{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":23962,"total_is_capped":false,"direct_labels_cover":39,"predictions_cover":23962,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"cdc3dc315bad","filters":{"venue":"bioRxiv (Cold Spring Harbor Laboratory)"}},"results":[{"id":"W2950635543","doi":"10.1101/672295","title":"PICRUSt2: An improved and customizable approach for metagenome inference","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":736,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"National Institute on Alcohol Abuse and Alcoholism; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; GlaxoSmithKline","keywords":"Metagenomics; Inference; Gene prediction; DNA sequencing; Reference database; Genomics","retraction":null,"screen_n_in":null,"score":{"opus":0.01629389083823218,"gpt":0.2457617375584072,"spread":0.229467846720175,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005503371,0.0005072,0.0005564913,0.0001186132,0.0001533545,0.0001723347,0.0004800227,0.0008266408,0.000009889165],"category_scores_gemma":[0.0001018174,0.0005304111,0.0001312788,0.0001030312,0.0001003975,0.00001316604,0.0005403575,0.0003929858,0.000006859865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006021722,"about_ca_system_score_gemma":0.0007909454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005390699,"about_ca_topic_score_gemma":0.000003189326,"domain_scores_codex":[0.9974992,0.00009351916,0.0003934239,0.001313275,0.0001010278,0.0005995491],"domain_scores_gemma":[0.9977215,0.0000166162,0.0002999162,0.001325496,0.0003459079,0.0002905935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007952563,0.0001175972,0.001359351,0.000665466,0.0001207584,7.408315e-7,0.000005470529,0.0001139771,0.9971759,0.0001487653,0.0002096509,0.000002776207],"study_design_scores_gemma":[0.003595489,0.00107892,0.03983725,0.0001650734,0.0004583699,9.742103e-8,0.00001743853,0.008515635,0.8824972,0.000005464917,0.06092642,0.002902641],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9551891,0.003098335,0.03807903,0.00005602855,0.0005712342,0.002162431,0.0007211122,0.00009522937,0.00002746471],"genre_scores_gemma":[0.9661506,0.0005823057,0.03188225,0.0003364612,0.0004573468,0.0004129909,0.00001247547,0.000126668,0.00003886603],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1146787,"threshold_uncertainty_score":0.9997147,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4282822545","doi":"10.1101/2022.06.11.495736","title":"CAT – A Computational Anatomy Toolbox for the Analysis of Structural MRI Data","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":626,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; National Institutes of Health; Alexander von Humboldt-Stiftung; Genentech; IXICO; H. Lundbeck A/S; Servier; Eisai; Bristol-Myers Squibb; Royal Society; Northern California Institute for Research and Education; Royal Society Te Apārangi; Pfizer; BioClinica; Biogen; F. Hoffmann-La Roche; University of Auckland; Eli Lilly and Company; U.S. Department of Defense; Meso Scale Diagnostics; Alzheimer's Disease Neuroimaging Initiative; Novartis Pharmaceuticals Corporation; Alzheimer's Association; Foundation for the National Institutes of Health","keywords":"Computer science; Toolbox; Workflow; Suite; Preprocessor; Visualization; USable; Graphical user interface; Data science; Human–computer interaction; Data mining; Artificial intelligence; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.0678759867942592,"gpt":0.3525822282139926,"spread":0.2847062414197334,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003558839,0.0002709111,0.000569673,0.0003058036,0.0002289517,0.00004388637,0.0009554063,0.0001057963,0.00009839983],"category_scores_gemma":[0.0001543185,0.0002312671,0.000233901,0.000978307,0.0001438616,0.00005665521,0.0008747582,0.0004082095,8.642725e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001401616,"about_ca_system_score_gemma":0.0004314992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005789856,"about_ca_topic_score_gemma":0.000001984097,"domain_scores_codex":[0.9980652,0.00004010051,0.0004646565,0.0008241629,0.0003688656,0.0002369764],"domain_scores_gemma":[0.9961754,0.0002893888,0.0004433193,0.002604939,0.0003919715,0.00009495578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001395782,0.002078745,0.301948,0.005658268,0.03784354,0.0001908037,0.000179965,0.2575685,0.2419465,0.103961,0.04696478,0.0002641689],"study_design_scores_gemma":[0.0007454451,0.00006649725,0.4538862,0.00009068976,0.006905109,6.414916e-8,0.00001032696,0.4814635,0.004240619,0.00006412738,0.05193899,0.0005884309],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4432635,0.002226454,0.5177588,0.008141618,0.0006940182,0.006308547,0.02060934,0.0009820481,0.0000157026],"genre_scores_gemma":[0.8418409,0.00007931479,0.1570174,0.0003584175,0.0001191699,0.0004760991,0.00004216845,0.00006115568,0.000005488471],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3985773,"threshold_uncertainty_score":0.9430798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2896352133","doi":"10.1101/447367","title":"Unraveling the polygenic architecture of complex traits using blood eQTL metaanalysis","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":546,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Expression quantitative trait loci; Genetic architecture; Genome-wide association study; Quantitative trait locus; Biology; Genetics; Genetic association; Gene; Locus (genetics); Trait; Genome; Computational biology; Single-nucleotide polymorphism; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.02411257243345517,"gpt":0.2516552511805142,"spread":0.2275426787470591,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001055064,0.0004641823,0.0007062736,0.0001605661,0.0002234814,0.00004535954,0.0007760946,0.0006929802,0.00004288782],"category_scores_gemma":[0.000492557,0.0003873994,0.0004584456,0.0003511444,0.0002864413,0.000002454164,0.0006476167,0.0004274392,0.000005419106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003961009,"about_ca_system_score_gemma":0.0004708301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001106124,"about_ca_topic_score_gemma":0.00001683293,"domain_scores_codex":[0.9972011,0.0004393195,0.0007409325,0.0008450642,0.000249124,0.0005244783],"domain_scores_gemma":[0.9972159,0.00006013612,0.000834209,0.001208022,0.0005469775,0.0001347036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001565493,0.00007058357,0.006489391,0.00007237559,0.001454209,0.00000174521,0.00001031038,0.002793454,0.9889214,0.00003105824,0.0001356755,0.000004142809],"study_design_scores_gemma":[0.001069185,0.000283784,0.422267,0.0001923272,0.003992165,2.67253e-7,0.00002127859,0.004738247,0.5592258,0.00003008659,0.006613179,0.001566643],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9731281,0.002272756,0.02342331,0.0002163111,0.0002770216,0.0003662698,0.0002774894,0.00002851129,0.00001020761],"genre_scores_gemma":[0.9746315,0.0002160951,0.02400683,0.0002573435,0.0007645959,0.0000356586,0.000002952517,0.00007861652,0.000006438814],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4296956,"threshold_uncertainty_score":0.9998578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3083653247","doi":"10.1101/2020.09.04.283077","title":"Improvements to the ARTIC multiplex PCR method for SARS-CoV-2 genome sequencing using nanopore","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"SARS-CoV-2 detection and testing","field":"Medicine","cited_by":431,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Centre for Disease Control; Michael Smith Health Research BC; University of British Columbia","funders":"Medical Research Council; Genome Canada; Canadian Institutes of Health Research; University of Glasgow; UK Research and Innovation; Wellcome Trust","keywords":"Nanopore sequencing; Genome; DNA sequencing; Multiplex; Computational biology; Protocol (science); Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Whole genome sequencing; Coronavirus disease 2019 (COVID-19); Genomics; Biology; Computer science; Genetics; Gene; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.09256253001115525,"gpt":0.3219268804233078,"spread":0.2293643504121526,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001278346,0.0007588678,0.0009618528,0.0003533516,0.0004217868,0.0002476993,0.0005340474,0.0004660045,0.000007861642],"category_scores_gemma":[0.001987485,0.0006770515,0.0003802124,0.0008992399,0.0000703406,0.0001117219,0.0006386893,0.001009712,0.00006346782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00104526,"about_ca_system_score_gemma":0.001125039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003207928,"about_ca_topic_score_gemma":0.00001295079,"domain_scores_codex":[0.9959646,0.0001699075,0.0009438465,0.001474483,0.0005574248,0.0008896983],"domain_scores_gemma":[0.9967265,0.0002042328,0.0005984127,0.001430971,0.0007920897,0.0002477594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001096411,0.00005648891,0.0004210992,0.0006785059,0.0003211682,0.00006220474,0.00007500672,0.0001132044,0.9980367,0.00003419522,0.00007325375,0.00001846991],"study_design_scores_gemma":[0.001171231,0.0001671427,0.001646408,0.0004977721,0.0004857582,3.168105e-7,0.00002094392,0.04004333,0.9473874,0.00000450572,0.007899692,0.0006755104],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8766083,0.0002947949,0.1164393,0.0007828236,0.001343439,0.003707783,0.0001741418,0.0006409963,0.000008438079],"genre_scores_gemma":[0.8198993,0.000004941209,0.1702887,0.007938573,0.001130945,0.0004820242,5.917445e-7,0.0002525677,0.000002292166],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05670893,"threshold_uncertainty_score":0.999568,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2611208896","doi":"10.1101/132753","title":"Modeling zero-inflated count data with glmmTMB","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":428,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Count data; Laplace's method; Generalized linear mixed model; Negative binomial distribution; Overdispersion; Markov chain Monte Carlo; Computer science; Poisson distribution; Statistics; Quasi-likelihood; Range (aeronautics); Generalized linear model; Bayesian probability; Algorithm; Mathematics; Applied mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.08572515254872412,"gpt":0.3282695346689558,"spread":0.2425443821202317,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001584265,0.0008021289,0.001104548,0.0001653413,0.0003923317,0.0007427236,0.00256641,0.0006688045,0.00007763351],"category_scores_gemma":[0.002927915,0.0006989607,0.00008799443,0.000184326,0.000229857,0.0003031279,0.001853712,0.001305941,0.00005840872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001879444,"about_ca_system_score_gemma":0.0009932303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001697584,"about_ca_topic_score_gemma":0.000009214026,"domain_scores_codex":[0.9958674,0.0002088816,0.0007870269,0.001639405,0.0007352238,0.0007620025],"domain_scores_gemma":[0.9912704,0.0004105539,0.000678583,0.006437441,0.0008214221,0.0003815739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009503427,0.00205111,0.007776225,0.01331222,0.004451272,0.002648325,0.0001285188,0.001124177,0.1344863,0.8238757,0.008942115,0.0002536938],"study_design_scores_gemma":[0.003459495,0.0003601011,0.005970415,0.01064801,0.002724972,3.136038e-7,0.000009172031,0.9132987,0.02291899,0.02923165,0.004127423,0.007250715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05727527,0.0002740581,0.9386422,0.0001550657,0.0007226011,0.0008214062,0.001511208,0.0005342204,0.00006398548],"genre_scores_gemma":[0.4920247,0.00009521785,0.5073319,0.00005362128,0.000264538,0.00007103712,0.000001152007,0.0001539736,0.00000388154],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9121746,"threshold_uncertainty_score":0.9995462,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2922257230","doi":"10.1101/563866","title":"Sequencing of 53,831 diverse genomes from the NHLBI TOPMed Program","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":423,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; University of British Columbia","funders":"National Heart, Lung, and Blood Institute","keywords":"Imputation (statistics); Biology; Genetics; 1000 Genomes Project; Genome; Genomics; Whole genome sequencing; Haplotype; Structural variation; Genome-wide association study; Computational biology; Precision medicine; DNA sequencing; Single-nucleotide polymorphism; Genotype; Gene; Computer science; Missing data","retraction":null,"screen_n_in":null,"score":{"opus":0.01898156326133077,"gpt":0.2397284785358168,"spread":0.220746915274486,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000635155,0.0003802345,0.0005259118,0.00005323789,0.0001168463,0.00004765271,0.0007418539,0.0007120998,0.00003400302],"category_scores_gemma":[0.0004016084,0.0003230893,0.0002431816,0.0001423006,0.0001619225,0.000004086165,0.0008758262,0.00039033,0.00003048966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001082158,"about_ca_system_score_gemma":0.0006779336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003322895,"about_ca_topic_score_gemma":0.00001955895,"domain_scores_codex":[0.9977587,0.0002595698,0.0005341109,0.0007982501,0.0002016863,0.0004476758],"domain_scores_gemma":[0.9973633,0.0000855121,0.0006019286,0.001474214,0.0003655473,0.0001094513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002759372,0.00009061714,0.1973553,0.00008834797,0.0005468895,0.000004080859,0.00002461278,0.000666664,0.7991515,0.00005606488,0.001953713,0.00003466185],"study_design_scores_gemma":[0.00085745,0.0002574066,0.7463713,0.0001850109,0.0003531972,2.131442e-8,0.00006481837,0.0007501666,0.2080954,0.00001246654,0.04200718,0.001045654],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993363,0.003327735,0.0007886401,0.0002317498,0.0008679222,0.0008531145,0.0004850292,0.00005427577,0.00002856272],"genre_scores_gemma":[0.9887998,0.0009519744,0.009093685,0.0003011675,0.0006121508,0.0001502943,0.000008899174,0.00006174578,0.00002032386],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.591056,"threshold_uncertainty_score":0.9999221,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2588400683","doi":"10.1101/108597","title":"<tt>mixOmics</tt> : an R package for ‘omics feature selection and multiple data integration","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":403,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Prevention of Organ Failure; St. Paul's Hospital","funders":"Diamantina Institute, University of Queensland; National Health and Medical Research Council; Medical Research Council; University of Queensland; Australian Cancer Research Foundation","keywords":"Univariate; Omics; Computer science; Feature selection; Identification (biology); Multivariate statistics; Data integration; Data mining; Biological data; Data type; Dimensionality reduction; Computational biology; Data science; Bioinformatics; Biology; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02009588761609814,"gpt":0.2458336579491071,"spread":0.2257377703330089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006470753,0.0004593165,0.0003739907,0.00008001619,0.0003566606,0.0004713873,0.0008968435,0.001060383,0.000001700728],"category_scores_gemma":[0.0002628398,0.0004798576,0.00008845125,0.00005173492,0.0000948138,0.00004078424,0.0009250228,0.0005048364,0.000002754781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005891945,"about_ca_system_score_gemma":0.0003382316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003313208,"about_ca_topic_score_gemma":0.00008795839,"domain_scores_codex":[0.9980939,0.0000518832,0.0003504478,0.0009841939,0.0001213325,0.0003982316],"domain_scores_gemma":[0.9966899,0.00001988344,0.0005129279,0.00225035,0.0003248132,0.0002021814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001494193,0.00007251836,0.001599056,0.000236007,0.0001799307,0.000001387681,0.00001202734,0.00007723543,0.9934108,0.0001982884,0.003935812,0.0001274805],"study_design_scores_gemma":[0.00259187,0.0005155025,0.01815751,0.0003188413,0.0004143932,2.806913e-7,0.00002057137,0.139791,0.7637925,0.00005995815,0.07203873,0.002298828],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8782253,0.001820641,0.112515,0.0003058938,0.001619208,0.001734594,0.00365529,0.0001108286,0.00001317995],"genre_scores_gemma":[0.97049,0.000901465,0.02666777,0.0001850005,0.001392385,0.00007090077,0.0001682887,0.0001060473,0.00001811271],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2296184,"threshold_uncertainty_score":0.9997653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2514763871","doi":"10.1101/070441","title":"DeepAD: Alzheimer’s Disease Classification via Deep Convolutional Neural Networks using MRI and fMRI","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":324,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University; York University; McMaster University; Baycrest Hospital","funders":"","keywords":"Convolutional neural network; Deep learning; Artificial intelligence; Neuroimaging; Computer science; Magnetic resonance imaging; Functional magnetic resonance imaging; Pattern recognition (psychology); Medical imaging; Machine learning; Medicine; Neuroscience; Psychology; Radiology","retraction":null,"screen_n_in":null,"score":{"opus":0.04609899768856122,"gpt":0.253107279817012,"spread":0.2070082821284508,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004469012,0.000683245,0.0005224163,0.0002737344,0.0006797742,0.0002443201,0.0004764647,0.0003764589,0.00002872254],"category_scores_gemma":[0.002180754,0.0006758653,0.0001721656,0.0003982616,0.0005538569,0.0004108833,0.0009078325,0.0006991066,0.00003120392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003623078,"about_ca_system_score_gemma":0.0003433883,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001563651,"about_ca_topic_score_gemma":0.000002415182,"domain_scores_codex":[0.995809,0.0003989788,0.0005323532,0.001929699,0.0006190808,0.0007108678],"domain_scores_gemma":[0.9962546,0.001317339,0.0005238532,0.001044735,0.0003862023,0.000473304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004287625,0.0003642191,0.05254814,0.0002610409,0.0003425619,0.0001621569,0.0000135776,0.007499,0.9253773,0.01184789,0.001121059,0.00003431464],"study_design_scores_gemma":[0.0008620138,0.00005310699,0.3558204,0.0002597664,0.0004536204,2.424646e-7,0.000002607903,0.6177722,0.02172561,0.0001185917,0.001360369,0.001571538],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7538819,0.007809903,0.2174808,0.00916535,0.007309972,0.002490938,0.0006133565,0.00122676,0.00002106779],"genre_scores_gemma":[0.9958932,0.0002212306,0.001026652,0.001401919,0.00111566,0.0002128112,3.830567e-7,0.0001257939,0.000002354422],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9036517,"threshold_uncertainty_score":0.9995692,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2618245351","doi":"10.1101/142760","title":"Opportunities and obstacles for deep learning in biology and medicine","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":309,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Princess Margaret Cancer Centre","funders":"U.S. National Library of Medicine; Natural Sciences and Engineering Research Council of Canada; Gordon and Betty Moore Foundation; Howard Hughes Medical Institute; National Institutes of Health; National Science Foundation","keywords":"Deep learning; Interpretability; Artificial intelligence; Variety (cybernetics); Computer science; Data science; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.0496381747885837,"gpt":0.311126466346927,"spread":0.2614882915583433,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001436696,0.0004138042,0.0006715619,0.0004185813,0.0003976413,0.0002680442,0.0009319048,0.0004587084,0.000004250706],"category_scores_gemma":[0.001459809,0.0004125441,0.00004035525,0.000108144,0.000341566,0.0002183334,0.001252199,0.0009505803,0.000001274358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009631592,"about_ca_system_score_gemma":0.0003027144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004255511,"about_ca_topic_score_gemma":0.00003110582,"domain_scores_codex":[0.9974618,0.0002903864,0.0004729683,0.001082889,0.0001653733,0.0005265753],"domain_scores_gemma":[0.9974169,0.0004376757,0.0005316756,0.001075845,0.0002797978,0.0002581048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007880667,0.0001085484,0.6319866,0.006487605,0.000230302,0.0002861946,0.0009650982,0.0002998153,0.03075138,0.325016,0.0002245966,0.003565037],"study_design_scores_gemma":[0.002299546,0.0006671242,0.8321785,0.002480105,0.00007764199,2.848327e-7,0.00004900478,0.1126116,0.001500968,0.0009064314,0.04520237,0.002026483],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8650146,0.02773943,0.08479314,0.01678031,0.002596722,0.001942359,0.00005835325,0.001022046,0.00005309129],"genre_scores_gemma":[0.9757391,0.002618808,0.02085379,0.0002429836,0.0003017722,0.0001807745,3.727843e-7,0.00005311719,0.000009274778],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3241096,"threshold_uncertainty_score":0.9998326,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034312851","doi":"10.1101/2020.06.12.148296","title":"DeepEMhancer: a deep learning solution for cryo-EM volume post-processing","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Electron Microscopy Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":269,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Ministerio de Ciencia e Innovación; Ministerio de Economía y Competitividad; Comunidad de Madrid","keywords":"Sharpening; Interpretability; Masking (illustration); Computer science; Artificial intelligence; Set (abstract data type); Contrast (vision); Deep learning; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.008776396629565157,"gpt":0.2635893274977237,"spread":0.2548129308681586,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002127882,0.0004499216,0.0003758425,0.00007458231,0.0003552083,0.0001540936,0.0004730806,0.0005901867,0.000009549579],"category_scores_gemma":[0.0001813261,0.000564641,0.0002059032,0.0001993777,0.00008180699,0.00001281083,0.0004310205,0.0005869076,0.00001316321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001407509,"about_ca_system_score_gemma":0.0003985363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006797583,"about_ca_topic_score_gemma":0.000003868712,"domain_scores_codex":[0.9976161,0.00004711608,0.0003966237,0.001153596,0.0001548381,0.0006317908],"domain_scores_gemma":[0.9981145,0.000009010587,0.0004171799,0.0006393188,0.0006206594,0.0001992888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006531071,0.0000538349,0.0001729181,0.0002528081,0.00005534913,9.223969e-7,0.000005436004,0.0001601114,0.9987617,0.0000929273,0.0002485543,0.0001300994],"study_design_scores_gemma":[0.0003385854,0.0002745148,0.00120788,0.0001273559,0.0001056745,2.254393e-8,0.000003710893,0.003849458,0.9460934,0.00002001475,0.04720727,0.0007721257],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1220428,0.003379851,0.8723475,0.0005667349,0.0001298391,0.00102527,0.0001515209,0.0003521351,0.000004373966],"genre_scores_gemma":[0.8738501,0.0005875558,0.1231766,0.0005069374,0.0007337327,0.0009341913,0.00001486387,0.0001726525,0.00002336955],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7518073,"threshold_uncertainty_score":0.9996805,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2990895847","doi":"10.1101/856591","title":"RepeatModeler2: automated genomic discovery of transposable element families","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":264,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health","keywords":"Genome; Annotation; Transposable element; Computational biology; Biology; Identification (biology); Genome project; Genomics; Tree (set theory); Genetics; Computer science; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01281386883890619,"gpt":0.1962674532148998,"spread":0.1834535843759936,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002435901,0.0003906203,0.0005365891,0.00003606529,0.0001244048,0.0001283704,0.0005469897,0.0003449731,0.0001162338],"category_scores_gemma":[0.0000261378,0.0001982172,0.0002434705,0.0003399634,0.00007046203,0.0001225671,0.0002781736,0.0002656722,0.00005021093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001106331,"about_ca_system_score_gemma":0.0001542353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002875217,"about_ca_topic_score_gemma":0.00004843209,"domain_scores_codex":[0.9978461,0.00009132514,0.0005903355,0.0007448447,0.0003141421,0.0004132437],"domain_scores_gemma":[0.9988579,0.00007849534,0.0003663876,0.0003754695,0.0002157556,0.0001060516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002018442,0.0001617641,0.01745291,0.0001267584,0.000105659,0.000003577798,0.000009881222,0.001438177,0.980323,0.0002851864,0.00006793856,0.000005010896],"study_design_scores_gemma":[0.0003940853,0.0002141359,0.687053,0.0003221037,0.0001776124,1.354693e-8,0.00001363957,0.008362543,0.2988027,0.00001052882,0.003774678,0.0008749674],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961108,0.0005429125,0.00006000516,0.0002403422,0.0005308462,0.0006852336,0.001436405,0.0003693774,0.00002405204],"genre_scores_gemma":[0.9983007,0.0003865292,0.0008731281,0.00006366584,0.0002638903,0.00008046032,0.000005004087,0.000007716932,0.00001886381],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6815202,"threshold_uncertainty_score":0.8083062,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2743277997","doi":"10.1101/173062","title":"Genome-wide association study identifies 30 Loci Associated with Bipolar Disorder","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bipolar Disorder and Treatment","field":"Medicine","cited_by":255,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Amgen (Canada)","funders":"National Institute of Mental Health; Medical Research Council; National Institutes of Health; Victoria General Hospital Foundation; Centro de Investigación Biomédica en Red de Salud Mental; Università di Bologna; European Commission; Canadian Institutes of Health Research; National Institute for Health and Care Research; National Alliance for Research on Schizophrenia and Depression; Michael Smith Health Research BC; Universitat de Barcelona; Wellcome Trust","keywords":"Bipolar disorder; Mania; Genome-wide association study; Schizophrenia (object-oriented programming); Major depressive disorder; Genetic association; Genetics; Psychiatry; Medicine; Psychology; Biology; Gene; Single-nucleotide polymorphism; Genotype; Lithium (medication); Mood","retraction":null,"screen_n_in":null,"score":{"opus":0.01366925396228573,"gpt":0.2363055116590957,"spread":0.22263625769681,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001021492,0.0008764585,0.001254732,0.0003391064,0.0006058419,0.0005029814,0.0005250365,0.0007832041,0.0001922025],"category_scores_gemma":[0.001250793,0.000793553,0.0002759268,0.0003228346,0.0001184503,0.0002104672,0.0004676261,0.001231485,0.0001960061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001426824,"about_ca_system_score_gemma":0.00085465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004868372,"about_ca_topic_score_gemma":0.0002634524,"domain_scores_codex":[0.9958121,0.0002631272,0.0006555213,0.001312035,0.00113424,0.0008230119],"domain_scores_gemma":[0.9950535,0.0001624286,0.001192106,0.002161344,0.001073462,0.000357158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006469108,0.002307766,0.9906137,0.000200428,0.003494446,0.0001143505,0.00008261162,0.000009874317,0.002958104,0.000009039401,0.0001426612,0.000002312737],"study_design_scores_gemma":[0.003326603,0.0003548392,0.986777,0.000359081,0.002300489,9.1059e-9,0.00002765072,0.000016864,0.001575573,0.000002145374,0.004472941,0.0007867803],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9854937,0.009766251,0.0001227419,0.0005202973,0.0005534369,0.002673727,0.000291492,0.0005425416,0.00003577412],"genre_scores_gemma":[0.9980703,0.0005633322,0.0001409134,0.0001051248,0.0002602642,0.0004641808,0.000008399555,0.0002402182,0.0001472423],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01257659,"threshold_uncertainty_score":0.9994515,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2462819058","doi":"10.1101/062109","title":"A simple proposal for the publication of journal citation distributions","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":233,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Citation; Impact factor; Skew; Computer science; Transparency (behavior); Protocol (science); Quality (philosophy); Simple (philosophy); Data science; Information retrieval; Library science; Political science; Medicine; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.23971129138092,"gpt":0.4459265289678294,"spread":0.2062152375869094,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.02406878,0.0002467917,0.0004089588,0.0142024,0.0006139516,0.003447544,0.003251721,0.0003150757,0.0001460775],"category_scores_gemma":[0.07723107,0.0001394876,0.0003341637,0.03924965,0.0002901113,0.0005449491,0.0009145553,0.0005373836,0.00005533304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003239919,"about_ca_system_score_gemma":0.002710719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001236134,"about_ca_topic_score_gemma":0.000001450968,"domain_scores_codex":[0.9924316,0.0003021142,0.001218174,0.0007719704,0.004682539,0.0005935882],"domain_scores_gemma":[0.9707084,0.004362883,0.001546005,0.001613188,0.02139913,0.0003703386],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002184462,0.001014111,0.1012056,0.0002716028,0.0006147059,0.000009710283,0.00004519526,0.0001140989,0.5381859,0.1414637,0.2150523,0.001804724],"study_design_scores_gemma":[0.001572467,0.0003184299,0.7252019,0.000155244,0.0001519678,7.697274e-8,0.00002821944,0.009022642,0.1273089,0.009396767,0.1259602,0.0008832382],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1580552,0.001579565,0.8197541,0.0122181,0.00271417,0.002218943,0.003348522,0.00007994952,0.00003146301],"genre_scores_gemma":[0.9942506,0.0002077819,0.004754541,0.00004456557,0.0004736533,0.0002151236,6.937249e-7,0.0000289688,0.00002409336],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8361954,"threshold_uncertainty_score":0.997587,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2798279033","doi":"10.1101/306951","title":"FMRIPrep: a robust preprocessing pipeline for functional MRI","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":217,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"National Institute of Neurological Disorders and Stroke; European Commission; National Institutes of Health; Laura and John Arnold Foundation","keywords":"Preprocessor; Computer science; Workflow; Pipeline (software); Data pre-processing; Interpretability; Data mining; Artificial intelligence; Inference; Machine learning; Pattern recognition (psychology); Database; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.04968285976328372,"gpt":0.2492344976028419,"spread":0.1995516378395582,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001072703,0.0008222607,0.0007390166,0.0003804349,0.0008929503,0.0004248158,0.0007444607,0.000558591,0.0001079069],"category_scores_gemma":[0.01445719,0.0008864719,0.0003400156,0.0006605006,0.0004793601,0.0003955092,0.001116658,0.0008087462,0.0001745064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004507196,"about_ca_system_score_gemma":0.0009375843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001360678,"about_ca_topic_score_gemma":0.000003803772,"domain_scores_codex":[0.9945562,0.000191771,0.00071338,0.002869977,0.0008060643,0.000862587],"domain_scores_gemma":[0.9940366,0.002315018,0.0006646849,0.001544617,0.001180242,0.0002588355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004439813,0.0004838257,0.002162116,0.001099646,0.0001536764,0.00002825232,0.00002256389,0.003507878,0.9237152,0.001424209,0.06695275,0.000005895255],"study_design_scores_gemma":[0.001460212,0.0001648624,0.01213397,0.0006829291,0.0002280881,1.449704e-7,0.00000444249,0.02306415,0.8961632,0.00009525539,0.06415377,0.001849024],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4421223,0.001563398,0.5131445,0.01107494,0.01958367,0.005917927,0.002303429,0.004015054,0.0002747849],"genre_scores_gemma":[0.9802418,0.00007450469,0.01083354,0.003044568,0.004075078,0.001359749,6.454932e-7,0.0002554943,0.000114615],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5381195,"threshold_uncertainty_score":0.9993586,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2923424663","doi":"10.1101/588020","title":"Recovery of trait heritability from whole genome sequence data","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":215,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Health and Medical Research Council; Australian Research Council; Medical Research Council; National Institutes of Health","keywords":"Heritability; Genetics; Biology; Genome-wide association study; Linkage disequilibrium; Minor allele frequency; Genetic association; Single-nucleotide polymorphism; Genetic architecture; Trait; Quantitative trait locus; Genotype; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03284004387215951,"gpt":0.2543028666177657,"spread":0.2214628227456062,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009777388,0.0003899999,0.0006703114,0.00006077988,0.00005846611,0.00003705044,0.001337411,0.0008951846,0.00005083645],"category_scores_gemma":[0.0007671138,0.0004329582,0.0001696127,0.0001286936,0.0001545847,0.000009785834,0.001649963,0.0003853288,0.00002782055],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008470521,"about_ca_system_score_gemma":0.0007797226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003202188,"about_ca_topic_score_gemma":0.00001669478,"domain_scores_codex":[0.9970087,0.0002876341,0.0006892121,0.00140553,0.0001895468,0.0004193505],"domain_scores_gemma":[0.9951544,0.00006760177,0.0006303791,0.003674968,0.0003373098,0.0001353498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002737183,0.00008327917,0.03582914,0.0001072234,0.0002533504,0.000001865456,0.000002625002,0.0005012455,0.9624807,0.0000061902,0.0007032572,0.000003777577],"study_design_scores_gemma":[0.0005796292,0.0001866845,0.8883217,0.0001180599,0.0002033285,1.432819e-8,0.000006544542,0.0007547567,0.0620153,0.0000164402,0.04680633,0.0009912328],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9749259,0.002398181,0.004799775,0.0001883659,0.0009726809,0.0004709535,0.01619565,0.00003460192,0.00001382744],"genre_scores_gemma":[0.9837892,0.0006191531,0.01469903,0.0001849679,0.0004457508,0.00004299698,0.0001303072,0.00006950863,0.00001907193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9004654,"threshold_uncertainty_score":0.9998122,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3040623586","doi":"10.1101/2020.07.05.188268","title":"VIRIDIC – a novel tool to calculate the intergenomic similarities of prokaryote-infecting viruses","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":195,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Genome; Biology; Prokaryote; Archaea; Computational biology; Genetics; Virus classification; Similarity (geometry); Gene; Computer science; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.0209061542997391,"gpt":0.2352066636096739,"spread":0.2143005093099348,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003417908,0.0004304821,0.0004511883,0.00008001205,0.0002023536,0.000179288,0.0007396515,0.0002181796,0.0004744703],"category_scores_gemma":[0.0002228907,0.000377935,0.0002289284,0.0003695698,0.0001830183,0.0001844168,0.00190074,0.0007003168,0.0003050198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003491247,"about_ca_system_score_gemma":0.000110689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00107643,"about_ca_topic_score_gemma":0.00003893617,"domain_scores_codex":[0.9979287,0.00007798165,0.0005958294,0.0007594124,0.0002208486,0.0004172673],"domain_scores_gemma":[0.9984724,0.00006908669,0.0003768206,0.0008548467,0.00006012715,0.0001667441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002857625,0.00008592212,0.000951198,0.0001004303,0.00008849353,0.000007661179,0.00009772205,0.0006491543,0.997313,0.00004111306,0.0006319197,0.00000483828],"study_design_scores_gemma":[0.000269697,0.00009489289,0.1508842,0.0003970174,0.0001515524,8.77246e-8,0.00001855272,0.0005108116,0.8213357,0.000002248828,0.02555594,0.0007793033],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931751,0.00005928268,0.003497572,0.0007667989,0.00111212,0.000883001,0.0003310016,0.00014921,0.0000259291],"genre_scores_gemma":[0.9952499,0.00002784728,0.003116691,0.00108834,0.0002890063,0.0001308809,1.823655e-7,0.00008815464,0.000009010615],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1759773,"threshold_uncertainty_score":0.9998673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3027467214","doi":"10.1101/2020.05.22.110833","title":"Towards complete and error-free genome assemblies of all vertebrate species","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":195,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Royal Ontario Museum","funders":"National Human Genome Research Institute; Leibniz-Gemeinschaft; Wellcome Trust; Danmarks Grundforskningsfond; Biotechnology and Biological Sciences Research Council; National Institutes of Health; Agencia Estatal de Investigación; Leibniz-Institut für Zoo- und Wildtierforschung; Max-Planck-Gesellschaft; National Key Research and Development Program of China; Korea Health Industry Development Institute; Generalitat de Catalunya; Bundesministerium für Bildung und Forschung; Centres de Recerca de Catalunya; Monash University; Biomedical Research Council; Hessisches Ministerium für Wissenschaft und Kunst; National Research Foundation; Irish Research Council; European Commission; European Molecular Biology Laboratory; Oxford Nanopore Technologies; Monash University Malaysia; National Science Foundation","keywords":"Genome; Vertebrate; Biology; Extant taxon; Evolutionary biology; Genomics; Reference genome; Computational biology; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03154378699902236,"gpt":0.2275919769337449,"spread":0.1960481899347226,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002180255,0.0004936649,0.0006333707,0.00008771932,0.00008597984,0.00007865075,0.0006876609,0.0003538904,0.00001128301],"category_scores_gemma":[0.0001582922,0.0005239738,0.0001638167,0.0001170649,0.0002548921,0.00000187548,0.002120742,0.0002605004,0.000005764298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002833655,"about_ca_system_score_gemma":0.0002589456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002892342,"about_ca_topic_score_gemma":0.000006900121,"domain_scores_codex":[0.9979903,0.0000777528,0.0004589376,0.0008796029,0.00021542,0.0003779981],"domain_scores_gemma":[0.9980264,0.00001406884,0.000333007,0.001130118,0.000301532,0.0001948735],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004029051,0.0000353354,0.00253745,0.0002892508,0.0004786771,0.000008350306,0.00002333195,0.00003626324,0.9956684,0.0003880684,0.0004936929,9.205558e-7],"study_design_scores_gemma":[0.0007781507,0.0002957739,0.2824033,0.00007414223,0.0001978912,4.556419e-8,0.00001929877,0.0001086281,0.6674984,0.0000316289,0.04765837,0.0009344245],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894261,0.007530162,0.0003945435,0.0005051215,0.00040909,0.0003933018,0.001246911,0.00002282142,0.00007197353],"genre_scores_gemma":[0.9916217,0.002861047,0.004660462,0.0002882192,0.0004265162,0.00004750548,0.000002588473,0.00008452234,0.000007453964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.32817,"threshold_uncertainty_score":0.9997212,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4392968035","doi":"10.1101/2024.03.14.585103","title":"Atomically accurate de novo design of antibodies with RFdiffusion","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":187,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Hospital for Sick Children","funders":"National Institute of General Medical Sciences; Institute for Basic Science; National Energy Research Scientific Computing Center; National Science Foundation; Open Philanthropy Project; Children's Hospital of Philadelphia; Office of Science; Bill and Melinda Gates Foundation; Amgen; Hospital for Sick Children; Washington Research Foundation; U.S. Department of Energy; National Institutes of Health","keywords":"Antibody; Domain (mathematical analysis); Computer science; Computational biology; Biology; Mathematics; Immunology","retraction":null,"screen_n_in":null,"score":{"opus":0.02723599354173894,"gpt":0.2763853102630544,"spread":0.2491493167213155,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007264116,0.0005964019,0.0009720103,0.0004292779,0.0001043742,0.0001110744,0.0004210573,0.0005007435,0.0001179288],"category_scores_gemma":[0.0001773827,0.0004537086,0.0002273831,0.0005104904,0.0003731474,0.00005425388,0.0009102667,0.001349423,0.0001116249],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002215713,"about_ca_system_score_gemma":0.002124816,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001124941,"about_ca_topic_score_gemma":0.000002878969,"domain_scores_codex":[0.9968452,0.0001609064,0.0006052489,0.0008883991,0.0007741736,0.0007260156],"domain_scores_gemma":[0.9975073,0.0001788943,0.0002563207,0.0009065673,0.0007126303,0.0004383004],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001252978,0.0002870775,0.01570651,0.003882514,0.0006489569,0.001079179,0.00002989581,0.0001217222,0.9756572,0.0006913906,0.000637011,0.000005559109],"study_design_scores_gemma":[0.001707177,0.0008489422,0.1474235,0.006928853,0.0008464447,0.000001676342,0.000008950271,0.00542801,0.832334,0.00004196565,0.003242783,0.001187679],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9915348,0.00302917,0.002530904,0.001055392,0.0002942224,0.001023503,0.0002204875,0.0002522751,0.00005928482],"genre_scores_gemma":[0.9793535,0.001572572,0.01811795,0.0001992825,0.0004183127,0.00009091006,7.678499e-7,0.0001529069,0.00009376062],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1433232,"threshold_uncertainty_score":0.9997914,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2750472843","doi":"10.1101/179648","title":"A Large-Scale Binding and Functional Map of Human RNA Binding Proteins","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":185,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Université de Montréal; Montreal Clinical Research Institute","funders":"","keywords":"Scale (ratio); Computational biology; RNA-binding protein; RNA; Computer science; Biology; Geography; Genetics; Cartography; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01819765346577848,"gpt":0.254517411873421,"spread":0.2363197584076425,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007647506,0.0003812913,0.0004247337,0.0002236373,0.0004706962,0.0001851623,0.0004390757,0.0005365159,0.00002886913],"category_scores_gemma":[0.0001553415,0.000403786,0.0001555988,0.00007591988,0.0001959567,0.00001441452,0.001058678,0.0005135646,0.00001585668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005365581,"about_ca_system_score_gemma":0.000365882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004135409,"about_ca_topic_score_gemma":0.00001306272,"domain_scores_codex":[0.9977213,0.00008717932,0.0003817595,0.0008720486,0.0003588297,0.0005788463],"domain_scores_gemma":[0.9978408,0.00001152256,0.0004388955,0.001135913,0.000308525,0.0002643043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004411559,0.00007885606,0.009658182,0.0004190347,0.000143871,0.00001251187,0.000004952732,0.000005447479,0.9892235,0.00008462848,0.0003231466,0.000001732376],"study_design_scores_gemma":[0.0006979364,0.0001556601,0.01952057,0.0003694537,0.00004241447,3.476766e-8,0.000006858444,0.00009942643,0.9763612,0.000001898892,0.002282118,0.0004624474],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9963765,0.0008358755,0.001439094,0.00008809827,0.0003116167,0.0005806385,0.0003113924,0.00003872601,0.00001803447],"genre_scores_gemma":[0.9974375,0.0001434918,0.00147338,0.00002124235,0.000515098,0.0001283126,0.000004742602,0.00008456365,0.0001916852],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01286234,"threshold_uncertainty_score":0.9998414,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2620643234","doi":"10.1101/145581","title":"Discovery of the first genome-wide significant risk loci for ADHD","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Attention Deficit Hyperactivity Disorder","field":"Medicine","cited_by":183,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Genome-wide association study; Attention deficit hyperactivity disorder; Polygenic risk score; Genome; Genetics; Genetic association; Copy-number variation; Gene; Biology; Meta-analysis; Population; Psychology; Clinical psychology; Single-nucleotide polymorphism; Medicine; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.03128563073633803,"gpt":0.2660512962430384,"spread":0.2347656655067003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006936343,0.0005699605,0.0009944437,0.0001766223,0.0004294971,0.0001881774,0.0008347846,0.0005483626,0.00003306615],"category_scores_gemma":[0.00221489,0.0004637254,0.0006957503,0.0001969713,0.0003425133,0.000215728,0.0006854018,0.0009858907,0.00003096634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002803127,"about_ca_system_score_gemma":0.0009755894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001914326,"about_ca_topic_score_gemma":0.00001252637,"domain_scores_codex":[0.9971445,0.0000967338,0.0006820299,0.0009811628,0.000561147,0.0005344542],"domain_scores_gemma":[0.9941031,0.0002496965,0.001532999,0.003237288,0.0007232268,0.0001537156],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004787311,0.001297405,0.7040154,0.004478135,0.001664103,0.0000415799,0.00006548235,0.0003608268,0.2847376,0.000362974,0.002492796,0.000004936614],"study_design_scores_gemma":[0.001619077,0.00009063611,0.9398067,0.0007954429,0.001132086,2.447626e-8,0.00002422399,0.0002399645,0.03766795,0.000006922589,0.01796333,0.0006536343],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9873776,0.0008308193,0.00468201,0.002016478,0.001116702,0.002637867,0.001186654,0.0001313363,0.000020474],"genre_scores_gemma":[0.9972578,0.0002899161,0.001025887,0.0002324781,0.0005404874,0.0003859657,0.000001209034,0.0001784829,0.00008772837],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2470697,"threshold_uncertainty_score":0.9997814,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220943881","doi":"10.1101/2022.03.24.485545","title":"sdmTMB: An R Package for Fast, Flexible, and User-Friendly Generalized Linear Mixed Effects Models with Spatial and Spatiotemporal Random Fields","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":183,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Fisheries and Oceans Canada","funders":"","keywords":"Computer science; R package; Random effects model; Mathematics; Computational science","retraction":null,"screen_n_in":null,"score":{"opus":0.01146466889708274,"gpt":0.2179257944969149,"spread":0.2064611255998322,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005490288,0.0005129814,0.0005972045,0.0001028647,0.0003672681,0.0002020281,0.0003119088,0.000281509,0.00007133579],"category_scores_gemma":[0.00008953009,0.0004995404,0.00006691291,0.0001852334,0.0001976798,0.0002371871,0.0007585005,0.0004427308,0.000002839181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001169022,"about_ca_system_score_gemma":0.00009668927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00151586,"about_ca_topic_score_gemma":0.0001188516,"domain_scores_codex":[0.9974363,0.0001782072,0.0003729736,0.00111389,0.0004000959,0.0004984687],"domain_scores_gemma":[0.9984236,0.0001548139,0.0003007611,0.0007295532,0.00005669165,0.0003346165],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01116284,0.002770152,0.2757249,0.01118851,0.002609383,0.001195632,0.001481277,0.1378499,0.5185906,0.02468087,0.01121258,0.001533389],"study_design_scores_gemma":[0.02723842,0.00320138,0.3053912,0.0008247998,0.001147411,4.340048e-7,0.00005627421,0.5267263,0.1124825,0.0002882624,0.016783,0.005860009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6840081,0.000188164,0.3135635,0.00006052541,0.0003680429,0.001323594,0.0003429744,0.0001344722,0.00001069647],"genre_scores_gemma":[0.8999208,0.0001385915,0.09892198,0.0001668221,0.0001705611,0.0005564755,0.00000543476,0.0001021706,0.00001713917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.406108,"threshold_uncertainty_score":0.9997456,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2796533672","doi":"10.1101/299859","title":"Parameterizing neural power spectra","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":181,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of Neurological Disorders and Stroke; Whitehall Foundation; National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada; University of California, San Diego; National Science Foundation","keywords":"Aperiodic graph; A priori and a posteriori; Computer science; Oscillation (cell signaling); Narrowband; Population; Spectral density; Algorithm; SIGNAL (programming language); Completeness (order theory); Mathematics; Telecommunications; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.0241181047702891,"gpt":0.2317852461257226,"spread":0.2076671413554335,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003744596,0.0006852936,0.0005455465,0.0002928918,0.0003125481,0.0005835505,0.0008722324,0.0004726277,0.0001756941],"category_scores_gemma":[0.0007156745,0.0006946904,0.0002608582,0.0005556798,0.0002812741,0.0002767688,0.0007675428,0.001085151,0.0003459024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002134241,"about_ca_system_score_gemma":0.0001928083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001615302,"about_ca_topic_score_gemma":6.782237e-7,"domain_scores_codex":[0.9960532,0.0002343887,0.0005597511,0.001744758,0.0005699712,0.0008379954],"domain_scores_gemma":[0.9973554,0.0001567962,0.000463938,0.001523251,0.0001918209,0.0003088025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003524061,0.00008336834,0.0005308514,0.00007569209,0.00001725929,0.0001198586,0.00000416229,0.00003576909,0.9976538,0.001048605,0.0003939078,0.000001505859],"study_design_scores_gemma":[0.0003771013,0.0002252086,0.02357176,0.0001875984,0.00005962608,1.247023e-7,8.484781e-7,0.007926031,0.9610884,0.00002812978,0.005297758,0.001237399],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9909185,0.0000802152,0.0008014842,0.0004183669,0.006138112,0.0006440475,0.0001697128,0.0007421456,0.0000873866],"genre_scores_gemma":[0.9959893,0.0000704841,0.001424163,0.001472744,0.0007744216,0.00008107763,1.35776e-7,0.0001707553,0.00001687974],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03656537,"threshold_uncertainty_score":0.9995504,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2580757382","doi":"10.1101/101030","title":"Real-time spike sorting platform for high-density extracellular probes with ground-truth validation and drift correction","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":179,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Howard Hughes Medical Institute","keywords":"Spike sorting; Spike (software development); Computer science; Ground truth; Sorting; Software; Noise (video); Artificial intelligence; Pipeline (software); Scalability; Pattern recognition (psychology); Cluster analysis; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.02090545389852464,"gpt":0.2231157205711518,"spread":0.2022102666726272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006776978,0.0005414472,0.0005292999,0.0002074934,0.0008993564,0.0008481815,0.000353813,0.0004197114,0.000007903644],"category_scores_gemma":[0.0008180038,0.0005121859,0.00009656431,0.0001713911,0.0001844441,0.0005841644,0.0002873044,0.000541009,0.00001349666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001921048,"about_ca_system_score_gemma":0.000216716,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002186428,"about_ca_topic_score_gemma":0.000007857523,"domain_scores_codex":[0.9970726,0.00008258117,0.0004791125,0.001436582,0.0004174981,0.0005115767],"domain_scores_gemma":[0.9971926,0.000242972,0.001090691,0.0009637342,0.0003296106,0.0001803621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001485801,0.000073632,0.0009501329,0.000265847,0.000024634,0.00001977579,0.000008721508,0.0001081127,0.9961226,0.002210068,0.00004290362,0.00002500844],"study_design_scores_gemma":[0.0006862516,0.0002511867,0.02918794,0.0003936502,0.0001545687,2.829481e-7,0.000002316325,0.01279864,0.9554774,0.00009211645,0.0001598295,0.0007957854],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896588,0.00002673962,0.005591874,0.0001030295,0.002577839,0.001516622,0.0000812805,0.0004300977,0.00001375798],"genre_scores_gemma":[0.9967357,0.0001356152,0.002205264,0.00003369493,0.0004731234,0.0002052248,0.000002152468,0.0001267332,0.00008248352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04064514,"threshold_uncertainty_score":0.999733,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3099052861","doi":"10.1101/400515","title":"Author-Reviewer Homophily in Peer Review","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":178,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"National Science Foundation","keywords":"Homophily; Confounding; Demographics; Logistic regression; Demography; Psychology; Medicine; Demographic economics; Social psychology; Sociology; Economics","retraction":null,"screen_n_in":null,"score":{"opus":0.3638006359188167,"gpt":0.4836889474673257,"spread":0.119888311548509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","bibliometrics","insufficient_payload"],"category_scores_codex":[0.08200852,0.000763354,0.001778029,0.0385141,0.000240635,0.00338491,0.007080552,0.0008425261,0.001612686],"category_scores_gemma":[0.1919454,0.0006093203,0.000561747,0.1419935,0.0003865289,0.0005720105,0.004526938,0.00192933,0.003937229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005955803,"about_ca_system_score_gemma":0.001697991,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008772712,"about_ca_topic_score_gemma":0.000005683486,"domain_scores_codex":[0.9738652,0.001069957,0.002520604,0.002969334,0.01808601,0.001488917],"domain_scores_gemma":[0.9525721,0.001749505,0.001423793,0.005871981,0.03714798,0.001234658],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002158237,0.0005437504,0.06723133,0.001746517,0.00009201357,0.0002430965,0.000009971846,0.000009749109,0.006332264,0.0006594496,0.9228542,0.0002560936],"study_design_scores_gemma":[0.0003479151,0.00008112756,0.2634701,0.002782657,0.00005002923,2.392518e-8,0.00000160228,0.0003880227,0.002495314,0.0000955949,0.7292637,0.001023912],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.517664,0.3947286,0.003643167,0.04749298,0.02504941,0.007994602,0.001573532,0.0007055147,0.001148232],"genre_scores_gemma":[0.9423407,0.04176798,0.008458409,0.003204332,0.001977487,0.0005735662,9.878969e-7,0.0002333427,0.001443144],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4246768,"threshold_uncertainty_score":0.9996358,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3091054887","doi":"10.1101/2020.09.30.318972","title":"LY-CoV555, a rapidly isolated potent neutralizing antibody, provides protection in a non-human primate model of SARS-CoV-2 infection","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":175,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"AbCellera (Canada)","funders":"Eli Lilly and Company","keywords":"Antibody; Virology; Rhesus macaque; Neutralizing antibody; Macaque; Respiratory tract; Biology; Viral replication; Primate; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Immunology; Coronavirus disease 2019 (COVID-19); Medicine; Respiratory system; Virus; Infectious disease (medical specialty); Disease","retraction":null,"screen_n_in":null,"score":{"opus":0.05422815699637865,"gpt":0.3386692338581752,"spread":0.2844410768617965,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001018767,0.0008242994,0.001383625,0.001252669,0.0001690396,0.0001855086,0.0004417809,0.0009560611,0.000001978542],"category_scores_gemma":[0.0003345977,0.0008681157,0.0004004535,0.001548238,0.0001993816,0.0003300947,0.0006145276,0.002086107,0.00002954392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000850771,"about_ca_system_score_gemma":0.001674913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00244256,"about_ca_topic_score_gemma":0.0000493249,"domain_scores_codex":[0.9951843,0.0002308449,0.001306858,0.001538021,0.0008431197,0.0008968374],"domain_scores_gemma":[0.9969657,0.00003412073,0.0007491519,0.001251531,0.0008723036,0.0001271809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006324843,0.0005796095,0.02101162,0.004955311,0.0002459527,0.0001190032,0.00007684722,0.0001506582,0.9721113,0.00008010424,0.00002504561,0.00001209134],"study_design_scores_gemma":[0.002065288,0.0004659245,0.03634169,0.002100269,0.0001840821,1.803965e-7,0.000002904681,0.086752,0.8710896,0.00001545455,0.0003139223,0.00066864],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9819438,0.0002320457,0.01214585,0.0003500255,0.0002870919,0.004434658,0.0000545293,0.0005243475,0.00002762634],"genre_scores_gemma":[0.9953103,0.00005154396,0.001234001,0.002220716,0.0002547355,0.0007034946,0.000001084018,0.0002234418,7.021661e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1010216,"threshold_uncertainty_score":0.999377,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4367602258","doi":"10.1101/2023.04.30.538439","title":"scGPT: Towards Building a Foundation Model for Single-Cell Multi-omics Using Generative AI","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":175,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Generative grammar; Inference; Synthetic biology; Computer science; Transformer; Systems biology; Artificial intelligence; Generative model; Codebase; Annotation; Computational biology; Biology; Software; Engineering; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.06310696845906083,"gpt":0.2756270159142196,"spread":0.2125200474551587,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005352391,0.0007427951,0.0006110782,0.0002263342,0.0003339569,0.0003514415,0.0005909919,0.00101699,0.000002805567],"category_scores_gemma":[0.0002051092,0.0008759835,0.0003793648,0.0002363501,0.0001337116,0.00002295024,0.0004535477,0.000500521,0.000008039124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003099082,"about_ca_system_score_gemma":0.001103676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008049155,"about_ca_topic_score_gemma":0.00001618596,"domain_scores_codex":[0.9967304,0.00009624502,0.0006825951,0.001484448,0.0002823942,0.0007238534],"domain_scores_gemma":[0.9974951,0.00002386504,0.0004348044,0.001006153,0.0008036583,0.0002364927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001116762,0.0002395976,0.0003097068,0.0003540572,0.0001565528,0.000004975249,0.00001960795,0.03608451,0.9625523,0.00006732268,0.00009418645,0.000005481518],"study_design_scores_gemma":[0.0008590381,0.0000943798,0.0000953567,0.0001046652,0.000135024,2.162275e-8,0.000002319468,0.3561772,0.6413161,0.00000634238,0.0005013194,0.0007082432],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4747638,0.0002866105,0.5223972,0.00007514066,0.001137033,0.0008064992,0.0004024384,0.0001296914,0.000001594524],"genre_scores_gemma":[0.823835,0.0001679254,0.174106,0.0003840744,0.0009317252,0.0002124211,0.00001587407,0.0003142586,0.00003275861],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3490711,"threshold_uncertainty_score":0.9993691,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3177472573","doi":"10.1101/2021.06.20.449169","title":"High-accuracy alignment ensembles enable unbiased assessments of sequence homology and phylogeny","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":162,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of British Columbia","keywords":"Phylogenetic tree; Phylogenetics; Inference; Polyphyly; Computer science; Multiple sequence alignment; Tree (set theory); Hidden Markov model; Computational biology; Biology; Artificial intelligence; Evolutionary biology; Sequence alignment; Mathematics; Clade; Genetics; Combinatorics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.01917017094318144,"gpt":0.2490745188194095,"spread":0.229904347876228,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003153529,0.0004732753,0.0006210991,0.00008435648,0.0001128549,0.00007457393,0.0003752621,0.0004725049,0.00001271237],"category_scores_gemma":[0.0001496874,0.0005194116,0.0001320956,0.0001252167,0.000225254,0.000002448454,0.001090894,0.0002232626,0.000001628818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005549655,"about_ca_system_score_gemma":0.0005380063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001818806,"about_ca_topic_score_gemma":0.000009124235,"domain_scores_codex":[0.9976777,0.000159478,0.0004999672,0.001020066,0.0002019648,0.0004408014],"domain_scores_gemma":[0.9978779,0.00004274069,0.0004494801,0.001067137,0.0004083055,0.0001544614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002921702,0.0001070347,0.00664947,0.0002427646,0.0004420558,0.00002749662,0.000007714077,0.000119823,0.9921516,0.0001343792,0.00008113619,0.000007311079],"study_design_scores_gemma":[0.0004902972,0.0001826989,0.04375839,0.0001019327,0.0001274222,9.696811e-8,0.00001381858,0.00002527665,0.9529222,0.00000712396,0.00186204,0.0005087046],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9910601,0.006982789,0.0005074799,0.00005565296,0.0006220085,0.000400463,0.0003513065,0.00001198844,0.000008203565],"genre_scores_gemma":[0.9849307,0.004525225,0.00994933,0.0001640304,0.0002279173,0.0001234696,0.000003751188,0.00006830881,0.000007292524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0392294,"threshold_uncertainty_score":0.9997258,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2756518443","doi":"10.1101/193144","title":"Multi-platform discovery of haplotype-resolved structural variation in human genomes","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":157,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"National Health and Medical Research Council; Defense Advanced Research Projects Agency; Advanced Research Projects Agency; National Institutes of Health; Medical Research Council; Ewha Womans University; European Molecular Biology Laboratory; Universiti Malaya; Wellcome Trust; Howard Hughes Medical Institute","keywords":"Indel; Structural variation; Haplotype; 1000 Genomes Project; Human genome; Genome; Biology; Computational biology; Genetics; DNA sequencing; Human genetic variation; Reference genome; Copy-number variation; Single-nucleotide polymorphism; Gene; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.01910857348246706,"gpt":0.2435442133565038,"spread":0.2244356398740367,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002752949,0.0003945705,0.0004790464,0.0001248081,0.0001578551,0.0001079208,0.000587897,0.0004553366,0.000003509212],"category_scores_gemma":[0.00009352151,0.0004115138,0.0001547875,0.00005869504,0.0001457027,0.000005445577,0.00077301,0.0002559816,0.000001832435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006351909,"about_ca_system_score_gemma":0.000252148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002273242,"about_ca_topic_score_gemma":0.00007121248,"domain_scores_codex":[0.9982613,0.00004332376,0.0004810083,0.000714298,0.0001559596,0.0003441649],"domain_scores_gemma":[0.9979546,0.000009856302,0.0005456556,0.001210775,0.0002089983,0.00007009352],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003215076,0.00004764273,0.03535691,0.0001303126,0.0001730157,0.00000400779,0.00001755441,0.0001779107,0.9639149,0.0001310531,0.00001249749,0.000002095589],"study_design_scores_gemma":[0.0005895747,0.00006462532,0.6450275,0.0000691926,0.00004748933,6.866075e-9,0.000002302564,0.0001422692,0.3532915,0.000008336555,0.0003573415,0.0003998413],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9948161,0.003366925,0.0004609178,0.00002151584,0.0005851719,0.0004343849,0.0002963203,0.00000995578,0.000008701375],"genre_scores_gemma":[0.9955091,0.0005355846,0.003468503,0.00002270476,0.00032113,0.00005962788,0.000002309595,0.00006830342,0.00001269524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6106233,"threshold_uncertainty_score":0.9998336,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3015347450","doi":"10.1101/2020.04.07.024752","title":"Human ACE2 receptor polymorphisms predict SARS-CoV-2 susceptibility","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":157,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Biology; Virus; Virology; Glycosylation; Coronavirus; Population; Angiotensin-converting enzyme 2; Genetics; Disease; Coronavirus disease 2019 (COVID-19); Infectious disease (medical specialty); Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.04888443749750188,"gpt":0.3102021881320735,"spread":0.2613177506345716,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.001375082,0.001274788,0.001788614,0.0006113135,0.0003612069,0.0003421853,0.001409817,0.001486755,0.000106693],"category_scores_gemma":[0.001059971,0.00131892,0.0007160436,0.001241234,0.0006267746,0.0002241011,0.001716372,0.003220036,0.0009728237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001221526,"about_ca_system_score_gemma":0.002774949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004153414,"about_ca_topic_score_gemma":0.00001936849,"domain_scores_codex":[0.992279,0.0003821046,0.001313494,0.002848196,0.00169178,0.001485424],"domain_scores_gemma":[0.994229,0.0000969823,0.0005752366,0.003658614,0.001051278,0.0003889518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003041737,0.00051644,0.05308444,0.001273334,0.0004555572,0.0003091417,0.0000320258,3.298823e-7,0.9371285,0.000228869,0.006662761,0.000004435603],"study_design_scores_gemma":[0.001973419,0.0004429409,0.05433838,0.0007024364,0.0003015557,9.653185e-8,0.000006106287,0.0001556336,0.8745471,0.000007971504,0.06644201,0.001082311],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904128,0.001161141,0.0003259268,0.00184969,0.001381487,0.002651155,0.0004917789,0.001562959,0.0001630487],"genre_scores_gemma":[0.9750931,0.00002333213,0.002003707,0.01972665,0.002295852,0.0004527707,0.000001820786,0.0003948558,0.000007886436],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06258135,"threshold_uncertainty_score":0.9998095,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3025078982","doi":"10.1101/2020.05.12.088716","title":"Potent neutralizing antibodies from COVID-19 patients define multiple targets of vulnerability","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":153,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Institute of Infection and Immunity; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Universiteit van Amsterdam; Amsterdam University Medical Centers; Bill and Melinda Gates Foundation","keywords":"Epitope; Antibody; Virology; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Coronavirus disease 2019 (COVID-19); Spike Protein; Neutralizing antibody; Vulnerability (computing); 2019-20 coronavirus outbreak; Antigen; Immunology; Biology; Medicine; Outbreak; Disease; Computer science; Infectious disease (medical specialty); Computer security; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.04948078299175647,"gpt":0.3053115363156871,"spread":0.2558307533239307,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007088429,0.0007852952,0.001514798,0.0003793145,0.0002015231,0.0001006007,0.0007038842,0.0006839548,0.00003043316],"category_scores_gemma":[0.003971903,0.0007797983,0.0004661525,0.0005414443,0.0003600144,0.0001287708,0.001134894,0.001465822,0.0000676167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007421742,"about_ca_system_score_gemma":0.002085694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001974902,"about_ca_topic_score_gemma":0.00002151843,"domain_scores_codex":[0.9948925,0.0003237725,0.001140153,0.001698751,0.001134927,0.0008098741],"domain_scores_gemma":[0.9956728,0.000404155,0.0006078326,0.001857708,0.0009668921,0.0004905845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004147562,0.0005350422,0.548777,0.00150089,0.000297148,0.0001042547,0.00004532059,0.00000928598,0.4479136,0.00003125795,0.0003677915,0.000003666313],"study_design_scores_gemma":[0.00252513,0.0001824599,0.4917383,0.0003607187,0.0001865459,1.08003e-8,0.000008070528,0.0004714568,0.4936365,0.0000138946,0.01030438,0.0005725185],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9917454,0.002035005,0.001031299,0.0009034595,0.0007486221,0.001734731,0.001354549,0.0004302989,0.00001666873],"genre_scores_gemma":[0.9833415,0.00007675402,0.003519113,0.0123246,0.000412192,0.0001643027,0.000004920504,0.0001561567,4.578108e-7],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05703872,"threshold_uncertainty_score":0.9994653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2905102064","doi":"10.1101/488460","title":"The consensus molecular classification of muscle-invasive bladder cancer","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bladder and Urothelial Cancer Treatments","field":"Medicine","cited_by":152,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University Health Network; Canada's Michael Smith Genome Sciences Centre; University of Toronto; BC Cancer Agency","funders":"National Cancer Institute; National Human Genome Research Institute; Cancerfonden","keywords":"Bladder cancer; Stromal cell; Disease; Transcriptome; Biology; Computational biology; Bioinformatics; Clinical trial; Medicine; Cancer; Pathology; Internal medicine; Gene; Gene expression; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02447907913308759,"gpt":0.2716072786808798,"spread":0.2471281995477922,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003000865,0.0004591384,0.0005787656,0.0001298885,0.0001715202,0.00006260337,0.0003301255,0.0004381404,0.00008958034],"category_scores_gemma":[0.000257886,0.0003591871,0.0002382996,0.000310771,0.0004690316,0.00002717183,0.0001938204,0.0004818637,0.00004509998],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003408942,"about_ca_system_score_gemma":0.002190736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002426527,"about_ca_topic_score_gemma":0.00001684511,"domain_scores_codex":[0.9975949,0.000128452,0.0005696271,0.0007495604,0.0005176286,0.0004398429],"domain_scores_gemma":[0.9963339,0.0001214342,0.0005478256,0.001546587,0.001216881,0.0002333912],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002005303,0.0002278481,0.01047688,0.0004856107,0.001312165,0.00007184256,0.00002445688,0.000007913375,0.9844149,0.0004909004,0.002265073,0.00002190957],"study_design_scores_gemma":[0.001358263,0.0001932212,0.3254968,0.0007765178,0.001060223,4.060717e-8,0.0000111037,0.00008996567,0.6642762,0.000009141996,0.006295701,0.0004328194],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9891399,0.005563322,0.0001644811,0.001612556,0.001377408,0.001449828,0.000404334,0.0001627155,0.0001254532],"genre_scores_gemma":[0.9963748,0.001340533,0.0008134648,0.00033012,0.0005349166,0.0004600445,5.828517e-7,0.0001238528,0.00002169808],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3201387,"threshold_uncertainty_score":0.999886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2809940376","doi":"10.1101/359513","title":"A large-scale, standardized physiological survey reveals higher order coding throughout the mouse visual cortex","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":152,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; National Science Foundation","keywords":"Visual cortex; Neural coding; Neuroscience; Coding (social sciences); Sensory system; Stimulus (psychology); Computer science; Convolutional neural network; Psychology; Artificial intelligence; Cognitive psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.03809633246254136,"gpt":0.2892965557796878,"spread":0.2512002233171464,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001911724,0.0008033486,0.000907574,0.0001348244,0.0007554527,0.0005610929,0.001083394,0.0006622413,0.0002479071],"category_scores_gemma":[0.00163922,0.0005805813,0.0002662508,0.0009656376,0.0005321635,0.0002155996,0.001273466,0.001327657,0.0001697604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002549595,"about_ca_system_score_gemma":0.0003065178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004394789,"about_ca_topic_score_gemma":0.000009521126,"domain_scores_codex":[0.9940749,0.001347357,0.000760873,0.001925203,0.0008704317,0.001021222],"domain_scores_gemma":[0.996303,0.0005054725,0.0006959054,0.001512539,0.0007297953,0.0002532449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0001847103,0.0002141173,0.00204841,0.00008163527,0.00004656253,0.00002507112,0.00001024673,0.0000244243,0.993686,0.0006526973,0.003025705,4.649991e-7],"study_design_scores_gemma":[0.001976758,0.0004202327,0.6056963,0.0002475747,0.0001601608,8.147441e-8,0.000005591543,0.006352683,0.3727283,0.0000425578,0.01022402,0.002145665],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904715,0.0000754584,0.00265029,0.0002958728,0.003049303,0.001187467,0.001653468,0.0005936173,0.00002299405],"genre_scores_gemma":[0.9959305,0.0002618638,0.0003744976,0.002111593,0.0008878597,0.0001646599,0.000002506876,0.0001651568,0.0001013765],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6209576,"threshold_uncertainty_score":0.9996645,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2547528004","doi":"10.1101/043430","title":"Computational Pan-Genomics: Status, Promises and Challenges","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":151,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency","funders":"Lorentz Center; Academy of Finland; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Koninklijke Nederlandse Akademie van Wetenschappen","keywords":"Genomics; Data science; Computer science; Computational genomics; Genome; Construct (python library); Homo sapiens; Computational biology; Computational model; Biology; Artificial intelligence; Genetics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01801472310791249,"gpt":0.2168702063329543,"spread":0.1988554832250418,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000220083,0.0004352611,0.0003662895,0.00007821312,0.0001324722,0.00007665288,0.0002610222,0.0003752992,0.000005011986],"category_scores_gemma":[0.00007928653,0.0004103232,0.0000966676,0.00003772699,0.00018508,0.00000167407,0.0008059616,0.0001648885,0.00001063566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005515759,"about_ca_system_score_gemma":0.0004108583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009157396,"about_ca_topic_score_gemma":0.000002937073,"domain_scores_codex":[0.9980735,0.00007305823,0.0003194943,0.0009389197,0.0001496262,0.0004454546],"domain_scores_gemma":[0.9986503,0.00002932131,0.0002274311,0.0006304579,0.0002774429,0.0001850862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00004766573,0.00006637401,0.006353012,0.0002869759,0.0004095117,0.000005438279,0.00001617464,0.00005970132,0.9917675,0.0007098115,0.0002328128,0.00004499125],"study_design_scores_gemma":[0.00177953,0.0003456118,0.469478,0.0002829944,0.0001963809,9.641532e-8,0.0000179623,0.00009496477,0.3389003,0.0001753957,0.1867133,0.002015557],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9506441,0.04692802,0.0003724074,0.0004731982,0.000460941,0.0004757768,0.0005863461,0.00002585189,0.00003333544],"genre_scores_gemma":[0.9640321,0.03118305,0.003838273,0.0001111997,0.0006165769,0.0001243292,0.000001096049,0.00008675299,0.000006628061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6528673,"threshold_uncertainty_score":0.9998348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891242822","doi":"10.1101/416859","title":"Polygenic Prediction via Bayesian Regression and Continuous Shrinkage Priors","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":150,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Horizon 2020 Framework Programme; Government of Canada; Cancer Research UK; National Institutes of Health; European Commission; Canadian Institutes of Health Research; Genome Canada","keywords":"Biobank; Prior probability; Bayesian probability; Regression; Computer science; Linkage disequilibrium; Multivariate statistics; Sample size determination; Genome-wide association study; Lasso (programming language); Polygenic risk score; Statistics; Posterior probability; Artificial intelligence; Machine learning; Mathematics; Bioinformatics; Biology; Single-nucleotide polymorphism; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.007167045890183553,"gpt":0.2218801174452537,"spread":0.2147130715550702,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006916554,0.0004751175,0.000499856,0.0001271674,0.0002161729,0.00006873638,0.0003237345,0.001153639,0.00002250631],"category_scores_gemma":[0.0003251787,0.0004731429,0.0001480274,0.0001284712,0.0002024562,0.000006270319,0.0006599864,0.0003957605,0.00001850317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007441325,"about_ca_system_score_gemma":0.0002514223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004270099,"about_ca_topic_score_gemma":0.000005971555,"domain_scores_codex":[0.9974083,0.0002508165,0.000538039,0.001100718,0.0001810992,0.0005209778],"domain_scores_gemma":[0.9978811,0.00002315944,0.0004875169,0.001042543,0.0003134827,0.0002522036],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003844847,0.0000685544,0.144376,0.00008982725,0.0002039765,0.000006604803,0.000008127884,0.00001254953,0.8523686,0.00001841345,0.002792819,0.00001611996],"study_design_scores_gemma":[0.000770674,0.0003829677,0.8718781,0.0002052077,0.0001957778,1.886787e-7,0.000006357559,0.0009328459,0.1130166,0.00001155062,0.01172898,0.0008706961],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9846108,0.002281633,0.01102903,0.0001910298,0.001056558,0.0005168896,0.0001917498,0.00009968913,0.00002260955],"genre_scores_gemma":[0.9912748,0.001017435,0.006154099,0.0002147773,0.001103639,0.0001023355,0.000005459411,0.00009281166,0.00003464588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.739352,"threshold_uncertainty_score":0.999772,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2519086121","doi":"10.1101/074153","title":"Improving genetic diagnosis in Mendelian disease with transcriptome sequencing","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Muscle Physiology and Disorders","field":"Biochemistry, Genetics and Molecular Biology","cited_by":150,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hospital for Sick Children","funders":"Common Fund; National Institute of Neurological Disorders and Stroke; National Institute of General Medical Sciences; National Cancer Institute; National Eye Institute; National Human Genome Research Institute; Medical Research Council; Orionin Tutkimussäätiö; National Institutes of Health; National Institute of Mental Health; National Heart, Lung, and Blood Institute; Emil Aaltosen Säätiö; Suomen Kulttuurirahasto; NIH Office of the Director; Academy of Finland; National Health and Medical Research Council; Muscular Dystrophy Association; Broad Institute; National Institute on Drug Abuse; University of Miami","keywords":"False discovery rate; Exome sequencing; Transcriptome; Genetics; Biology; Exome; Computational biology; Whole genome sequencing; Mendelian inheritance; Genetic testing; splice; Alternative splicing; Genetic heterogeneity; Bioinformatics; Disease; Gene; Genome; Mutation; Medicine; Internal medicine; Phenotype; Gene expression; Exon","retraction":null,"screen_n_in":null,"score":{"opus":0.009084199820832795,"gpt":0.2054461952049585,"spread":0.1963619953841257,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002059156,0.0005398606,0.0003927112,0.0001851623,0.00009968115,0.00005588914,0.0004789755,0.0004723178,0.00002788668],"category_scores_gemma":[0.0001023916,0.0004792285,0.0001429941,0.0001813995,0.000180293,0.00001182339,0.0002563298,0.0003648649,0.00001199194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001249375,"about_ca_system_score_gemma":0.0009054497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008174339,"about_ca_topic_score_gemma":0.00002637869,"domain_scores_codex":[0.997409,0.0001448877,0.0003900022,0.001231739,0.0001950961,0.0006292344],"domain_scores_gemma":[0.9981586,0.00001797875,0.0002205389,0.001127621,0.0001523552,0.0003228576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000232024,0.00008827051,0.04734895,0.0003063557,0.00009487419,0.00005900747,0.000005701912,0.0002214165,0.951517,0.00004313939,0.00007309839,0.00001012346],"study_design_scores_gemma":[0.002563626,0.0003718403,0.4201124,0.0009529704,0.0002282984,3.498171e-8,0.0000112081,0.0002783471,0.5713965,0.00002620093,0.001856998,0.002201565],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928675,0.002759422,0.002962947,0.0002068325,0.0003176892,0.0005945903,0.000207706,0.00007338347,0.000009888702],"genre_scores_gemma":[0.9966348,0.0006310191,0.001307545,0.000341245,0.0003063649,0.000654578,0.000001584395,0.0001187918,0.000004071799],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3801205,"threshold_uncertainty_score":0.9997659,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3122528890","doi":"10.1101/2021.01.18.426733","title":"Universal DNA methylation age across mammalian tissues","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":150,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"LGL (Canada); Vancouver Aquarium; BC Children's Hospital; Fisheries and Oceans Canada","funders":"NHLBI Division of Intramural Research; Center for Information Technology; National Heart, Lung, and Blood Institute; Open Philanthropy Project; Jonsson Comprehensive Cancer Center; National Institute on Aging; National Institutes of Health; U.S. Department of Health and Human Services; Cancer Research UK; Paul G. Allen Frontiers Group; Department of Science and Technology, Ministry of Science and Technology, India; National Geographic Society","keywords":"Epigenetics; Biology; DNA methylation; Methylation; Chromatin; Genomic imprinting; Genetics; Evolutionary biology; Gene; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.01447566630768377,"gpt":0.2530437108179064,"spread":0.2385680445102226,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005330741,0.0004814176,0.0004064968,0.00009021607,0.000179087,0.0003013639,0.0004275692,0.0009015381,0.0000363621],"category_scores_gemma":[0.0001899121,0.0005776616,0.000213588,0.0002372327,0.0001164717,0.0000127326,0.0007229777,0.0003982976,0.00001903105],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000100982,"about_ca_system_score_gemma":0.0003403981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006857907,"about_ca_topic_score_gemma":0.00003256708,"domain_scores_codex":[0.9974329,0.0002158,0.0004312566,0.001094405,0.0003134466,0.0005121724],"domain_scores_gemma":[0.9976849,0.0000176004,0.0003324967,0.001266179,0.0004746753,0.0002241226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002256764,0.00006531004,0.00252141,0.0001183243,0.0001216174,0.00006502816,0.00002554213,0.0002025763,0.9967142,0.00005892074,0.00006991567,0.00001459259],"study_design_scores_gemma":[0.0003564709,0.00007391526,0.03865251,0.00007809185,0.00006566261,6.5333e-9,0.00001773449,0.00004759274,0.9360762,0.000002468768,0.02399381,0.0006355054],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869413,0.005010651,0.006243633,0.00009400193,0.001002815,0.0004152613,0.0001745241,0.00008305456,0.00003479339],"genre_scores_gemma":[0.9924393,0.001084493,0.005364778,0.00007497209,0.0007877863,0.00004970438,0.00001791824,0.0001222699,0.00005875996],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06063795,"threshold_uncertainty_score":0.9996675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3037906880","doi":"10.1101/2020.06.26.173724","title":"Large-scale association analyses identify host factors influencing human gut microbiome composition","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":149,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Hospital for Sick Children; University of Toronto; Mount Sinai Hospital","funders":"","keywords":"Genome-wide association study; Biology; Microbiome; Genetics; Heritability; Locus (genetics); Genetic association; Bifidobacterium; Mendelian randomization; Quantitative trait locus; Genotype; Gene; Single-nucleotide polymorphism; Bacteria; Lactobacillus; Genetic variants","retraction":null,"screen_n_in":null,"score":{"opus":0.02258849247789296,"gpt":0.2918691860487045,"spread":0.2692806935708115,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004305534,0.0005918788,0.0006252892,0.0002200018,0.0003968707,0.0002814366,0.000524085,0.00105128,0.00003415507],"category_scores_gemma":[0.00008169561,0.0006790319,0.0003257102,0.0003415326,0.0000550526,0.00001784624,0.0006785278,0.0007016401,0.00005952761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004708765,"about_ca_system_score_gemma":0.0004145201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001170247,"about_ca_topic_score_gemma":0.00002737268,"domain_scores_codex":[0.9969344,0.0002230108,0.0006839178,0.001181331,0.0002824619,0.0006949522],"domain_scores_gemma":[0.9975013,0.00001578798,0.0008159248,0.0008719193,0.0004970116,0.0002980699],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001448921,0.0001089418,0.0495037,0.0002913909,0.0002599413,0.000006360922,0.00003994757,0.00001353859,0.9483668,0.000008022686,0.001386835,4.255638e-8],"study_design_scores_gemma":[0.000347205,0.00005465155,0.3810223,0.0001196073,0.0001413507,1.136249e-8,0.00001321689,0.000009722376,0.6155128,4.353315e-7,0.002281658,0.0004970692],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9960296,0.0006309638,0.00076622,0.0001969264,0.0006621506,0.0005190289,0.001038246,0.0001498936,0.000006991195],"genre_scores_gemma":[0.9975913,0.0001605051,0.0008157338,0.0005328801,0.000675662,0.00003549626,0.00005597185,0.0001208614,0.00001156899],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.332854,"threshold_uncertainty_score":0.9995661,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3001500463","doi":"10.1101/2020.01.21.911859","title":"A Connectome of the Adult <i>Drosophila</i> Central Brain","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neurobiology and Insect Physiology Research","field":"Neuroscience","cited_by":148,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Connectome; Computer science; Biological neural network; Connectomics; Set (abstract data type); Neuroscience; Drosophila melanogaster; Neuronal circuits; Artificial intelligence; Theoretical computer science; Machine learning; Biology; Functional connectivity","retraction":null,"screen_n_in":null,"score":{"opus":0.02532568541591913,"gpt":0.2457847737487293,"spread":0.2204590883328102,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002573048,0.0004898882,0.000661625,0.0001171894,0.0002571326,0.00006020479,0.001926323,0.0005482908,0.00004703207],"category_scores_gemma":[0.003429183,0.0003940603,0.0003215458,0.0007569549,0.0009877355,0.0001005191,0.001653667,0.001932998,0.00007265066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007614045,"about_ca_system_score_gemma":0.000711928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001986508,"about_ca_topic_score_gemma":8.59317e-7,"domain_scores_codex":[0.9959973,0.0009375286,0.0005441469,0.0013164,0.0003881195,0.0008164704],"domain_scores_gemma":[0.9969792,0.0005213889,0.000468212,0.001521782,0.0002503541,0.0002590272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009028893,0.0001143974,0.002278971,0.0002240805,0.00003136172,0.00003839315,0.00001168818,0.00002044564,0.9886018,0.007420974,0.001167479,1.180848e-7],"study_design_scores_gemma":[0.0004269183,0.0001053698,0.04817713,0.0001339697,0.00002693475,4.91288e-8,6.004233e-7,0.0001316305,0.9499241,0.00006439265,0.000647267,0.0003616771],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9907577,0.00008592504,0.00002804785,0.00581829,0.001632497,0.0008747448,0.000552002,0.0002197549,0.00003105962],"genre_scores_gemma":[0.9929126,0.0001159938,0.00008013596,0.006330885,0.0003710897,0.0001001704,1.153118e-7,0.00008249539,0.00000650294],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04589817,"threshold_uncertainty_score":0.9998511,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3016263801","doi":"10.1101/2020.04.07.030650","title":"The spatial and cell-type distribution of SARS-CoV-2 receptor ACE2 in human and mouse brain","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Long-Term Effects of COVID-19","field":"Medicine","cited_by":145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre for Addiction and Mental Health","funders":"Zhejiang Chinese Medical University; Natural Science Foundation of Zhejiang Province; National Natural Science Foundation of China","keywords":"Olfactory bulb; Biology; Human brain; Hippocampal formation; Hippocampus; Neuroscience; Cell type; Angiotensin-converting enzyme 2; Choroid plexus; Central nervous system; Cell; Pathology; Coronavirus disease 2019 (COVID-19); Medicine; Disease; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.0176609400284353,"gpt":0.2685096965620769,"spread":0.2508487565336416,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007551527,0.0004299906,0.0006886834,0.0001264333,0.0001384042,0.0001119672,0.0002694156,0.0004546283,0.000004724743],"category_scores_gemma":[0.001522069,0.0003779477,0.00008118479,0.0003104409,0.0003156765,0.00008270972,0.0005629602,0.0008130877,0.000006852985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002326518,"about_ca_system_score_gemma":0.0004754301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003659823,"about_ca_topic_score_gemma":0.00003167924,"domain_scores_codex":[0.9977342,0.0002232431,0.0005492604,0.0007600132,0.0003575153,0.000375736],"domain_scores_gemma":[0.9979608,0.0003549722,0.0003899724,0.000829326,0.0002531294,0.0002118126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002534377,0.00008920612,0.03245774,0.001504631,0.00006707459,0.00003889377,0.00002573056,0.000001471948,0.9638388,0.0002580655,0.001461565,0.000003461245],"study_design_scores_gemma":[0.00165159,0.0002934928,0.1442364,0.0005259407,0.0001027851,3.002701e-8,0.000003267432,0.0002176118,0.8489442,0.000005112805,0.003649542,0.0003699865],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9934416,0.00103805,0.0002109076,0.003284159,0.0003192904,0.001394429,0.0001814252,0.0001265789,0.000003601279],"genre_scores_gemma":[0.998457,0.000357494,0.0003429194,0.0004247995,0.000266018,0.00006189424,0.000003821704,0.00008187287,0.000004156122],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1148945,"threshold_uncertainty_score":0.9998673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2899795521","doi":"10.1101/459529","title":"Nanopore native RNA sequencing of a human poly(A) transcriptome","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"RNA modifications and cancer","field":"Biochemistry, Genetics and Molecular Biology","cited_by":142,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of Toronto; Ontario Institute for Cancer Research","funders":"Biotechnology and Biological Sciences Research Council; Canadian Institutes of Health Research; Medical Research Council; Surgical Reconstruction and Microbiology Research Centre; Government of Ontario; National Institutes of Health; Ontario Institute for Cancer Research; Oxford Nanopore Technologies; Wellcome Trust","keywords":"Nanopore sequencing; Nanopore; RNA; Computational biology; Transcriptome; cDNA library; Complementary DNA; Gene isoform; Biology; DNA sequencing; Genetics; Gene; Gene expression; Nanotechnology; Materials science","retraction":null,"screen_n_in":null,"score":{"opus":0.01930009420118048,"gpt":0.2511233921775433,"spread":0.2318232979763628,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003508369,0.0004121584,0.0004168019,0.0001585364,0.0001558324,0.00005539766,0.00059302,0.0005694829,0.00005019419],"category_scores_gemma":[0.00005949032,0.0004444842,0.0002205367,0.0002281843,0.0002961967,0.000008206614,0.0002332354,0.0003154093,0.000008310661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001439632,"about_ca_system_score_gemma":0.0007542346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007859887,"about_ca_topic_score_gemma":0.0000061677,"domain_scores_codex":[0.9978942,0.00009512064,0.0005012726,0.0008617132,0.0002725547,0.0003751476],"domain_scores_gemma":[0.9974125,0.000006038166,0.0004531969,0.001270925,0.0007068082,0.0001505115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002280956,0.00005994178,0.0005645557,0.000172818,0.0001848673,0.000003810266,0.00002012175,0.000007706692,0.9982147,0.0003301127,0.0004162095,0.000002325009],"study_design_scores_gemma":[0.0003471426,0.0001610169,0.006798107,0.0001977333,0.0000791921,1.329463e-8,0.000009665305,0.00002628157,0.9882179,0.000005035183,0.00366912,0.0004888155],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937236,0.002964088,0.001793684,0.00006138071,0.0005073848,0.0004114298,0.0003777118,0.0000553763,0.0001053969],"genre_scores_gemma":[0.9970162,0.00028174,0.001711976,0.0001037006,0.0006015773,0.0001479206,0.000002911147,0.00009818691,0.00003581533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009996845,"threshold_uncertainty_score":0.9998007,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3144086685","doi":"10.1101/2021.03.31.437925","title":"SARS-CoV-2 immune evasion by variant B.1.427/B.1.429","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":140,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; Fast Grants; Natural Sciences and Engineering Research Council of Canada; Burroughs Wellcome Fund","keywords":"Virology; Antibody; Neutralization; Immune escape; Antigen; Monoclonal antibody; Titer; Neutralizing antibody; Signal peptide; Biology; Immune system; Immunology; Peptide sequence; Gene; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.03105230959616127,"gpt":0.2927208488339115,"spread":0.2616685392377502,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.001539033,0.001181405,0.001746673,0.0006296842,0.0003024506,0.0005584577,0.001097281,0.001508054,0.00006467634],"category_scores_gemma":[0.001003248,0.001200974,0.0006751561,0.001327146,0.0002943988,0.0002594845,0.001629823,0.002753163,0.0004134915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001089857,"about_ca_system_score_gemma":0.003574427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006285129,"about_ca_topic_score_gemma":0.000008029289,"domain_scores_codex":[0.9929017,0.0003688387,0.001261763,0.002325888,0.001665284,0.001476497],"domain_scores_gemma":[0.9939548,0.0001868212,0.0005325246,0.003629094,0.001461954,0.0002347715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002455538,0.0007559746,0.004191912,0.001060713,0.0005550203,0.001749375,0.00002415844,7.719202e-7,0.988426,0.00009979905,0.002877663,0.00001306781],"study_design_scores_gemma":[0.001971804,0.0001844335,0.008311366,0.001519738,0.0003436047,6.33869e-7,0.000009794011,0.0003645145,0.9020913,0.000001613746,0.08412533,0.001075871],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9815899,0.01137648,0.001633229,0.0006744443,0.001827117,0.00174985,0.0002189103,0.0007628289,0.000167218],"genre_scores_gemma":[0.980378,0.0002962952,0.00221786,0.01532854,0.0009168488,0.0004563356,0.000002733986,0.000392041,0.00001133634],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08633468,"threshold_uncertainty_score":0.9997882,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3118356453","doi":"10.1101/2021.01.14.426475","title":"N-terminal domain antigenic mapping reveals a site of vulnerability for SARS-CoV-2","year":2021,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Fast Grants; University of Washington; National Institute of General Medical Sciences; National Institute of Allergy and Infectious Diseases; Natural Sciences and Engineering Research Council of Canada; Burroughs Wellcome Fund","keywords":"Epitope; Virology; Monoclonal antibody; Glycoprotein; Antigen; Biology; Antibody; Effector; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Neutralization; Epitope mapping; Coronavirus disease 2019 (COVID-19); Cell biology; Molecular biology; Genetics; Virus; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.04800187617893253,"gpt":0.3219942797676448,"spread":0.2739924035887122,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002560625,0.0007671963,0.001777873,0.0006202977,0.0001904053,0.0001797501,0.0006027016,0.0009009902,0.00001349314],"category_scores_gemma":[0.001155346,0.0008098898,0.0007929037,0.0008565169,0.0003413661,0.0001562937,0.0007966525,0.001314677,0.00002774359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005708031,"about_ca_system_score_gemma":0.002576414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001611513,"about_ca_topic_score_gemma":0.00001149419,"domain_scores_codex":[0.9945928,0.0003440208,0.001320989,0.001751999,0.0009320804,0.001058089],"domain_scores_gemma":[0.994693,0.00030855,0.0006543543,0.00260625,0.001596895,0.0001409184],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003212432,0.0004376097,0.05192857,0.005199727,0.0003952858,0.0003394847,0.00006784432,4.747392e-7,0.9410096,0.00006904678,0.0002224384,0.000008702733],"study_design_scores_gemma":[0.001834737,0.0001907116,0.06695214,0.001880578,0.0001898857,3.886059e-7,0.0000192037,0.0001867747,0.9153173,0.00001303535,0.01271638,0.00069886],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894552,0.002172638,0.004340049,0.0002203538,0.0006273257,0.002573609,0.0003541303,0.000234182,0.00002251158],"genre_scores_gemma":[0.9792774,0.00003991984,0.01443825,0.004831593,0.0006509341,0.0005764674,0.000001257737,0.0001818591,0.000002296981],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02569227,"threshold_uncertainty_score":0.9994352,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2403520411","doi":"10.1101/054262","title":"Best Practices in Data Analysis and Sharing in Neuroimaging using MRI","year":2016,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":136,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Instituto Nacional de Psiquiatría Ramón de la Fuente Muñiz; National University of Singapore; Child Mind Institute; Medical Research Council; University of Warwick; McGill University","keywords":"Neuroimaging; Best practice; Transparency (behavior); Data sharing; Open science; Data science; Computer science; Psychology; Medicine; Political science; Neuroscience; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.1212943592223996,"gpt":0.3211161601627231,"spread":0.1998218009403235,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001541351,0.0005066308,0.0007396498,0.001446145,0.0001951769,0.0004269578,0.001212776,0.0002212551,0.00001196277],"category_scores_gemma":[0.01668942,0.0005236317,0.00007433748,0.002051727,0.0002146649,0.001143637,0.004714279,0.0009264678,0.00001306528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003241312,"about_ca_system_score_gemma":0.0002902417,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000817958,"about_ca_topic_score_gemma":0.0003040404,"domain_scores_codex":[0.994994,0.0003441631,0.000596569,0.002977586,0.000474472,0.0006132467],"domain_scores_gemma":[0.994118,0.00244707,0.0008671227,0.002318307,0.0001171393,0.0001323533],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00003136248,0.0001282607,0.432193,0.0001794188,0.0001002066,0.0002302253,0.0000148609,0.0004366651,0.5664572,0.0002064605,0.00001945359,0.000002977549],"study_design_scores_gemma":[0.00140598,0.00004177392,0.7678447,0.001618504,0.0008795935,2.274142e-7,0.00002098358,0.1042893,0.1195609,0.00004931005,0.002072611,0.002215975],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941058,0.0006235152,0.00133809,0.002355113,0.0006386339,0.000504786,0.0002721765,0.0001365352,0.00002537304],"genre_scores_gemma":[0.9968577,0.0004462691,0.001882332,0.0004781329,0.0002053603,0.00004791118,1.500996e-7,0.00007788878,0.000004277161],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4468962,"threshold_uncertainty_score":0.9997215,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2898626731","doi":"10.1101/457739","title":"Image processing and analysis methods for the Adolescent Brain Cognitive Development Study","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":134,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"National Institute on Minority Health and Health Disparities; Office of Research on Women's Health; Office of Behavioral and Social Sciences Research; National Institute on Drug Abuse; U.S. Department of Health and Human Services; National Institutes of Health; National Institute of Mental Health; National Institute on Alcohol Abuse and Alcoholism","keywords":"Neuroimaging; Cognition; Functional magnetic resonance imaging; Psychology; Functional neuroimaging; Neuroscience","retraction":null,"screen_n_in":null,"score":{"opus":0.0504529378185759,"gpt":0.3257347586694593,"spread":0.2752818208508834,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002813102,0.0005908504,0.0007105973,0.0004019599,0.001169987,0.0005046721,0.0005147739,0.0001817826,0.00001130865],"category_scores_gemma":[0.01611335,0.0004815835,0.0001773463,0.001173912,0.0004676653,0.0001728538,0.00120044,0.0005430561,0.00001014406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002318053,"about_ca_system_score_gemma":0.0005506803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001039875,"about_ca_topic_score_gemma":0.000008777146,"domain_scores_codex":[0.9959922,0.0006658123,0.0005214426,0.001840327,0.0004494741,0.0005307428],"domain_scores_gemma":[0.9912333,0.006568806,0.0004988515,0.0006956132,0.0008566328,0.0001468115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000686553,0.002695987,0.05748465,0.001914736,0.005368666,0.00005332945,0.001244511,0.00004509911,0.9277992,0.0001302574,0.001652052,0.000924937],"study_design_scores_gemma":[0.001155017,0.0001979942,0.595498,0.0003388434,0.002183915,2.527316e-8,0.0001313543,0.006798624,0.3878678,0.000005954265,0.004629285,0.00119314],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5806954,0.001204378,0.4094822,0.002218728,0.0009700049,0.004802686,0.0002046232,0.0004148342,0.000007146318],"genre_scores_gemma":[0.9560145,0.00003315749,0.04030005,0.00180509,0.0002975348,0.001451871,1.288141e-7,0.00009025687,0.000007463348],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5399314,"threshold_uncertainty_score":0.9997636,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2917862094","doi":"10.1101/554170","title":"A global synthesis reveals biodiversity-mediated benefits for crop production","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Plant and animal studies","field":"Agricultural and Biological Sciences","cited_by":126,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Biodiversa+","keywords":"Ecosystem services; Species richness; Biodiversity; Agroecosystem; Ecosystem; Agroforestry; Context (archaeology); Land use; Abundance (ecology); Environmental resource management; Agricultural biodiversity; Ecology; Business; Geography; Environmental science; Agriculture; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.0354730834110209,"gpt":0.1968787640979781,"spread":0.1614056806869572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003845504,0.0004197728,0.000539265,0.00002735544,0.0003681788,0.000159001,0.0004800867,0.000418103,0.00003683702],"category_scores_gemma":[0.0005615006,0.0002115437,0.0002186747,0.0004241425,0.00007254051,0.0001077127,0.0004235005,0.000189549,0.000160343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001590899,"about_ca_system_score_gemma":0.0000454441,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001442576,"about_ca_topic_score_gemma":0.00009879838,"domain_scores_codex":[0.9978832,0.00006662268,0.000303462,0.0009554164,0.0002751071,0.0005161809],"domain_scores_gemma":[0.9988424,0.0001576273,0.0003174442,0.0001239617,0.0004131216,0.0001454881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.000156707,0.0001854865,0.1782886,0.0002779742,0.0002399965,0.000008064086,0.000003459231,0.00003047687,0.8106051,0.0001305952,0.01004199,0.0000315378],"study_design_scores_gemma":[0.0001162773,0.00009781834,0.9622717,0.0002886029,0.0001417344,1.400955e-8,0.000005359955,0.0000246276,0.02534577,0.000002325008,0.01105085,0.0006548626],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.989167,0.001147754,0.000004221438,0.001054962,0.0007217068,0.0009614804,0.006629605,0.0003045713,0.000008735267],"genre_scores_gemma":[0.9981662,0.0005362711,0.0002844222,0.0001409299,0.0007079858,0.0001498152,0.000002978184,0.000003155547,0.000008229416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7852593,"threshold_uncertainty_score":0.86265,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3098627931","doi":"10.1101/388165","title":"Expanding Parkinson’s disease genetics: novel risk loci, genomic context, causal insights and heritable risk","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Parkinson's Disease Mechanisms and Treatments","field":"Medicine","cited_by":126,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Mendelian randomization; Biology; Genome-wide association study; Genetics; Genetic architecture; Context (archaeology); Disease; Single-nucleotide polymorphism; Genetic association; Mendelian inheritance; Biobank; Gene; Quantitative trait locus; Evolutionary biology; Genetic variants; Genotype; Medicine; Internal medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01605741581703032,"gpt":0.2335633876661556,"spread":0.2175059718491253,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003993747,0.001029581,0.001114945,0.0003739947,0.000525168,0.000276069,0.0003289556,0.0005590499,0.000124833],"category_scores_gemma":[0.0002370154,0.001010299,0.0002868739,0.0002624936,0.0002772725,0.0001445511,0.00067867,0.0008363799,0.0001280142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006776783,"about_ca_system_score_gemma":0.00091478,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003256965,"about_ca_topic_score_gemma":0.00001871946,"domain_scores_codex":[0.9957551,0.000180572,0.0006913781,0.001935484,0.000558732,0.0008787807],"domain_scores_gemma":[0.9956667,0.00007253606,0.0007638028,0.001497088,0.0004284851,0.001571356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001378664,0.002160282,0.7767573,0.001387176,0.003307486,0.001031901,0.0001221768,0.00004435385,0.2126264,0.000181272,0.0009102569,0.00009265914],"study_design_scores_gemma":[0.004596856,0.0002792707,0.9148572,0.0007682365,0.002920039,1.477571e-7,0.00001376262,0.00160277,0.03445898,0.00002326467,0.03928149,0.001197972],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9734076,0.01991941,0.001960787,0.00003796744,0.001017335,0.001570562,0.001715231,0.0003606062,0.00001045387],"genre_scores_gemma":[0.9850655,0.007564704,0.005463819,0.0002230942,0.001000201,0.0003821415,0.000004142467,0.0002739575,0.00002248399],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1781675,"threshold_uncertainty_score":0.9992347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2734697660","doi":"10.1101/162784","title":"Pan-cancer analysis of whole genomes","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research","funders":"","keywords":"Genome; Germline; Computational biology; 1000 Genomes Project; Biology; Coding (social sciences); Coding region; Evolutionary biology; Genetics; Gene; Single-nucleotide polymorphism; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01351393771310497,"gpt":0.2483093514134329,"spread":0.234795413700328,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002726169,0.0004066525,0.0007042483,0.0002610132,0.0001230237,0.0001321911,0.0008100835,0.0005404806,0.00003801778],"category_scores_gemma":[0.0001783658,0.0004545015,0.0004428686,0.000228675,0.0001728955,0.00000463801,0.0008507303,0.0002528417,0.000009803028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008008314,"about_ca_system_score_gemma":0.0007336973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002181439,"about_ca_topic_score_gemma":0.0000606082,"domain_scores_codex":[0.9980383,0.00004324062,0.0004467338,0.000878772,0.0002190803,0.0003738986],"domain_scores_gemma":[0.9964571,0.00002181847,0.0007033022,0.002176969,0.0004792322,0.0001615642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003657741,0.00009483713,0.0398575,0.0001421192,0.002614673,0.000007517773,0.000004548515,0.001070059,0.9550456,0.00008790869,0.001020096,0.00001854304],"study_design_scores_gemma":[0.00046167,0.00008090393,0.267998,0.0001178593,0.002441214,2.819038e-9,0.000002028909,0.0003845427,0.6486748,0.000002387493,0.0789721,0.0008644458],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9786181,0.01664748,0.0007760653,0.0001443411,0.0008752021,0.0003206067,0.002559003,0.000027412,0.00003178655],"genre_scores_gemma":[0.9898371,0.008150178,0.0009791657,0.000146386,0.0006411914,0.0001313633,0.000006219317,0.00008080608,0.00002760299],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3063708,"threshold_uncertainty_score":0.9997907,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2949097965","doi":"10.1101/128835","title":"Nanopore sequencing and assembly of a human genome with ultra-long reads","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":123,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Ontario Institute for Cancer Research; Michael Smith Health Research BC; University of British Columbia","funders":"National Cancer Institute; Biotechnology and Biological Sciences Research Council; Canadian Institutes of Health Research; Rosetrees Trust; Genome British Columbia; Michael Smith Health Research BC; Government of Ontario; National Institutes of Health; Cancer Research UK; Medical Research Council; Amazon Web Services; National Human Genome Research Institute; Wellcome Trust; Ontario Institute for Cancer Research; Oxford Nanopore Technologies; Fondation Brain Canada","keywords":"Minion; Nanopore sequencing; Nanopore; Sequence assembly; Computational biology; Genome; Hybrid genome assembly; Contig; DNA sequencing; Human genome; Biology; Whole genome sequencing; Computer science; Genetics; Nanotechnology; DNA; Gene; Materials science","retraction":null,"screen_n_in":null,"score":{"opus":0.01561787204509524,"gpt":0.2275952617630861,"spread":0.2119773897179909,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003284542,0.0004527066,0.0005264033,0.00008707873,0.0002648545,0.0001001315,0.0004667147,0.0004101665,0.000002315231],"category_scores_gemma":[0.00006114858,0.0004352498,0.00009753379,0.00005534969,0.0002929046,0.00000236701,0.0004638958,0.0002483079,0.000001086255],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004759193,"about_ca_system_score_gemma":0.0003982459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009835247,"about_ca_topic_score_gemma":0.00002635709,"domain_scores_codex":[0.99818,0.00005231786,0.0003545355,0.0008545312,0.000182968,0.0003756029],"domain_scores_gemma":[0.9975969,0.000009645682,0.0005490758,0.001322105,0.0003746219,0.0001476344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002597866,0.00002736546,0.02166625,0.0002829111,0.0003122129,0.00002004646,0.00001628198,0.00002737325,0.9775407,0.00006588242,0.00001385984,0.000001103152],"study_design_scores_gemma":[0.0003649166,0.000237162,0.2308414,0.000171452,0.0001215302,1.010009e-7,0.000006808413,0.000004118514,0.7672056,0.000001894387,0.000540817,0.000504157],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9948642,0.004160437,0.0001488242,0.00003335351,0.0001505684,0.0003932792,0.0001716588,0.00001413863,0.00006350414],"genre_scores_gemma":[0.9968437,0.0009970451,0.001668631,0.00003795918,0.0002827294,0.00006358022,0.000001425685,0.00009098267,0.0000139385],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2103351,"threshold_uncertainty_score":0.9998099,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034961138","doi":"10.1101/2020.06.14.151357","title":"The Spike D614G mutation increases SARS-CoV-2 infection of multiple human cell types","year":2020,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"SARS-CoV-2 and COVID-19 Research","field":"Medicine","cited_by":122,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Cancer Institute; Advanced Research Projects Agency; National Institutes of Health; Sidney Kimmel Foundation; Searle Scholars Program; Defense Advanced Research Projects Agency; Melanoma Research Alliance; York University; American Heart Association","keywords":"Mutation; Point mutation; Mutagenesis; Population; Linkage disequilibrium; Cell; Mutant; Virus","retraction":null,"screen_n_in":null,"score":{"opus":0.03854676446553029,"gpt":0.3034311932518088,"spread":0.2648844287862785,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006784213,0.0004675505,0.0006545309,0.0003096075,0.0002855081,0.0001490575,0.0004004978,0.0004674029,0.000005180925],"category_scores_gemma":[0.001083657,0.000402348,0.0002708065,0.0006671629,0.0002534873,0.0001092421,0.0004457599,0.0009906868,0.0001041414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002958273,"about_ca_system_score_gemma":0.0009646488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002661619,"about_ca_topic_score_gemma":0.00009385755,"domain_scores_codex":[0.9971173,0.0002133689,0.0006798043,0.0007971982,0.0007109177,0.000481432],"domain_scores_gemma":[0.9971652,0.0002507394,0.0004952447,0.001134677,0.0008682903,0.00008583161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001866394,0.0002769506,0.08142898,0.001016284,0.0001642807,0.00007071117,0.00001687162,0.000002453726,0.916338,0.0001336826,0.0003584281,0.000006664807],"study_design_scores_gemma":[0.001036461,0.0002164264,0.114561,0.0003024123,0.0001989142,5.327496e-8,0.0000035068,0.0004724691,0.8669358,0.00000731346,0.01593765,0.0003280359],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9963487,0.001127453,0.0002968399,0.0001678689,0.0004086789,0.001181285,0.00007308237,0.0003148613,0.00008125266],"genre_scores_gemma":[0.9964492,0.00006815317,0.0003754567,0.00223524,0.0005463953,0.0001998995,8.858078e-7,0.000123275,0.000001543929],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04940227,"threshold_uncertainty_score":0.9998428,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285008006","doi":"10.1101/2022.07.11.499243","title":"CheckM2: a rapid, scalable and accurate tool for assessing microbial genome quality using machine learning","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":119,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Parks Canada","funders":"Australian Government; McMaster University; National Science Foundation","keywords":"Genome; Metagenomics; Scalability; Computer science; Tree (set theory); Computational biology; Quality (philosophy); Data mining; Artificial intelligence; Machine learning; Biology; Gene; Genetics; Mathematics; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.02819325749494164,"gpt":0.2692766303489962,"spread":0.2410833728540545,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001120383,0.0005354117,0.0005897015,0.0001037591,0.0006377962,0.0002870324,0.0003654262,0.0003799698,0.00002184984],"category_scores_gemma":[0.0002586253,0.000620317,0.000210607,0.0001404915,0.0001244973,0.000004846448,0.001497291,0.0004905048,9.14938e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001140728,"about_ca_system_score_gemma":0.0004321578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007464863,"about_ca_topic_score_gemma":0.000003723176,"domain_scores_codex":[0.9972901,0.0002416051,0.0005644925,0.001164024,0.0001684182,0.0005713223],"domain_scores_gemma":[0.9984201,0.000045712,0.0005136175,0.0006954405,0.0001939247,0.0001311717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007050542,0.00005285681,0.01203523,0.0003238856,0.0002700897,0.000003341069,0.0000105167,0.0009538079,0.9862331,0.00002206586,0.00001955534,0.000005096777],"study_design_scores_gemma":[0.002521599,0.0003004992,0.1746912,0.0001350501,0.0004582174,2.404764e-7,0.00003393515,0.002994663,0.725086,0.000005388184,0.09107917,0.002694116],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866654,0.008838622,0.002339751,0.00007330153,0.0005717893,0.0007784693,0.0006983022,0.00003011887,0.000004297284],"genre_scores_gemma":[0.9828886,0.001112353,0.01493771,0.0001787148,0.00055325,0.0001708583,0.000007791411,0.0001388303,0.00001192065],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2611471,"threshold_uncertainty_score":0.9996248,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}