesoscale convective system; Regression analysis; Meteorology; Flood myth; Geography; Mathematics; Geology","score_opus":0.06433382728355574,"score_gpt":0.29693473832307515,"score_spread":0.2326009110395194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367598648","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":[0.95703334,0.00008291645,0.021035872,0.000890197,0.00034916692,0.0008149393,0.00020078846,0.00007985089,0.019512922],"genre_scores_gemma":[0.99828136,0.000016714366,0.0012363178,0.00015773514,0.000042767522,0.00003347467,0.000023007651,0.000014315432,0.00019432089],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831116,0.00028709823,0.0003994532,0.00026009622,0.00045409985,0.00028811072],"domain_scores_gemma":[0.99720985,0.0017779515,0.00037630153,0.00054587494,0.000034726294,0.000055311328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001992907,0.00019140508,0.00043378244,0.000043487693,0.00026591934,0.0000117923355,0.00044489704,0.00008290796,0.00012371693],"category_scores_gemma":[0.0003531744,0.00010061278,0.00008652558,0.000452911,0.0007031616,0.000032851596,0.00019712083,0.0002274557,0.0002080715],"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":[0.002681953,0.0002939192,0.023160327,0.0005565424,0.0013507555,0.000116097035,0.013960602,0.61649835,0.040962804,0.12212513,0.14881611,0.029477434],"study_design_scores_gemma":[0.0012450514,0.0013578538,0.044685166,0.00024762427,0.0006054122,0.000015045635,0.0013107762,0.7780538,0.050747342,0.12054952,0.0005256217,0.0006567376],"about_ca_topic_score_codex":0.00031388682,"about_ca_topic_score_gemma":0.00003280907,"teacher_disagreement_score":0.16155551,"about_ca_system_score_codex":0.000021146212,"about_ca_system_score_gemma":0.000009709378,"threshold_uncertainty_score":0.410287},"labels":[],"label_agreement":null},{"id":"W4386514870","doi":"10.1214/23-aoas1729","title":"A Bayesian growth mixture model for complex survey data: Clustering postdisaster PTSD trajectories","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Statistical Methods and Bayesian 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":false,"ca_institutions":"University of Waterloo","funders":"National Institute of Environmental Health Sciences; National Institute on Aging; National Institutes of Health","keywords":"Computer science; Mixture model; Statistics; Cluster analysis; Bayesian probability; Artificial intelligence; Data mining; Mathematics","score_opus":0.41289666394850244,"score_gpt":0.45495789631561145,"score_spread":0.042061232367109014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386514870","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":[0.00036397163,0.0000064573296,0.9718457,0.0002942909,0.00008575347,0.0005735796,0.026053501,0.00008101626,0.0006957325],"genre_scores_gemma":[0.14894639,0.000033858523,0.8494669,0.00029599003,0.000086227985,0.00005057695,0.00095579535,0.000060024,0.000104245955],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99806565,0.00013023916,0.00059879315,0.00037188028,0.00035352027,0.0004799351],"domain_scores_gemma":[0.99111897,0.007338848,0.0002576193,0.0008451558,0.00033819175,0.00010124148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019617735,0.00025945177,0.00054078957,0.00007307236,0.00019459432,0.00006958332,0.0008029612,0.000092205264,0.00003681942],"category_scores_gemma":[0.0023380804,0.00018951329,0.000047547208,0.0003254889,0.00023874857,0.00005932244,0.0003168543,0.0001722209,0.000009204408],"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":[0.00043231552,0.00007294274,0.00003127185,0.0006513505,0.00012030333,0.0000025781326,0.0025137612,0.00012442365,0.00045002543,0.89739084,0.08893364,0.009276544],"study_design_scores_gemma":[0.00019614314,0.000043551103,0.00084658887,0.000018890607,0.0000421202,7.730723e-7,0.00019117392,0.39718547,0.00010737372,0.6011561,0.00005755174,0.00015424767],"about_ca_topic_score_codex":0.000051722403,"about_ca_topic_score_gemma":0.0002809113,"teacher_disagreement_score":0.39706105,"about_ca_system_score_codex":0.0000074898953,"about_ca_system_score_gemma":0.00007398193,"threshold_uncertainty_score":0.7728127},"labels":[],"label_agreement":null},{"id":"W4388054702","doi":"10.1214/23-aoas1776","title":"Continuous-time modelling of behavioural responses in animal movement","year":2023,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Marine animal studies overview","field":"Environmental Science","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":"Dalhousie University","funders":"Bureau of Medicine and Surgery; National Marine Fisheries Service; U.S. Department of Defense; U.S. Fleet Forces Command; Office of Naval Research; U.S. Navy","keywords":"Baseline (sea); Nonparametric statistics; Computer science; Covariate; Stochastic modelling; Sound exposure; Statistics; Machine learning; Mathematics","score_opus":0.13857183501729953,"score_gpt":0.31002161568547715,"score_spread":0.17144978066817762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388054702","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":[0.9918398,0.000025460202,0.00056324125,0.00019651339,0.000009558359,0.00024762182,0.000200645,0.000016490465,0.0069006374],"genre_scores_gemma":[0.99670047,0.00022135637,0.0025352167,0.00018439669,0.000005971212,0.000016217326,0.000009671573,0.00001170348,0.000315017],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99891096,0.000033759872,0.0003544404,0.00014537464,0.00031782186,0.0002376422],"domain_scores_gemma":[0.99937016,0.00023996257,0.00015434202,0.0001906642,0.000016302016,0.000028592014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006372123,0.000102086145,0.0002381237,0.000031744887,0.000046348094,0.0000051918473,0.00023979228,0.0000234814,0.0004213406],"category_scores_gemma":[0.00003287011,0.000080871236,0.00002961628,0.0002654108,0.00018969203,0.00002320613,0.00037672036,0.00007564111,0.00014365294],"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":[0.008666168,0.0017164679,0.2307207,0.0005989735,0.00039181393,0.00014139981,0.016476342,0.24739961,0.102059856,0.14842328,0.13266665,0.11073872],"study_design_scores_gemma":[0.00073684234,0.0005905165,0.87166345,0.000050853774,0.000054103843,6.3679835e-7,0.0009635003,0.06908851,0.015172698,0.039349444,0.0019115863,0.00041787222],"about_ca_topic_score_codex":0.0015324684,"about_ca_topic_score_gemma":0.00019646449,"teacher_disagreement_score":0.64094275,"about_ca_system_score_codex":0.000015788886,"about_ca_system_score_gemma":0.0000069525754,"threshold_uncertainty_score":0.4613384},"labels":[],"label_agreement":null},{"id":"W4391418111","doi":"10.1214/23-aoas1795","title":"Network-level traffic flow prediction: Functional time series vs. functional neural network approach","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Traffic Prediction and Management Techniques","field":"Engineering","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 Toronto","funders":"","keywords":"Time series; Computer science; Series (stratigraphy); Artificial neural network; Traffic flow (computer networking); Artificial intelligence; Machine learning; Geology; Computer network","score_opus":0.045327854834515825,"score_gpt":0.2309017812429498,"score_spread":0.18557392640843398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391418111","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":[0.00030130646,0.0004864441,0.9760524,0.00030236717,0.0013498592,0.00039130394,0.00089102075,0.00406791,0.016157404],"genre_scores_gemma":[0.9410669,0.00063643756,0.05022205,0.0007463479,0.0034353023,0.00027211817,0.0017433189,0.00013663861,0.001740847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864155,0.000023535102,0.00038307687,0.00023119384,0.00036500374,0.00035566854],"domain_scores_gemma":[0.99945706,0.0001233514,0.000041590476,0.00024484337,0.000063988504,0.000069175934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038279674,0.00023584224,0.00022627557,0.00007237021,0.00018316339,0.00008390478,0.00016738907,0.00009465709,0.00019865458],"category_scores_gemma":[0.0000055264695,0.00019866426,0.000073122115,0.00036325242,0.00014025035,0.00012331519,0.000053813965,0.00030791355,0.000070453745],"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":[0.00006552333,0.000012065612,7.1301406e-7,0.00006815075,0.000110688285,0.0000011972288,0.000045498968,0.4821236,0.000009775099,0.04163096,0.46232548,0.01360633],"study_design_scores_gemma":[0.0001257302,0.00006218448,0.0013265669,0.000024986894,0.00007632868,0.000012243891,0.000028506654,0.92171913,0.00001957558,0.00583454,0.07059396,0.00017623171],"about_ca_topic_score_codex":6.7393285e-7,"about_ca_topic_score_gemma":0.0000017483317,"teacher_disagreement_score":0.9407656,"about_ca_system_score_codex":0.000020213927,"about_ca_system_score_gemma":0.000027882352,"threshold_uncertainty_score":0.81012934},"labels":[],"label_agreement":null},{"id":"W4393975851","doi":"10.1214/23-aoas1854","title":"How are PreLaunch online movie reviews related to box office revenues?","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Digital Marketing and Social Media","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; York University","funders":"","keywords":"Box office; Revenue; Advertising; Computer science; Business; Data science; Accounting","score_opus":0.08587048036631538,"score_gpt":0.382266476417505,"score_spread":0.2963959960511896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393975851","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13519272,0.032311484,0.0075540305,0.15943919,0.0054386323,0.0072825076,0.009827205,0.0011707905,0.6417834],"genre_scores_gemma":[0.94384867,0.01014538,0.007316721,0.0025883566,0.0008633082,0.000085718406,0.00013447525,0.00007382309,0.034943573],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99856037,0.00018436652,0.00031368286,0.00020856598,0.0004264421,0.00030659494],"domain_scores_gemma":[0.99838984,0.0009187504,0.00016534248,0.00023869496,0.00014794587,0.00013941384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019416454,0.00012710017,0.00029697275,0.00004822139,0.00021019757,0.00018094778,0.0003557412,0.000086842796,0.000030744854],"category_scores_gemma":[0.0029697164,0.00009765818,0.000067828885,0.0005499731,0.0002459381,0.00006373096,0.0000614444,0.00022474503,0.000117419],"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":[0.00006610011,0.0000835565,0.000012630124,0.0002569453,0.00006098577,0.000011603923,0.02167914,0.000011388751,0.0000706384,0.34561962,0.36376867,0.2683587],"study_design_scores_gemma":[0.00004676358,0.000040944004,0.00043391326,0.00033729078,0.00003699903,2.1588511e-7,0.0037698455,0.000019854273,0.000029576591,0.06892676,0.92620426,0.00015357071],"about_ca_topic_score_codex":0.00006884707,"about_ca_topic_score_gemma":0.00022418227,"teacher_disagreement_score":0.8086559,"about_ca_system_score_codex":0.000022213284,"about_ca_system_score_gemma":0.00012051518,"threshold_uncertainty_score":0.3982385},"labels":[],"label_agreement":null},{"id":"W4394006165","doi":"10.1214/23-aoas1825","title":"A population-aware retrospective regression to detect genome-wide variants with sex difference in allele frequency","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Hospital for Sick Children","funders":"","keywords":"Allele; Allele frequency; Regression; Genetics; Regression analysis; Population; Genome; Biology; Computer science; Medicine; Statistics; Gene; Machine learning; Mathematics; Environmental health","score_opus":0.02478594328100024,"score_gpt":0.3053104523246091,"score_spread":0.28052450904360887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394006165","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":[0.86848384,0.0002591951,0.12922369,0.000491247,0.00003813407,0.00033859586,0.00034346024,0.000011651542,0.0008101995],"genre_scores_gemma":[0.98559815,0.00015178778,0.013457699,0.00031122574,0.000049172144,0.000038819802,0.00019949437,0.000017298884,0.00017634981],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990834,0.000057418,0.00024816513,0.00027535504,0.00011767371,0.00021797373],"domain_scores_gemma":[0.99942356,0.00009237308,0.000086858665,0.000269475,0.00008026363,0.00004747863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032477514,0.00012732415,0.00020666991,0.000050714814,0.000058002788,0.000013761279,0.00015868944,0.000087735825,0.00001654078],"category_scores_gemma":[0.00014342794,0.00008490018,0.000023601986,0.00016371798,0.000044013206,0.0000013391311,0.00006372763,0.00010591047,0.000006444675],"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":[0.0017021617,0.00038393127,0.50042355,0.0005187063,0.0013370279,0.000085064894,0.0069768215,0.019111728,0.30524838,0.06568961,0.032406233,0.06611675],"study_design_scores_gemma":[0.0001404603,0.00029874436,0.95228803,0.000029069903,0.000015940353,0.0000019546299,0.00010689317,0.0004650108,0.001598271,0.044638705,0.00026145135,0.00015545408],"about_ca_topic_score_codex":0.00016743816,"about_ca_topic_score_gemma":0.00045942937,"teacher_disagreement_score":0.45186448,"about_ca_system_score_codex":0.00001687714,"about_ca_system_score_gemma":0.000056128603,"threshold_uncertainty_score":0.3462129},"labels":[],"label_agreement":null},{"id":"W4401373758","doi":"10.1214/24-aoas1877","title":"Probabilistic contrastive dimension reduction for case-control study data","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"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 Center for Advancing Translational Sciences; National Human Genome Research Institute; National Heart, Lung, and Blood Institute; Canadian Institute for Advanced Research; National Cancer Institute; National Science Foundation; National Institutes of Health; National Institute of Environmental Health Sciences; Leona M. and Harry B. Helmsley Charitable Trust","keywords":"Dimensionality reduction; Dimension (graph theory); Reduction (mathematics); Probabilistic logic; Computer science; Statistics; Data reduction; Artificial intelligence; Natural language processing; Mathematics","score_opus":0.08856121255749513,"score_gpt":0.37194932954972393,"score_spread":0.28338811699222877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401373758","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":[0.23020299,0.0015331621,0.75226665,0.0010802685,0.0008453505,0.0047247065,0.008618321,0.000053964563,0.000674581],"genre_scores_gemma":[0.9980373,0.000052524312,0.0010934346,0.00007208587,0.00018199066,0.0001256611,0.00030858346,0.000017054674,0.00011138819],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991999,0.000041730156,0.00021313077,0.00031882327,0.00010573591,0.00012062742],"domain_scores_gemma":[0.9991201,0.000089131994,0.00007988784,0.0005367504,0.00014213423,0.000031967633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047498438,0.0000977247,0.00011326862,0.000025373478,0.00008625281,0.000026351714,0.0001815156,0.00004429366,0.000007841327],"category_scores_gemma":[0.00009952002,0.00006927795,0.000022011614,0.00006896704,0.00007434025,0.0000028777547,0.00006112267,0.00005496619,0.0000023978034],"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":[0.0023296045,0.00047708562,0.000010314347,0.00026239216,0.0006118977,0.000019145491,0.0012062306,0.0015507472,0.66042405,0.0316538,0.16078113,0.14067361],"study_design_scores_gemma":[0.010005459,0.008310993,0.004756493,0.00026682296,0.0028906942,0.00049478933,0.023618197,0.16095485,0.51479435,0.10510166,0.16654833,0.00225735],"about_ca_topic_score_codex":0.0000056581057,"about_ca_topic_score_gemma":0.00000907161,"teacher_disagreement_score":0.7678343,"about_ca_system_score_codex":0.00000403731,"about_ca_system_score_gemma":0.000072051196,"threshold_uncertainty_score":0.28250727},"labels":[],"label_agreement":null},{"id":"W4403577681","doi":"10.1214/25-aoas2115","title":"K-contact distance for noisy nonhomogeneous spatial point data with application to repeating fast radio burst sources","year":2024,"lang":"en","type":"preprint","venue":"The Annals of Applied Statistics","topic":"Robotics and Sensor-Based Localization","field":"Engineering","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":"McGill University; York University; McGill University Health Centre; Simon Fraser University; Canadian Institute for Theoretical Astrophysics","funders":"Smithsonian Astrophysical Observatory; University of Toronto","keywords":"Point (geometry); Computer science; Algorithm; Mathematics; Geometry","score_opus":0.032036673803525095,"score_gpt":0.28131462166736615,"score_spread":0.24927794786384105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403577681","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":[0.0028201675,0.00023148613,0.9858149,0.00022291776,0.00020505325,0.0014335053,0.008582038,0.00012526476,0.0005646131],"genre_scores_gemma":[0.9220634,0.00015296036,0.0731816,0.00010588448,0.00041637357,0.00021285981,0.0036618456,0.00015991564,0.000045172703],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982795,0.000014668927,0.00056277495,0.00052083284,0.0003202981,0.00030191315],"domain_scores_gemma":[0.99796146,0.00022131513,0.00021862502,0.0013229117,0.00018562305,0.0000900691],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036001796,0.00034633343,0.0004646546,0.00008297738,0.00009967634,0.00012897974,0.00066856854,0.00012519688,0.000004591189],"category_scores_gemma":[0.00004522606,0.0002784322,0.00004571842,0.00013415793,0.00005384343,0.000017345445,0.00034380262,0.00031183838,0.000012293468],"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":[0.00017809983,0.000021889113,0.0000055517744,0.0011987495,0.00020963344,0.0000033538913,0.0007952077,0.9483474,0.0007424483,0.017727299,0.0035011831,0.027269166],"study_design_scores_gemma":[0.00017028922,0.00008872263,0.000062495295,0.00023349868,0.00019700355,0.0000023683858,0.00014556502,0.980224,0.0039926465,0.011773945,0.002694607,0.00041485843],"about_ca_topic_score_codex":0.0001426541,"about_ca_topic_score_gemma":0.00032459488,"teacher_disagreement_score":0.9192432,"about_ca_system_score_codex":0.000041308,"about_ca_system_score_gemma":0.00006805183,"threshold_uncertainty_score":0.9999668},"labels":[],"label_agreement":null},{"id":"W4403924989","doi":"10.1214/24-aoas1917","title":"Statistical curve models for inferring 3D chromatin architecture","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","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 Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; University of Toronto; National Institutes of Health; National Science Foundation","keywords":"Computer science; Architecture; Artificial intelligence; Natural language processing; Computational biology; Geography; Biology; Archaeology","score_opus":0.030417245872816058,"score_gpt":0.30504001709156947,"score_spread":0.2746227712187534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403924989","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":[0.041953035,0.00038491157,0.9515187,0.00015581187,0.00009269425,0.00034609233,0.0031882387,0.000017513696,0.0023430006],"genre_scores_gemma":[0.88445634,0.00016111229,0.11408628,0.00023728237,0.00016035548,0.00005521365,0.00069394417,0.00004524101,0.000104260595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990627,0.000017968969,0.00029083397,0.00024422936,0.0001307303,0.00025351896],"domain_scores_gemma":[0.9993212,0.00016140449,0.00007328324,0.00030583228,0.00008307878,0.000055192206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028149984,0.00016195813,0.00018242859,0.000032314347,0.00007684976,0.000048023037,0.00023007457,0.00008579425,0.000012826886],"category_scores_gemma":[0.000048898517,0.0001247707,0.00005436942,0.000056306326,0.00012801125,0.0000017160561,0.00010193231,0.0001078856,0.000004675394],"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":[0.00023203004,0.00007071686,0.0000033831473,0.00069142564,0.00032093882,0.00000474415,0.0007026864,0.064275935,0.077183805,0.79183966,0.016811917,0.04786274],"study_design_scores_gemma":[0.00040258485,0.00042035664,0.0001552004,0.00005477744,0.00009750753,0.000015210883,0.00014677168,0.4267308,0.025336001,0.5260518,0.020149065,0.00043986228],"about_ca_topic_score_codex":0.000007314662,"about_ca_topic_score_gemma":0.0000175541,"teacher_disagreement_score":0.8425033,"about_ca_system_score_codex":0.0000050101935,"about_ca_system_score_gemma":0.00009408792,"threshold_uncertainty_score":0.50880015},"labels":[],"label_agreement":null},{"id":"W4403925054","doi":"10.1214/24-aoas1933","title":"Learning risk preferences in Markov decision processes: An application to the fourth down decision in the national football league","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","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 Toronto; University of British Columbia","funders":"","keywords":"Football; League; Computer science; Artificial intelligence; Econometrics; Economics; Political science","score_opus":0.0637202319053105,"score_gpt":0.3171072281836259,"score_spread":0.2533869962783154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403925054","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":[0.6617839,0.0009889831,0.32273966,0.0014827714,0.00014607521,0.0010080232,0.00079295045,0.000022786531,0.0110349115],"genre_scores_gemma":[0.9947368,0.0021943862,0.002446228,0.00036090304,0.00008620872,0.00008739874,0.00004232266,0.000012771891,0.00003298056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987256,0.000018962377,0.0005993503,0.00029033478,0.00017807817,0.00018770559],"domain_scores_gemma":[0.9984988,0.00089942984,0.00023510033,0.00024382264,0.00009392377,0.000028916482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031783911,0.0001197598,0.00019646632,0.00028041555,0.00013810914,0.00015457624,0.000540641,0.000050837694,0.000048732127],"category_scores_gemma":[0.0003073313,0.00007130031,0.000027837848,0.00078982126,0.000049812657,0.000093108814,0.000054728207,0.0002978133,0.00007764956],"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":[0.00024892177,0.00015011462,0.0104872,0.00009503152,0.000034632143,0.0000016037441,0.0096679665,0.25390455,0.000004283998,0.44144124,0.0052443547,0.2787201],"study_design_scores_gemma":[0.00016273635,0.000131624,0.09460575,0.000061949584,0.000007404969,0.0000010329608,0.00075986865,0.29199898,0.000012714284,0.55770457,0.054379944,0.00017339535],"about_ca_topic_score_codex":0.00033828767,"about_ca_topic_score_gemma":0.0017888751,"teacher_disagreement_score":0.33295295,"about_ca_system_score_codex":0.000022333339,"about_ca_system_score_gemma":0.00006284786,"threshold_uncertainty_score":0.29075423},"labels":[],"label_agreement":null},{"id":"W4403936075","doi":"10.1214/24-aoas1942","title":"Learning brain connectivity in social cognition with dynamic network regression","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","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 Toronto","funders":"","keywords":"Cognition; Regression; Cognitive psychology; Artificial intelligence; Regression analysis; Psychology; Computer science; Machine learning; Neuroscience","score_opus":0.06496974438133032,"score_gpt":0.3407465099376238,"score_spread":0.2757767655562935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403936075","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":[0.86189413,0.0002785026,0.07579194,0.032838292,0.0005470377,0.0012999248,0.00053733925,0.00041817277,0.026394658],"genre_scores_gemma":[0.9980462,0.000046837984,0.0003260656,0.0012815783,0.000097892334,0.00003275627,0.000011566544,0.000021787191,0.00013528143],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99880886,0.00016716389,0.00017148012,0.00030326965,0.00030310682,0.00024613107],"domain_scores_gemma":[0.9894131,0.010328606,0.00009517974,0.000093855284,0.00004953895,0.00001970944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063372654,0.00013478083,0.00019571219,0.00006719528,0.0003269474,0.00004131855,0.00010445634,0.000042035346,0.000017296334],"category_scores_gemma":[0.001482443,0.00009257391,0.000025257674,0.00048768029,0.0002752502,0.00006056425,0.00007248986,0.00035950856,0.000017560282],"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":[0.00249833,0.0002298221,0.00022195122,0.00045823632,0.00012070417,0.00012341386,0.0058398927,0.023572208,0.060873885,0.75055647,0.077933125,0.07757196],"study_design_scores_gemma":[0.0013148994,0.0010621138,0.024417667,0.0006196158,0.000093777286,0.000030556446,0.0017085413,0.08121446,0.02759512,0.8491829,0.0119233,0.0008370611],"about_ca_topic_score_codex":0.0000063141138,"about_ca_topic_score_gemma":0.00007495478,"teacher_disagreement_score":0.1361521,"about_ca_system_score_codex":0.000020413901,"about_ca_system_score_gemma":0.000050756902,"threshold_uncertainty_score":0.37750545},"labels":[],"label_agreement":null},{"id":"W4403936079","doi":"10.1214/24-aoas1943","title":"Modeling trajectories using functional linear differential equations","year":2024,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Control Systems and Identification","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Neurological Disorders and Stroke; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Applied mathematics; Mathematics; Computer science","score_opus":0.10356006756529802,"score_gpt":0.30158981968118304,"score_spread":0.19802975211588503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403936079","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":[0.041967098,0.0003453055,0.9565164,0.0000227212,0.0004857159,0.00010233836,0.00020972456,0.000085371,0.00026532073],"genre_scores_gemma":[0.99846315,0.000033369895,0.0010706794,0.0000052475925,0.00029150402,0.000011261483,0.00005570802,0.000018552222,0.000050543484],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999442,0.000006820337,0.00022687313,0.000075927506,0.0001484686,0.00009990124],"domain_scores_gemma":[0.9996824,0.00010006631,0.00001642911,0.0001163928,0.00006514736,0.000019529694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010864912,0.00007436936,0.00009915537,0.00004902308,0.00006761551,0.000049468046,0.00005741336,0.000027763544,0.00004081504],"category_scores_gemma":[0.000012881314,0.00005933628,0.000030590745,0.000099604484,0.000020672285,0.000038107893,0.000009093927,0.000079125435,0.000015377775],"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":[0.000010090919,0.000006393538,3.7410408e-7,0.000104446946,0.000079163685,2.505073e-7,0.00039848321,0.8309853,0.027304817,0.13753733,0.00075813365,0.0028151863],"study_design_scores_gemma":[0.000043980046,0.000003788169,0.000035531786,0.000017453025,0.00003463299,3.9673964e-7,0.000073582196,0.9908688,0.00085936615,0.0077418485,0.00025914586,0.00006146167],"about_ca_topic_score_codex":0.000033574288,"about_ca_topic_score_gemma":0.000014272842,"teacher_disagreement_score":0.95649606,"about_ca_system_score_codex":0.000010192891,"about_ca_system_score_gemma":0.00002019173,"threshold_uncertainty_score":0.24196632},"labels":[],"label_agreement":null},{"id":"W4403936291","doi":"10.1214/24-aoas1915","title":"Multisite disease analytics with applications to estimating COVID-19 undetected cases in Canada","year":2024,"lang":"en","type":"article","venue":"The Annals 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":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria; Simon Fraser University","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Analytics; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Data science; Pandemic; Computer science; Disease; Medicine; Infectious disease (medical specialty); Virology; Outbreak","score_opus":0.34565989660508173,"score_gpt":0.4734745204622825,"score_spread":0.12781462385720077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403936291","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":[0.02178525,0.00019990627,0.96861476,0.005536334,0.000032544172,0.0012801373,0.002237019,0.00010957795,0.00020446436],"genre_scores_gemma":[0.87201434,0.00003509696,0.12436093,0.0031608255,0.000045804856,0.0002895535,0.000029789984,0.00002925221,0.000034427238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983468,0.00006670857,0.0005471419,0.0003399981,0.0003490616,0.0003503062],"domain_scores_gemma":[0.9856203,0.013378733,0.00014878552,0.00044284615,0.00010770406,0.00030159432],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000580927,0.00021646779,0.00041431017,0.00008936324,0.00016683576,0.000029251014,0.00028811867,0.00002818744,0.00003367481],"category_scores_gemma":[0.004472071,0.00014131109,0.000030722495,0.00070387486,0.00014217687,0.000018177787,0.00014680049,0.00019711301,0.00000849912],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005221132,0.00016327313,0.0031153255,0.0028598164,0.00036102088,0.00040624692,0.0013707721,0.17373599,0.00005435254,0.7479241,0.052474834,0.017012142],"study_design_scores_gemma":[0.0003961986,0.00012628706,0.009663935,0.00022917977,0.00030718496,0.000006995689,0.0012160814,0.16771854,0.00009805453,0.80655897,0.013021424,0.0006571581],"about_ca_topic_score_codex":0.1974391,"about_ca_topic_score_gemma":0.6416392,"teacher_disagreement_score":0.8502291,"about_ca_system_score_codex":0.000288576,"about_ca_system_score_gemma":0.0008730949,"threshold_uncertainty_score":0.8079052},"labels":[],"label_agreement":null},{"id":"W4408584528","doi":"10.1214/24-aoas1914","title":"Leveraging cellphone-derived mobility networks to assess Covid-19 travel risk","year":2025,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","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 Toronto; University of Guelph","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Computer science; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Geography; Data science; Econometrics; Mathematics; Medicine; Virology","score_opus":0.11589663114758272,"score_gpt":0.4026240938907544,"score_spread":0.2867274627431716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408584528","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":[0.042825412,0.000053291657,0.9456875,0.0026351335,0.00008643231,0.00050542713,0.00016889491,0.000042748245,0.007995207],"genre_scores_gemma":[0.99383694,0.00019001124,0.001846499,0.0036289473,0.00007155151,0.000049496433,0.0000280177,0.0000074123545,0.00034113132],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982346,0.00036695972,0.00041103835,0.00029520947,0.00035778605,0.00033435112],"domain_scores_gemma":[0.99683326,0.0020507597,0.00019148948,0.000468748,0.00025232657,0.0002033865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033617427,0.0001319689,0.0002946737,0.00009158056,0.0010591457,0.00007696663,0.0005129855,0.00008254684,0.00025894147],"category_scores_gemma":[0.0010310321,0.00011579341,0.000077291545,0.0007034961,0.0005025817,0.000027220278,0.00006650759,0.00022118856,0.000015262494],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042429793,0.0005647958,0.0019135836,0.00021881437,0.0004398105,0.0000028554055,0.08344149,0.3845469,0.0006405325,0.40992996,0.03729506,0.0805819],"study_design_scores_gemma":[0.0012671063,0.00013574901,0.056899603,0.000074606054,0.00075471407,1.249334e-7,0.12684058,0.08351671,0.004586045,0.67408454,0.050691187,0.0011490282],"about_ca_topic_score_codex":0.010655655,"about_ca_topic_score_gemma":0.0074626217,"teacher_disagreement_score":0.95101154,"about_ca_system_score_codex":0.000077653116,"about_ca_system_score_gemma":0.0006064485,"threshold_uncertainty_score":0.99593246},"labels":[],"label_agreement":null},{"id":"W4408584779","doi":"10.1214/24-aoas1964","title":"A three-state coupled Markov switching model for COVID-19 outbreaks across Quebec based on hospital admissions","year":2025,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"COVID-19 epidemiological studies","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":true,"ca_institutions":"McGill University","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Outbreak; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Markov chain; Markov model; Statistics; State (computer science); Geography; Computer science; Econometrics; Virology; Medicine; Mathematics; Algorithm; Infectious disease (medical specialty)","score_opus":0.25073335402443636,"score_gpt":0.47628581849535473,"score_spread":0.22555246447091837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408584779","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":[0.008930438,0.000034978868,0.9701421,0.016479373,0.000070320195,0.0015499451,0.002312441,0.0001282769,0.00035210996],"genre_scores_gemma":[0.831948,0.00006427603,0.1432702,0.023287013,0.000056759443,0.0005911856,0.000068443966,0.000060787588,0.0006533493],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9976274,0.00006146231,0.00085657305,0.0004661459,0.00035585935,0.00063260744],"domain_scores_gemma":[0.9796067,0.01867719,0.0004927854,0.0007263509,0.0002481481,0.0002488151],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0022468192,0.00036744826,0.0008022925,0.0000670226,0.00065864576,0.000045300974,0.0005795845,0.00012491507,0.000027088261],"category_scores_gemma":[0.017454341,0.000244935,0.00018663045,0.0002175467,0.00022096203,0.000023992883,0.0002819496,0.00030450404,0.000004490496],"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":[0.0028089804,0.0008542431,0.00017406174,0.0015177701,0.00042971066,0.000006921042,0.0050180885,0.10247924,0.00023951243,0.7004051,0.17035635,0.015709978],"study_design_scores_gemma":[0.0006141143,0.00008039689,0.00024363182,0.00004349174,0.00005396401,4.3972566e-8,0.000185267,0.48675084,0.000056479596,0.51073176,0.0010755667,0.00016443257],"about_ca_topic_score_codex":0.0007725967,"about_ca_topic_score_gemma":0.0030669547,"teacher_disagreement_score":0.82687193,"about_ca_system_score_codex":0.00011376898,"about_ca_system_score_gemma":0.0005712711,"threshold_uncertainty_score":0.998816},"labels":[],"label_agreement":null},{"id":"W4408585636","doi":"10.1214/24-aoas1958","title":"Poisson cluster process models for detecting ultra-diffuse galaxies","year":2025,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","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 Waterloo; University of Toronto","funders":"","keywords":"Computer science; Cluster (spacecraft); Poisson distribution; Statistical physics; Statistics; Mathematics; Physics","score_opus":0.05633146807322464,"score_gpt":0.34934960217812083,"score_spread":0.2930181341048962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408585636","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":[0.0008778773,0.00008776939,0.9929473,0.0010896573,0.00010290567,0.00047243945,0.000051219275,0.000055508644,0.0043153623],"genre_scores_gemma":[0.47606134,0.000027847555,0.5229937,0.0006736569,0.000025546244,0.000058642516,0.0000024185522,0.000009430526,0.00014741054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99887264,0.000043744505,0.00032297135,0.00027475206,0.00018263931,0.00030327885],"domain_scores_gemma":[0.99824333,0.0007877488,0.00017099023,0.00049752643,0.00025634415,0.000044043274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008319571,0.00015453275,0.00025334643,0.00007791069,0.00018397706,0.00008453341,0.0007890146,0.000063367,0.0000010290836],"category_scores_gemma":[0.00010521674,0.00011236085,0.000052507792,0.00025486026,0.00007602385,0.00010808124,0.00006278367,0.0001298819,0.0000010107888],"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":[0.00007106003,0.000044966433,0.0000015780959,0.00017231677,0.000035796933,2.6116265e-7,0.001938158,0.0010974624,0.00083969434,0.90894496,0.001996434,0.08485731],"study_design_scores_gemma":[0.00027586997,0.000034338176,0.000030129722,0.000025388785,0.00001560688,6.3357305e-7,0.000049133076,0.18539885,0.03805694,0.7758914,0.0001200495,0.00010164037],"about_ca_topic_score_codex":0.0000062860095,"about_ca_topic_score_gemma":0.000004903586,"teacher_disagreement_score":0.47518346,"about_ca_system_score_codex":0.0000061518417,"about_ca_system_score_gemma":0.00007946326,"threshold_uncertainty_score":0.45819426},"labels":[],"label_agreement":null},{"id":"W4410804643","doi":"10.1214/24-aoas2009","title":"A privacy-preserved and high-utility synthesis strategy for risk-based stratified subgroups of the Canadian scleroderma patient registry data","year":2025,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"Medicine; Data science; Family medicine; Computer science","score_opus":0.11185211933707181,"score_gpt":0.31742714614673184,"score_spread":0.20557502680966003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410804643","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":[0.12845129,0.00024511648,0.80191976,0.032434985,0.00023059969,0.0023190386,0.033286646,0.00016645151,0.00094612513],"genre_scores_gemma":[0.85400826,0.000040920557,0.14559284,0.00020571875,0.000005836964,0.000050734245,0.00008273478,0.000009141224,0.000003811285],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979508,0.00015743326,0.0005672491,0.0005641302,0.00036069733,0.000399688],"domain_scores_gemma":[0.9822645,0.0020892452,0.00056790735,0.014739179,0.00026029648,0.000078853656],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0013299471,0.00020869345,0.00034505813,0.00009977149,0.00039335687,0.00013192391,0.025383718,0.00013802324,0.0000049214655],"category_scores_gemma":[0.017691744,0.0001464975,0.000038237104,0.00045681655,0.0006526476,0.00013382954,0.019470837,0.00028606792,4.0831682e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033160238,0.00027348535,0.0015136431,0.0008449687,0.00035318255,0.0000034148982,0.00021406656,0.0007141818,0.0007576522,0.34628636,0.4721595,0.17654794],"study_design_scores_gemma":[0.00028801858,0.000053506614,0.026663478,0.00008220294,0.00006379693,3.058801e-7,0.00008424771,0.2496885,0.029591493,0.69271153,0.0005947034,0.00017821383],"about_ca_topic_score_codex":0.019080957,"about_ca_topic_score_gemma":0.033081707,"teacher_disagreement_score":0.72555697,"about_ca_system_score_codex":0.000028102453,"about_ca_system_score_gemma":0.0008313778,"threshold_uncertainty_score":0.99058264},"labels":[],"label_agreement":null},{"id":"W4417045360","doi":"10.1214/25-aoas2106","title":"Statistical learning of trade credit insurance network data with applications to ratemaking and reserving","year":2025,"lang":"","type":"article","venue":"The Annals of Applied Statistics","topic":"Financial Distress and Bankruptcy Prediction","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":"University of Toronto","funders":"","keywords":"Statistical learning; Artificial neural network; Statistical analysis; Statistical model; Credit risk","score_opus":0.05797655912212767,"score_gpt":0.31871985938234126,"score_spread":0.2607433002602136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417045360","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":[0.007937417,0.0010172334,0.97764087,0.0017236075,0.00018173462,0.0013006356,0.002144619,0.000039813545,0.0080140745],"genre_scores_gemma":[0.98753434,0.00054701715,0.010337285,0.0005646421,0.0004484078,0.00006275075,0.0004175611,0.000030275356,0.000057737743],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99785364,0.000035294226,0.00078830426,0.0004992033,0.00040326198,0.00042030626],"domain_scores_gemma":[0.99764174,0.00060680124,0.0006673506,0.0007699025,0.0002860516,0.000028170874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009985203,0.0002701706,0.0005320622,0.00013581115,0.0005510924,0.00019650145,0.00074116205,0.000087424734,0.000030468711],"category_scores_gemma":[0.00026110478,0.00022236284,0.000020447682,0.0010680597,0.00038136175,0.00024204057,0.0007984462,0.00034299147,0.0000045499332],"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":[0.0010019334,0.00012987896,0.004076908,0.002692747,0.00017922324,0.0000027342894,0.00017521807,0.011923506,0.00012367047,0.87431127,0.02712235,0.07826053],"study_design_scores_gemma":[0.0018040311,0.0002765592,0.51447594,0.0034893944,0.0011976967,0.0000014795958,0.0025100126,0.13906002,0.00018928097,0.14217025,0.19378354,0.0010417886],"about_ca_topic_score_codex":0.00021282521,"about_ca_topic_score_gemma":0.00012768038,"teacher_disagreement_score":0.9795969,"about_ca_system_score_codex":0.000007897102,"about_ca_system_score_gemma":0.00008852291,"threshold_uncertainty_score":0.9067694},"labels":[],"label_agreement":null},{"id":"W4417045508","doi":"10.1214/25-aoas2085","title":"The dynamic interplay of clan culture and socioeconomic factors on fertility: Evidence from China","year":2025,"lang":"","type":"article","venue":"The Annals of Applied Statistics","topic":"Family Dynamics and Relationships","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Clan; Socioeconomic status; Fertility; Population; China; Population growth; Birth rate","score_opus":0.040165505688895306,"score_gpt":0.35746637972926654,"score_spread":0.3173008740403712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417045508","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":[0.98418975,0.0022221701,0.0032986694,0.0032081313,0.00047043705,0.0005578029,0.0015985096,0.00001032371,0.0044442136],"genre_scores_gemma":[0.98808444,0.010778425,0.0002639701,0.00014152913,0.00001998663,0.000007017438,0.000027208413,0.000010537434,0.00066687143],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981905,0.00024464302,0.00066739315,0.0003066901,0.00028811005,0.00030262256],"domain_scores_gemma":[0.9948205,0.0039829346,0.00054235855,0.0004551762,0.00013047387,0.0000685819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011273898,0.00023388403,0.00040462494,0.000051033992,0.0010683052,0.00011553453,0.0006971664,0.00020981333,0.000030160452],"category_scores_gemma":[0.00034499945,0.00013861389,0.000095601456,0.00018074467,0.0019873495,0.00005346793,0.00017564141,0.0005030532,0.0000071148347],"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":[0.001269141,0.00019080828,0.007103033,0.00018616513,0.0008667714,5.889144e-7,0.13548498,0.0009933681,0.0005331522,0.8198905,0.0045202174,0.028961299],"study_design_scores_gemma":[0.00021189022,0.00014618933,0.4332537,0.0003234341,0.00019030455,2.9405777e-8,0.03056694,0.024543269,0.00015537236,0.5095757,0.0008133262,0.00021983494],"about_ca_topic_score_codex":0.0010560498,"about_ca_topic_score_gemma":0.0016377156,"teacher_disagreement_score":0.42615068,"about_ca_system_score_codex":0.000052101946,"about_ca_system_score_gemma":0.00022119394,"threshold_uncertainty_score":0.82166487},"labels":[],"label_agreement":null},{"id":"W4417071687","doi":"10.1214/25-aoas2091","title":"Tomographic reconstruction of disease transmission landscapes from GPS-recorded random paths","year":2025,"lang":"","type":"article","venue":"The Annals of Applied Statistics","topic":"Data-Driven Disease Surveillance","field":"Medicine","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":"York University","funders":"","keywords":"Pattern recognition (psychology); Tomography; Transmission (telecommunications); Tomographic reconstruction; Iterative reconstruction","score_opus":0.02081823664402697,"score_gpt":0.2968701473228377,"score_spread":0.2760519106788107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417071687","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":[0.69603735,0.018826295,0.1824131,0.0028507104,0.0017433506,0.0043361844,0.08572805,0.00016642967,0.007898517],"genre_scores_gemma":[0.98319995,0.010538124,0.0041432437,0.00030654704,0.00013832332,0.000045285902,0.0014762172,0.00003950713,0.000112803566],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966587,0.00026869605,0.0014464108,0.00055280403,0.00062992016,0.00044346973],"domain_scores_gemma":[0.9955333,0.0016345453,0.0008118996,0.0011343451,0.00053485134,0.00035106594],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000787686,0.00043149976,0.0012344493,0.00029501526,0.0001661972,0.000028253593,0.00047361126,0.00014833943,0.0008083814],"category_scores_gemma":[0.00037232766,0.0003371743,0.0002951306,0.0007485032,0.00066361733,0.00006323919,0.00009944965,0.00034623515,0.000016930786],"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":[0.059359215,0.0012397579,0.005592129,0.0030071044,0.0023052578,0.000032978147,0.0011345149,0.00045525303,0.006644725,0.013409253,0.02085309,0.8859667],"study_design_scores_gemma":[0.045427702,0.0012406383,0.37034175,0.009881494,0.010875222,0.0000045716306,0.0031654753,0.04925058,0.035816204,0.44672638,0.025140429,0.0021295494],"about_ca_topic_score_codex":0.00014222735,"about_ca_topic_score_gemma":0.00003084203,"teacher_disagreement_score":0.88383716,"about_ca_system_score_codex":0.000014662693,"about_ca_system_score_gemma":0.0005314408,"threshold_uncertainty_score":0.99990803},"labels":[],"label_agreement":null}]}