{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":449,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":449,"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":"9817ffbb3252","filters":{"venue":"Genome Research"}},"results":[{"id":"W2112364185","doi":"10.1101/gr.186072.114","title":"CheckM: assessing the quality of microbial genomes recovered from isolates, single cells, and metagenomes","year":2015,"lang":"en","type":"article","venue":"Genome Research","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12819,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Australian Research Council; Joint Genome Institute; Natural Sciences and Engineering Research Council of Canada; Great Barrier Reef Foundation; U.S. Department of Energy","keywords":"Biology; Genome; Metagenomics; Computational biology; Genetics; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.1745532526589507,"gpt":0.4126723215200291,"spread":0.2381190688610784,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002549025,0.0001372272,0.0002505669,0.00007552861,0.0001931138,0.0001012752,0.0003476654,0.0001597679,0.0000375033],"category_scores_gemma":[0.0001432952,0.0001062055,0.00006909238,0.0001797394,0.0003020154,0.000008435831,0.0004116986,0.0002401485,0.00001895254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006347419,"about_ca_system_score_gemma":0.0004411729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009956728,"about_ca_topic_score_gemma":0.000140143,"domain_scores_codex":[0.9979573,0.0006088543,0.0003448009,0.000413953,0.0002184611,0.0004566095],"domain_scores_gemma":[0.9987849,0.0001027188,0.0001143066,0.0005173968,0.000312591,0.0001680903],"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":[0.00006419702,0.00007091464,0.000968789,0.00004618768,0.00006198753,8.45591e-7,0.0004442204,0.000006506168,0.9962992,0.00001305809,0.0008845732,0.0011395],"study_design_scores_gemma":[0.001358904,0.0005694712,0.02233987,0.00002112292,0.00002762532,0.000007906834,0.002190355,0.0000157092,0.711531,0.0005405983,0.2610305,0.0003669091],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9806132,0.01739007,0.0001381558,0.0004498012,0.00009909675,0.0002792079,0.000240139,0.000006030823,0.0007842939],"genre_scores_gemma":[0.9954708,0.001329666,0.001658277,0.0001029551,0.000263404,0.000007207749,0.0002391796,0.00002553323,0.000902975],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2847682,"threshold_uncertainty_score":0.4330936,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158804744","doi":"10.1101/gr.092759.109","title":"Circos: An information aesthetic for comparative genomics","year":2009,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11925,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency; Canada's Michael Smith Genome Sciences Centre","funders":"Terry Fox Foundation; Genome British Columbia; Michael Smith Health Research BC; National Cancer Institute; Genome Canada","keywords":"Biology; Genome; Visualization; Computational biology; Comparative genomics; Genomics; Reference genome; ENCODE; Silhouette; Data visualization; Computer science; Genetics; Data mining; Artificial intelligence; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.09469652756015814,"gpt":0.3836350681741679,"spread":0.2889385406140098,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005935481,0.0001088358,0.0001300031,0.00009533855,0.0002607679,0.00006498713,0.0002661196,0.00008593082,0.000006655863],"category_scores_gemma":[0.00002487962,0.0001073213,0.00005645552,0.0001019737,0.00008610913,0.00000246929,0.00006894226,0.00009002106,0.0000263762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003574969,"about_ca_system_score_gemma":0.0001149631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008829516,"about_ca_topic_score_gemma":0.00001196222,"domain_scores_codex":[0.9989725,0.0000697805,0.0001847333,0.0002213687,0.0001544729,0.0003970985],"domain_scores_gemma":[0.9991528,0.00001222765,0.00003866661,0.000331564,0.0003590068,0.000105717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001987008,0.00009100825,0.00007605978,0.0000136373,0.00003147767,4.094854e-7,0.001460251,0.0005334148,0.9766074,0.001100452,0.001099947,0.01878723],"study_design_scores_gemma":[0.001186318,0.004012039,0.01567275,0.000004567293,0.00001189501,0.00001948117,0.001649426,0.000462126,0.0469995,0.005052539,0.9245252,0.0004041863],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993871,0.001035615,0.001424222,0.0003541025,0.00004797143,0.0006318846,0.00009368647,0.000003305956,0.002538237],"genre_scores_gemma":[0.9965841,0.0003412651,0.002258196,0.0001889777,0.0001770082,0.00006252031,0.0002386089,0.000008232217,0.0001410643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9296079,"threshold_uncertainty_score":0.4376435,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1966822396","doi":"10.1101/gr.089532.108","title":"ABySS: A parallel assembler for short read sequence data","year":2009,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3765,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency","funders":"Washington University School of Medicine in St. Louis; Genome British Columbia; Michael Smith Health Research BC; Genome Canada","keywords":"Contig; Sequence assembly; Biology; Hybrid genome assembly; Massive parallel sequencing; Genome; Reference genome; Human genome; Computational biology; DNA sequencing; Sequence (biology); Genetics; Software; Massively parallel; Computer science; DNA; Parallel computing; Gene; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.3038703311146536,"gpt":0.4524103728411613,"spread":0.1485400417265077,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001165366,0.000131427,0.0001496787,0.00006136484,0.0002283912,0.0000511889,0.0008785023,0.000112875,0.00001608838],"category_scores_gemma":[0.0001650264,0.000122457,0.00005274671,0.0001262721,0.00009779896,0.000001142485,0.0004558697,0.0001244725,0.0000124438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002105894,"about_ca_system_score_gemma":0.0001579278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002082577,"about_ca_topic_score_gemma":0.00002710228,"domain_scores_codex":[0.9982877,0.0000687393,0.0001810372,0.0006315793,0.0002411436,0.0005897467],"domain_scores_gemma":[0.9984171,0.00003762918,0.0000200962,0.001156784,0.0002575195,0.0001108524],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009098352,0.00005191538,0.0003310036,0.00001433101,0.00006165536,0.000003504047,0.00004090301,0.00004425285,0.9798403,0.0002390042,0.00503313,0.01424895],"study_design_scores_gemma":[0.0004753234,0.001078464,0.01531972,0.000008982344,0.00001664607,0.00001690377,0.0001245814,0.0002994313,0.009124886,0.001787721,0.9714042,0.0003431274],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9571363,0.01831141,0.007137612,0.00309536,0.000181503,0.001882589,0.001108627,0.00001222451,0.01113433],"genre_scores_gemma":[0.9831653,0.003615748,0.009902326,0.000212616,0.0005279594,0.00007660325,0.0006298518,0.00002280385,0.001846777],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9707155,"threshold_uncertainty_score":0.4993651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124514674","doi":"10.1101/gr.136184.111","title":"ChIP-seq guidelines and practices of the ENCODE and modENCODE consortia","year":2012,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2223,"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":"National Human Genome Research Institute","keywords":"ENCODE; Biology; Metadata; Chromatin immunoprecipitation; Computational biology; Computer science; Genetics; World Wide Web; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.1110899151962238,"gpt":0.4116946994631419,"spread":0.3006047842669181,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001079104,0.00007429191,0.00008946631,0.00003294817,0.0001263502,0.00002433568,0.0001875649,0.0000821143,0.000009130585],"category_scores_gemma":[0.0003956051,0.00005338576,0.00002506176,0.00007448747,0.0002393889,0.000005189995,0.0004549093,0.000116819,0.000002071125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007321672,"about_ca_system_score_gemma":0.00007883977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006077933,"about_ca_topic_score_gemma":0.00004139033,"domain_scores_codex":[0.9990928,0.000114048,0.0001712539,0.0001694253,0.000176418,0.000276055],"domain_scores_gemma":[0.9992731,0.00003717416,0.0001127493,0.0003089705,0.000182147,0.00008581531],"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":[0.00002056679,0.00003226128,0.03189031,0.00005362903,0.00003444443,2.494744e-7,0.0002001881,0.00003570677,0.9661137,0.0004422438,0.0002713464,0.0009052908],"study_design_scores_gemma":[0.001881339,0.0008011063,0.5489172,0.00009106061,0.0001112976,0.0002923901,0.003399973,0.007749116,0.2623293,0.004161359,0.1693043,0.0009614981],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9900118,0.008074082,0.00007910012,0.0004812368,0.00003862289,0.0001560773,0.0000222961,0.000001837519,0.001134919],"genre_scores_gemma":[0.9950079,0.002627075,0.001628862,0.00004458757,0.0001496473,0.000009850238,0.000009343978,0.00001163038,0.0005111427],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7037844,"threshold_uncertainty_score":0.2177008,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140679462","doi":"10.1101/gr.126516.111","title":"<i>Fusobacterium nucleatum</i> infection is prevalent in human colorectal carcinoma","year":2011,"lang":"en","type":"article","venue":"Genome Research","topic":"Otolaryngology and Infectious Diseases","field":"Medicine","cited_by":2063,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of Guelph; Simon Fraser University; BC Cancer Agency","funders":"Canadian Institutes of Health Research; Genome British Columbia","keywords":"Fusobacterium nucleatum; Fusobacteria; Fusobacterium; Biology; Colorectal cancer; Pathology; Carcinoma; Bacteroidaceae; Microbiology; Cancer; Bacteroides; Medicine; Bacteria; 16S ribosomal RNA; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.09559426067453582,"gpt":0.358163130983294,"spread":0.2625688703087582,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006946233,0.0001253364,0.0002265406,0.0004974375,0.0001995826,0.00001581144,0.0001005307,0.0001654058,0.003560015],"category_scores_gemma":[0.00007798059,0.0001192564,0.00009128491,0.0004752277,0.0002393947,0.0001149696,0.0001257675,0.0006043401,0.000512659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003109533,"about_ca_system_score_gemma":0.0001897491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001257051,"about_ca_topic_score_gemma":0.0001839715,"domain_scores_codex":[0.9983062,0.0002518054,0.0002241602,0.0003577467,0.0003023196,0.0005577594],"domain_scores_gemma":[0.9992195,0.0000354166,0.00003021305,0.0003068968,0.0001991935,0.0002087414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000241314,0.0007589422,0.9542863,0.0001932008,0.00003517499,0.0001200361,0.001525136,8.340876e-8,0.04148684,0.0001692515,0.0009744109,0.0002092993],"study_design_scores_gemma":[0.0009392495,0.001533248,0.9853281,0.0000312766,0.00002116555,0.00008009748,0.00006068604,0.000007149853,0.00849651,0.0002818074,0.003114369,0.0001062831],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9361843,0.0002613511,0.000001367527,0.0001083805,0.00009642672,0.0006600326,0.000008923259,0.00005899511,0.06262024],"genre_scores_gemma":[0.9980227,0.0001344956,0.00001840873,0.0001410162,0.0001463594,0.0001058599,0.00002234312,0.00002721034,0.001381641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06183838,"threshold_uncertainty_score":0.9973509,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107097628","doi":"10.1101/gr.126573.111","title":"Genomic analysis identifies association of <i>Fusobacterium</i> with colorectal carcinoma","year":2011,"lang":"en","type":"article","venue":"Genome Research","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1969,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Center for Advancing Translational Sciences; National Institute of Diabetes and Digestive and Kidney Diseases; National Cancer Institute; National Human Genome Research Institute; University of Guelph; Natural Sciences and Engineering Research Council of Canada; Broad Institute; Albert J. Ryan Foundation; Damon Runyon Cancer Research Foundation","keywords":"Fusobacteria; Biology; Colorectal cancer; Fusobacterium; Carcinoma; Carcinogenesis; Firmicutes; Cancer; Genetics; Gene; Bacteroides; 16S ribosomal RNA; Bacteria","retraction":null,"screen_n_in":null,"score":{"opus":0.03300477784526228,"gpt":0.2963286537008464,"spread":0.2633238758555841,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008728235,0.00008665661,0.0001845138,0.0002245911,0.0001037418,0.00001789717,0.0002182623,0.0001221473,0.000128393],"category_scores_gemma":[0.00002911612,0.00007722363,0.00008767554,0.0004894393,0.00009431864,0.000003338498,0.000131236,0.0001348951,0.00002942048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008223512,"about_ca_system_score_gemma":0.000215741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004384161,"about_ca_topic_score_gemma":0.0009301516,"domain_scores_codex":[0.998737,0.0001727057,0.0001885279,0.0002841062,0.0002215701,0.0003960409],"domain_scores_gemma":[0.9991454,0.00001521295,0.00009573289,0.0002807117,0.0003801536,0.00008279713],"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":[0.0001324675,0.00004322856,0.2781935,0.00002469048,0.000244033,0.000002000091,0.0003097029,0.000001956121,0.7208681,0.00001085007,0.0001404743,0.00002898151],"study_design_scores_gemma":[0.0002314612,0.000398383,0.8373795,0.000001850071,0.00006220431,0.000002746095,0.0001635745,0.000002309596,0.1602969,0.00001157008,0.001367342,0.00008216001],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9965579,0.0003425321,0.00005965603,0.00002988593,0.00002390704,0.0001827958,0.00004958584,0.000004431256,0.002749296],"genre_scores_gemma":[0.997596,0.0001681372,0.0002806665,0.0000147401,0.00006301016,0.00001533068,0.0001407196,0.00001398571,0.00170742],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5605713,"threshold_uncertainty_score":0.3149088,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150934173","doi":"10.1101/gr.361602","title":"The Bioperl Toolkit: Perl Modules for the Life Sciences","year":2002,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1705,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Agriculture and Agri-Food Canada; Plant Biotechnology Institute","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health","keywords":"Perl; Computer science; Python (programming language); Scripting language; Interoperation; Programming language; Structural bioinformatics; Java; Software engineering; Ensembl; Suite; World Wide Web; Biology; Interoperability; Genomics","retraction":null,"screen_n_in":null,"score":{"opus":0.1350746097583428,"gpt":0.3535496854451144,"spread":0.2184750756867715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00151322,0.0000935314,0.00007596858,0.00003118095,0.002114344,0.0001103566,0.000735258,0.00005350489,0.00002772707],"category_scores_gemma":[0.0003627047,0.00004911737,0.00008056693,0.0001665111,0.0008056529,4.930644e-7,0.0003257137,0.0000991345,0.00003175208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008940329,"about_ca_system_score_gemma":0.00005563842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002574416,"about_ca_topic_score_gemma":0.000047782,"domain_scores_codex":[0.9987056,0.00008966949,0.0001299985,0.0003015911,0.0002516579,0.0005214568],"domain_scores_gemma":[0.9990557,0.00025552,0.00002321168,0.0004049627,0.0001939121,0.00006666983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009025903,0.00009095748,0.001153618,0.00003098376,0.0003442616,9.992651e-7,0.0007413094,0.0006270011,0.8992636,0.004856817,0.039472,0.0533282],"study_design_scores_gemma":[0.0001987963,0.000404494,0.004502732,0.000001826949,0.000008119993,0.000003301172,0.0009421257,0.0008850865,0.004587879,0.000484632,0.9878639,0.000117105],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.790795,0.1878792,0.0002676853,0.01273996,0.0002908114,0.001051803,0.00009194599,0.000003917627,0.006879672],"genre_scores_gemma":[0.976227,0.01873055,0.0002662627,0.0001415789,0.0005649979,0.0001859287,0.000003185615,0.00001369825,0.003866729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9483919,"threshold_uncertainty_score":0.9991848,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2004791359","doi":"10.1101/gr.7179508","title":"Application of massively parallel sequencing to microRNA profiling and discovery in human embryonic stem cells","year":2008,"lang":"en","type":"article","venue":"Genome Research","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"BC Cancer Agency","funders":"BC Cancer Foundation; Deutsche Forschungsgemeinschaft; Michael Smith Health Research BC; Stem Cell Network; Canadian Institutes of Health Research; Canada's Michael Smith Genome Sciences Centre","keywords":"Biology; microRNA; Embryonic stem cell; Deep sequencing; Gene expression profiling; Embryoid body; Gene; Genetics; Computational biology; Small RNA; MiRBase; Gene expression; Regulation of gene expression; Induced pluripotent stem cell; Genome","retraction":null,"screen_n_in":null,"score":{"opus":0.04612339180942388,"gpt":0.3187717010365685,"spread":0.2726483092271446,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004260613,0.00008129056,0.0001110945,0.0001527596,0.00009479834,0.00001466572,0.0001560612,0.00008139813,0.000001471106],"category_scores_gemma":[0.00001243646,0.00008573836,0.00002845736,0.0002087026,0.0001039888,0.000007014659,0.000185678,0.00009990255,0.000007225464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009624418,"about_ca_system_score_gemma":0.0001612993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004927708,"about_ca_topic_score_gemma":0.00001705748,"domain_scores_codex":[0.9989117,0.000104433,0.0001885139,0.0003374147,0.0001875102,0.0002704577],"domain_scores_gemma":[0.999464,0.00001283119,0.00004840445,0.0002833171,0.0001136354,0.0000777941],"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":[0.00004507167,0.00002253548,0.004237036,0.00007665615,0.000009418176,0.000003654374,0.0001077872,0.0007417632,0.9944704,0.00007649811,0.00002340551,0.0001858367],"study_design_scores_gemma":[0.0002947653,0.0001082416,0.02949596,0.00001782201,0.000002202517,0.000007528967,0.0001559892,0.0001153398,0.9691104,0.00005661651,0.0005250449,0.0001100433],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954029,0.0009182623,0.002934584,0.00005160764,0.000007147859,0.0005691231,0.00001693299,0.000003370348,0.00009606013],"genre_scores_gemma":[0.9982336,0.0001228547,0.001065031,0.000009463043,0.00005054661,0.00006556663,0.00005417306,0.0000161436,0.0003826339],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02535989,"threshold_uncertainty_score":0.3496309,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162210817","doi":"10.1101/gr.640303","title":"Genome Duplication, a Trait Shared by 22,000 Species of Ray-Finned Fish","year":2003,"lang":"en","type":"article","venue":"Genome Research","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":892,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft","keywords":"Biology; Zebrafish; Takifugu rubripes; Synteny; Gene duplication; Danio; Genetics; Genome; Fugu; Gene; Phylogenetics; Evolutionary biology","retraction":null,"screen_n_in":null,"score":{"opus":0.06485210548497149,"gpt":0.2829716606480334,"spread":0.2181195551630619,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006479685,0.0001026211,0.0001658449,0.00003157027,0.0003288626,0.00006991237,0.0004017927,0.00008921027,0.01392011],"category_scores_gemma":[0.0001366237,0.00004691007,0.00007767649,0.0007727231,0.0001319817,0.00005694507,0.00007289692,0.0001515559,0.0001249021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004571417,"about_ca_system_score_gemma":0.00003339862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001597879,"about_ca_topic_score_gemma":0.0001411464,"domain_scores_codex":[0.9983012,0.0001926282,0.0002643157,0.0003299947,0.0004752016,0.0004366354],"domain_scores_gemma":[0.9992049,0.0002129762,0.000040356,0.000126659,0.0002686867,0.0001464251],"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":[0.000009279417,0.0001363449,0.0007329163,0.000008399797,0.00001459572,6.267069e-7,0.0001786921,0.000005411318,0.9956064,0.0006883877,0.001398503,0.001220494],"study_design_scores_gemma":[0.0001781609,0.000234876,0.4934963,0.000004834485,0.000004372937,0.000002820606,0.0003626096,0.000005735414,0.01572574,0.001434121,0.4884105,0.0001398656],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9811205,0.0004677007,0.000009945019,0.00264332,0.0000240321,0.0003885702,0.0008055518,0.0000255295,0.01451487],"genre_scores_gemma":[0.991313,0.0001855076,0.0001403197,0.00005453094,0.0001212282,0.00006367075,0.0003496884,0.000001615014,0.007770473],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9798806,"threshold_uncertainty_score":0.9869813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138258120","doi":"10.1101/gr.107920.110","title":"A ChIP-seq defined genome-wide map of vitamin D receptor binding: Associations with disease and evolution","year":2010,"lang":"en","type":"article","venue":"Genome Research","topic":"Vitamin D Research Studies","field":"Medicine","cited_by":882,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Medical Research Council; University of Oxford; Multiple Sclerosis Society; Multiple Sclerosis Society of Canada; Wellcome Trust","keywords":"Calcitriol receptor; Biology; Vitamin D and neurology; Chromatin immunoprecipitation; Genetics; Single-nucleotide polymorphism; Genome-wide association study; Gene; Gene expression; Promoter; Endocrinology; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.03817510076834888,"gpt":0.3337567107268939,"spread":0.295581609958545,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002078158,0.0001758664,0.0003739955,0.0007710931,0.0004601434,0.00004585359,0.0002107689,0.0001136829,0.0002378615],"category_scores_gemma":[0.002794315,0.0001369968,0.00006962163,0.0008417842,0.0007812597,0.0001079555,0.00033582,0.0009631711,0.0002511809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003450254,"about_ca_system_score_gemma":0.0007034833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009416681,"about_ca_topic_score_gemma":0.0001155609,"domain_scores_codex":[0.9967809,0.0002104296,0.0002913088,0.0004579662,0.001433165,0.0008261849],"domain_scores_gemma":[0.9971785,0.0006240288,0.00008442738,0.0005444409,0.0009666966,0.0006019275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004056994,0.0004360598,0.5300552,0.0006007059,0.0003618293,0.00005084603,0.0008222109,0.000002184378,0.4645443,0.0006356731,0.001762079,0.0003232611],"study_design_scores_gemma":[0.001350135,0.0005899963,0.9926542,0.00006184541,0.00005508655,0.00000460394,0.0004465608,0.00002516533,0.0004845309,0.0001873556,0.003998457,0.0001420678],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9909638,0.0007607181,0.00005986156,0.005681274,0.00005234886,0.001145361,0.0002475831,0.00004369612,0.001045377],"genre_scores_gemma":[0.9914563,0.0002253172,0.001625747,0.00001553194,0.0001966711,0.0001824317,0.000181484,0.00004193176,0.006074593],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4640597,"threshold_uncertainty_score":0.5586568,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102941013","doi":"10.1101/gr.3677206","title":"Copy number variation: New insights in genome diversity","year":2006,"lang":"en","type":"review","venue":"Genome Research","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":870,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Hospital for Sick Children; University of Toronto","funders":"Ontario Genomics Institute; Wellcome Trust; Canadian Institutes of Health Research; Ontario Genomics; Leukemia and Lymphoma Society; Genome Canada; Massachusetts General Hospital; Brigham and Women's Hospital; Howard Hughes Medical Institute","keywords":"Copy-number variation; Biology; Genetics; Genome; Variation (astronomy); Structural variation; Human genetic variation; Genetic variation; Gene; Phenotype; Human genome; Gene dosage; Genomics; Computational biology; Evolutionary biology; Comparative genomic hybridization; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.08744079754405808,"gpt":0.362651021416473,"spread":0.2752102238724149,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000673897,0.0003428126,0.0007091538,0.0003059949,0.0003842001,0.0000987992,0.0007969113,0.0005901221,0.0004442189],"category_scores_gemma":[0.00004159598,0.0003262461,0.0002734381,0.0006169807,0.00009743142,0.000008078868,0.001542545,0.0005546475,0.0006693348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003035729,"about_ca_system_score_gemma":0.001190311,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00144512,"about_ca_topic_score_gemma":0.0003462124,"domain_scores_codex":[0.9971272,0.000489978,0.0005336875,0.0007205501,0.0004624986,0.0006660884],"domain_scores_gemma":[0.9987566,0.00004938745,0.0001381506,0.0006965863,0.0001816714,0.0001775432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007466834,0.005262104,0.01911022,0.08403794,0.007333512,0.001445376,0.01450627,0.001274562,0.004416996,0.03309878,0.08244908,0.7463185],"study_design_scores_gemma":[0.0002686669,0.00006841707,0.0007205626,0.000166225,0.00004728709,0.00002894043,0.00003129859,4.670523e-7,0.000007319556,0.000378642,0.9979339,0.0003482853],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001052853,0.9862078,0.0001292055,0.00002641143,0.0001237115,0.0007367806,0.0001218981,0.00001220574,0.01158917],"genre_scores_gemma":[0.002704649,0.9749135,0.0003080333,0.00001500846,0.001135137,0.00006787972,0.001665958,0.00005264564,0.01913714],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9154848,"threshold_uncertainty_score":0.9999189,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167155938","doi":"10.1101/gr.094607.109","title":"JBrowse: A next-generation genome browser","year":2009,"lang":"en","type":"article","venue":"Genome Research","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":776,"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":"National Human Genome Research Institute; National Institutes of Health","keywords":"JavaScript; Upload; Computer science; Web server; Genome; Genome browser; Annotation; Zoom; Panning (audio); Biology; Rendering (computer graphics); Web browser; World Wide Web; The Internet; Genomics; Genetics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.2085239895237908,"gpt":0.3744306107962284,"spread":0.1659066212724375,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00130605,0.0001343909,0.0001484583,0.0003226646,0.0005025326,0.0007123923,0.001565268,0.00009038977,0.0001507661],"category_scores_gemma":[0.00005792727,0.0001173494,0.00005292392,0.0009310833,0.00005263073,0.001039837,0.0005576097,0.0003890582,0.0008034891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00011586,"about_ca_system_score_gemma":0.0001586643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000036522,"about_ca_topic_score_gemma":0.000003793022,"domain_scores_codex":[0.9972675,0.0002223514,0.0002285394,0.0006074698,0.0009640348,0.0007101012],"domain_scores_gemma":[0.9982404,0.00005583962,0.00003672137,0.00110516,0.0003238522,0.0002380354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001363668,0.0002002746,0.00001952308,0.00001285551,0.00001297192,0.0000885431,0.0007834302,0.0002958679,0.7620985,0.02859981,0.006369177,0.2015054],"study_design_scores_gemma":[0.001335932,0.001489979,0.03764862,0.00004036762,0.000006196723,0.0001133313,0.0001081275,0.2427864,0.007864508,0.02496697,0.6825506,0.001088979],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07093951,0.006150089,0.8956273,0.009207138,0.0004826525,0.001036107,0.00002473983,0.0004592837,0.01607323],"genre_scores_gemma":[0.9229944,0.0004967198,0.07086654,0.0006059538,0.001388114,0.00004206041,0.0001066626,0.00002147719,0.003478056],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8520549,"threshold_uncertainty_score":0.9999745,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2589379462","doi":"10.1101/gr.214346.116","title":"ABySS 2.0: resource-efficient assembly of large genomes using a Bloom filter","year":2017,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":740,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Bloom filter; Sequence assembly; Genome; Genomics; Computational biology; De Bruijn graph; Biology; Computer science; k-mer; Structural variation; Hybrid genome assembly; Reference genome; DNA sequencing; Genetics; Graph; Gene; Theoretical computer science; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.08335564250981123,"gpt":0.3776353302280352,"spread":0.294279687718224,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001395515,0.0001510889,0.0002280416,0.0001156697,0.0007657463,0.0000817145,0.0007478814,0.0001283394,0.00004075249],"category_scores_gemma":[0.0001639826,0.0001408445,0.0001264062,0.00007396937,0.0002982511,6.410032e-7,0.001224691,0.0001568102,0.00001422652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002642339,"about_ca_system_score_gemma":0.0001363191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000710743,"about_ca_topic_score_gemma":0.00002786469,"domain_scores_codex":[0.998144,0.0001331918,0.0002513153,0.0004443305,0.0003653081,0.0006618199],"domain_scores_gemma":[0.9982712,0.00002923366,0.0001287129,0.001159259,0.0002962214,0.0001153174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006646755,0.0001036072,0.005449607,0.00003850833,0.0001185082,0.000006621871,0.0002366454,0.0003327446,0.9925345,0.000112289,0.0002162906,0.0007842698],"study_design_scores_gemma":[0.00221951,0.0008836328,0.1143709,0.00005121226,0.00005606275,0.00002918667,0.001078988,0.001697431,0.3630888,0.0002024421,0.5156049,0.0007170854],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896219,0.005064144,0.0001293639,0.0001379739,0.00006760468,0.0002788679,0.0001510396,0.000001549831,0.004547527],"genre_scores_gemma":[0.9974923,0.0004415627,0.0007703315,0.00002710129,0.0003172777,0.00001668253,0.00002057224,0.00003078207,0.0008833628],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6294457,"threshold_uncertainty_score":0.5889578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2049110540","doi":"10.1101/gr.177790.114","title":"Widespread intron retention in mammals functionally tunes transcriptomes","year":2014,"lang":"en","type":"article","venue":"Genome Research","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":702,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Occupational Cancer Research Centre; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Biology; Intron; RNA splicing; Transcriptome; Nonsense-mediated decay; Alternative splicing; Gene; Genetics; Genome; Splicing factor; RNA; RNA polymerase II; Cell biology; Function (biology); Computational biology; Gene expression; Messenger RNA","retraction":null,"screen_n_in":null,"score":{"opus":0.04316954231012315,"gpt":0.3314776632872115,"spread":0.2883081209770883,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002525388,0.00009987323,0.0001250388,0.000272484,0.0001259956,0.00005861223,0.0002704353,0.0001248772,0.0001058347],"category_scores_gemma":[0.000397123,0.00009355685,0.00006739811,0.0002867881,0.0001337547,0.000007746929,0.0001073196,0.0002769615,0.0001022494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004518265,"about_ca_system_score_gemma":0.00009923785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001486957,"about_ca_topic_score_gemma":0.0002096322,"domain_scores_codex":[0.9979075,0.0004035305,0.000196966,0.0003903656,0.0004918395,0.0006097839],"domain_scores_gemma":[0.9992597,0.00005600653,0.00001932795,0.0003318093,0.0001969061,0.0001363088],"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":[0.0002022358,0.00003949537,0.003988349,0.00003536929,0.00001582339,0.000003433106,0.00002912875,0.00005505882,0.987113,0.0003928489,0.0006099073,0.007515352],"study_design_scores_gemma":[0.003895931,0.003397036,0.3773052,0.0001282093,0.00001131426,0.00004329814,0.0008184906,0.001364909,0.2678373,0.003764117,0.3406158,0.0008183492],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927301,0.0008814635,0.001406035,0.000792103,0.0000634565,0.0002555859,0.000005936329,0.000009536677,0.003855735],"genre_scores_gemma":[0.9876482,0.0003499903,0.0002288924,0.00004753816,0.0003036175,0.00006643125,0.0001072972,0.00002025307,0.01122776],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7192757,"threshold_uncertainty_score":0.3815138,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096064375","doi":"10.1101/gr.165985.113","title":"Neo-antigens predicted by tumor genome meta-analysis correlate with increased patient survival","year":2014,"lang":"en","type":"review","venue":"Genome Research","topic":"Cancer Immunotherapy and Biomarkers","field":"Medicine","cited_by":617,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of Victoria; Canada's Michael Smith Genome Sciences Centre; University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research; National Institutes of Health; U.S. Department of Defense","keywords":"Biology; CTL*; Missense mutation; Epitope; Major histocompatibility complex; Cytotoxic T cell; Human leukocyte antigen; Genome; Genetics; Antigen; Mutation; Gene; Immunology; Cancer research; CD8","retraction":null,"screen_n_in":null,"score":{"opus":0.1626058555653995,"gpt":0.4020613126508298,"spread":0.2394554570854303,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004151327,0.0008743502,0.006931863,0.00182198,0.0003565531,0.0001492067,0.0007350497,0.0004424005,0.005078235],"category_scores_gemma":[0.0001381334,0.0005405361,0.003729242,0.004992343,0.0005488791,0.00005611598,0.0002592079,0.001772347,0.0002577195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007294547,"about_ca_system_score_gemma":0.001652523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001419316,"about_ca_topic_score_gemma":0.00009420442,"domain_scores_codex":[0.9907586,0.002252372,0.001456459,0.0014093,0.002700613,0.001422672],"domain_scores_gemma":[0.9951518,0.0007085238,0.0005943141,0.00204876,0.0008031849,0.0006934313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002390887,0.0007758306,0.00006287899,0.01697729,0.8745626,0.0007324758,0.0003068459,0.000007568495,0.0002219848,0.000009241078,0.002777767,0.1011747],"study_design_scores_gemma":[0.0007867777,0.001100267,0.0001645229,0.0003035314,0.1824765,0.00008802492,0.00003579066,0.000009989709,0.00000207384,0.000001207573,0.8145747,0.0004566215],"study_design_candidate":"meta_analysis","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002719893,0.9918433,0.0001270894,0.0001083608,0.00008194613,0.003412034,0.002229456,0.00009250599,0.00183335],"genre_scores_gemma":[0.0003559529,0.9889293,0.0001615265,0.0001192287,0.0002038131,0.0007563733,0.005229708,0.0002011367,0.004042934],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8117969,"threshold_uncertainty_score":0.9997046,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2003870059","doi":"10.1101/gr.152942.112","title":"<i>CCAT2</i>, a novel noncoding RNA mapping to 8q24, underlies metastatic progression and chromosomal instability in colon cancer","year":2013,"lang":"en","type":"article","venue":"Genome Research","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":611,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Mount Sinai Hospital","funders":"National Cancer Institute; University of Texas MD Anderson Cancer Center; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Cancer Research UK; Wellcome Trust","keywords":"Biology; Wnt signaling pathway; Long non-coding RNA; Genetics; Colorectal cancer; TCF7L2; SNP; Chromosome instability; Cancer; Single-nucleotide polymorphism; Cancer research; Gene; RNA; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.07986426816052025,"gpt":0.3852895155334752,"spread":0.305425247372955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001432413,0.0001957966,0.000242506,0.0003829473,0.000216987,0.0001440637,0.0003516276,0.0001613829,0.0001691075],"category_scores_gemma":[0.0003256119,0.0001890802,0.00005005382,0.0007800994,0.0002058022,0.00001639271,0.0008685487,0.000497432,0.00004011918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000300005,"about_ca_system_score_gemma":0.0004689297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008434313,"about_ca_topic_score_gemma":0.0006414198,"domain_scores_codex":[0.9970577,0.0002907483,0.0003047567,0.000760267,0.0006526602,0.00093387],"domain_scores_gemma":[0.9987527,0.00006051404,0.00004336593,0.0004645354,0.0003629022,0.000316057],"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":[0.00008780372,0.0001062069,0.0001589645,0.0001383402,0.00003909669,0.00000942549,0.0003850941,0.0001676746,0.9842998,0.00005212652,0.00009458851,0.01446086],"study_design_scores_gemma":[0.003311966,0.001781351,0.01562914,0.0004089553,0.00001560182,0.00004977403,0.002334336,0.002777478,0.9407492,0.0004546122,0.03159552,0.0008920649],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9893762,0.00265343,0.003637543,0.001398697,0.00005713138,0.001993453,0.00002902242,0.00001428258,0.0008401755],"genre_scores_gemma":[0.994427,0.000658385,0.00316823,0.0001055796,0.00009917423,0.001130983,0.00003206154,0.00004413471,0.0003344216],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04355061,"threshold_uncertainty_score":0.7710467,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W189143987","doi":"10.1101/gr.2596504","title":"The Status, Quality, and Expansion of the NIH Full-Length cDNA Project: The Mammalian Gene Collection (MGC)","year":2004,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":590,"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","funders":"National Center for Research Resources; National Institute of Dental and Craniofacial Research; National Human Genome Research Institute; National Cancer Institute; National Institutes of Health; U.S. Public Health Service; National Institute on Deafness and Other Communication Disorders; University of British Columbia; Canada's Michael Smith Genome Sciences Centre","keywords":"Biology; Complementary DNA; Genetics; cDNA library; Open reading frame; Expressed sequence tag; Gene; Computational biology; Genomic library; Genome; Peptide sequence","retraction":null,"screen_n_in":null,"score":{"opus":0.06666755145254524,"gpt":0.3570247026661348,"spread":0.2903571512135896,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001468347,0.0001119227,0.0001092728,0.00003662546,0.0009977634,0.00005327531,0.0003628656,0.00008224886,0.000002942402],"category_scores_gemma":[0.0001888701,0.00005713007,0.00006792993,0.0002829084,0.0005072046,6.715379e-7,0.0005950041,0.0001851387,0.00000196182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004646281,"about_ca_system_score_gemma":0.0003902847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007986949,"about_ca_topic_score_gemma":0.0008522216,"domain_scores_codex":[0.998297,0.0003517809,0.0002300508,0.0002823198,0.0003541051,0.0004846988],"domain_scores_gemma":[0.9989771,0.00007516098,0.000071808,0.0005769079,0.0002449893,0.00005402728],"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":[0.0001247977,0.00002734016,0.001809279,0.00002128767,0.00006563684,3.686953e-7,0.0007911256,0.00005673457,0.9941638,0.0003791998,0.0002849763,0.002275511],"study_design_scores_gemma":[0.001673577,0.001328837,0.3940324,0.00002081445,0.00003385492,0.00003871317,0.005868472,0.00001687871,0.428812,0.004039044,0.1637779,0.0003575191],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9896685,0.006885702,0.00002678627,0.001945817,0.00009785595,0.0006473323,0.00004543485,0.000001374382,0.0006811885],"genre_scores_gemma":[0.989976,0.008819165,0.0001346468,0.00004768848,0.0001520746,0.0000680747,0.000008617028,0.00001575626,0.0007779038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5653517,"threshold_uncertainty_score":0.767409,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160838716","doi":"10.1101/gr.185579.114","title":"The Release 6 reference sequence of the <i>Drosophila melanogaster</i> genome","year":2015,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":576,"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":"National Institute of General Medical Sciences; National Human Genome Research Institute; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro; National Institutes of Health; Istituto Pasteur-Fondazione Cenci Bolognetti; Ministerio de Economía y Competitividad; U.S. Department of Energy; Howard Hughes Medical Institute","keywords":"Biology; Reference genome; Genetics; Contig; Genome; Sequence assembly; Genome project; Computational biology; Positional cloning; Bacterial artificial chromosome; Gene; Locus (genetics)","retraction":null,"screen_n_in":null,"score":{"opus":0.1332856756943138,"gpt":0.3451502554487031,"spread":0.2118645797543893,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001366623,0.0001175964,0.0001206139,0.00002783765,0.0003512359,0.0000360833,0.0009329672,0.00008321312,0.000004841262],"category_scores_gemma":[0.0002208234,0.00006927519,0.00006792726,0.0002221195,0.0005790803,6.353423e-7,0.0008956541,0.0002167931,0.00002504484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003457663,"about_ca_system_score_gemma":0.0003373123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007873894,"about_ca_topic_score_gemma":0.00006766447,"domain_scores_codex":[0.9982941,0.0002823976,0.0002184838,0.0003040967,0.0004488666,0.000452098],"domain_scores_gemma":[0.9983708,0.00005488761,0.00007033392,0.0008981237,0.0004761882,0.0001297022],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006999049,0.00001969168,0.001015981,0.00001061691,0.00004022037,0.000001563212,0.0001622628,0.00009874786,0.9970917,0.0004353714,0.0003816221,0.0006722501],"study_design_scores_gemma":[0.0006043332,0.0006360552,0.02032716,0.00001208036,0.00001508418,0.00002922596,0.000825074,0.00002016074,0.05610969,0.003567456,0.9176061,0.000247589],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9801919,0.008026659,0.00001021269,0.001120992,0.0001155038,0.0003351728,0.0001230288,0.000001648133,0.01007491],"genre_scores_gemma":[0.996016,0.001928849,0.00009727943,0.00007062181,0.000188168,0.00003907754,0.00001521496,0.00001690189,0.001627913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.940982,"threshold_uncertainty_score":0.2824961,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135361281","doi":"10.1101/gr.126599.111","title":"Assemblathon 1: A competitive assessment of de novo short read assembly methods","year":2011,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":539,"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":"National Human Genome Research Institute; National Institute on Alcohol Abuse and Alcoholism; National Key Research and Development Program of China; National High-tech Research and Development Program; National Natural Science Foundation of China; Division of Emerging Frontiers; European Bioinformatics Institute; Howard Hughes Medical Institute; National Cancer Institute; National Institutes of Health; National Science Foundation","keywords":"Biology; Sequence assembly; Benchmark (surveying); Genome; Computational biology; Genomics; Contiguity; Hybrid genome assembly; Set (abstract data type); Computer science; Genetics; Gene; Transcriptome","retraction":null,"screen_n_in":null,"score":{"opus":0.1601811763475329,"gpt":0.460701532668836,"spread":0.3005203563213031,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002799548,0.0001460081,0.0002400376,0.0001267147,0.0001256163,0.00001453105,0.000386051,0.0001413194,0.00007181468],"category_scores_gemma":[0.0001156054,0.0001397582,0.0001066237,0.0002006605,0.0002089936,7.087378e-7,0.0004782374,0.0002102556,0.000004453337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005175633,"about_ca_system_score_gemma":0.0003110003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001033387,"about_ca_topic_score_gemma":0.00006638716,"domain_scores_codex":[0.9979785,0.0005435202,0.0002625724,0.0004052007,0.0002705984,0.0005395708],"domain_scores_gemma":[0.9988037,0.00007614351,0.00004738146,0.000501887,0.0004405995,0.0001302676],"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":[0.00004542914,0.0001252142,0.01125976,0.00002911503,0.0001505138,0.000007794355,0.0003304948,0.000007256544,0.9826763,0.001826734,0.00003616339,0.003505269],"study_design_scores_gemma":[0.000398625,0.001471892,0.4266691,0.00001903281,0.00003285471,0.00003424747,0.00112982,0.00007275633,0.5344819,0.0009365436,0.03443043,0.000322767],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9119543,0.001233713,0.007747469,0.00003771114,0.00006541347,0.0003072061,0.00004638958,0.000002759099,0.07860506],"genre_scores_gemma":[0.9116717,0.00087166,0.08678994,0.00002407099,0.00011533,0.0000600773,0.00002118273,0.00002638484,0.0004196629],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4481944,"threshold_uncertainty_score":0.5699173,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099755355","doi":"10.1101/gr.132662.111","title":"Genome-scale analysis of DNA methylation in lung adenocarcinoma and integration with mRNA expression","year":2012,"lang":"en","type":"article","venue":"Genome Research","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":536,"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 Cancer Institute; National Institutes of Health","keywords":"DNA methylation; Biology; Adenocarcinoma; Epigenetics; Methylation; Cancer research; Lung cancer; KRAS; Epigenomics; Gene; Cancer; Genetics; Gene expression; Colorectal cancer; Pathology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.0338198380818476,"gpt":0.3362047196645843,"spread":0.3023848815827367,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001386129,0.00009340657,0.0001660372,0.0005100741,0.00006626871,0.00001845205,0.000097378,0.0001024003,0.00002427915],"category_scores_gemma":[0.00005368151,0.00007815631,0.00003619213,0.0007470019,0.00008300568,0.00001244445,0.00009988435,0.0001256624,0.000001277093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003597686,"about_ca_system_score_gemma":0.00003766889,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006489916,"about_ca_topic_score_gemma":0.0001532268,"domain_scores_codex":[0.9986884,0.0002534649,0.0002179728,0.0002534681,0.0002918404,0.000294879],"domain_scores_gemma":[0.999345,0.00003802258,0.00006788301,0.0002755095,0.0001758937,0.00009769708],"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":[0.00008758291,0.00005101617,0.1694954,0.00001594418,0.00005873468,2.509161e-7,0.0004373307,0.0003472875,0.8286248,0.00001324397,9.633676e-7,0.0008673561],"study_design_scores_gemma":[0.0001938323,0.0001937178,0.6211663,0.000005629185,0.00003960343,2.862996e-7,0.0001811519,0.0003740883,0.377587,0.00002176021,0.0001640179,0.00007251916],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9819162,0.01034656,0.006923847,0.00002518423,0.00001224214,0.0002297733,0.00001041428,0.000002556864,0.0005331778],"genre_scores_gemma":[0.9974061,0.0007680704,0.001367711,0.00000300659,0.00007392608,0.0000264953,0.0002392319,0.0000132222,0.0001022012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4516709,"threshold_uncertainty_score":0.3187122,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3118238647","doi":"10.1101/gr.257246.119","title":"Accurate and efficient detection of gene fusions from RNA sequencing data","year":2021,"lang":"en","type":"article","venue":"Genome Research","topic":"Pancreatic and Hepatic Oncology Research","field":"Medicine","cited_by":524,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Heidelberger Zentrum für Personalisierte Onkologie Deutsches Krebsforschungszentrum In Der Helmholtz-Gemeinschaft; Nationales Centrum für Tumorerkrankungen Heidelberg; Ontario Institute for Cancer Research; Government of Ontario; Deutsches Krebsforschungszentrum","keywords":"KRAS; Biology; Fusion gene; ROS1; Computational biology; Druggability; Gene; Cancer; Identification (biology); Cancer research; Bioinformatics; Mutation; Genetics; Adenocarcinoma","retraction":null,"screen_n_in":null,"score":{"opus":0.266035831030826,"gpt":0.449513237461834,"spread":0.183477406431008,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001752516,0.00007428259,0.000313019,0.0001907838,0.0002032671,0.00002071818,0.0001919701,0.0001010535,0.0004266343],"category_scores_gemma":[0.001230756,0.00006362855,0.00002538096,0.0005305201,0.0002557933,0.00003769989,0.0006275384,0.0004502509,0.00005658234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001684912,"about_ca_system_score_gemma":0.00109055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000753316,"about_ca_topic_score_gemma":0.0001030661,"domain_scores_codex":[0.9979777,0.0003223023,0.0002425693,0.0004143974,0.0006510121,0.0003919806],"domain_scores_gemma":[0.9977233,0.0006103691,0.00003480844,0.0008904839,0.000517392,0.0002236767],"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":[0.0001137966,0.00008188641,0.003227437,0.00007517289,0.00009600388,0.0002159215,0.0004595928,0.0000107815,0.9905297,0.00001987564,0.0000391809,0.005130648],"study_design_scores_gemma":[0.004651643,0.001055557,0.4873775,0.0003313835,0.0003280712,0.000428737,0.007405338,0.0826513,0.4091918,0.000637311,0.005607721,0.0003337216],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898489,0.004020305,0.002109387,0.0005884695,0.00003756947,0.0003005071,0.0001181307,0.00001255629,0.00296414],"genre_scores_gemma":[0.9944094,0.001445566,0.002964391,0.00002346199,0.0001528452,0.00001449199,0.0001701903,0.00001284995,0.0008068324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5813379,"threshold_uncertainty_score":0.4671346,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2751663599","doi":"10.1101/gr.220962.117","title":"An atlas of alternative splicing profiles and functional associations reveals new regulatory programs and genes that simultaneously express multiple major isoforms","year":2017,"lang":"en","type":"article","venue":"Genome Research","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":513,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Canadian Institutes of Health Research; Centro Nacional de Investigaciones Cardiovasculares; Ministerio de Economía y Competitividad","keywords":"Biology; Alternative splicing; Gene; RNA splicing; Genetics; Computational biology; Gene isoform; Intron; Exon; Regulatory sequence; Regulation of gene expression; RNA","retraction":null,"screen_n_in":null,"score":{"opus":0.07028093416800928,"gpt":0.3502530743269423,"spread":0.279972140158933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009686973,0.0001261959,0.0001781274,0.00009821939,0.0007206347,0.0001984292,0.0003029608,0.0001282683,0.000009695668],"category_scores_gemma":[0.0004154219,0.000108716,0.00004079236,0.00004995702,0.0003591621,0.00003114613,0.0003902646,0.0001835912,0.000002398845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003144082,"about_ca_system_score_gemma":0.0001447909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001187476,"about_ca_topic_score_gemma":0.0003550623,"domain_scores_codex":[0.9983082,0.0001288083,0.0001746963,0.0004294651,0.0004901307,0.0004686595],"domain_scores_gemma":[0.9986539,0.00008527558,0.0001248076,0.0005377895,0.0003283875,0.0002698737],"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":[0.0001187674,0.00004650823,0.1190321,0.00004273872,0.0000691579,0.000004899643,0.0001493225,0.0000323024,0.8654199,0.00005775027,0.0000633808,0.0149632],"study_design_scores_gemma":[0.00203271,0.001354552,0.6118962,0.00009045243,0.00001760687,0.00003040129,0.001281643,0.002138722,0.3777716,0.001056586,0.001932584,0.0003968951],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9974834,0.001220178,0.0004310087,0.0001388242,0.0000230555,0.0005449374,0.00004139369,0.000007064894,0.000110178],"genre_scores_gemma":[0.9942895,0.0004641199,0.001083525,0.000007552306,0.0002880286,0.00004403151,0.0001227719,0.00002297385,0.003677496],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4928642,"threshold_uncertainty_score":0.5542613,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135740919","doi":"10.1101/gr.073676.107","title":"The amphioxus genome illuminates vertebrate origins and cephalochordate biology","year":2008,"lang":"en","type":"article","venue":"Genome Research","topic":"Developmental Biology and Gene Regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":511,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria; University of Toronto; Sunnybrook Health Science Centre","funders":"Biotechnology and Biological Sciences Research Council; Centre National de la Recherche Scientifique; Ministero dell’Istruzione, dell’Università e della Ricerca; National Institute of Allergy and Infectious Diseases; European Commission; Wellcome Trust; Japan Society for the Promotion of Science; Ministry of Education, Culture, Sports, Science and Technology; National Institutes of Health; National Science Foundation","keywords":"Chordate; Biology; Hox gene; Genome; Homeobox; Vertebrate; Genetics; Evolutionary biology; Gene; Enhancer; Gene duplication; Transcription factor","retraction":null,"screen_n_in":null,"score":{"opus":0.03640453326177989,"gpt":0.3225527918107469,"spread":0.286148258548967,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007732864,0.0001264448,0.0001103051,0.00007678711,0.0009394449,0.0000232341,0.0002752843,0.0001713899,0.00002321445],"category_scores_gemma":[0.00007132482,0.00009014961,0.00003548227,0.0001835955,0.001202744,0.000004275591,0.0003120265,0.0001686558,0.000110756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003688298,"about_ca_system_score_gemma":0.0001337731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000236085,"about_ca_topic_score_gemma":0.00004186203,"domain_scores_codex":[0.9985511,0.0002370003,0.0001649572,0.0003974341,0.0001227554,0.0005267007],"domain_scores_gemma":[0.9993657,0.00004293221,0.00003211097,0.0003106268,0.0001417472,0.0001068412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009924139,0.00002408,0.01055083,0.000007604114,0.00007765055,0.000009779227,0.0001242463,0.000003973243,0.9808403,0.001039823,0.0003032265,0.006919298],"study_design_scores_gemma":[0.0005521477,0.0005137105,0.1680173,0.000002912604,0.000004904247,0.0001842161,0.0001473661,0.00002254006,0.08105161,0.001433478,0.7477859,0.0002838897],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9905764,0.006868721,0.00007498451,0.0005671998,0.00009011223,0.0002268322,0.00001909229,0.00001053838,0.001566092],"genre_scores_gemma":[0.986796,0.009354569,0.0001740429,0.00006276924,0.0001743778,0.00004156971,0.0002607446,0.00001463788,0.003121342],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8997886,"threshold_uncertainty_score":0.7225545,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152791321","doi":"10.1101/gr.185272.114","title":"The pluripotent regulatory circuitry connecting promoters to their long-range interacting elements","year":2015,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":506,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Ontario Ministry of Research and Innovation; Biotechnology and Biological Sciences Research Council; Medical Research Council; Canadian Institutes of Health Research; Cancer Research UK; Canada Foundation for Innovation; Francis Crick Institute","keywords":"Biology; Promoter; Transcription factor; Chromatin; Genetics; Gene; ChIA-PET; Regulatory sequence; Genome; Regulation of gene expression; Chromatin immunoprecipitation; Histone; Computational biology; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.06085026846415899,"gpt":0.3343343832508382,"spread":0.2734841147866792,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002830783,0.0001427142,0.0001148898,0.00007473699,0.000439572,0.0001631171,0.0005881887,0.00008933972,0.000008659442],"category_scores_gemma":[0.0004568651,0.0001102578,0.00006738349,0.0001659615,0.00007422049,0.000004399778,0.0006800093,0.0002695124,0.00005945906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001605964,"about_ca_system_score_gemma":0.000185664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002697577,"about_ca_topic_score_gemma":0.0001030042,"domain_scores_codex":[0.9980795,0.0002090567,0.0002757244,0.0004015733,0.0003789363,0.0006552183],"domain_scores_gemma":[0.9986123,0.00005788167,0.00007148118,0.0006392954,0.0003503382,0.0002687185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002469498,0.0001465127,0.008408274,0.0000791994,0.0002992593,0.00002855755,0.003519325,0.001000874,0.926611,0.0001578428,0.002731907,0.05677029],"study_design_scores_gemma":[0.004392087,0.004181938,0.047728,0.0002600001,0.00004490867,0.0003562968,0.04175913,0.006274316,0.1185508,0.002246408,0.7719529,0.002253225],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9955335,0.000928573,0.000584406,0.0005789,0.0002220794,0.0004910866,0.00001365739,0.00001223065,0.001635579],"genre_scores_gemma":[0.9980677,0.00006898648,0.0004356807,0.00007746723,0.0003305842,0.00005089346,0.00004742622,0.00004156691,0.0008797088],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8080602,"threshold_uncertainty_score":0.4496183,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2054810412","doi":"10.1101/gr.157651.113","title":"The million mutation project: A new approach to genetics in <i>Caenorhabditis elegans</i>","year":2013,"lang":"en","type":"article","venue":"Genome Research","topic":"Genetics, Aging, and Longevity in Model Organisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":473,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research","keywords":"Biology; Genetics; Caenorhabditis elegans; Indel; Gene; Nonsynonymous substitution; Nonsense mutation; Mutation; Mutant; Missense mutation; Genome; Single-nucleotide polymorphism; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.04547436601114383,"gpt":0.3203043019064186,"spread":0.2748299358952747,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009246682,0.0001572152,0.0001264577,0.000175103,0.0002615816,0.0001552621,0.0005925697,0.0001575937,0.00002148594],"category_scores_gemma":[0.000144214,0.000131529,0.00005023788,0.0004860701,0.0001201684,0.000005794335,0.0002936297,0.0002734346,0.0002800759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006101594,"about_ca_system_score_gemma":0.0003282488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001136185,"about_ca_topic_score_gemma":0.0003775157,"domain_scores_codex":[0.9977628,0.0002483286,0.0002626859,0.0005234359,0.0004702596,0.0007324974],"domain_scores_gemma":[0.9988256,0.00003502055,0.00003462116,0.0006406059,0.000275346,0.0001887714],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007387409,0.0002309471,0.001609277,0.00006767813,0.00005409963,0.000006961076,0.004370026,0.002612165,0.9234334,0.0001872326,0.0369001,0.03045428],"study_design_scores_gemma":[0.002292401,0.001801228,0.07292558,0.00003525359,0.00002364119,0.0001122664,0.004331618,0.003018315,0.178626,0.00408213,0.7314327,0.001318873],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9768885,0.002802395,0.01077784,0.001353939,0.0001226192,0.002220276,0.0000107207,0.00001618563,0.005807516],"genre_scores_gemma":[0.9836975,0.001388144,0.006140791,0.0002515042,0.000528767,0.0003072914,0.0001105783,0.00005347348,0.007521949],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7448074,"threshold_uncertainty_score":0.5363597,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152121035","doi":"10.1101/gr.100552.109","title":"Multiplexed massively parallel SELEX for characterization of human transcription factor binding specificities","year":2010,"lang":"en","type":"article","venue":"Genome Research","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":462,"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":"Academy of Finland","keywords":"Biology; Systematic evolution of ligands by exponential enrichment; Computational biology; Massive parallel sequencing; DNA binding site; Transcription factor; Oligonucleotide; DNA; DNA sequencing; DNA microarray; Genetics; SELEX Aptamer Technique; Gene; Promoter; RNA; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.08674435645434864,"gpt":0.3413351557012052,"spread":0.2545907992468565,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005226617,0.0000975348,0.0001286547,0.0001285756,0.000193941,0.00003378882,0.0002127163,0.000173615,0.0001351862],"category_scores_gemma":[0.00006797183,0.00009419525,0.00008009459,0.00008454918,0.00008895376,0.000006525113,0.00003507841,0.0001250194,0.000009159154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001029659,"about_ca_system_score_gemma":0.00004747132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008890697,"about_ca_topic_score_gemma":0.00001341775,"domain_scores_codex":[0.9989378,0.00008754389,0.000197476,0.0002599534,0.0002159313,0.0003013116],"domain_scores_gemma":[0.9993791,0.00002189921,0.00006503355,0.0002326661,0.0002388868,0.00006242965],"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":[0.0001168178,0.00003548564,0.000123488,0.00005824503,0.0000206343,2.909576e-7,0.0001608099,6.7464e-7,0.9971941,0.0005900897,0.000009722147,0.001689656],"study_design_scores_gemma":[0.0003513386,0.0003001339,0.00459537,0.000007069666,0.000002917061,9.878444e-7,0.0001100539,0.000009660169,0.9847404,0.0001878158,0.009588697,0.0001055787],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9944047,0.00003337262,0.004372239,0.00007257864,0.00009374839,0.00064593,0.0001911099,0.000008076076,0.0001782797],"genre_scores_gemma":[0.9946587,0.00006968138,0.002420781,0.000005314857,0.0003043511,0.0001348365,0.0004638778,0.00002656394,0.001915863],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01245371,"threshold_uncertainty_score":0.3841171,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151529778","doi":"10.1101/gr.082081.108","title":"genBlastA: Enabling BLAST to identify homologous gene sequences","year":2008,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":448,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Michael Smith Health Research BC","keywords":"Biology; Gene; Homologous chromosome; Genome; Genetics; Computational biology; Candidate gene; Homologous recombination; Gene prediction","retraction":null,"screen_n_in":null,"score":{"opus":0.08839709977521111,"gpt":0.3692360436837064,"spread":0.2808389439084953,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007617616,0.0001732886,0.0001886734,0.0001976155,0.0006085592,0.00004462229,0.0005149592,0.0001249666,0.00005648038],"category_scores_gemma":[0.0001579141,0.000167767,0.0000884247,0.0003684947,0.0002937411,8.873761e-7,0.0006893675,0.0001895451,0.0002178373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004424382,"about_ca_system_score_gemma":0.0002229898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001260364,"about_ca_topic_score_gemma":0.00005861744,"domain_scores_codex":[0.9978175,0.0001469539,0.0002358974,0.0006147779,0.0003984804,0.0007863457],"domain_scores_gemma":[0.9988037,0.00003464346,0.00003312259,0.0005259161,0.0003691461,0.0002334485],"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":[0.00004238043,0.00003472385,0.002006491,0.0000106765,0.00006787155,0.00005508751,0.000329452,0.0003601842,0.9955488,0.00001316938,0.0009391701,0.0005920085],"study_design_scores_gemma":[0.0005358843,0.001185128,0.07101327,0.000009066993,0.00001115842,0.0003192773,0.0005986904,0.000008926007,0.7096293,0.0003109123,0.2158395,0.0005389053],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9921417,0.005031733,0.0004128244,0.0002710424,0.0001331384,0.0003367389,0.00006327705,0.000005253735,0.001604248],"genre_scores_gemma":[0.9915883,0.003206291,0.002044842,0.0001312063,0.0006336097,0.00008217876,0.00003253685,0.00003317158,0.002247895],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2859195,"threshold_uncertainty_score":0.6841341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2096746187","doi":"10.1101/gr.180281.114","title":"TITAN: inference of copy number architectures in clonal cell populations from tumor whole-genome sequence data","year":2014,"lang":"en","type":"article","venue":"Genome Research","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":429,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vancouver General Hospital; Ontario Genomics; University of British Columbia; British Columbia Centre on Substance Use; BC Cancer Agency","funders":"Natural Sciences and Engineering Research Council of Canada; Terry Fox Research Institute; Canadian Cancer Society Research Institute; Genome Canada; Canadian Institutes of Health Research; Genome British Columbia; Michael Smith Health Research BC","keywords":"Biology; Loss of heterozygosity; Genome; Genetics; Computational biology; Copy-number variation; Population; Somatic cell; Whole genome sequencing; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.1119003118096085,"gpt":0.3951657348059641,"spread":0.2832654229963555,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006824275,0.0001275297,0.0001836372,0.0001010561,0.00007785887,0.00003967765,0.0008643536,0.00009321189,0.0001311042],"category_scores_gemma":[0.0004673252,0.000131425,0.00003698351,0.0002264241,0.0002006496,0.000004241301,0.0008336237,0.0002639665,0.00006409286],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004275951,"about_ca_system_score_gemma":0.0003193637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001441273,"about_ca_topic_score_gemma":0.001217344,"domain_scores_codex":[0.998301,0.0001659151,0.0002882429,0.0005230938,0.0003191884,0.0004025575],"domain_scores_gemma":[0.9984002,0.0001678509,0.00006690811,0.001079962,0.0001619909,0.0001230602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007736887,0.00009731788,0.05421851,0.00003637044,0.00001466376,0.00000664155,0.00009666415,0.001752604,0.942283,0.0002928508,0.0004259562,0.0006980021],"study_design_scores_gemma":[0.0028113,0.0009309865,0.4026343,0.00009955785,0.0000378579,0.0000202904,0.0002449447,0.003650089,0.07667991,0.01434084,0.4973552,0.001194796],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9921827,0.0009103362,0.001388215,0.0001808105,0.00008566862,0.0002313145,0.002838697,0.000004555086,0.002177671],"genre_scores_gemma":[0.9925565,0.0001984052,0.003454797,0.00007884334,0.0002871795,0.00001967572,0.003169202,0.00002249632,0.0002129076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8656031,"threshold_uncertainty_score":0.5359356,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978391087","doi":"10.1101/gr.092924.109","title":"Profiling the T-cell receptor beta-chain repertoire by massively parallel sequencing","year":2009,"lang":"en","type":"article","venue":"Genome Research","topic":"T-cell and B-cell Immunology","field":"Immunology and Microbiology","cited_by":415,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"Genome British Columbia; Genome Canada","keywords":"Biology; T-cell receptor; Genetics; Complementarity determining region; Repertoire; Gene; T cell; Peptide sequence; Immune system","retraction":null,"screen_n_in":null,"score":{"opus":0.04682168957192249,"gpt":0.2908226063671601,"spread":0.2440009167952376,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002082546,0.0002770621,0.0003691736,0.0002049937,0.001297458,0.0000656183,0.001007554,0.0004709267,0.0009919379],"category_scores_gemma":[0.000128065,0.0001916475,0.0001466153,0.0004687893,0.0006873654,0.0000943001,0.0002521691,0.001734729,0.003472477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002637962,"about_ca_system_score_gemma":0.0003051994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001221326,"about_ca_topic_score_gemma":0.000006235577,"domain_scores_codex":[0.9960784,0.001196238,0.0004519672,0.0006801003,0.0001692281,0.00142407],"domain_scores_gemma":[0.9983695,0.0004001021,0.0001170112,0.0008029633,0.0002520366,0.00005845796],"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":[0.00014874,0.000125734,0.0000838112,0.00001520581,0.0000718819,0.0000157554,0.0006021392,0.00001129394,0.9790973,0.0009147046,0.01548889,0.003424551],"study_design_scores_gemma":[0.001102028,0.0006456157,0.00008207839,0.00001850466,0.00001518433,0.00006189648,0.001996325,0.000008086588,0.7663835,0.0006085092,0.2287762,0.0003020522],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9288525,0.04006187,0.0002311128,0.01058179,0.0004887595,0.001236118,0.00007033502,0.0001891884,0.01828831],"genre_scores_gemma":[0.9411316,0.001073082,0.0003377139,0.0003500448,0.0001048553,0.00008048378,0.0002392407,0.00003268316,0.05665031],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2132873,"threshold_uncertainty_score":0.9999213,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3011678041","doi":"10.1101/gr.258640.119","title":"Accurate and complete genomes from metagenomes","year":2020,"lang":"en","type":"review","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":403,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Biological and Environmental Research; National Institute of Allergy and Infectious Diseases; Lawrence Berkeley National Laboratory; National Institute of General Medical Sciences; Office of Science; National Institutes of Health; Innovative Genomics Institute; Genome Canada; University of California Berkeley; U.S. Department of Energy","keywords":"Genome; Biology; Metagenomics; Bacterial genome size; Computational biology; Genomics; Shotgun sequencing; Genetics; Sequence assembly; Gene; Transcriptome","retraction":null,"screen_n_in":null,"score":{"opus":0.2194429092067851,"gpt":0.4100852115075093,"spread":0.1906423023007242,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006075453,0.0005199484,0.001416615,0.0001844548,0.0003211578,0.0001535403,0.0007884198,0.0003509471,0.0000883701],"category_scores_gemma":[0.0001024016,0.0004438373,0.000346213,0.0003123922,0.0003398488,6.870982e-7,0.001800664,0.0005300037,0.000188796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004758463,"about_ca_system_score_gemma":0.0003934586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006093963,"about_ca_topic_score_gemma":0.00002254493,"domain_scores_codex":[0.9966862,0.0005301793,0.0005213134,0.001185704,0.0003515683,0.0007250866],"domain_scores_gemma":[0.998442,0.0001735958,0.0001545826,0.0007600713,0.00016017,0.0003096049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002927763,0.00003625198,0.00001310592,0.002876243,0.002235173,0.00005473932,0.0002126227,0.000002000489,0.01048173,0.00009737178,0.0007767639,0.9831847],"study_design_scores_gemma":[0.0001563813,0.0001857206,0.00006450981,0.0001365558,0.0002039847,0.00001486598,0.00006363293,0.000002157108,0.000016195,0.0001368457,0.9985834,0.0004357423],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000309795,0.9956129,0.00002277948,0.00009282838,0.0001025356,0.0008783461,0.002046787,0.000004918417,0.0009290669],"genre_scores_gemma":[0.0003525924,0.9962969,0.0006384265,0.00004652812,0.001008637,0.0001784563,0.0007858843,0.0001117341,0.0005808795],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9978067,"threshold_uncertainty_score":0.9998013,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2010789111","doi":"10.1101/gr.164079.113","title":"Combinatorial effects of multiple enhancer variants in linkage disequilibrium dictate levels of gene expression to confer susceptibility to common traits","year":2013,"lang":"en","type":"article","venue":"Genome Research","topic":"RNA Research and Splicing","field":"Biochemistry, Genetics and Molecular Biology","cited_by":392,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Princess Margaret Cancer Centre; University Health Network","funders":"National Institute of General Medical Sciences; National Cancer Institute; National Institutes of Health","keywords":"Enhancer; Biology; Genome-wide association study; Genetics; Linkage disequilibrium; Single-nucleotide polymorphism; Locus (genetics); Genetic association; Gene; Expression quantitative trait loci; Gene expression; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.02978646353067047,"gpt":0.3345184245374788,"spread":0.3047319610068083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012102,0.0001461589,0.0003333118,0.0002254193,0.00005745344,0.00002664751,0.0004994371,0.0001603704,0.00008265648],"category_scores_gemma":[0.0009062132,0.0001314297,0.00007069629,0.0003770575,0.0001276445,0.00001165845,0.0005422694,0.0002469593,0.00003633888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005309821,"about_ca_system_score_gemma":0.0001802669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000587545,"about_ca_topic_score_gemma":0.0001026615,"domain_scores_codex":[0.9973165,0.0005295918,0.0003893714,0.0004891582,0.0005811105,0.0006942167],"domain_scores_gemma":[0.9983945,0.0001977081,0.00004681871,0.0005461461,0.0004427032,0.0003720664],"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":[0.0003817571,0.0001863166,0.005079684,0.0002324192,0.00001825408,0.000005518913,0.0003092215,0.00004435286,0.9921631,0.00001301098,0.0001112498,0.001455064],"study_design_scores_gemma":[0.0009702573,0.0008612318,0.2180813,0.00006761034,0.000001257462,3.95209e-7,0.00004047194,0.00005260115,0.7796437,0.00009269461,0.00008668102,0.0001018156],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9972302,0.0001928972,0.0005337543,0.00009759764,0.00007837764,0.001584479,0.00006257195,0.000004411633,0.0002156908],"genre_scores_gemma":[0.9987679,0.00002955779,0.000515084,0.00001734618,0.0001081701,0.0001639335,0.00002619508,0.00002503274,0.0003468318],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2130016,"threshold_uncertainty_score":0.5359547,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165247488","doi":"10.1101/gr.097378.109","title":"Gene regulatory networks and the role of robustness and stochasticity in the control of gene expression","year":2011,"lang":"en","type":"article","venue":"Genome Research","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":382,"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 Diabetes and Digestive and Kidney Diseases; National Institute of General Medical Sciences; Canadian Institutes of Health Research","keywords":"Biology; Gene regulatory network; Gene; Robustness (evolution); Gene expression; Regulation of gene expression; Computational biology; Genetics; Phenotype; Systems biology; Gene expression profiling; Regulator gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02115922042942472,"gpt":0.2580567786374276,"spread":0.2368975582080029,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002631366,0.0001000188,0.0002256915,0.00008036126,0.00009985494,0.00000906478,0.0003219596,0.0001216161,0.000008590136],"category_scores_gemma":[0.0000575448,0.00006058287,0.00005723314,0.0002082224,0.0007560956,0.000002949955,0.0001890659,0.0001618065,1.616205e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006624651,"about_ca_system_score_gemma":0.00004066661,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000645125,"about_ca_topic_score_gemma":0.00002675089,"domain_scores_codex":[0.9982568,0.0006835515,0.000245136,0.0002581392,0.0002804348,0.0002759173],"domain_scores_gemma":[0.9990808,0.00009323004,0.00008898589,0.0005249973,0.0001590145,0.0000529552],"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":[0.0007542638,0.00007235984,0.007643549,0.00002168427,0.00009910245,0.000001963761,0.000650346,0.01835264,0.9697375,0.0001720759,0.00001477387,0.002479721],"study_design_scores_gemma":[0.004793542,0.000547433,0.2215182,0.00005002171,0.0001379949,0.00004085975,0.002477593,0.04957688,0.7194144,0.0008715109,0.0002251813,0.0003463858],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9653037,0.02188237,0.0122795,0.00002832097,0.000008733406,0.0003464805,0.000005479893,0.000001306977,0.0001441208],"genre_scores_gemma":[0.9988988,0.0006096226,0.0003185897,0.00001145747,0.00008495516,0.00003724304,0.000007414782,0.00001142561,0.00002048686],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2503231,"threshold_uncertainty_score":0.2785866,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135598172","doi":"10.1101/gr.217802","title":"Control Genes and Variability: Absence of Ubiquitous Reference Transcripts in Diverse Mammalian Expression Studies","year":2002,"lang":"en","type":"article","venue":"Genome Research","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":378,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill Genome Centre; McGill University Health Centre","funders":"Takeda Oncology; Mitacs; Canadian Institutes of Health Research; Bristol-Myers Squibb","keywords":"Biology; Housekeeping gene; Gene; Microarray; Gene expression; Microarray analysis techniques; Genetics; Gene expression profiling; Computational biology; Reference genes; Phenotype; DNA microarray","retraction":null,"screen_n_in":null,"score":{"opus":0.1415979883306038,"gpt":0.3668231029196328,"spread":0.225225114589029,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007623829,0.00008820318,0.0001470026,0.0001135835,0.00008076797,0.00001183064,0.0001848225,0.0001037633,0.00005512703],"category_scores_gemma":[0.0001278519,0.000076324,0.0000242985,0.0001705925,0.0002780138,0.000005533494,0.0001023438,0.0001277167,0.00000489398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002345885,"about_ca_system_score_gemma":0.0000288479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002812519,"about_ca_topic_score_gemma":0.00002645822,"domain_scores_codex":[0.9986574,0.0002720558,0.0001983675,0.0003712478,0.0002509681,0.0002499603],"domain_scores_gemma":[0.9993096,0.00003653055,0.00004030774,0.0003385701,0.0002014815,0.00007350926],"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":[0.00008102434,0.00005836738,0.003293221,0.00007230443,0.000009883771,0.000002294156,0.00037271,0.00001288038,0.9901646,0.0000689833,0.0003714962,0.005492213],"study_design_scores_gemma":[0.003041512,0.0008763015,0.06630449,0.0001469534,0.00001331044,0.0000101862,0.004406113,0.0002581466,0.8622676,0.0009665425,0.06126997,0.0004388725],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885306,0.009696269,0.0003959564,0.0003133986,0.00004677868,0.000290939,0.00002056767,0.000004683953,0.0007008194],"genre_scores_gemma":[0.9937988,0.005474958,0.000180762,0.00002209116,0.00005074546,0.00006022916,0.000006739951,0.000007747168,0.00039795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.127897,"threshold_uncertainty_score":0.3112403,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098980484","doi":"10.1101/gr.146886.112","title":"Widespread and extensive lengthening of 3′ UTRs in the mammalian brain","year":2013,"lang":"en","type":"article","venue":"Genome Research","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":373,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Burroughs Wellcome Fund; National Human Genome Research Institute; Canadian Institutes of Health Research; National Cancer Institute; National Institutes of Health; National Institute of General Medical Sciences; New York State Stem Cell Science","keywords":"Biology; Polyadenylation; Untranslated region; Gene; microRNA; Transcriptome; Ensembl; Computational biology; Three prime untranslated region; Genetics; Gene isoform; Gene expression; RNA; Genomics; Genome","retraction":null,"screen_n_in":null,"score":{"opus":0.03471362173205859,"gpt":0.3358022314830689,"spread":0.3010886097510103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001749425,0.0001031722,0.0001264255,0.0002037251,0.00009412078,0.000052986,0.0004153592,0.0001398875,0.00008535155],"category_scores_gemma":[0.0005510989,0.00008198992,0.00004447963,0.0003618877,0.0002662097,0.000005499098,0.0003360521,0.0003912183,0.00003312505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002428,"about_ca_system_score_gemma":0.0001256113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005626955,"about_ca_topic_score_gemma":0.00009760123,"domain_scores_codex":[0.9979438,0.0005157103,0.0001894158,0.0003486282,0.0004813954,0.0005210821],"domain_scores_gemma":[0.9989236,0.0001417599,0.00003150878,0.0004987044,0.000316784,0.00008765627],"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":[0.00004095219,0.00002667103,0.00006836437,0.00003169403,0.00001867827,0.00001195453,0.0003713031,0.00002938996,0.9926128,0.0002545735,0.001050679,0.005482942],"study_design_scores_gemma":[0.002200166,0.002061583,0.03144781,0.0001077463,0.00001086555,0.0001573454,0.006780529,0.0004018322,0.8925301,0.003756065,0.0600144,0.0005315644],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908525,0.002854442,0.0006719577,0.00216179,0.00002523345,0.0008728734,0.000008510189,0.000003654568,0.002549061],"genre_scores_gemma":[0.9979967,0.0004017086,0.0002904544,0.0001665707,0.00007319152,0.0001358369,0.00002060448,0.0000233545,0.0008915399],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1000827,"threshold_uncertainty_score":0.3343452,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2074813718","doi":"10.1101/gr.388902","title":"Retroelement Distributions in the Human Genome: Variations Associated With Age and Proximity to Genes","year":2002,"lang":"en","type":"article","venue":"Genome Research","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":371,"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; BC Cancer Agency","funders":"BC Cancer Agency; Canadian Institutes of Health Research; Knut och Alice Wallenbergs Stiftelse","keywords":"Biology; Retrotransposon; Alu element; Genome; Transposable element; Genetics; Gene; Human genome; GC-content; Gene density; Genome evolution; Chromosome","retraction":null,"screen_n_in":null,"score":{"opus":0.1012901746558254,"gpt":0.304731860185852,"spread":0.2034416855300265,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008259966,0.00007666043,0.00009049466,0.0000295258,0.0008518528,0.0001373177,0.0002591448,0.00004469914,0.0005434054],"category_scores_gemma":[0.00009351689,0.00002737001,0.00002073879,0.001121869,0.00008199073,0.00004314,0.0001112902,0.0001819561,0.0000314243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008306442,"about_ca_system_score_gemma":0.000007004823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002828243,"about_ca_topic_score_gemma":0.005856985,"domain_scores_codex":[0.9985653,0.0002783464,0.0001438717,0.0002448101,0.000384478,0.0003831538],"domain_scores_gemma":[0.999498,0.0001922372,0.00001735513,0.00008717661,0.0001107806,0.00009445756],"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":[0.00001655663,0.001794661,0.0660157,0.00001492946,0.00009656754,0.00007697855,0.005921041,0.00006935872,0.8873773,0.02254144,0.0005392525,0.01553619],"study_design_scores_gemma":[0.0001100852,0.0003258666,0.9870966,0.000005186226,0.000004834236,0.000002674382,0.0002585539,0.00003227324,0.00003970906,0.001368213,0.01067427,0.00008171119],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894581,0.0001553928,0.00001142722,0.008284395,0.000006201982,0.0006123639,0.0001925683,0.00001543237,0.001264101],"genre_scores_gemma":[0.9990132,0.00004500047,0.00006286692,0.00005235599,0.00007075761,0.0001616642,0.0001901582,7.753695e-7,0.0004032488],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9210809,"threshold_uncertainty_score":0.6551849,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153992812","doi":"10.1101/gr.100396.109","title":"A single-base resolution map of an archaeal transcriptome","year":2009,"lang":"en","type":"article","venue":"Genome Research","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":368,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Azrieli Foundation","keywords":"Biology; Sulfolobus solfataricus; Archaea; Genetics; RNA; Operon; Transcription (linguistics); Transcriptome; Sulfolobus; Computational biology; Gene; Gene expression; Escherichia coli","retraction":null,"screen_n_in":null,"score":{"opus":0.0634780951462023,"gpt":0.328387448422196,"spread":0.2649093532759937,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001199279,0.00009558244,0.0001235938,0.0001407379,0.0001003342,0.00001822028,0.0003066342,0.0001379607,0.00006665222],"category_scores_gemma":[0.00005165042,0.00009261829,0.00007110366,0.0001325104,0.0001162337,0.000004815635,0.00003908337,0.0001232598,0.00002651865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002155143,"about_ca_system_score_gemma":0.00008517875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002548132,"about_ca_topic_score_gemma":0.00001129464,"domain_scores_codex":[0.9983827,0.0003258625,0.0001820802,0.0003208601,0.0003679581,0.0004205549],"domain_scores_gemma":[0.9991871,0.00001268599,0.00003147213,0.000461111,0.0001647191,0.000142973],"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":[0.0002790776,0.0001609873,0.000005468832,0.00002135572,0.00001000498,0.000006789677,0.0001133261,0.00001440222,0.9783303,0.0003343549,0.00006863341,0.02065537],"study_design_scores_gemma":[0.0003116349,0.002665578,0.0005235485,0.00001186094,0.000003530922,0.000008521191,0.00009089998,0.00002263754,0.9728292,0.002223462,0.02119548,0.0001136006],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9925545,0.001831035,0.002928209,0.0007713859,0.0000411412,0.0003409749,0.00002779268,0.00001193233,0.00149301],"genre_scores_gemma":[0.9950474,0.00006744346,0.0037005,0.00004835115,0.0002096072,0.00001737879,0.00007317629,0.00001447976,0.0008216744],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02112685,"threshold_uncertainty_score":0.3776864,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165759219","doi":"10.1101/gr.112169.110","title":"Comparative genomics of citric-acid-producing<i>Aspergillus niger</i>ATCC 1015 versus enzyme-producing CBS 513.88","year":2011,"lang":"en","type":"article","venue":"Genome Research","topic":"Enzyme Production and Characterization","field":"Biochemistry, Genetics and Molecular Biology","cited_by":367,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Lawrence Berkeley National Laboratory; Biomass Program; Los Alamos National Laboratory; Biological and Environmental Research; Office of Science; Lawrence Livermore National Laboratory; U.S. Department of Energy","keywords":"Biology; Genetics; Aspergillus niger; Genome; Gene; Transcriptome; Reference genome; Whole genome sequencing; Single-nucleotide polymorphism; Genotype; Biochemistry; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.1493636227696736,"gpt":0.3502610496640595,"spread":0.2008974268943859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001311857,0.0002234828,0.0003158416,0.0002566735,0.0002390993,0.00003394965,0.000466783,0.0001812027,0.0002712663],"category_scores_gemma":[0.0002761549,0.0002298347,0.0001027994,0.0005904482,0.0002808567,0.00001680407,0.0003527796,0.0003261207,0.0001266302],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009473341,"about_ca_system_score_gemma":0.0002738907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000953139,"about_ca_topic_score_gemma":0.00003187939,"domain_scores_codex":[0.997368,0.0002956138,0.0004301686,0.000879221,0.0004369826,0.0005899877],"domain_scores_gemma":[0.9978448,0.00002137581,0.0001575962,0.000983808,0.0008226647,0.0001697576],"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":[0.0007398148,0.0001476049,0.0004621128,0.00005390327,0.0001082911,0.000003175568,0.003104286,0.00003826789,0.9940287,0.00006940807,0.0007242946,0.0005200878],"study_design_scores_gemma":[0.000701608,0.0006211366,0.004936676,0.000009501099,0.00001408635,0.000009258455,0.0008247859,0.00002214453,0.9682785,0.00004585459,0.02428484,0.0002516611],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9911814,0.002051134,0.0005687326,0.0001356252,0.0004592035,0.0004674453,0.0000441611,0.00002550996,0.005066748],"genre_scores_gemma":[0.9946818,0.0007388888,0.001377514,0.00003617061,0.0007742501,0.00004156155,0.0002812568,0.00004338536,0.002025137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02575031,"threshold_uncertainty_score":0.9372388,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1977957409","doi":"10.1101/gr.124107.111","title":"Accurate identification of A-to-I RNA editing in human by transcriptome sequencing","year":2011,"lang":"en","type":"article","venue":"Genome Research","topic":"RNA regulation and disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":366,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"March of Dimes Foundation; National Institutes of Health; National Institute on Drug Abuse; BC Cancer Agency; American Heart Association; Alfred P. Sloan Foundation","keywords":"RNA editing; Biology; RNA; Computational biology; Transcriptome; RNA-Seq; Genetics; Gene; DNA sequencing; Genome; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.09683065621439993,"gpt":0.3666134514430814,"spread":0.2697827952286815,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008332208,0.00005755984,0.00007230112,0.0001612244,0.00006501839,0.00001521454,0.0001990908,0.0000598592,0.00007288319],"category_scores_gemma":[0.00008154527,0.00006132165,0.00003319209,0.0002482164,0.00006199763,0.000005912362,0.00004938135,0.00007717381,0.00001698457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000346353,"about_ca_system_score_gemma":0.00006630067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001003106,"about_ca_topic_score_gemma":0.00001923439,"domain_scores_codex":[0.9989674,0.0001121673,0.0002447907,0.0002242224,0.0002120268,0.0002393655],"domain_scores_gemma":[0.9994556,0.00000488123,0.00004037701,0.0002409809,0.0001517367,0.0001063951],"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":[0.00002987283,0.0000336428,0.001079998,0.00002389159,0.00000574966,0.000001477031,0.0004069026,0.00003069319,0.9977325,0.00009613704,0.000240707,0.0003184167],"study_design_scores_gemma":[0.0003569795,0.0001202797,0.04964232,0.00001241553,0.000002613474,9.156121e-7,0.0006407184,0.00006832131,0.9473819,0.0002375576,0.001427983,0.0001080467],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.995898,0.0002417657,0.0009490557,0.00005492891,0.00002580871,0.0001982063,0.00002363628,0.000004394659,0.002604213],"genre_scores_gemma":[0.9988306,0.0000208105,0.00008607384,0.00002213867,0.00006424705,0.00002643104,0.00008008094,0.00001122,0.0008584193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05035067,"threshold_uncertainty_score":0.2500625,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165567657","doi":"10.1101/gr.115428.110","title":"Exhaustive T-cell repertoire sequencing of human peripheral blood samples reveals signatures of antigen selection and a directly measured repertoire size of at least 1 million clonotypes","year":2011,"lang":"en","type":"article","venue":"Genome Research","topic":"T-cell and B-cell Immunology","field":"Immunology and Microbiology","cited_by":365,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"BC Cancer Agency; Canadian Institutes of Health Research; Genome British Columbia; Genome Canada","keywords":"Repertoire; Biology; Genetics; Deep sequencing; T-cell receptor; Computational biology; T cell; Gene; Immune system; Genome","retraction":null,"screen_n_in":null,"score":{"opus":0.06331595217996244,"gpt":0.280635940177459,"spread":0.2173199879974965,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001241561,0.0002413006,0.0006875335,0.0003413659,0.0004454649,0.000006154478,0.0003397937,0.0005086702,0.0005566191],"category_scores_gemma":[0.0002623398,0.0002099537,0.0001407087,0.0004311654,0.001135625,0.00007958795,0.0002857843,0.0005591893,0.000008884559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001148566,"about_ca_system_score_gemma":0.0001755079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002963759,"about_ca_topic_score_gemma":0.0003141679,"domain_scores_codex":[0.997235,0.0007897887,0.000657097,0.0005541635,0.0001635326,0.0006004084],"domain_scores_gemma":[0.9981492,0.0002926783,0.0003444518,0.0004273122,0.0007445547,0.00004186742],"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":[0.0009050025,0.0003243169,0.01558153,0.0002686417,0.0003632661,0.000007738544,0.00449057,0.000003271796,0.9774266,0.0001142886,0.00006851544,0.0004462792],"study_design_scores_gemma":[0.001164375,0.001516894,0.02432178,0.0001059562,0.00006302191,0.00005578482,0.001164409,0.000001184404,0.9708927,0.0002175623,0.0003093179,0.000187024],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9750032,0.02288316,0.000005335685,0.00002147548,0.00007245471,0.0004318526,0.00005440248,0.0000298285,0.001498265],"genre_scores_gemma":[0.9949577,0.001164006,0.0003137559,0.000005481012,0.00002451309,0.00002226047,0.00004293392,0.00003171453,0.003437602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02171916,"threshold_uncertainty_score":0.8561662,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2015364707","doi":"10.1101/gr.171439.113","title":"The effect of genotype and in utero environment on interindividual variation in neonate DNA methylomes","year":2014,"lang":"en","type":"article","venue":"Genome Research","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":362,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Child and Family Research Institute; McGill University; Douglas Mental Health University Institute; University of British Columbia","funders":"National Research Foundation; National Medical Research Council; National Research Foundation Singapore; National Institute for Health and Care Research; Agency for Science, Technology and Research; Medical Research Council; Canadian Institute for Advanced Research","keywords":"DNA methylation; Biology; Epigenetics; Genetics; Genotype; In utero; Methylation; Genetic variation; DNA; Fetus; Gene; Pregnancy; Gene expression","retraction":null,"screen_n_in":null,"score":{"opus":0.01671615804003995,"gpt":0.3084512473536649,"spread":0.291735089313625,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028774,0.00006370828,0.00008628213,0.0001017312,0.00004529383,0.00001617699,0.0001183882,0.0000709216,0.000004701951],"category_scores_gemma":[0.0001757162,0.00004663632,0.00001705254,0.00007544211,0.00007070706,0.00000151781,0.0001391652,0.0001139224,0.000004857846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002247022,"about_ca_system_score_gemma":0.00001109647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003966269,"about_ca_topic_score_gemma":0.00004515923,"domain_scores_codex":[0.9987108,0.0005731905,0.0001464271,0.0001942039,0.0001846423,0.0001907549],"domain_scores_gemma":[0.9995286,0.000187293,0.00002953804,0.0002097983,0.00001523615,0.00002956861],"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":[0.0001983838,0.00001493913,0.004792904,0.00001650765,0.00001186306,7.577984e-7,0.0001271118,0.0004671198,0.9590487,0.00005732533,0.000001487144,0.03526285],"study_design_scores_gemma":[0.00076298,0.001948081,0.4270773,0.000009637649,0.000002828101,4.467933e-7,0.00001792221,0.0002878175,0.5559298,0.0006227497,0.01325245,0.00008800039],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9976156,0.001449128,0.0002789129,0.00009947825,0.00002236591,0.0002063747,0.000002740178,7.899208e-7,0.0003245891],"genre_scores_gemma":[0.9984761,0.001259336,0.00009925805,0.000004287656,0.00003690033,0.00002647246,0.00001246068,0.000007929416,0.00007726822],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4222844,"threshold_uncertainty_score":0.1901774,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2125910143","doi":"10.1101/gr.165555.113","title":"Genome-wide identification of long noncoding natural antisense transcripts and their responses to light in <i>Arabidopsis</i>","year":2014,"lang":"en","type":"article","venue":"Genome Research","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":362,"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 Research Foundation of Korea; Rural Development Administration; National Research Foundation","keywords":"Biology; Intergenic region; Arabidopsis; Genetics; Gene; Intron; Histone; Antisense RNA; Non-coding RNA; Genome; Tiling array; RNA; Long non-coding RNA; Transcription (linguistics); Noncoding DNA; Computational biology; Sense (electronics); Gene expression; DNA microarray","retraction":null,"screen_n_in":null,"score":{"opus":0.02253360959874689,"gpt":0.311861210957368,"spread":0.2893276013586211,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002888554,0.0001628904,0.0002280639,0.0005599115,0.0001287594,0.00006667698,0.000385259,0.0001672795,0.00001023518],"category_scores_gemma":[0.000664579,0.000157227,0.0000722442,0.0006440108,0.0001329746,0.000009284267,0.0002704045,0.0003684216,0.00001589956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007642711,"about_ca_system_score_gemma":0.0001491568,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004793427,"about_ca_topic_score_gemma":0.0001584386,"domain_scores_codex":[0.9973439,0.0006299046,0.000374549,0.0006053871,0.0004394843,0.000606795],"domain_scores_gemma":[0.9987476,0.0001019616,0.00005130838,0.0005866327,0.0003342925,0.0001782091],"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":[0.0004251758,0.00004007493,0.00037241,0.00007281578,0.00002758698,0.00001041747,0.0004046501,0.00007146633,0.995419,0.00002660119,0.00003447225,0.003095368],"study_design_scores_gemma":[0.0005277395,0.0003199956,0.03198265,0.00003426268,0.000003505715,0.00001803323,0.0001729265,0.0001284256,0.9584036,0.00006807412,0.008166566,0.0001741942],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9860298,0.002930721,0.009214778,0.0008037392,0.0000722283,0.0006217152,0.00002326882,0.000008262849,0.0002955006],"genre_scores_gemma":[0.9979983,0.0007306389,0.0001441706,0.00006670078,0.00009861687,0.00005665572,0.00004639326,0.00003959406,0.0008189479],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03701533,"threshold_uncertainty_score":0.641153,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2114014715","doi":"10.1101/gr.1649303","title":"The Human Transcriptome Map Reveals Extremes in Gene Density, Intron Length, GC Content, and Repeat Pattern for Domains of Highly and Weakly Expressed Genes","year":2003,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":351,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute of Infection and Immunity","funders":"National Institutes of Health; U.S. National Library of Medicine; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Biology; Gene; Intron; Transcriptome; Genetics; Genome; Human genome; Gene expression; GC-content; Gene density; Computational biology","retraction":null,"screen_n_in":null,"score":{"opus":0.04667008905673253,"gpt":0.3028698307907383,"spread":0.2561997417340057,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001286429,0.0001354913,0.0002033491,0.00008199027,0.0002402982,0.00005736354,0.0002105202,0.0001208985,0.000002617773],"category_scores_gemma":[0.00006579387,0.0001112905,0.00005226681,0.00006244177,0.0002536623,0.00000408288,0.000128776,0.0001155211,4.599107e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002379441,"about_ca_system_score_gemma":0.00004245259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006559082,"about_ca_topic_score_gemma":0.0002662522,"domain_scores_codex":[0.9985117,0.0002186751,0.0003059996,0.0003759284,0.0001700582,0.0004176004],"domain_scores_gemma":[0.9992231,0.00007354167,0.0000635192,0.0003883245,0.0001688058,0.00008268622],"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":[0.00004586786,0.00003566065,0.00712957,0.0001077524,0.00004070914,0.000002513706,0.0001619877,0.000003900017,0.9903474,0.0004441656,0.00005497199,0.001625469],"study_design_scores_gemma":[0.004273904,0.001287114,0.07568573,0.00006541291,0.00003911861,0.00004110257,0.00205036,0.0002035904,0.8861316,0.006494366,0.02313449,0.0005931507],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9903456,0.008122992,0.0005580208,0.0002403658,0.00003283071,0.0005613629,0.00005800607,0.00000292072,0.00007793282],"genre_scores_gemma":[0.9948733,0.003803268,0.0004849856,0.00002038116,0.00005676913,0.00006836902,0.00004896766,0.00002566246,0.00061832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1042158,"threshold_uncertainty_score":0.4538295,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098264076","doi":"10.1101/gr.116301.110","title":"A genome-wide perspective on the evolutionary history of enigmatic wolf-like canids","year":2011,"lang":"en","type":"article","venue":"Genome Research","topic":"Genetic diversity and population structure","field":"Biochemistry, Genetics and Molecular Biology","cited_by":348,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"EuroNatur Stiftung; National Human Genome Research Institute; Tel Aviv University; Fundacja na rzecz Nauki Polskiej; Searle Scholars Program; National Institutes of Health; National Science Foundation","keywords":"Biology; Evolutionary biology; Genotyping; Gray wolf; Haplotype; Population; Canis; Demographic history; Endangered species; Genetics; Allele; Genetic variation; Genotype; Ecology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.07296253122079208,"gpt":0.2897574074935526,"spread":0.2167948762727605,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004490083,0.00009542853,0.0001004719,0.0001130712,0.0001278411,0.000004956369,0.0003892933,0.0001086157,0.0009284525],"category_scores_gemma":[0.0001310498,0.00007618326,0.00007842048,0.0001321094,0.0003171859,0.000002401243,0.0001969572,0.0002020138,0.00007718113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002582901,"about_ca_system_score_gemma":0.0003449601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003042225,"about_ca_topic_score_gemma":0.00003790716,"domain_scores_codex":[0.9987367,0.0002403156,0.0001314215,0.0002609626,0.0003631116,0.0002675058],"domain_scores_gemma":[0.9990168,0.00004028107,0.00004881604,0.0004577267,0.0003591858,0.00007721986],"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":[0.001786524,0.0007209314,0.03558872,0.0002441382,0.0009983049,0.00005273115,0.0508001,0.000478898,0.8060637,0.03000692,0.0725456,0.0007134809],"study_design_scores_gemma":[0.0006247772,0.00114131,0.6102147,0.00001775399,0.00003214447,0.00001774174,0.008868704,0.00002146101,0.005442436,0.005394889,0.3678575,0.0003666485],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9207311,0.003617089,0.0001142849,0.000307352,0.0001609208,0.0003725463,0.00003575274,0.000007137223,0.07465381],"genre_scores_gemma":[0.9892304,0.0001363293,0.0002934612,0.0001419272,0.00008283641,0.00001421055,0.00003073322,0.00001135326,0.01005873],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8006212,"threshold_uncertainty_score":0.9999849,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2165913026","doi":"10.1101/gr.086082.108","title":"Newly introduced genomic prophage islands are critical determinants of in vivo competitiveness in the Liverpool Epidemic Strain of <i>Pseudomonas aeruginosa</i>","year":2008,"lang":"en","type":"article","venue":"Genome Research","topic":"Cystic Fibrosis Research Advances","field":"Medicine","cited_by":340,"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; Université Laval; Simon Fraser University","funders":"Canadian Institutes of Health Research; Cystic Fibrosis Trust; Michael Smith Health Research BC; Wellcome Trust","keywords":"Prophage; Biology; Genetics; Genome; Genomic island; Gene; Pseudomonas aeruginosa; Strain (injury); Whole genome sequencing; Bacteriophage; Microbiology; Bacteria; Escherichia coli","retraction":null,"screen_n_in":null,"score":{"opus":0.06793628400722844,"gpt":0.3851347371039215,"spread":0.3171984530966931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003959897,0.0001965374,0.0008117741,0.0008063677,0.0001037534,0.00001239189,0.0006550123,0.0001198047,0.0002634294],"category_scores_gemma":[0.003719899,0.0001481289,0.0001064399,0.001261807,0.002184886,0.0001146888,0.0002658313,0.0009790525,0.00002472735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002603413,"about_ca_system_score_gemma":0.0007540431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000351921,"about_ca_topic_score_gemma":0.000264571,"domain_scores_codex":[0.9950327,0.001199654,0.0008043853,0.0005180174,0.001449093,0.0009961145],"domain_scores_gemma":[0.9958245,0.002707296,0.000102883,0.0006931528,0.0004944346,0.0001777856],"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":[0.001287392,0.0006701516,0.2411483,0.001244489,0.00001747632,0.001412255,0.002570958,0.00003713716,0.7501652,0.0002165063,0.00005362671,0.001176573],"study_design_scores_gemma":[0.003062363,0.00134314,0.9457663,0.0007304896,0.00001102774,0.0003684487,0.002926702,0.0005468949,0.04432122,0.0003660427,0.0003676376,0.0001896958],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9954553,0.001594658,0.00007178156,0.0006364528,0.00003030864,0.001359375,0.0001892013,0.000008600291,0.0006542746],"genre_scores_gemma":[0.9979797,0.0006932043,0.0008657256,0.00003319663,0.0001248015,0.0001176783,0.00001140901,0.00002515226,0.0001491194],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7058439,"threshold_uncertainty_score":0.8050303,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1994624068","doi":"10.1101/gr.093955.109","title":"Quantitative phenotyping via deep barcode sequencing","year":2009,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":332,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Human Genome Research Institute; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Biology; Barcode; Deep sequencing; Computational biology; DNA sequencing; Genomics; Cancer genome sequencing; Genome; Personal genomics; Multiplex; Exome sequencing; Whole genome sequencing; Genetics; Massive parallel sequencing; Gene; Computer science; Mutation","retraction":null,"screen_n_in":null,"score":{"opus":0.07971096724446586,"gpt":0.3630725983264532,"spread":0.2833616310819873,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006338672,0.0001311832,0.0001404682,0.0001013827,0.0003128292,0.00003845188,0.0002886375,0.00008827104,0.00002910192],"category_scores_gemma":[0.0001161992,0.0001281063,0.00006687371,0.0002031403,0.0001208265,7.490432e-7,0.000167392,0.0001802764,0.00005595728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005816387,"about_ca_system_score_gemma":0.0001097794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003639116,"about_ca_topic_score_gemma":0.00003716417,"domain_scores_codex":[0.998462,0.0001411649,0.0001732712,0.0004064646,0.0002439243,0.000573186],"domain_scores_gemma":[0.9992187,0.00003430083,0.00003112675,0.0003511049,0.0002537251,0.0001110495],"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":[0.00005472895,0.00001948366,0.0001196797,0.000007822432,0.00003980874,0.000005071046,0.0003499513,0.0004383285,0.9908158,0.0007183533,0.00007042772,0.007360609],"study_design_scores_gemma":[0.00327877,0.00893937,0.0968341,0.00008593466,0.00007338383,0.0001342002,0.008062305,0.0102222,0.6311507,0.05141577,0.187047,0.002756209],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9761204,0.007942749,0.006588896,0.000389909,0.00006010348,0.0002651417,0.00001430796,0.00000465841,0.00861388],"genre_scores_gemma":[0.9936851,0.000733578,0.004777557,0.0001628185,0.0002378969,0.00001571256,0.00002519873,0.00001761325,0.000344543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.359665,"threshold_uncertainty_score":0.5224025,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1992680333","doi":"10.1101/gr.5322306","title":"Phylogenetic analyses of cyanobacterial genomes: Quantification of horizontal gene transfer events","year":2006,"lang":"en","type":"article","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":331,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"National Aeronautics and Space Administration; National Science Foundation","keywords":"Horizontal gene transfer; Biology; Phylogenetic tree; Phylum; Phylogenetics; Genome; Gene; Cyanobacteria; Evolutionary biology; Genetics; Monophyly; Phylogenetic network; Clade; Bacteria","retraction":null,"screen_n_in":null,"score":{"opus":0.0779731620853741,"gpt":0.3579743710909025,"spread":0.2800012090055284,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005425578,0.0001501442,0.0002703673,0.0001751817,0.00009322339,0.000009049766,0.0003305814,0.0001234007,0.0000362768],"category_scores_gemma":[0.00002212148,0.0001435757,0.0001507968,0.0002706644,0.0002271882,7.204684e-7,0.0001250995,0.0000760023,0.00000590574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002037136,"about_ca_system_score_gemma":0.0001290265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003217968,"about_ca_topic_score_gemma":0.00007090713,"domain_scores_codex":[0.9982761,0.0001709966,0.0004502264,0.0003841064,0.0003493938,0.0003692051],"domain_scores_gemma":[0.9989905,0.00002466225,0.00006821534,0.0004709336,0.0003905355,0.00005520436],"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":[0.0001440482,0.0001519239,0.006316829,0.00004999415,0.0001306837,7.059946e-7,0.00004628357,0.0002499059,0.992259,0.00006793533,0.00001561167,0.0005671225],"study_design_scores_gemma":[0.0004198704,0.0004743313,0.1309211,0.000004529907,0.00002517996,0.000001848437,0.00005762514,0.000007322653,0.8655381,0.0001826172,0.002245212,0.0001222199],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931613,0.005074679,0.0006647115,0.00002189809,0.00007604242,0.000309674,0.0002777707,0.000001337965,0.000412652],"genre_scores_gemma":[0.9974314,0.001380373,0.0004900905,0.000002658823,0.0002964209,0.0000301034,0.00022939,0.00002496451,0.0001145739],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1267209,"threshold_uncertainty_score":0.5854846,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2041726559","doi":"10.1101/gr.6902","title":"Discovery of Regulatory Elements by a Computational Method for Phylogenetic Footprinting","year":2002,"lang":"en","type":"letter","venue":"Genome Research","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":330,"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; Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Phylogenetic tree; Biology; Footprinting; Phylogenetic network; Computational biology; Phylogenetics; Conserved sequence; Computational phylogenetics; Function (biology); Evolutionary biology; Set (abstract data type); Genetics; Gene; Computer science; Base sequence","retraction":null,"screen_n_in":null,"score":{"opus":0.05476859112072156,"gpt":0.3510958603509624,"spread":0.2963272692302408,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001105563,0.0002803181,0.0003991238,0.0001772213,0.0001880497,0.00004817449,0.0005500405,0.0004744871,0.00001460791],"category_scores_gemma":[0.00008415619,0.0002902482,0.0002420302,0.0001353219,0.0002072874,5.507491e-7,0.0004834799,0.0004673,0.000003624557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004840941,"about_ca_system_score_gemma":0.0001509332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002314999,"about_ca_topic_score_gemma":0.000001853295,"domain_scores_codex":[0.9971629,0.0002814665,0.0005085917,0.0007539847,0.000576929,0.0007160716],"domain_scores_gemma":[0.9985121,0.0001928222,0.0002107702,0.0005534847,0.0004847551,0.00004604573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003724158,0.0000540532,0.0003522471,0.0004061644,0.0005200924,0.000003038131,0.0000425373,0.0002225227,0.6582977,0.00002548618,0.3380091,0.002029845],"study_design_scores_gemma":[0.0007269321,0.0006102081,0.001658045,0.00003053416,0.00004983385,0.000007182057,0.00005100608,0.0001780865,0.01788467,0.001263942,0.9770995,0.000440098],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7373409,0.07734009,0.07306293,0.08583812,0.001106166,0.009023529,0.01103201,0.00001872177,0.005237564],"genre_scores_gemma":[0.5647157,0.005572003,0.2668275,0.06957043,0.01815038,0.002968918,0.01191951,0.001116062,0.05915946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.640413,"threshold_uncertainty_score":0.9999549,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124362171","doi":"10.1101/gr.086538.108","title":"A high-density SNP-based linkage map of the chicken genome reveals sequence features correlated with recombination rate","year":2008,"lang":"en","type":"article","venue":"Genome Research","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":326,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Vetenskapsrådet; Stiftelsen för Strategisk Forskning; Svenska Forskningsrådet Formas; U.S. Department of Agriculture","keywords":"Biology; Recombination; Genetics; Autosome; Genetic linkage; Single-nucleotide polymorphism; Linkage disequilibrium; Population; X chromosome; Gene; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.04339989654809318,"gpt":0.2916913681133052,"spread":0.248291471565212,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007755372,0.000155956,0.0001829855,0.00007810709,0.000331391,0.00001549294,0.0005186682,0.0002046947,0.00008668264],"category_scores_gemma":[0.000105907,0.0001109643,0.00006859601,0.0003027787,0.0005531843,0.000003646504,0.0001701106,0.0004102846,0.00005338955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003904027,"about_ca_system_score_gemma":0.0003819415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001154465,"about_ca_topic_score_gemma":0.00003226862,"domain_scores_codex":[0.9980612,0.0005034097,0.0002190399,0.0004101486,0.0004092392,0.0003969259],"domain_scores_gemma":[0.9986066,0.00005826278,0.0001070227,0.0006802416,0.0004490217,0.00009886124],"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":[0.0003954615,0.000151551,0.003642102,0.00009734253,0.00008868703,0.000007890122,0.0003025391,0.003490329,0.9899439,0.0007036855,0.0008877878,0.0002887553],"study_design_scores_gemma":[0.00102648,0.00100866,0.9051285,0.00003775174,0.00001638427,0.00003794207,0.00004838025,0.00001347763,0.08879301,0.001635968,0.002032512,0.000220889],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9964536,0.0005735513,0.001022858,0.0005794839,0.0001014128,0.0005719527,0.0000397475,0.000009821662,0.0006475393],"genre_scores_gemma":[0.9872006,0.00006095956,0.004165642,0.00009272484,0.0001049631,0.00002955597,0.0001430143,0.00002377454,0.008178832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9014865,"threshold_uncertainty_score":0.4524994,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136490136","doi":"10.1101/gr.1687304","title":"Development and Application of a Salmonid EST Database and cDNA Microarray: Data Mining and Interspecific Hybridization Characteristics","year":2004,"lang":"en","type":"article","venue":"Genome Research","topic":"Aquaculture disease management and microbiota","field":"Immunology and Microbiology","cited_by":325,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"BC Cancer Agency; Natural Sciences and Engineering Research Council of Canada; Genome British Columbia; Canada's Michael Smith Genome Sciences Centre; Genome Canada","keywords":"Biology; Expressed sequence tag; Complementary DNA; cDNA library; Salmo; Oncorhynchus; Rainbow trout; Genetics; Rapid amplification of cDNA ends; Microarray; Gene; Molecular biology; Gene expression; Fishery; Molecular cloning; Fish <Actinopterygii>","retraction":null,"screen_n_in":null,"score":{"opus":0.05942269214870017,"gpt":0.3175539583810691,"spread":0.2581312662323689,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005681998,0.0001008744,0.0001460044,0.0001555123,0.0002282534,0.00003638291,0.0001958078,0.00006143357,0.0000154271],"category_scores_gemma":[0.00004749675,0.00009466914,0.000006313657,0.0001300679,0.0003560963,0.0001055039,0.0007545056,0.0001198502,0.00002219003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000326896,"about_ca_system_score_gemma":0.00005715612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003883611,"about_ca_topic_score_gemma":0.00003552161,"domain_scores_codex":[0.9990653,0.00005827763,0.0002013559,0.0004044283,0.00004352941,0.0002270764],"domain_scores_gemma":[0.9994428,0.00003609533,0.00006312608,0.0003435615,0.00008047168,0.00003399632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008286269,0.00007366353,0.001044489,0.0001625296,0.00007491458,0.000004275379,0.002010722,1.091087e-7,0.9610601,0.000523744,0.000250569,0.03471199],"study_design_scores_gemma":[0.006413473,0.0003275588,0.174858,0.0004687201,0.0002007796,0.0002144176,0.01722217,0.00005580274,0.1337595,0.0001688618,0.665244,0.00106671],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9918961,0.004986748,0.002098282,0.0002102054,0.00002758013,0.0003809884,0.0002590716,0.0000139736,0.0001270619],"genre_scores_gemma":[0.991402,0.001005513,0.003653931,0.00001752756,0.00001906483,0.00001432203,0.003616669,0.00001199612,0.0002589849],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8273006,"threshold_uncertainty_score":0.3860495,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1988589573","doi":"10.1101/gr.3147604","title":"Extensive and breed-specific linkage disequilibrium in <i>Canis familiaris</i>","year":2004,"lang":"en","type":"article","venue":"Genome Research","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":320,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"National Human Genome Research Institute; National Institute of Mental Health; National Institutes of Health; National Cancer Institute; WALTHAM Foundation","keywords":"Biology; Linkage disequilibrium; Breed; Disequilibrium; Canis; Genetics; Evolutionary biology; Haplotype; Zoology; Allele; Ecology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03340082966364018,"gpt":0.3018683426752811,"spread":0.268467513011641,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004160357,0.0001407698,0.0001434268,0.0001066724,0.000105174,0.00004159031,0.0002691991,0.0001718066,0.00002950412],"category_scores_gemma":[0.00004062906,0.000138989,0.00003892891,0.000224552,0.0003379745,0.000003805755,0.0003239182,0.0003100318,0.00004731804],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003666027,"about_ca_system_score_gemma":0.0001429684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006784758,"about_ca_topic_score_gemma":0.00003993607,"domain_scores_codex":[0.9983844,0.0001052344,0.0001879196,0.0005179062,0.0002647096,0.000539823],"domain_scores_gemma":[0.9992352,0.00002535427,0.00002158219,0.0004263341,0.000125227,0.0001663463],"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":[0.0001886417,0.0001916365,0.00290916,0.0000666725,0.00003471828,0.00002657329,0.000723203,0.0008295249,0.9765432,0.01383364,0.0008109806,0.003841992],"study_design_scores_gemma":[0.002159347,0.001153437,0.8564071,0.00003915198,0.000005764821,0.00003954425,0.0005097928,0.000002372875,0.01660277,0.03423429,0.08838054,0.0004658764],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9836432,0.008791592,0.0007461703,0.0006514437,0.0001031846,0.0003574418,0.00002857555,0.000009488387,0.005668941],"genre_scores_gemma":[0.9940479,0.001088239,0.003104295,0.0001154166,0.0003225374,0.00003349663,0.00004547923,0.00002806847,0.001214527],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9599405,"threshold_uncertainty_score":0.5667806,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}