{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":105,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":105,"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":"aac46070376e","filters":{"venue":"Database"}},"results":[{"id":"W2156564520","doi":"10.1093/database/bar030","title":"Ensembl BioMarts: a hub for data retrieval across taxonomic space","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1542,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Bill and Melinda Gates Foundation; European Commission; Directorate for Biological Sciences; Ontario Institute for Cancer Research; Wellcome Trust","keywords":"Ensembl; Computer science; Genome; World Wide Web; Annotation; Data science; Biology; Genomics; Artificial intelligence; Gene; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.1077534063098806,"gpt":0.3091795235511951,"spread":0.2014261172413145,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000288807,0.0001517968,0.0001343577,0.0000158462,0.0001294623,0.00001797985,0.0005016865,0.00007011741,0.00001588642],"category_scores_gemma":[0.000147654,0.0001469264,0.00005149315,0.00004340569,0.00009095299,0.000002232052,0.0008648976,0.00003776995,0.00002087431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005917344,"about_ca_system_score_gemma":0.00004805752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001200417,"about_ca_topic_score_gemma":0.0001976974,"domain_scores_codex":[0.9989195,0.00001962052,0.000165403,0.0005309656,0.00005249586,0.0003120405],"domain_scores_gemma":[0.9984652,0.00001586844,0.00007315078,0.00131368,0.00005126559,0.00008083208],"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":[0.0005053582,0.00009294627,0.002053123,0.00003282346,0.0001463533,0.000004653548,0.0001309251,5.248579e-7,0.9447855,0.0001678618,0.05064204,0.001437884],"study_design_scores_gemma":[0.0009941044,0.0002491891,0.002193173,0.000008330561,0.00004651925,0.00001445615,0.0002265451,0.0001032588,0.3446783,0.00005429231,0.6510985,0.0003332114],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9781812,0.001778013,0.005075559,0.00008417237,0.0003741281,0.0003949381,0.01353697,0.000007126871,0.0005679348],"genre_scores_gemma":[0.9725448,0.0004321234,0.02064148,0.0002630748,0.0003826618,0.00002841123,0.005329119,0.00003482477,0.000343543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6004565,"threshold_uncertainty_score":0.5991483,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137417655","doi":"10.1093/database/bap024","title":"Phenol-Explorer: an online comprehensive database on polyphenol contents in foods","year":2010,"lang":"en","type":"article","venue":"Database","topic":"Phytochemicals and Antioxidant Activities","field":"Medicine","cited_by":1414,"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":"Institut National de la Recherche Agronomique; Danone","keywords":"Metabolome; Polyphenol; Food science; Database; Computer science; Biotechnology; Biology; Bioinformatics; Metabolomics; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.09133406312008532,"gpt":0.3308574217588724,"spread":0.2395233586387871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009090985,0.0002557921,0.0004031524,0.0001733149,0.00005701727,0.00002203635,0.0001976305,0.00008202272,0.0001959899],"category_scores_gemma":[0.0001613221,0.0002206013,0.00006425632,0.0001792589,0.000150684,0.0004359237,0.0001322353,0.0007260363,0.00006793081],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002553263,"about_ca_system_score_gemma":0.00005582771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002862522,"about_ca_topic_score_gemma":0.000291157,"domain_scores_codex":[0.9984638,0.00003909301,0.0002998858,0.0004890877,0.0003185309,0.0003895737],"domain_scores_gemma":[0.9984697,0.0001049772,0.00008087626,0.0009729449,0.00007838831,0.0002931485],"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":[0.0006155073,0.002301248,0.004256954,0.00008965431,0.00003006761,0.0002676139,0.0001559888,5.075842e-7,0.9867392,0.0005328149,0.001985474,0.003025036],"study_design_scores_gemma":[0.01638906,0.001610441,0.09103515,0.001449994,0.0001863364,0.0002672307,0.003486891,0.003589222,0.8413929,0.000246899,0.03900682,0.001339057],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9938189,0.0000872751,0.00002781036,0.0004559405,0.0002785271,0.000374193,0.004432708,0.0001250898,0.0003995415],"genre_scores_gemma":[0.9864857,0.00006804163,0.002556263,0.001953279,0.0004269728,0.00002609368,0.008375613,0.00004058964,0.00006749885],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1453462,"threshold_uncertainty_score":0.8995859,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100190412","doi":"10.1093/database/bat070","title":"Phenol-Explorer 3.0: a major update of the Phenol-Explorer database to incorporate data on the effects of food processing on polyphenol content","year":2013,"lang":"en","type":"article","venue":"Database","topic":"Phytochemicals and Antioxidant Activities","field":"Medicine","cited_by":868,"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":"Institut National Du Cancer; Danone","keywords":"Polyphenol; Database; Phenol; Food science; Computer science; Chemistry; Biochemistry; Organic chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.06410583990095763,"gpt":0.2677329195989637,"spread":0.2036270796980061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003488967,0.0003656272,0.0005551243,0.000122304,0.0001410331,0.00004166341,0.0009776376,0.00006011516,0.0001245425],"category_scores_gemma":[0.0009165209,0.0001938559,0.0001025881,0.0004299387,0.0002888057,0.000564674,0.0009962575,0.0003990591,0.0001019829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000039233,"about_ca_system_score_gemma":0.0001454742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001668389,"about_ca_topic_score_gemma":0.00001499909,"domain_scores_codex":[0.9975973,0.000127659,0.0005209012,0.0006243706,0.0006996056,0.000430133],"domain_scores_gemma":[0.9959297,0.0003613359,0.0004039798,0.002924325,0.0001850756,0.0001956333],"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":[0.000615549,0.001188245,0.0006057305,0.001103216,0.0001990421,0.00001439624,0.0006349387,0.000001062977,0.9653504,0.001499289,0.02475225,0.004035844],"study_design_scores_gemma":[0.002073611,0.0006745822,0.002308783,0.003565111,0.0002524078,0.000009569616,0.0009931119,0.0003987112,0.9878734,0.0002741488,0.001269435,0.0003071509],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9903519,0.0003020034,0.0002046178,0.003295232,0.0001896393,0.001964438,0.003387813,0.00005995465,0.000244378],"genre_scores_gemma":[0.9943049,0.00004940326,0.0006938269,0.003359681,0.0001912986,0.0002190962,0.001057479,0.00006032963,0.00006398006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02348282,"threshold_uncertainty_score":0.7905214,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118527670","doi":"10.1093/database/bar026","title":"International Cancer Genome Consortium Data Portal--a one-stop shop for cancer genomics data","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":672,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Computer science; Genome; Genomics; Interface (matter); Genome browser; Software; Computational biology; World Wide Web; Biology; Gene; Genetics; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.1220212605109674,"gpt":0.3372931504936901,"spread":0.2152718899827227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002585547,0.0001913667,0.0001741884,0.00004227145,0.0000810026,0.00004040848,0.001963382,0.00009486498,0.0006813174],"category_scores_gemma":[0.0001786579,0.0002113803,0.00004015465,0.00004694524,0.00009442149,0.00002968113,0.002240586,0.0000882864,0.00001308072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003819407,"about_ca_system_score_gemma":0.0004623342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001624192,"about_ca_topic_score_gemma":0.00416578,"domain_scores_codex":[0.9983488,0.00001295534,0.0003053554,0.0008954048,0.0001260118,0.0003114832],"domain_scores_gemma":[0.9968737,0.00002288356,0.0001588815,0.002668346,0.0001312808,0.0001448511],"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":[0.001204218,0.0007647421,0.01336149,0.00016433,0.001415941,0.00004611183,0.0002384963,0.0001314914,0.5993649,0.001463344,0.3627036,0.01914137],"study_design_scores_gemma":[0.0007927033,0.00004499093,0.001047136,0.0000144045,0.000142157,0.000006774563,0.000059062,0.001272851,0.01506033,0.00002242644,0.9811937,0.0003434847],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2437976,0.01215908,0.02451043,0.001019282,0.004071543,0.00130998,0.7091202,0.00004635748,0.003965491],"genre_scores_gemma":[0.3351246,0.06175594,0.04042679,0.004871588,0.006466711,0.0005162797,0.5490809,0.0002272381,0.001529985],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.61849,"threshold_uncertainty_score":0.8619838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1993679825","doi":"10.1093/database/bau061","title":"Finding needles in haystacks: linking scientific names, reference specimens and molecular data for Fungi","year":2014,"lang":"en","type":"article","venue":"Database","topic":"Plant Pathogens and Fungal Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":481,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Alberta Biodiversity Monitoring Institute","funders":"National Human Genome Research Institute; Agricultural Research Service; College of Pharmacy, University of Michigan; National Institutes of Health; National Brain Research Centre; University of Michigan; Ministry of Agriculture, Forestry and Fisheries; U.S. National Library of Medicine; University of Alberta; Beef Cattle Research Council; Université Catholique de Louvain","keywords":"RefSeq; Biology; Phylogenetic tree; Identification (biology); DNA sequencing; Cistron; Computational biology; Ribosomal DNA; Internal transcribed spacer; Information retrieval; Genome; Computer science; Genetics; DNA; Gene; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.04203084470135757,"gpt":0.282761934017969,"spread":0.2407310893166114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003979858,0.000113761,0.0001070852,0.00006386597,0.00009750931,0.00008497748,0.0002925392,0.0000547901,0.000005551115],"category_scores_gemma":[0.0002270173,0.0001113402,0.00001901715,0.00007218309,0.00006036094,0.0000142325,0.0003993524,0.00005349985,0.000004025414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004436502,"about_ca_system_score_gemma":0.00004018554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000104902,"about_ca_topic_score_gemma":0.00008456661,"domain_scores_codex":[0.9989679,0.00003683414,0.0001382446,0.00054063,0.00008740242,0.0002290324],"domain_scores_gemma":[0.9990433,0.00003130061,0.00004435194,0.000767777,0.00002820417,0.00008510663],"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":[0.00003892783,0.00003240379,0.002813286,0.00005786439,0.000009201136,0.000008951563,0.000009954709,0.000007082937,0.9926749,0.0005324586,0.002444192,0.001370785],"study_design_scores_gemma":[0.002679745,0.000373908,0.01295695,0.0005439476,0.0001462405,0.00005108587,0.0003358912,0.01536438,0.1649969,0.0004236148,0.8008494,0.00127794],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9545464,0.003408401,0.01020286,0.00003222854,0.0001381505,0.0002492114,0.03106469,0.00001232446,0.0003457606],"genre_scores_gemma":[0.9463183,0.0001529121,0.004536026,0.0001503211,0.00009348719,0.00001277759,0.04864261,0.00001463375,0.00007893569],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.827678,"threshold_uncertainty_score":0.4540323,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2807602500","doi":"10.1093/database/bay044","title":"CircR2Disease: a manually curated database for experimentally supported circular RNAs associated with various diseases","year":2018,"lang":"en","type":"article","venue":"Database","topic":"Circular RNAs in diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":248,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Database; Circular RNA; Mechanism (biology); Disease; Computational biology; Bioinformatics; Biology; Gene; microRNA; Medicine; Genetics; Pathology","retraction":null,"screen_n_in":null,"score":{"opus":0.01495526027209911,"gpt":0.2832629041751686,"spread":0.2683076439030695,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002050469,0.0004526373,0.0003186541,0.0001013692,0.0003194827,0.0001068292,0.0005870064,0.0001308799,0.0003018308],"category_scores_gemma":[0.0008246255,0.0004424157,0.0001849486,0.000270431,0.0004284086,0.00004410298,0.0003351453,0.00009893424,0.0000407552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007291872,"about_ca_system_score_gemma":0.0005290095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000547698,"about_ca_topic_score_gemma":0.0001168414,"domain_scores_codex":[0.9972718,0.0001379051,0.0003804579,0.001084352,0.0004362991,0.0006891898],"domain_scores_gemma":[0.9972011,0.00004819017,0.0002164674,0.001566108,0.0004241219,0.0005440057],"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":[0.00189546,0.002079661,0.01066139,0.0001479084,0.001103619,0.0003863567,0.00006351616,0.00001086945,0.9152968,0.0001877976,0.06760307,0.0005635393],"study_design_scores_gemma":[0.01958384,0.003447691,0.03794043,0.0005920319,0.002503189,0.0002170825,0.0006236264,0.001465072,0.7752742,0.0001582188,0.1542642,0.003930495],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9371914,0.002483832,0.01922327,0.00009080095,0.0003195855,0.001624617,0.03857033,0.0002018254,0.0002943329],"genre_scores_gemma":[0.9006192,0.00004959019,0.0008266128,0.0008870713,0.0004372718,0.0003483634,0.09648461,0.0001211501,0.0002261182],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1400227,"threshold_uncertainty_score":0.9998028,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2568859793","doi":"10.1093/database/baw160","title":"FirebrowseR: an R client to the Broad Institute’s Firehose Pipeline","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":224,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Alberta Children's Hospital; University of Calgary","funders":"","keywords":"Computer science; Workflow; Pipeline (software); Application programming interface; Web service; Software; Database; World Wide Web; Interface (matter); Software engineering; Task (project management); Service (business); Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.01408169806154593,"gpt":0.2552758913824826,"spread":0.2411941933209366,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002426885,0.0001220695,0.00007888664,0.0000177186,0.0001045653,0.00002536669,0.0003590561,0.00006058592,0.00005466482],"category_scores_gemma":[0.00005311024,0.00006648264,0.00004217533,0.00005792992,0.00005888888,0.00001221784,0.0002823525,0.00005164701,0.0002337969],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009444834,"about_ca_system_score_gemma":0.00004399308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005290318,"about_ca_topic_score_gemma":0.0005554553,"domain_scores_codex":[0.9992206,0.0000237475,0.000189414,0.0002345252,0.00009526633,0.0002364425],"domain_scores_gemma":[0.9988702,0.000006966324,0.00004551971,0.0008810028,0.00003781503,0.0001584944],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001830095,0.0001453532,0.0004836209,0.00001540918,0.00003605768,0.000006852755,0.000144777,0.0001218223,0.1173448,0.001122413,0.5762122,0.3041836],"study_design_scores_gemma":[0.000385342,0.0001194635,0.0003044,0.00001973001,0.000008502373,0.000009910288,0.00002315962,0.0003625128,0.009955897,0.00003139675,0.9886195,0.0001601758],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8492385,0.0007701184,0.1356202,0.007630552,0.001414745,0.0007418809,0.002247005,0.00004768862,0.002289318],"genre_scores_gemma":[0.9874388,0.0002759806,0.00228529,0.005237132,0.001056523,0.0000371203,0.001515444,0.00002093628,0.002132772],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4124073,"threshold_uncertainty_score":0.3005064,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158197251","doi":"10.1093/database/baq023","title":"iRefWeb: interactive analysis of consolidated protein interaction data and their supporting evidence","year":2010,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":223,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Computer science; Interface (matter); Interaction information; World Wide Web; Reliability (semiconductor); Database; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.02602835155197479,"gpt":0.3164998662923536,"spread":0.2904715147403788,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003897612,0.00009436159,0.0001456866,0.00006990107,0.00003566689,0.00002494971,0.0002467635,0.00005993276,0.00005184491],"category_scores_gemma":[0.0002498524,0.00007703217,0.00003300155,0.0001324735,0.00007430971,0.00003224406,0.0005075449,0.0001497224,0.000001918236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002483208,"about_ca_system_score_gemma":0.00003531151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007752089,"about_ca_topic_score_gemma":0.0004236044,"domain_scores_codex":[0.9993151,0.00002720011,0.0002556873,0.0002394674,0.00004588335,0.0001166156],"domain_scores_gemma":[0.9988373,0.00003509224,0.0002267707,0.0007832608,0.00006501495,0.00005254301],"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":[0.00009722054,0.00002852846,0.001057077,0.00002389272,0.0003505314,8.820716e-7,0.0001347354,0.000006259585,0.9877806,0.00003199555,0.0007364245,0.00975181],"study_design_scores_gemma":[0.0005880952,0.000207394,0.002572084,0.0001766706,0.0006304167,0.0000345085,0.001706487,0.1778972,0.7853457,0.00004848801,0.03029118,0.000501791],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9915993,0.00009073283,0.006512306,0.00005653869,0.00007876634,0.0001434752,0.001397114,0.00000486991,0.0001169493],"genre_scores_gemma":[0.9923065,0.00004469851,0.001491153,0.00006736784,0.00005016786,0.000005459839,0.006003526,0.000005992271,0.00002509832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2024349,"threshold_uncertainty_score":0.3141281,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3170771812","doi":"10.1093/database/baab069","title":"OBO Foundry in 2021: operationalizing open data principles to evaluate ontologies","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":206,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Human Genome Research Institute; National Institutes of Health","keywords":"Computer science; Operationalization; World Wide Web; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.2031218362382894,"gpt":0.4157198848331276,"spread":0.2125980485948382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006690712,0.0001161333,0.0001604376,0.00003171723,0.00007169529,0.0001066637,0.001071629,0.00008485681,0.0001700377],"category_scores_gemma":[0.002310896,0.0001055491,0.0000186242,0.0001487099,0.0000634168,0.00001678359,0.004450098,0.00009035323,0.00005500557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001550529,"about_ca_system_score_gemma":0.0003482744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002244967,"about_ca_topic_score_gemma":0.003848924,"domain_scores_codex":[0.9986271,0.0001331722,0.0002223211,0.00063499,0.0001505609,0.0002318976],"domain_scores_gemma":[0.998533,0.00004521611,0.00003358912,0.001235192,0.00006869196,0.00008438672],"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":[0.0003990593,0.0006435062,0.02600783,0.0001051295,0.0002052516,0.0006415655,0.0002883013,0.0003044052,0.6102062,0.002595247,0.1837941,0.1748095],"study_design_scores_gemma":[0.0007493924,0.00008473951,0.007018701,0.00007741098,0.00001425417,0.00003025051,0.0004721,0.0004641301,0.02760129,0.00005329312,0.9631705,0.0002639691],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.952533,0.009935922,0.01109766,0.01108793,0.001004742,0.0008698606,0.004395448,0.00005333234,0.009022096],"genre_scores_gemma":[0.5188601,0.002619842,0.3774148,0.008894127,0.001036079,0.0002951922,0.08226245,0.00007805302,0.008539435],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7793764,"threshold_uncertainty_score":0.5546728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105772474","doi":"10.1093/database/bas031","title":"Phenol-Explorer 2.0: a major update of the Phenol-Explorer database integrating data on polyphenol metabolism and pharmacokinetics in humans and experimental animals","year":2012,"lang":"en","type":"article","venue":"Database","topic":"Phytochemicals and Antioxidant Activities","field":"Medicine","cited_by":188,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"European Social Fund; Instituto de Salud Carlos III; Institut National Du Cancer; Ministerio de Ciencia e Innovación; Centro de Investigación Biomédica en Red-Fisiopatología de la Obesidad y Nutrición; University of Alberta; Danone","keywords":"Polyphenol; Database; Phenol; Chemistry; Computer science; Biochemistry; Organic chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.05155692238144675,"gpt":0.3239772984076218,"spread":0.2724203760261751,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004081042,0.0003127773,0.0004704384,0.0001267252,0.0000982405,0.00003094686,0.0003188393,0.00005279934,0.0001460253],"category_scores_gemma":[0.0001591538,0.0002160496,0.00004275628,0.0001976205,0.0003067986,0.0007693365,0.0009978936,0.0003818824,0.000006324103],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002459632,"about_ca_system_score_gemma":0.00003655885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000129047,"about_ca_topic_score_gemma":0.00001185343,"domain_scores_codex":[0.9982108,0.00009449489,0.0004179532,0.0004891462,0.0003460842,0.0004415206],"domain_scores_gemma":[0.9984257,0.0001042058,0.0001657419,0.001077606,0.00002965274,0.0001971424],"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":[0.0003650302,0.0007500732,0.008662005,0.0001639436,0.00008217464,0.00001294985,0.001960514,1.283221e-7,0.9836436,0.001475111,0.00213441,0.0007500756],"study_design_scores_gemma":[0.004128569,0.0000884757,0.01116414,0.0006691394,0.0003165622,0.00004263225,0.004978073,0.0005406815,0.9713572,0.00004108546,0.006263112,0.0004103004],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9885117,0.00674882,0.00003637431,0.0003526694,0.0001454717,0.0004755589,0.003439858,0.00003674432,0.0002527339],"genre_scores_gemma":[0.9952515,0.0004550591,0.002261896,0.000640584,0.000324789,0.00003935717,0.0009670921,0.00004500552,0.00001469548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01228636,"threshold_uncertainty_score":0.8810247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2149671003","doi":"10.1093/database/bar041","title":"BioMart Central Portal: an open database network for the biological community","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":170,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"Ontario Institute for Cancer Research; Cancer Research UK; Wellcome Trust","keywords":"Computer science; Variety (cybernetics); Interface (matter); Ontology; Database; Resource (disambiguation); World Wide Web; Biological database; Bioinformatics; Artificial intelligence; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.09830288862401737,"gpt":0.3035580759883937,"spread":0.2052551873643763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009854884,0.0001681365,0.0001408392,0.00001030659,0.000470678,0.00006331066,0.001267721,0.0001097535,0.0001092053],"category_scores_gemma":[0.00005483112,0.0001121131,0.00005869549,0.00006596072,0.0001609364,0.00002172148,0.001108546,0.0001819225,0.000009592775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004687102,"about_ca_system_score_gemma":0.00005594637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005726091,"about_ca_topic_score_gemma":0.0009073549,"domain_scores_codex":[0.998902,0.000126214,0.0002545411,0.000223374,0.00005775459,0.0004361783],"domain_scores_gemma":[0.9983127,0.00004431625,0.0001064548,0.0013318,0.00004301304,0.0001617025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002905216,0.001842152,0.01009913,0.0001078421,0.0006856819,0.00002614019,0.0009573734,0.0001315358,0.06198271,0.0221277,0.8644991,0.03463545],"study_design_scores_gemma":[0.002895704,0.002053855,0.01426986,0.00005358593,0.0001623881,0.00009160917,0.001457104,0.004875028,0.01414879,0.001841589,0.9570268,0.001123673],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7407761,0.002648358,0.2181892,0.0004092116,0.002314203,0.004971731,0.02169184,0.0001119281,0.008887442],"genre_scores_gemma":[0.9256312,0.0003892664,0.02946161,0.002920412,0.0008025867,0.0001500349,0.04047907,0.00003727518,0.0001285654],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1887275,"threshold_uncertainty_score":0.4571838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170283197","doi":"10.1093/database/bat026","title":"The PhosphoGRID Saccharomyces cerevisiae protein phosphorylation site database: version 2.0 update","year":2013,"lang":"en","type":"article","venue":"Database","topic":"Fungal and yeast genetics research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; Université de Montréal; Institute for Research in Immunology and Cancer; University of British Columbia","funders":"Biotechnology and Biological Sciences Research Council; Canadian Cancer Society Research Institute; Canadian Institutes of Health Research; National Center for Research Resources; Directorate for Biological Sciences; National Institutes of Health; Wellcome Trust","keywords":"Phosphorylation; Proteome; Saccharomyces cerevisiae; Computational biology; Protein phosphorylation; Protein function; Database; Function (biology); Biology; Yeast; Bioinformatics; Computer science; Biochemistry; Protein kinase A; Cell biology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.007943784022554383,"gpt":0.2427444477371843,"spread":0.23480066371463,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003375718,0.0001830062,0.000101873,0.00003101078,0.0003487591,0.0001451095,0.0004258184,0.00007656239,0.0005414903],"category_scores_gemma":[0.0001282727,0.0001303974,0.00006422082,0.0001491415,0.0001131458,0.00002490182,0.0005420178,0.0001698753,0.001444393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001459276,"about_ca_system_score_gemma":0.00007078159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002398471,"about_ca_topic_score_gemma":0.00005926962,"domain_scores_codex":[0.9985185,0.00009468122,0.0002094597,0.0004441995,0.000331191,0.0004020151],"domain_scores_gemma":[0.9986683,0.00002209999,0.00007590587,0.0009121492,0.0001585793,0.00016297],"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":[0.0001023587,0.00004094385,0.0007561758,0.00002722392,0.00002386094,0.000002907938,0.000007342405,0.000005363576,0.9049791,0.00008234546,0.08587816,0.008094228],"study_design_scores_gemma":[0.0003612568,0.00009056717,0.0008763454,0.00002595372,0.000007700457,0.000003773312,0.00003591394,0.0003513746,0.5870636,0.00002180039,0.4109929,0.0001687975],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9902554,0.005275484,0.0004623186,0.001089809,0.0001744118,0.0008586978,0.001307642,0.00002390822,0.0005522883],"genre_scores_gemma":[0.9780493,0.003306373,0.001863762,0.0003258501,0.0004042239,0.0002388534,0.01273244,0.0000464594,0.003032745],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3251147,"threshold_uncertainty_score":0.9993331,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2141158585","doi":"10.1093/database/bar020","title":"Curation of characterized glycoside hydrolases of Fungal origin","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Biofuel production and bioconversion","field":"Engineering","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Glycoside hydrolase; Enzyme; Ascomycota; Hemicellulose; Biology; Biochemistry; Cell wall; Glycoside; Cellulase; Gene; Database; Cellulose; Botany","retraction":null,"screen_n_in":null,"score":{"opus":0.03900584823951406,"gpt":0.2227837736201414,"spread":0.1837779253806274,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006492267,0.0000546125,0.00008415254,0.00005211325,0.000008792656,0.000001523292,0.00005377977,0.00002534372,0.0003625888],"category_scores_gemma":[0.00001135896,0.00004979451,0.00002337773,0.00007181754,0.00002388513,0.0002419427,0.00001488907,0.00004312945,0.0000260356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006013435,"about_ca_system_score_gemma":0.000006202351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005176746,"about_ca_topic_score_gemma":0.000001887989,"domain_scores_codex":[0.9996496,0.00001018167,0.0001424044,0.00007261933,0.00006377885,0.00006142964],"domain_scores_gemma":[0.9997326,0.000005578282,0.00003765729,0.0001764625,0.00002194126,0.0000258082],"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":[0.00007643335,0.00005065147,0.001043824,0.0002503692,0.00001486893,0.000002176644,0.0001176522,0.000003051183,0.9960369,0.0001572135,0.001205395,0.001041424],"study_design_scores_gemma":[0.0002770613,0.00002888026,0.001919561,0.00002233424,0.0000123484,0.000003798836,0.00002487033,0.001444914,0.9875134,0.000009500073,0.008677372,0.00006590839],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9973745,0.00007295652,0.001060273,0.00001268963,0.0003352089,0.00008104236,0.0003236834,0.00006497103,0.0006747078],"genre_scores_gemma":[0.9986104,0.00008650918,0.0009878,0.000009614292,0.00003984409,0.000002090329,0.0002257697,0.000006283657,0.00003170709],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008523489,"threshold_uncertainty_score":0.3970094,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138782665","doi":"10.1093/database/bap026","title":"PhosphoGRID: a database of experimentally verified in vivo protein phosphorylation sites from the budding yeast Saccharomyces cerevisiae","year":2010,"lang":"en","type":"article","venue":"Database","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":101,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lunenfeld-Tanenbaum Research Institute; University of British Columbia","funders":"Canadian Cancer Society Research Institute; Biotechnology and Biological Sciences Research Council; National Center for Research Resources; Directorate for Biological Sciences; National Institutes of Health; Scottish Funding Council","keywords":"Phosphorylation; Saccharomyces cerevisiae; Protein phosphorylation; Proteome; Biology; Proteomics; Phosphatase; Computational biology; Function (biology); Kinase; Biochemistry; Signal transduction; Yeast; Cell biology; Gene; Protein kinase A","retraction":null,"screen_n_in":null,"score":{"opus":0.01552481348131759,"gpt":0.2758113290470898,"spread":0.2602865155657723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001553542,0.0001767534,0.0001740209,0.00002889352,0.00009939379,0.00003352382,0.0004475064,0.00007506469,0.002083679],"category_scores_gemma":[0.00008401188,0.0001497582,0.00004834746,0.0001658678,0.00009557614,0.0002746721,0.0002244942,0.0003599275,0.00001411099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002782665,"about_ca_system_score_gemma":0.00003884786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001415277,"about_ca_topic_score_gemma":0.0002940149,"domain_scores_codex":[0.9989046,0.00001275053,0.0003403082,0.0003714373,0.0001788047,0.0001920599],"domain_scores_gemma":[0.9986346,0.00007973699,0.0002098529,0.0009812689,0.00003477831,0.00005977306],"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":[0.00005804515,0.0001126116,0.001828089,0.00003125828,0.000008416888,0.000002773557,0.0001452625,0.000001627171,0.9946938,0.00199275,0.0004973572,0.0006280494],"study_design_scores_gemma":[0.0003840124,0.000006630744,0.00008643069,0.0001534144,0.00001060651,0.000001421164,0.0003707992,0.0002858089,0.9892261,0.0002601233,0.009042222,0.0001724377],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895946,0.0002993815,0.001926237,0.0001023607,0.00002381452,0.0004545464,0.006825733,0.00008259439,0.0006907728],"genre_scores_gemma":[0.9186323,0.00007306309,0.07818242,0.00004621623,0.00009763709,0.0004582186,0.00242249,0.00002945582,0.00005825272],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07625619,"threshold_uncertainty_score":0.9988285,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2516150684","doi":"10.1093/database/baw119","title":"Overview of the interactive task in BioCreative V","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Biomedical and Engineering Education","field":"Engineering","cited_by":99,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer; Ontario Institute for Cancer Research","funders":"U.S. National Library of Medicine; National Human Genome Research Institute; National Institute of General Medical Sciences; European Molecular Biology Laboratory; U.S. Department of Energy; Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México; National Institutes of Health; National Science Foundation","keywords":"Computer science; Task (project management); Natural language processing; Information retrieval; World Wide Web; Artificial intelligence; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01775898622899843,"gpt":0.252505487475985,"spread":0.2347465012469866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000421639,0.00003837679,0.0000475663,0.00002870303,0.000003689389,0.000001167123,0.00007233275,0.00001436826,0.00007405499],"category_scores_gemma":[0.00004388728,0.00001956088,0.0000133893,0.0001278501,0.00002115052,0.00007140706,0.00002271405,0.0000401947,0.00001443923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003141204,"about_ca_system_score_gemma":0.000006520901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003384489,"about_ca_topic_score_gemma":0.00001114328,"domain_scores_codex":[0.9997714,0.000007811152,0.00007011682,0.00004558664,0.00004506041,0.00006008229],"domain_scores_gemma":[0.9997872,0.00004531367,0.000008468266,0.0001342663,0.00000650706,0.00001822128],"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":[0.00005294213,0.0004072326,0.01584092,0.002673287,0.0001885682,0.000009433461,0.003680715,0.0002848475,0.6460127,0.008158434,0.144757,0.1779339],"study_design_scores_gemma":[0.002445348,0.00005832695,0.3875935,0.00729149,0.00005763864,0.00001326999,0.0003933284,0.01634614,0.382071,0.0009528557,0.2019676,0.0008095521],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9780673,0.002000424,0.0131802,0.001375519,0.001632349,0.0002487519,0.001212617,0.0001243323,0.002158477],"genre_scores_gemma":[0.9996135,0.0001598833,0.0001172406,0.00001690492,0.00002339398,0.000008251683,0.00001418301,0.000004869881,0.0000417791],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3717526,"threshold_uncertainty_score":0.08108502,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099131261","doi":"10.1093/database/baq037","title":"The Biomolecular Interaction Network Database in PSI-MI 2.5","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":97,"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; National Institutes of Health; Ontario Genomics; Ontario Genomics Institute; Genome Canada","keywords":"Identifier; Computer science; Database; Download; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.01974043939788008,"gpt":0.2499452691828738,"spread":0.2302048297849937,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004352955,0.0001267134,0.00008030609,0.00002540845,0.0001203363,0.00002988883,0.0002847775,0.00007150271,0.00004427614],"category_scores_gemma":[0.00003947037,0.00009946756,0.00004768746,0.0001169039,0.00006869715,0.00001209123,0.0002813137,0.0001448108,0.00005405131],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009765919,"about_ca_system_score_gemma":0.00003495621,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001218891,"about_ca_topic_score_gemma":0.0005492129,"domain_scores_codex":[0.9990901,0.00005349186,0.0002507388,0.0002147518,0.00007884423,0.0003121174],"domain_scores_gemma":[0.9991025,0.00001499367,0.00008517496,0.0006995071,0.0000255044,0.00007237566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002291149,0.0007035779,0.01053588,0.0001472432,0.0003864869,0.0002293395,0.0008803477,0.0005147123,0.3040234,0.01714569,0.561444,0.1016981],"study_design_scores_gemma":[0.001469823,0.0002743512,0.001955673,0.0001089367,0.00004486248,0.00008261391,0.0004868225,0.004348795,0.05220541,0.0008796711,0.9374338,0.000709261],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7529288,0.01041369,0.1855454,0.0007768613,0.005309637,0.001812653,0.001347746,0.000104215,0.04176097],"genre_scores_gemma":[0.9895911,0.001082982,0.004851771,0.000860808,0.0004473777,0.00004289949,0.002890844,0.00002897269,0.0002032378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3759897,"threshold_uncertainty_score":0.4056169,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4225573257","doi":"10.1093/database/baac034","title":"GrainGenes: a data-rich repository for small grains genetics and genomics","year":2022,"lang":"en","type":"article","venue":"Database","topic":"Wheat and Barley Genetics and Pathology","field":"Agricultural and Biological Sciences","cited_by":96,"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","funders":"Agricultural Research Service","keywords":"Genome browser; Genome; Triticeae; Genomics; Biology; Interoperability; Metadata; World Wide Web; Genetics; Database; Computational biology; Computer science; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.06471702717790244,"gpt":0.244767272532867,"spread":0.1800502453549645,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002986402,0.00009101495,0.0001042656,0.000009093608,0.0005882284,0.00003581357,0.0003738509,0.000027307,0.00004123589],"category_scores_gemma":[0.00001602324,0.00004292878,0.0000246886,0.00009820853,0.000040667,0.00002576019,0.0006795677,0.00007339181,0.000001265774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008987208,"about_ca_system_score_gemma":0.00001291201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008064782,"about_ca_topic_score_gemma":0.0003588474,"domain_scores_codex":[0.9991627,0.00005913965,0.0001387555,0.0003660034,0.00007402974,0.0001994164],"domain_scores_gemma":[0.999584,0.000101299,0.00004660397,0.0001745153,0.00002134636,0.0000721954],"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":[0.00006433915,0.0001410469,0.004758934,0.00002021312,0.00002151872,0.0000345903,0.0001783313,0.00001362074,0.9239274,0.0003760316,0.01101262,0.05945136],"study_design_scores_gemma":[0.0003291249,0.0005845541,0.007478594,0.000002859727,0.00005797588,0.0001284062,0.0006565065,0.001777024,0.005096198,0.0004120592,0.9831524,0.0003243018],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898322,0.002048922,0.00005794088,0.0003953787,0.000226498,0.0002369483,0.007083368,0.00002106922,0.00009763089],"genre_scores_gemma":[0.9712386,0.0006987486,0.00566243,0.001267742,0.0008815651,0.0001428563,0.01951801,0.000004128713,0.0005859393],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9721398,"threshold_uncertainty_score":0.4524237,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135504399","doi":"10.1093/database/bas006","title":"Aptamer base: a collaborative knowledge base to describe aptamers and SELEX experiments","year":2012,"lang":"en","type":"article","venue":"Database","topic":"Advanced biosensing and bioanalysis techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Aptamer; Systematic evolution of ligands by exponential enrichment; Computer science; Knowledge base; Molecular recognition; SELEX Aptamer Technique; Computational biology; Nucleic acid; Resource (disambiguation); Chemistry; Biology; World Wide Web; RNA; Molecular biology; Biochemistry; Gene; Molecule","retraction":null,"screen_n_in":null,"score":{"opus":0.02383674109648314,"gpt":0.3238841180193217,"spread":0.3000473769228385,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002480564,0.0002036024,0.0001659957,0.00007540159,0.0001042471,0.00002255729,0.0001003777,0.00008007373,0.00001067996],"category_scores_gemma":[0.0001294597,0.0001795845,0.00004256613,0.0002505986,0.0001012341,0.00001772404,0.0002265104,0.0000686753,0.0000212768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002202264,"about_ca_system_score_gemma":0.0000437317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002087214,"about_ca_topic_score_gemma":0.00003143075,"domain_scores_codex":[0.9988965,0.00008707002,0.0001593173,0.000385627,0.0001001297,0.0003713805],"domain_scores_gemma":[0.9990664,0.00001302891,0.00005370182,0.0004337792,0.0001127078,0.0003204395],"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":[0.00008223674,0.0001644777,0.001150929,0.00001001427,0.00005256593,0.00000296808,0.0001906609,1.567062e-7,0.9726048,0.00004562903,0.02159064,0.004104887],"study_design_scores_gemma":[0.0002479804,0.0001173186,0.0001833307,0.00002012036,0.00003609883,0.000008520407,0.0006208204,0.00002245726,0.8673945,0.000001732804,0.131089,0.0002581053],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890319,0.002497864,0.005799453,0.0001825757,0.0001298422,0.0003928486,0.0009705689,0.00006927222,0.0009256385],"genre_scores_gemma":[0.9628462,0.0002067911,0.03469071,0.0007076293,0.0002027172,0.00003525877,0.0008663699,0.00002408148,0.000420199],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1094984,"threshold_uncertainty_score":0.7323241,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148200511","doi":"10.1093/database/bar038","title":"BioMart: a data federation framework for large collaborative projects","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Institute for Cancer Research","funders":"","keywords":"Computer science; Server; Annotation; Software; World Wide Web; Selection (genetic algorithm); Database; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.1032471517953839,"gpt":0.3467581119531795,"spread":0.2435109601577956,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001759806,0.00008609179,0.00006236635,0.0000275122,0.0001205199,0.0000251756,0.0002383772,0.00008185912,0.00004757688],"category_scores_gemma":[0.000231156,0.00007834758,0.00001712406,0.0001061426,0.00001708567,0.00001319942,0.0001669812,0.00003621355,0.00001261754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005231791,"about_ca_system_score_gemma":0.0001232789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000699918,"about_ca_topic_score_gemma":0.00006104558,"domain_scores_codex":[0.9992503,0.00003706058,0.000112425,0.0003891517,0.0000691452,0.0001419005],"domain_scores_gemma":[0.998913,0.000008340717,0.00007129523,0.0008572182,0.00009860484,0.00005152574],"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":[0.0005641891,0.0003454229,0.001171071,0.00005413126,0.00005997384,0.000001758324,0.0004223489,1.661213e-7,0.6662821,0.02030573,0.3078595,0.002933639],"study_design_scores_gemma":[0.000676476,0.0001603879,0.0006953979,0.00002531566,0.00002019889,0.000001722155,0.000562907,0.000252367,0.4353295,0.0003994834,0.5616824,0.0001938018],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02965349,0.0007940853,0.9570661,0.0002998192,0.0004965594,0.001094664,0.008869789,0.0000369419,0.001688565],"genre_scores_gemma":[0.8280147,0.0002016172,0.1293499,0.0008964777,0.0004730917,0.0003552296,0.040194,0.0000330793,0.0004819267],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8277162,"threshold_uncertainty_score":0.3194922,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2338762894","doi":"10.1093/database/baw007","title":"2P2Idb v2: update of a structural database dedicated to orthosteric modulation of protein–protein interactions","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Protein Structure and Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Nautical Research Society","funders":"Agence Nationale de la Recherche","keywords":"Protein Data Bank; Protein Data Bank (RCSB PDB); Database; Protein structure database; Protein–protein interaction; Planarity testing; Computer science; Protein structure; Protein ligand; Affinities; Interface (matter); Small molecule; Computational biology; Chemistry; Data mining; Information retrieval; Crystallography; Biology; Molecule; Stereochemistry; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.009674534010869559,"gpt":0.2678753414436307,"spread":0.2582008074327611,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001173763,0.0001598215,0.0001742809,0.00009704643,0.00003868962,0.000006601641,0.0002395643,0.00006620906,0.0000937282],"category_scores_gemma":[0.0002063495,0.0001179913,0.00005933509,0.0001730621,0.00008204631,0.00002798457,0.0003027164,0.00006218097,0.00001066914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001380318,"about_ca_system_score_gemma":0.00007148262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000107564,"about_ca_topic_score_gemma":0.0001144945,"domain_scores_codex":[0.9988897,0.00005931171,0.0003473546,0.0003450525,0.0001665242,0.0001919868],"domain_scores_gemma":[0.9987378,0.000007860026,0.0002103983,0.0007841521,0.0001494717,0.0001103895],"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":[0.0002710163,0.00002390658,0.0006576778,0.00005061478,0.00003435437,0.00000242385,0.00001123922,0.00001022139,0.9905009,0.0003407265,0.0001736621,0.007923267],"study_design_scores_gemma":[0.000680785,0.0001776903,0.003010899,0.0001678215,0.00002214214,0.00001284969,0.00001166323,0.00020988,0.9899404,0.0001794424,0.005373592,0.0002128508],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9305257,0.00007192743,0.06478913,0.0001778815,0.00007571129,0.0005387596,0.003768292,0.00001261325,0.00003996945],"genre_scores_gemma":[0.9851537,0.000008966917,0.01168992,0.00007238166,0.0000784533,0.00005187772,0.002786489,0.00002003787,0.0001381798],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05462798,"threshold_uncertainty_score":0.4811544,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166240318","doi":"10.1093/database/bas056","title":"An overview of the BioCreative 2012 Workshop Track III: interactive text mining task","year":2013,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Research in Immunology and Cancer","funders":"U.S. National Library of Medicine; National Human Genome Research Institute","keywords":"Computer science; Data curation; Annotation; Task (project management); Usability; Information retrieval; Data science; Biomedical text mining; Set (abstract data type); World Wide Web; Text mining; Natural language processing; Artificial intelligence; Human–computer interaction; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0459006993030045,"gpt":0.3375506222957032,"spread":0.2916499229926987,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001280818,0.0001237238,0.0001438989,0.00002260349,0.00005640617,0.00001630875,0.0003333971,0.0001008309,0.0002320439],"category_scores_gemma":[0.0002182563,0.00007925399,0.00006836761,0.0001093494,0.0002491907,0.00001590174,0.0001905573,0.0001068915,0.00002151005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006217421,"about_ca_system_score_gemma":0.00004009921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001160608,"about_ca_topic_score_gemma":0.00006430574,"domain_scores_codex":[0.999168,0.0001089019,0.0001752904,0.000261946,0.0001055005,0.0001803259],"domain_scores_gemma":[0.9991208,0.00005212902,0.0001134501,0.0005686774,0.00006694943,0.00007802359],"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":[0.0001362858,0.0003728547,0.002315727,0.00005696046,0.000163143,0.00000351959,0.0011281,0.000004367678,0.7473103,0.0001110644,0.1205566,0.1278411],"study_design_scores_gemma":[0.002349389,0.0008894436,0.04297654,0.0007069174,0.0001634033,0.00004759093,0.01489273,0.0005639925,0.6075033,0.0001478495,0.3288307,0.0009281509],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9933136,0.003959665,0.0008079797,0.0004935715,0.0001943631,0.0002091119,0.0003532264,0.0000154635,0.0006530971],"genre_scores_gemma":[0.9957055,0.0002697974,0.002372187,0.0004300658,0.0001128519,0.0000300607,0.0004535195,0.00001190818,0.000614137],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2082741,"threshold_uncertainty_score":0.3231884,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2914171828","doi":"10.1093/database/bay147","title":"Overview of the BioCreative VI Precision Medicine Track: mining protein interactions and mutations for precision medicine","year":2018,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Cancer Institute; National Institutes of Health","keywords":"Computer science; Task (project management); Precision medicine; Triage; F1 score; Relationship extraction; Precision and recall; Annotation; Information extraction; Named-entity recognition; Information retrieval; Relation (database); Personalized medicine; Natural language processing; Data science; Data mining; Artificial intelligence; Bioinformatics; Medicine; Genetics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.07326093043933397,"gpt":0.3871233921750868,"spread":0.3138624617357528,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003656371,0.0001032391,0.0001576,0.00004566834,0.0001360428,0.000003853531,0.0001541912,0.0000639827,0.00006449738],"category_scores_gemma":[0.002363009,0.00005861583,0.00003309932,0.0001321446,0.0007471367,0.000006263047,0.0001301984,0.00005714258,0.000001126951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005825013,"about_ca_system_score_gemma":0.00003371853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005818109,"about_ca_topic_score_gemma":0.0001100693,"domain_scores_codex":[0.9991817,0.00007478458,0.0002476328,0.0002522478,0.0001287034,0.0001149197],"domain_scores_gemma":[0.9991452,0.0001801872,0.0001377969,0.0003345426,0.0001473141,0.00005502225],"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":[0.0002943175,0.00008085088,0.0003578714,0.0001059335,0.00006258376,5.833111e-7,0.0009361195,3.228634e-7,0.8125358,0.0002522801,0.02877603,0.1565973],"study_design_scores_gemma":[0.003073554,0.003237747,0.008418423,0.002766217,0.0002039296,0.00004004377,0.002552429,0.0005294118,0.4916208,0.001054236,0.4862135,0.0002897705],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9582034,0.003882903,0.03115817,0.004018608,0.0004341729,0.0008917603,0.0006820555,0.000019626,0.0007093024],"genre_scores_gemma":[0.9872432,0.000271616,0.0102333,0.0002433686,0.0004900059,0.00008642489,0.0006876171,0.00001397107,0.0007305174],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4574375,"threshold_uncertainty_score":0.2828913,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1967204795","doi":"10.1093/database/bar044","title":"Tripal: a construction toolkit for online genome databases","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Agriculture and Agri-Food Canada; Saskatchewan Pulse Growers; Agricultural Research Service; Clemson University; U.S. Department of Agriculture; National Science Foundation","keywords":"Computer science; World Wide Web; Python (programming language); Database; Biological database; User interface; Application programming interface; Bioinformatics; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.0671172462474224,"gpt":0.2781780268173692,"spread":0.2110607805699468,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009675841,0.0001267051,0.0001160534,0.00003026513,0.00008177153,0.000006495801,0.0001385998,0.00003576727,0.00004034888],"category_scores_gemma":[0.00007656275,0.0001212736,0.00006210607,0.00004096454,0.00008054145,0.000001550168,0.0001519255,0.0000343675,0.000006916967],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004809916,"about_ca_system_score_gemma":0.00004005696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006711941,"about_ca_topic_score_gemma":0.0001210117,"domain_scores_codex":[0.9992604,0.00001619321,0.0001627242,0.0003159421,0.00004886524,0.0001959282],"domain_scores_gemma":[0.9993684,0.00001032769,0.00005997503,0.0004322654,0.00006592324,0.00006308889],"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":[0.0003580237,0.0002166076,0.003203039,0.00004821612,0.0001558087,0.000003904194,0.00007764492,0.000003225953,0.9832863,0.001343854,0.003973529,0.007329875],"study_design_scores_gemma":[0.001623194,0.0004208513,0.01674723,0.00001145118,0.0001045337,0.00004281349,0.0003273308,0.00003825003,0.1227503,0.000150696,0.8573297,0.0004536794],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9753979,0.001376412,0.009635872,0.00003362748,0.0002963826,0.0003344896,0.01246164,0.000007851872,0.0004558023],"genre_scores_gemma":[0.7749609,0.001501118,0.2033603,0.000673816,0.0008962692,0.0001347119,0.01803891,0.00005457846,0.0003794544],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8605359,"threshold_uncertainty_score":0.4945395,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2051020903","doi":"10.1093/database/bat087","title":"DBM-DB: the diamondback moth genome database","year":2014,"lang":"en","type":"article","venue":"Database","topic":"Insect Resistance and Genetics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":69,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ministry of Agriculture; University of British Columbia","funders":"National Natural Science Foundation of China; Yuhan","keywords":"Diamondback moth; dBm; Genome; Annotation; Gene Annotation; Plutella; Genomics; Biology; Computer science; Database; Computational biology; Gene; Bioinformatics; Genetics; Larva; Ecology","retraction":null,"screen_n_in":null,"score":{"opus":0.007791138652176461,"gpt":0.229161108559944,"spread":0.2213699699077676,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003234151,0.0001708801,0.0001110883,0.00002357539,0.0001628946,0.0000370368,0.0004399076,0.00006830609,0.00007955054],"category_scores_gemma":[0.0001080168,0.0001252428,0.00006715198,0.00008840384,0.000115751,0.000005789988,0.0002715947,0.0001170091,0.000171076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006834789,"about_ca_system_score_gemma":0.00004614941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004017022,"about_ca_topic_score_gemma":0.0002106723,"domain_scores_codex":[0.9988854,0.00009028916,0.0001676058,0.0003743647,0.0001617493,0.0003205685],"domain_scores_gemma":[0.9984264,0.00002199782,0.00006005412,0.001340559,0.0000527022,0.00009826758],"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":[0.00007028512,0.00006563541,0.0005767482,0.00003188321,0.0000364056,0.000006458584,0.00003479121,0.00003767074,0.9652584,0.0006375934,0.03206605,0.001178074],"study_design_scores_gemma":[0.0005055915,0.0001176434,0.001555511,0.00001097852,0.00003398505,0.00001290198,0.00004566653,0.000147889,0.2725094,0.00004876947,0.7247229,0.0002887832],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9726033,0.00258833,0.0157102,0.0005177639,0.0003460633,0.0003541387,0.002172473,0.00003230248,0.005675392],"genre_scores_gemma":[0.9844607,0.0008116484,0.002130604,0.002820827,0.0009988627,0.00003516836,0.006999266,0.00004248199,0.001700492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.692749,"threshold_uncertainty_score":0.5107253,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135548107","doi":"10.1093/database/baq026","title":"Literature curation of protein interactions: measuring agreement across major public databases","year":2010,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Hospital for Sick Children","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Data curation; Database; Focus (optics); Organism; Computer science; Data science; Information retrieval; Biology; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.02698590957156888,"gpt":0.2828197224518299,"spread":0.255833812880261,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002951734,0.0001139041,0.00008985797,0.00003236451,0.00009085584,0.0000596073,0.000173856,0.00005561689,0.00006554498],"category_scores_gemma":[0.0001182935,0.0001020928,0.00004729967,0.00008962597,0.00005006381,0.00004861001,0.0002195595,0.0001935791,0.00001060169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005180614,"about_ca_system_score_gemma":0.00004193794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002466791,"about_ca_topic_score_gemma":0.000511482,"domain_scores_codex":[0.999232,0.00002094902,0.0002533713,0.0001908924,0.0001133417,0.0001894739],"domain_scores_gemma":[0.9990609,0.000006410532,0.0001385318,0.0005956728,0.0001269194,0.00007161946],"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":[0.00004461228,0.00008660779,0.0003313409,0.00008210087,0.00003726696,0.00000153194,0.00009549277,0.000002886841,0.9863319,0.001220483,0.00240668,0.009359049],"study_design_scores_gemma":[0.0008673307,0.00009055121,0.0004960045,0.0001697744,0.00001885482,0.00004142126,0.0001908965,0.0006927589,0.5784946,0.0001025299,0.4184888,0.0003464779],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9724824,0.0005814368,0.02264842,0.0002478485,0.0004484126,0.0004122392,0.002625363,0.00001254921,0.000541363],"genre_scores_gemma":[0.9849272,0.00004725184,0.006364353,0.00009950921,0.0002969469,0.00004062285,0.007963139,0.00001069498,0.000250281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4160821,"threshold_uncertainty_score":0.4163225,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2952216057","doi":"10.1093/database/baw015","title":"Wikidata as a semantic framework for the Gene Wiki initiative","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Wikis in Education and Collaboration","field":"Social Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Institute of General Medical Sciences; National Institute on Drug Abuse; National Institutes of Health","keywords":"SPARQL; Computer science; UniProt; World Wide Web; Dissemination; Metadata; XML; Linked data; JSON; Open data; Semantic Web; Database; RDF; Gene; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.0685358047867713,"gpt":0.3994968071533139,"spread":0.3309610023665426,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005949555,0.00005709751,0.00005524728,0.00002504502,0.0005615337,0.00007309484,0.0002892366,0.00004245331,0.0006880834],"category_scores_gemma":[0.003237155,0.00003344345,0.00002232437,0.0002564564,0.0001794556,0.0003865162,0.00003972371,0.00004669681,0.0002783531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004814426,"about_ca_system_score_gemma":0.0004127556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003383933,"about_ca_topic_score_gemma":0.0009860838,"domain_scores_codex":[0.9992595,0.0001068299,0.0001011575,0.0001601939,0.0002033839,0.0001689072],"domain_scores_gemma":[0.9982049,0.001156774,0.00006692929,0.0003568928,0.0001492739,0.00006525252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003763434,0.00007408641,0.0005320892,0.000005448795,0.00002524274,0.000001092709,0.009130755,2.628549e-7,0.0004570755,0.8642065,0.1014223,0.02410751],"study_design_scores_gemma":[0.0001998962,0.00002055958,0.0005653776,0.00004340662,0.00002425125,3.999651e-7,0.008396095,0.00001179425,0.001250916,0.02909161,0.9602913,0.0001043487],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06543783,0.0007992699,0.6611092,0.2459976,0.00516521,0.002622753,0.004632004,0.0002558021,0.01398033],"genre_scores_gemma":[0.9762948,0.0006736611,0.0117284,0.006153515,0.002001645,0.0003270746,0.0002706269,0.00001728803,0.002533059],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9108569,"threshold_uncertainty_score":0.753403,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3130317325","doi":"10.1093/database/baab006","title":"Curation of over 10 000 transcriptomic studies to enable data reuse","year":2021,"lang":"en","type":"article","venue":"Database","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"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; Genome British Columbia; University of British Columbia","funders":"National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada","keywords":"Metadata; Computer science; Reuse; Software; Data curation; Gemma; World Wide Web; Database; Information retrieval; Data science; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.09921660307901177,"gpt":0.3764284461266624,"spread":0.2772118430476506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001140649,0.0000663417,0.00008453682,0.00002386572,0.00003092311,0.000008962059,0.0003796448,0.00003307928,0.0001824689],"category_scores_gemma":[0.000392777,0.00006288498,0.00001956812,0.0001031803,0.00001990054,0.00001382181,0.0004429398,0.00002740508,0.00001272355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006845168,"about_ca_system_score_gemma":0.00007598367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001496011,"about_ca_topic_score_gemma":0.00008402701,"domain_scores_codex":[0.9993147,0.00004085686,0.0001445322,0.0003195024,0.00009333382,0.00008705322],"domain_scores_gemma":[0.9977704,0.000005570218,0.00004173083,0.00203069,0.0001064096,0.00004523718],"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":[0.00003979097,0.00003198958,0.00008114253,0.00002146625,0.0000195308,0.000001020177,0.00004094569,0.000005071131,0.7144995,0.00004391541,0.2847947,0.0004209184],"study_design_scores_gemma":[0.000197736,0.00002184531,0.0002366851,0.00001769049,0.00001294342,0.000001166641,0.0001666822,0.00002525478,0.6092438,0.00002040737,0.3899991,0.00005664242],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9750338,0.008697136,0.007736288,0.002196505,0.0005575391,0.0002762487,0.004509044,0.00001923291,0.0009741718],"genre_scores_gemma":[0.9653775,0.002485586,0.007145513,0.0009998312,0.0002785509,0.00003651248,0.01885782,0.00002298452,0.004795699],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1052557,"threshold_uncertainty_score":0.2564375,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974274010","doi":"10.1093/database/bas025","title":"HAltORF: a database of predicted out-of-frame alternative open reading frames in human","year":2012,"lang":"en","type":"article","venue":"Database","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":59,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Université de Sherbrooke","funders":"Canadian Institutes of Health Research","keywords":"Open reading frame; Human proteome project; Human genome; Ribosome profiling; Biology; Frame (networking); Computational biology; Transcriptome; Computer science; Genome; Translation (biology); Genetics; Gene; Gene expression; Messenger RNA; Proteomics; Peptide sequence","retraction":null,"screen_n_in":null,"score":{"opus":0.04269381016478672,"gpt":0.3292702306601261,"spread":0.2865764204953393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006230026,0.0001409064,0.0002335616,0.00007286449,0.00003387043,0.0000119629,0.0005469742,0.00009156632,0.0001084925],"category_scores_gemma":[0.0003128558,0.000133962,0.0000433461,0.00008251787,0.00006913106,0.00003541064,0.0006340253,0.00009133796,0.000004794143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009488508,"about_ca_system_score_gemma":0.00003993554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000558025,"about_ca_topic_score_gemma":0.00006453781,"domain_scores_codex":[0.9988655,0.0001426238,0.0003224591,0.0002672884,0.0001484466,0.0002537089],"domain_scores_gemma":[0.9988942,0.00003260629,0.0002022706,0.0007206526,0.00005177111,0.00009857157],"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":[0.0001029202,0.0002091058,0.004911589,0.00006212565,0.00004085665,0.000003097085,0.0002318459,0.000001814031,0.9916642,0.001529006,0.0007426569,0.0005007688],"study_design_scores_gemma":[0.0005406591,0.0001258764,0.0005613024,0.0001853222,0.00001915671,0.000001919857,0.0001370436,0.00002060133,0.9917431,0.0001065777,0.006406749,0.0001516486],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.987973,0.0005059912,0.006486098,0.00002886794,0.0002464145,0.0005220056,0.002971785,0.000006909787,0.001258906],"genre_scores_gemma":[0.9894112,0.0001011255,0.00764019,0.00006795314,0.0001560177,0.00005115113,0.002416771,0.00002171401,0.0001338986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005664092,"threshold_uncertainty_score":0.546281,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1829370794","doi":"10.1093/database/bav059","title":"G4RNA: an RNA G-quadruplex database","year":2015,"lang":"it","type":"article","venue":"Database","topic":"DNA and Nucleic Acid Chemistry","field":"Biochemistry, Genetics and Molecular Biology","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; G-quadruplex; Information retrieval; Sequence (biology); Computational biology; Theoretical computer science; Data mining; Biology; DNA; Genetics","retraction":null,"screen_n_in":null,"score":{"opus":0.03413014463313407,"gpt":0.2888167434363996,"spread":0.2546865988032656,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006305733,0.0005615088,0.0003818956,0.0000594426,0.000154942,0.0001233028,0.000995697,0.000382597,0.0004992753],"category_scores_gemma":[0.0003996548,0.0005882237,0.0001473794,0.0001916284,0.0002899664,0.00006043258,0.001002433,0.0004015405,0.0005934869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005834089,"about_ca_system_score_gemma":0.0005222927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002186063,"about_ca_topic_score_gemma":0.00004531603,"domain_scores_codex":[0.996833,0.0001484054,0.0005070031,0.001226368,0.0004865836,0.0007987029],"domain_scores_gemma":[0.9954295,0.00001678754,0.000217195,0.002817133,0.0002314194,0.001287959],"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":[0.0003707084,0.0005986401,0.0004110734,0.0001091815,0.0001139864,0.0002295279,0.00009811432,0.000009491318,0.7809949,0.0001245967,0.2138777,0.003062064],"study_design_scores_gemma":[0.001838178,0.0003251613,0.00003927733,0.0000665264,0.0001309,0.00009338839,0.0006207696,0.0004972792,0.490465,0.00001936449,0.505164,0.0007401262],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9666015,0.004326929,0.001431515,0.0004820703,0.001157991,0.0003159889,0.01246546,0.0000765479,0.01314199],"genre_scores_gemma":[0.9279459,0.001103879,0.003914476,0.001463199,0.00285478,0.00002814784,0.05712194,0.0001433019,0.005424334],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2912863,"threshold_uncertainty_score":0.9996569,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170802261","doi":"10.1093/database/bar021","title":"A comprehensive manually curated reaction map of RANKL/RANK-signaling pathway","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Bone Metabolism and Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"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":"The Wellcome Trust DBT India Alliance; Council of Scientific and Industrial Research, India; Department of Biotechnology, Ministry of Science and Technology, India; Wellcome Trust","keywords":"RANKL; RANK Ligand; Osteoclast; NFAT; Activator (genetics); Cell biology; Biology; Signal transduction; Cancer research; PI3K/AKT/mTOR pathway; Transcription factor; Receptor; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.03295461600734513,"gpt":0.2515163771703015,"spread":0.2185617611629564,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007197999,0.0001164806,0.0001351665,0.00003602512,0.00003698732,0.000005232492,0.0001196617,0.00005815671,0.00008877012],"category_scores_gemma":[0.00002943641,0.0001088864,0.00006730233,0.00005164165,0.00006164423,0.000009701441,0.00008710247,0.00004775623,0.0000336401],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002127714,"about_ca_system_score_gemma":0.00005041573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001631799,"about_ca_topic_score_gemma":0.00001029358,"domain_scores_codex":[0.9992734,0.00006043244,0.0001883665,0.0002374296,0.00009668111,0.0001437115],"domain_scores_gemma":[0.9993054,0.000007576399,0.00009541407,0.0003901049,0.0001209877,0.00008056605],"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":[0.0003727911,0.0001421621,0.0003467313,0.00006012285,0.0000378875,0.0000138401,0.00005110962,0.000001110684,0.9952389,0.0001657189,0.002649459,0.000920145],"study_design_scores_gemma":[0.000826792,0.00008127477,0.003196866,0.00002238149,0.00005108307,0.000007915282,0.0001646374,0.000009333611,0.9512604,0.0000478968,0.04416977,0.0001616004],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9950188,0.00192094,0.0009969434,0.00001170568,0.0001748741,0.0001368083,0.001147148,0.00001646143,0.0005762705],"genre_scores_gemma":[0.9951239,0.0000951902,0.001301443,0.0001625258,0.0001036523,0.00001118816,0.003059879,0.00001507409,0.0001271039],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04397847,"threshold_uncertainty_score":0.4440258,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3036787676","doi":"10.1093/databa/baaa033","title":"FOBI: an ontology to represent food intake data and associate it with metabolomic data","year":2020,"lang":"en","type":"article","venue":"Database","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"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":"European Institute of Innovation and Technology","keywords":"Ontology; Computer science; Open Biomedical Ontologies; Visualization; Data science; Ontology-based data integration; Information retrieval; Annotation; Workflow; Identification (biology); Data mining; Suggested Upper Merged Ontology; Database; Semantic Web; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1022735384683664,"gpt":0.3213407420082993,"spread":0.2190672035399329,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003958357,0.0002099958,0.0003239022,0.00003795821,0.00009857445,0.00004687703,0.001162965,0.00006704699,0.00002860532],"category_scores_gemma":[0.0005814664,0.000176528,0.0000161013,0.0001445891,0.00007394573,0.00003126193,0.003966822,0.0001256717,0.00001171117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000520924,"about_ca_system_score_gemma":0.00006568592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001277676,"about_ca_topic_score_gemma":0.002622424,"domain_scores_codex":[0.9979591,0.00009780636,0.0002230629,0.001258028,0.0001450288,0.0003169859],"domain_scores_gemma":[0.9969077,0.00002095842,0.0000950929,0.002644937,0.00004920435,0.0002821452],"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":[0.001744111,0.0004206711,0.01765397,0.0001093781,0.002011594,0.0000843948,0.0004546897,0.00001142862,0.594026,0.001502753,0.3737832,0.008197825],"study_design_scores_gemma":[0.001343922,0.001301829,0.003592505,0.000008857483,0.0002497841,0.00002894487,0.0005265138,0.0005754513,0.02042421,0.00002310118,0.971431,0.0004939516],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9500591,0.003417616,0.007366362,0.01131202,0.0001556699,0.0005159094,0.02666619,0.00003504166,0.0004720532],"genre_scores_gemma":[0.936976,0.001433447,0.02056111,0.006987911,0.00052095,0.00002372426,0.03335211,0.0000474687,0.00009728417],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5976477,"threshold_uncertainty_score":0.7198603,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2626120835","doi":"10.1093/database/bax048","title":"PigVar: a database of pig variations and positive selection signatures","year":2017,"lang":"en","type":"article","venue":"Database","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":44,"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":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Selection (genetic algorithm); Database; Computer science; Information retrieval; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01137428249328636,"gpt":0.2650252092062056,"spread":0.2536509267129193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001015282,0.0000911182,0.00008244991,0.0000228283,0.0002081111,0.00002334465,0.0001652429,0.00006300759,0.00002623377],"category_scores_gemma":[0.0002057627,0.0000881305,0.00002295257,0.00001978087,0.0001177531,0.00001020978,0.0001760236,0.000068628,0.000002531035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000256578,"about_ca_system_score_gemma":0.00004628618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001554039,"about_ca_topic_score_gemma":0.00009155973,"domain_scores_codex":[0.9994366,0.00003379905,0.0001057572,0.0002408374,0.000071997,0.0001110695],"domain_scores_gemma":[0.9992756,0.00001879385,0.0001052541,0.0004781828,0.00006306529,0.00005905127],"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":[0.0001840058,0.0001868648,0.01146297,0.00005366204,0.0001172899,0.000001369978,0.0001114605,0.00005137086,0.944718,0.03347207,0.006948129,0.002692803],"study_design_scores_gemma":[0.001233961,0.0005162929,0.7444906,0.00006932097,0.0001267938,0.00002275682,0.00005018619,0.0001829299,0.245722,0.0009178823,0.006313624,0.0003537106],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9056377,0.0008853086,0.08555085,0.0001969992,0.0002328569,0.0003044822,0.005095296,0.00001184658,0.002084689],"genre_scores_gemma":[0.971545,0.00006144994,0.02648678,0.00007959647,0.0001467101,0.000008061464,0.001471456,0.000009288264,0.0001917058],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7330276,"threshold_uncertainty_score":0.3593858,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151991601","doi":"10.1093/database/bau095","title":"WholeCellSimDB: a hybrid relational/HDF database for whole-cell model predictions","year":2014,"lang":"en","type":"article","venue":"Database","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Prince Edward Island","funders":"National Center for Chronic Disease Prevention and Health Promotion; U.S. National Library of Medicine; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Computer science; Python (programming language); JSON; Metadata; JavaScript; Database; Interface (matter); Relational database; Graphical user interface; Interoperability; SQL; Relational database management system; Information retrieval; World Wide Web; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01507083620479464,"gpt":0.2365658045377128,"spread":0.2214949683329181,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003972223,0.0002163618,0.0001765928,0.0000833096,0.0002119932,0.00002561336,0.0002646087,0.00008331684,0.00002949412],"category_scores_gemma":[0.0001281163,0.0002291885,0.0001704854,0.000119604,0.00007209474,0.00001643071,0.0002036568,0.0001022293,0.00006531934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001805703,"about_ca_system_score_gemma":0.000105365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008758178,"about_ca_topic_score_gemma":0.00003247264,"domain_scores_codex":[0.9984834,0.00006639247,0.0002877405,0.0006294881,0.0002010912,0.0003319497],"domain_scores_gemma":[0.9983574,0.0000367283,0.0001182335,0.001160464,0.0001383056,0.0001888826],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001072368,0.0002578072,0.0006793439,0.00007515022,0.0001252297,0.000001789039,0.00001230831,0.1126664,0.522112,0.0007697673,0.3626854,0.0005075447],"study_design_scores_gemma":[0.00102448,0.00008485978,0.00005035761,0.00001517747,0.0001854304,0.000007597374,0.00001052638,0.5462779,0.06218841,0.0001498765,0.3896956,0.000309829],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1032562,0.0004930152,0.8879591,0.0002625621,0.0001369526,0.0003469672,0.006574514,0.00004290074,0.0009277683],"genre_scores_gemma":[0.8836184,0.000108494,0.0420424,0.000682688,0.0008318839,0.0001798821,0.06613497,0.00008151512,0.006319764],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8459167,"threshold_uncertainty_score":0.9346037,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3099269015","doi":"10.1093/database/baaa096","title":"The IMEx coronavirus interactome: an evolving map of <i>Coronaviridae</i> –host molecular interactions","year":2020,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Discovery Centre; University Health Network","funders":"H2020 European Research Council; National Institute of Diabetes and Digestive and Kidney Diseases; National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Cancer Institute; Wellcome Trust; National Human Genome Research Institute; National Institute of Mental Health; National Heart, Lung, and Blood Institute; National Eye Institute; National Institute on Aging; Associazione Italiana per la Ricerca sul Cancro; Fondation pour la Recherche Médicale; Canada Foundation for Innovation; European Molecular Biology Laboratory; Natural Sciences and Engineering Research Council of Canada; International Business Machines Corporation","keywords":"Interactome; Coronaviridae; Coronavirus disease 2019 (COVID-19); Coronavirus; Computational biology; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Pandemic; Proteomics; Biology; Computer science; Disease; Medicine; Genetics; Infectious disease (medical specialty); Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.02022750701950962,"gpt":0.2844711788815303,"spread":0.2642436718620207,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001445312,0.0001421167,0.0001196228,0.00001338736,0.0001129339,0.00005330573,0.0003835816,0.00005095851,0.00007338588],"category_scores_gemma":[0.00006031859,0.0001144762,0.0000795305,0.00005858818,0.00009297005,0.0000233262,0.000316086,0.0001709651,0.00004965748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009139587,"about_ca_system_score_gemma":0.00005008177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003860259,"about_ca_topic_score_gemma":0.00005903035,"domain_scores_codex":[0.9991077,0.00004622709,0.000305487,0.0002199396,0.0001118345,0.0002087722],"domain_scores_gemma":[0.9990566,0.00002208169,0.0001454863,0.0005423574,0.00008626406,0.0001471917],"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":[0.0001947782,0.0000666663,0.0003389109,0.00003884334,0.00009449694,0.000008506819,0.0001890473,0.0001007752,0.9661389,0.0004961604,0.02281827,0.009514639],"study_design_scores_gemma":[0.0009331286,0.0005246769,0.0007057665,0.00005612231,0.00007415585,0.00003333965,0.0008503874,0.01603919,0.1857553,0.00006954799,0.7944581,0.0005003125],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9147621,0.006153769,0.06708673,0.003626632,0.001356732,0.0008072538,0.002747261,0.00006304847,0.003396411],"genre_scores_gemma":[0.9953229,0.0001128339,0.001398961,0.001414397,0.0002021076,0.00001169692,0.001433619,0.00002168417,0.00008182812],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7803836,"threshold_uncertainty_score":0.4668205,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3177341850","doi":"10.1093/database/baab032","title":"MetamORF: a repository of unique short open reading frames identified by both experimental and computational approaches for gene and metagene analyses","year":2021,"lang":"en","type":"article","venue":"Database","topic":"RNA and protein synthesis mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Agence Nationale de la Recherche; Canadian Institutes of Health Research; Aix-Marseille Université","keywords":"ORFS; Open reading frame; Genome; Biology; Gene; Genome browser; Computational biology; Genetics; Computer science; Genomics","retraction":null,"screen_n_in":null,"score":{"opus":0.08106924100586585,"gpt":0.3401370640228913,"spread":0.2590678230170255,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000220287,0.00009755673,0.0001755885,0.00002001532,0.00008497139,0.00005936273,0.0001056667,0.00005092013,0.000006079957],"category_scores_gemma":[0.00004368872,0.00009366239,0.00003820501,0.00003390366,0.00005433084,0.00001435034,0.0002439488,0.00002212618,6.769552e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000332649,"about_ca_system_score_gemma":0.00003938212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004072773,"about_ca_topic_score_gemma":0.000003051421,"domain_scores_codex":[0.9992514,0.00008714486,0.000169155,0.0003332813,0.00007292416,0.00008611128],"domain_scores_gemma":[0.999603,0.00003114898,0.0000588257,0.0002185675,0.00003511852,0.00005338204],"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":[0.00005721666,0.00006043292,0.0001213792,0.00002971147,0.0001770042,0.000004309971,0.00003279034,0.00001001717,0.9983122,0.0002467943,0.000490324,0.0004578033],"study_design_scores_gemma":[0.0002367785,0.00005766777,0.00008527436,0.00001112439,0.00007573491,0.00002814752,0.0002646303,0.0003289367,0.9976946,0.00008049348,0.001028394,0.0001082736],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9024368,0.009213028,0.08716283,0.00003117782,0.00003285748,0.0003050613,0.0007207586,0.000003823322,0.00009370225],"genre_scores_gemma":[0.919852,0.00009376547,0.07699339,0.00006317822,0.00002857862,0.00008049678,0.002637768,0.00001308958,0.0002377512],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01741521,"threshold_uncertainty_score":0.3819441,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111476723","doi":"10.1093/database/bar032","title":"NetSlim: high-confidence curated signaling maps","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"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":"Scheme for Promotion of Academic and Research Collaboration","keywords":"Computer science; Visualization; Set (abstract data type); Resource (disambiguation); Computational biology; Database; Information retrieval; Data science; World Wide Web; Data mining; Biology; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.0226126113160794,"gpt":0.2250225638603589,"spread":0.2024099525442795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001619068,0.0001190367,0.00008979045,0.00002238848,0.00006259781,0.0000178817,0.0002176972,0.00008317584,0.0001856296],"category_scores_gemma":[0.00001977825,0.0001107549,0.00003555862,0.00006135346,0.00004925996,0.000007762435,0.0001433924,0.00008692695,0.0001117533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004208612,"about_ca_system_score_gemma":0.0000378656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001294279,"about_ca_topic_score_gemma":0.00003107812,"domain_scores_codex":[0.9992968,0.00002011809,0.0001905626,0.0002001496,0.00006848392,0.0002238394],"domain_scores_gemma":[0.9993432,0.00000508288,0.00007225992,0.0004431589,0.00004431634,0.00009195567],"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":[0.0003135563,0.000172277,0.0009089886,0.00008222806,0.0001654025,0.00005348479,0.0004316634,0.00009086006,0.8589731,0.0131808,0.1163962,0.009231461],"study_design_scores_gemma":[0.001724022,0.0004572916,0.000911505,0.00009843077,0.00008513871,0.00008007626,0.0004047105,0.001483087,0.8240206,0.003031242,0.1665938,0.00111012],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8898342,0.001582882,0.09440958,0.0001283078,0.0009980878,0.0004870373,0.001490933,0.00007755117,0.01099137],"genre_scores_gemma":[0.9879013,0.0001187395,0.008016425,0.0006797523,0.0002001745,0.000009483812,0.002786324,0.00001600025,0.000271796],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09806706,"threshold_uncertainty_score":0.4516455,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4224325974","doi":"10.1093/database/baac069","title":"Multi-label classification for biomedical literature: an overview of the BioCreative VII LitCovid Track for COVID-19 literature topic annotations","year":2022,"lang":"en","type":"article","venue":"Database","topic":"Topic Modeling","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"U.S. National Library of Medicine; Medical Research Council; National Institutes of Health","keywords":"Computer science; Coronavirus disease 2019 (COVID-19); Annotation; Named-entity recognition; Scientific literature; Information retrieval; Data science; Artificial intelligence; Natural language processing; World Wide Web; Task (project management); Medicine; Infectious disease (medical specialty)","retraction":null,"screen_n_in":null,"score":{"opus":0.2046024088696558,"gpt":0.4089928303778776,"spread":0.2043904215082218,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005893763,0.0001326921,0.0001577994,0.0001212457,0.0004620696,0.0001177836,0.001031977,0.00005491254,0.00001312205],"category_scores_gemma":[0.0005225941,0.0001031118,0.00009429118,0.0008185813,0.00005778573,0.0005630208,0.0002874008,0.0001922685,5.811016e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009847521,"about_ca_system_score_gemma":0.0002935803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001895693,"about_ca_topic_score_gemma":0.00001510689,"domain_scores_codex":[0.9984652,0.0002096351,0.00032236,0.0005128819,0.0002877922,0.0002021246],"domain_scores_gemma":[0.9981571,0.000318254,0.0001792041,0.001038457,0.0001649724,0.0001420148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000210451,0.002875393,0.0004744379,0.002328692,0.0001284418,0.00001774941,0.04446766,0.0004650312,0.03714182,0.797538,0.026107,0.08824534],"study_design_scores_gemma":[0.002021123,0.0002071305,0.0004321043,0.00009573454,0.00003106381,0.00001661267,0.0002731414,0.8489129,0.0004354249,0.002865037,0.1444968,0.0002129569],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003593328,0.002214431,0.9734788,0.007575963,0.0005042857,0.001193191,0.01136444,0.00006995558,0.000005597626],"genre_scores_gemma":[0.08294737,0.000137929,0.8932693,0.00823726,0.0003196147,0.001821616,0.01277533,0.00003178602,0.0004597814],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8484479,"threshold_uncertainty_score":0.4204777,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168670121","doi":"10.1093/database/bar051","title":"The Chado Natural Diversity module: a new generic database schema for large-scale phenotyping and genotyping data","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Division of Emerging Frontiers; National Institute of Allergy and Infectious Diseases; Division of Biological Infrastructure; National Institute of General Medical Sciences; Smithsonian Tropical Research Institute; National Human Genome Research Institute; Agricultural Research Service; National Institutes of Health; National Institute of Food and Agriculture; Smithsonian Institution; U.S. Department of Agriculture; Commonwealth Scientific and Industrial Research Organisation; National Evolutionary Synthesis Center; Agriculture and Agri-Food Canada; National Science Foundation","keywords":"Computer science; Modular design; Genotyping; Biological database; Relational database; Schema (genetic algorithms); Database; Information retrieval; Data mining; Bioinformatics; Biology; Programming language; Genotype","retraction":null,"screen_n_in":null,"score":{"opus":0.05710983984248658,"gpt":0.2576520730126977,"spread":0.2005422331702111,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003598423,0.0001783775,0.0001340009,0.00002003297,0.0008003676,0.00003096504,0.0006312899,0.0000504444,0.000005850192],"category_scores_gemma":[0.0001230222,0.0001438669,0.00003966337,0.00005743239,0.00007776283,0.000007737749,0.004023836,0.00008267981,0.00000327318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006605868,"about_ca_system_score_gemma":0.0000559557,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002499144,"about_ca_topic_score_gemma":0.0007800041,"domain_scores_codex":[0.9987867,0.00002790435,0.0001547799,0.0005758991,0.0000875449,0.0003671528],"domain_scores_gemma":[0.9985297,0.00002698513,0.00007858586,0.001191034,0.00005646569,0.0001172081],"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":[0.001037643,0.0002640639,0.02097065,0.0002205146,0.0008647817,0.00001309533,0.001760694,0.000006481016,0.8556826,0.002426234,0.07645788,0.04029538],"study_design_scores_gemma":[0.005258526,0.0002890018,0.02553086,0.00007554149,0.0005030078,0.00005775721,0.001867119,0.01544317,0.1009636,0.0006052936,0.8477192,0.001686913],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9098391,0.0335113,0.04709829,0.0002459231,0.0006927742,0.000720221,0.007706202,0.00001585832,0.0001703141],"genre_scores_gemma":[0.9431549,0.003582857,0.04632545,0.0006251623,0.0007104075,0.00002404559,0.005200845,0.00004111366,0.000335193],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7712613,"threshold_uncertainty_score":0.6155862,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4365135058","doi":"10.1093/database/baad021","title":"NbThermo: a new thermostability database for nanobodies","year":2023,"lang":"en","type":"article","venue":"Database","topic":"Monoclonal and Polyclonal Antibodies Research","field":"Medicine","cited_by":39,"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":"","keywords":"Thermostability; Database; Computer science; Melting temperature; Chemistry; Materials science; Biochemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.1107826829314793,"gpt":0.3938353857990054,"spread":0.2830527028675262,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005618333,0.0001886657,0.0002988701,0.0001363634,0.0001739765,0.00002418665,0.0001954448,0.00005123683,0.001020687],"category_scores_gemma":[0.0006248452,0.0001415754,0.000152568,0.0003887292,0.0001338744,0.0001485303,0.0002680011,0.0001856,0.0009461275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003200759,"about_ca_system_score_gemma":0.0002818445,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006910771,"about_ca_topic_score_gemma":0.0001131866,"domain_scores_codex":[0.9983151,0.00004412592,0.0002537974,0.0004463426,0.0004000899,0.0005405203],"domain_scores_gemma":[0.998293,0.0004320943,0.00003977845,0.0007376609,0.0001080608,0.0003894479],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003502368,0.000335127,0.01132576,0.00122904,0.0002092229,0.0003269748,0.000457848,0.000001716523,0.1718729,0.004545344,0.7631386,0.04305507],"study_design_scores_gemma":[0.003275937,0.0003895606,0.0192818,0.0002264679,0.0001108221,0.00006727396,0.0003162913,0.001784388,0.02427752,0.0009932062,0.9488899,0.000386884],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9571347,0.001232085,0.001278016,0.01784821,0.0004654926,0.002206021,0.01475605,0.0005470671,0.004532417],"genre_scores_gemma":[0.581168,0.00515741,0.0399895,0.01071811,0.006423979,0.001168372,0.1123081,0.0004668777,0.2425996],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3759666,"threshold_uncertainty_score":0.9998925,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2920215701","doi":"10.1093/database/baz033","title":"Update on cpnDB: a reference database of chaperonin sequences","year":2019,"lang":"en","type":"article","venue":"Database","topic":"Heat shock proteins research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Chaperonin; GroEL; Biology; Phylogenetic tree; Computational biology; Identification (biology); Sequence analysis; Sequence (biology); Database; Computer science; Genetics; Ecology; Gene","retraction":null,"screen_n_in":null,"score":{"opus":0.03033648656265123,"gpt":0.3165121856923562,"spread":0.2861756991297049,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003686598,0.0001363198,0.0001446704,0.000068856,0.00003658169,0.00001250959,0.0004240997,0.00007684337,0.0005634641],"category_scores_gemma":[0.0001715677,0.0001187044,0.00003552503,0.0001193588,0.0000895252,0.00001173908,0.0003738867,0.0001626877,0.0005736129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001384702,"about_ca_system_score_gemma":0.0001785544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001829812,"about_ca_topic_score_gemma":0.0000549774,"domain_scores_codex":[0.9986582,0.00009951638,0.0001886028,0.0004619462,0.0002932722,0.0002984645],"domain_scores_gemma":[0.9985867,0.0000193801,0.00005303759,0.001148387,0.00007777818,0.0001147871],"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":[0.0001685064,0.00007904601,0.0008738259,0.00007938876,0.00001754948,0.00001049929,0.000008313329,0.000009148887,0.9940237,0.0009749472,0.002513347,0.001241769],"study_design_scores_gemma":[0.0004675828,0.0004046898,0.0002475072,0.00007890903,0.000004380222,0.000006865149,0.00003410463,0.00009960746,0.9028697,0.00001047052,0.09561004,0.0001661179],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9930727,0.0002997642,0.0002304791,0.0001729105,0.00005765916,0.0003507557,0.002483574,0.00001075556,0.003321383],"genre_scores_gemma":[0.9924149,0.0004191236,0.001293389,0.0002488851,0.00006272356,0.00003130949,0.004824557,0.00001881644,0.0006863227],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0930967,"threshold_uncertainty_score":0.7372824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147119862","doi":"10.1093/database/bar031","title":"The Reactome BioMart","year":2011,"lang":"pt","type":"article","venue":"Database","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"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; European Commission","keywords":"Computer science; Suite; Interface (matter); Information retrieval; User interface; World Wide Web; Simple (philosophy); Database; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02621110658924923,"gpt":0.2401013397079518,"spread":0.2138902331187026,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047343,0.0002208335,0.0001295177,0.00002398631,0.0002959031,0.00006134628,0.0005247204,0.0001824788,0.0001191174],"category_scores_gemma":[0.00004575757,0.0001582144,0.0001114932,0.00009508806,0.0001955125,0.000007766676,0.0004756102,0.0001756577,0.0003853262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001078596,"about_ca_system_score_gemma":0.00009391752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007013332,"about_ca_topic_score_gemma":0.0001337281,"domain_scores_codex":[0.9987425,0.00005327561,0.000345918,0.0002825899,0.00011858,0.0004571355],"domain_scores_gemma":[0.9983837,0.00002031644,0.0001566784,0.001214362,0.00005814279,0.0001668098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007247002,0.0003714975,0.001275527,0.0001379672,0.0006740745,0.00005595812,0.001095214,8.128029e-7,0.05099827,0.006443268,0.8363752,0.1018475],"study_design_scores_gemma":[0.0005048552,0.0002134756,0.0006765754,0.00003233344,0.00006473519,0.00003825399,0.0003847367,0.0004527105,0.01443402,0.0001876436,0.9826349,0.0003757742],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4055947,0.1200572,0.07625847,0.005157605,0.02344236,0.005364603,0.0209781,0.0002625303,0.3428845],"genre_scores_gemma":[0.9773796,0.006400167,0.001594266,0.001457705,0.001006912,0.00003582845,0.003877134,0.00007098565,0.008177374],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5717849,"threshold_uncertainty_score":0.6451796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169425537","doi":"10.1093/database/bau067","title":"Assisting manual literature curation for protein-protein interactions using BioQRator","year":2014,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Institute for Research in Immunology and Cancer","funders":"U.S. National Library of Medicine; National Institutes of Health; Ministry of Education, Science and Technology; National Research Foundation of Korea; National Research Foundation","keywords":"Annotation; Computer science; Data curation; Task (project management); Information retrieval; World Wide Web; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03099098564368279,"gpt":0.3347915863824545,"spread":0.3038006007387717,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002057149,0.0001054229,0.00008659378,0.00003642501,0.0001387798,0.00004951612,0.0001019984,0.00009420453,0.000008784784],"category_scores_gemma":[0.0008111132,0.00009116931,0.00004830426,0.00007079821,0.00004940209,0.00001122178,0.00007082133,0.0000911657,0.000005232006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008773378,"about_ca_system_score_gemma":0.0000290549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001437309,"about_ca_topic_score_gemma":0.00001889014,"domain_scores_codex":[0.9993009,0.00005327164,0.0001441825,0.0002666514,0.00006982413,0.0001651586],"domain_scores_gemma":[0.9995154,0.00001488717,0.00007218268,0.0002587528,0.00007949382,0.00005935343],"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":[0.00004974476,0.00003181853,0.00005124902,0.00005381936,0.00001362685,9.755894e-7,0.00002141379,0.000001959072,0.98378,0.0002674818,0.001511277,0.01421663],"study_design_scores_gemma":[0.0007102205,0.0002884101,0.0001361301,0.0003230734,0.00002650277,0.00002196606,0.00007236128,0.004924553,0.6542705,0.000229268,0.3386782,0.0003187466],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6354731,0.0002329067,0.3626858,0.0002703711,0.0002128762,0.0003342621,0.0006257937,0.00003689357,0.0001280695],"genre_scores_gemma":[0.9243482,0.000002335939,0.07161738,0.0001619156,0.0006914627,0.00008815578,0.002689499,0.0000161004,0.0003848968],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3371669,"threshold_uncertainty_score":0.3717777,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3121051245","doi":"10.1093/database/baaa072","title":"People are essential to linking biodiversity data","year":2020,"lang":"en","type":"article","venue":"Database","topic":"Species Distribution and Climate Change","field":"Environmental Science","cited_by":35,"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","funders":"Horizon 2020 Framework Programme; European Cooperation in Science and Technology; European Commission","keywords":"Digitization; Metadata; Biodiversity; Computer science; Herbarium; Data curation; Data science; Incentive; Citizen science; World Wide Web; Information retrieval; Ecology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.07942744792015947,"gpt":0.2676297436586908,"spread":0.1882022957385313,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00006768416,0.00006401836,0.00006739326,0.000006815022,0.0001141836,0.000033441,0.0007317442,0.00001713284,0.06805146],"category_scores_gemma":[0.0001254942,0.00006529855,0.00001459441,0.00023231,0.0000298328,0.0002524076,0.003215736,0.00005696939,0.01833949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005844127,"about_ca_system_score_gemma":0.000002969706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005454718,"about_ca_topic_score_gemma":0.00173443,"domain_scores_codex":[0.9992562,0.00001334437,0.0000643966,0.0003250024,0.0001885162,0.0001525304],"domain_scores_gemma":[0.9991418,0.00001050677,0.00002776023,0.0006153958,0.00000346853,0.0002011367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002038011,0.00004152807,0.1380201,0.00001035826,0.000003305839,0.00002288864,0.0003121034,0.000005329243,0.004768314,0.00002609115,0.8565921,0.0001775419],"study_design_scores_gemma":[0.0003556148,0.00002341025,0.1815169,0.000007742835,0.00002241931,0.000002341715,0.003014853,0.0004598958,0.002083833,0.00000192222,0.8122647,0.0002463501],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9554787,0.0000125484,0.00119442,0.01348463,0.0001470944,0.0001404525,0.0270081,0.00008972327,0.002444381],"genre_scores_gemma":[0.9687755,0.00003180264,0.0005698575,0.009850895,0.0001114277,0.000003005778,0.02061236,0.000006163764,0.00003895865],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04971197,"threshold_uncertainty_score":0.9824249,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106831214","doi":"10.1093/database/bar023","title":"The modENCODE Data Coordination Center: lessons in harvesting comprehensive experimental details","year":2011,"lang":"en","type":"article","venue":"Database","topic":"Evolution and Genetic Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"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":"Basic Energy Sciences; Office of Science; National Institutes of Health; Wellcome Trust; National Human Genome Research Institute; U.S. Department of Energy","keywords":"Computer science; Metadata; Protocol (science); Research center; Encyclopedia; Caenorhabditis elegans; Set (abstract data type); World Wide Web; Information retrieval; Library science; Biology; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.1012342081328602,"gpt":0.332068989890459,"spread":0.2308347817575987,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001474609,0.0000861324,0.0000578763,0.00001954555,0.0001049892,0.00001905794,0.0003959695,0.00003814196,0.000009837336],"category_scores_gemma":[0.00006046323,0.00007334303,0.00001664198,0.0000502851,0.00007911039,0.00001183788,0.0004891275,0.00006348077,0.0000113153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001120873,"about_ca_system_score_gemma":0.00003354271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001762977,"about_ca_topic_score_gemma":0.00119601,"domain_scores_codex":[0.9992628,0.00006814169,0.0001456861,0.0002764256,0.0000774687,0.0001694432],"domain_scores_gemma":[0.999141,0.00001134767,0.00004977464,0.0007173127,0.00003441277,0.00004611486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002479728,0.0007940229,0.01647972,0.00002490819,0.0000669173,0.000024753,0.0004040021,0.0002319838,0.9491851,0.004205945,0.02083745,0.007497249],"study_design_scores_gemma":[0.006857238,0.000625741,0.05181755,0.0001506093,0.00006159369,0.0001753476,0.006734073,0.326557,0.2842726,0.0003003719,0.3208576,0.001590227],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9728816,0.001926572,0.02022756,0.000317329,0.0002887258,0.0003291458,0.001698412,0.00002155384,0.002309098],"genre_scores_gemma":[0.991537,0.0001374019,0.003155586,0.000136682,0.00004058226,0.00001232318,0.004708968,0.00001068628,0.0002607392],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6649125,"threshold_uncertainty_score":0.2990842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166516661","doi":"10.1093/database/bas017","title":"How to link ontologies and protein-protein interactions to literature: text-mining approaches and the BioCreative experience","year":2012,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Institute for Research in Immunology and Cancer","funders":"Biotechnology and Biological Sciences Research Council; National Center for Research Resources; Directorate for Biological Sciences; National Institutes of Health; Office of Research Infrastructure Programs, National Institutes of Health; Canadian Institutes of Health Research; European Commission; Wellcome Trust","keywords":"Computer science; Ontology; Information retrieval; Pipeline (software); Context (archaeology); Data curation; Information extraction; Consistency (knowledge bases); Workflow; Open Biomedical Ontologies; Biomedical text mining; Controlled vocabulary; Process (computing); Annotation; Vocabulary; Natural language processing; Upper ontology; Data science; Suggested Upper Merged Ontology; Artificial intelligence; Text mining; Semantic Web; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.04548647227863387,"gpt":0.294178056247657,"spread":0.2486915839690232,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002363002,0.0001468006,0.0001368181,0.00004185022,0.0001479533,0.0001169919,0.0001505901,0.00007447702,0.000002866897],"category_scores_gemma":[0.001210766,0.00009076399,0.00002360876,0.0001217056,0.0003229362,0.00001970119,0.0004033156,0.0001123586,0.000002398868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005513061,"about_ca_system_score_gemma":0.0000121793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002341959,"about_ca_topic_score_gemma":0.00002696516,"domain_scores_codex":[0.9991629,0.00009372459,0.000101352,0.0003086152,0.00008087417,0.0002525317],"domain_scores_gemma":[0.9993927,0.00005258112,0.00004036665,0.0003201268,0.00002856929,0.0001656335],"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":[0.001323155,0.0001556543,0.003410094,0.0001298604,0.00015537,0.0000118971,0.02638577,7.720527e-7,0.6326645,0.004296289,0.006673136,0.3247935],"study_design_scores_gemma":[0.001521392,0.0006190072,0.005215343,0.0004223797,0.00004410509,0.0001220632,0.02135658,0.00005862735,0.4009281,0.00009723218,0.5688807,0.0007345551],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9774803,0.004392403,0.008853842,0.008255932,0.00008043815,0.0005337961,0.00014704,0.0000269184,0.0002293227],"genre_scores_gemma":[0.9743015,0.00003952028,0.02368358,0.000397901,0.0002259126,0.0003586652,0.0001058403,0.000008778559,0.0008783588],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5622075,"threshold_uncertainty_score":0.3701248,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2113769137","doi":"10.1093/database/bav008","title":"mycoCLAP, the database for characterized lignocellulose-active proteins of fungal origin: resource and text mining curation support","year":2015,"lang":"en","type":"article","venue":"Database","topic":"Biofuel production and bioconversion","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Resource (disambiguation); Database; World Wide Web; Data curation; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.04390842278676899,"gpt":0.2526945376424777,"spread":0.2087861148557087,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003981124,0.0001297075,0.0001361876,0.00005821998,0.00006940919,0.00002482658,0.0001071724,0.00004893655,0.00004569109],"category_scores_gemma":[0.00009593831,0.00009825822,0.00002729133,0.0001117732,0.00006642483,0.00047616,0.00006244033,0.0001130538,0.00001174865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002768792,"about_ca_system_score_gemma":0.00004022848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001671246,"about_ca_topic_score_gemma":0.000004103608,"domain_scores_codex":[0.9992508,0.00003381727,0.0001959272,0.0002099222,0.0001496822,0.0001598679],"domain_scores_gemma":[0.99938,0.00004327225,0.00007136037,0.0003402319,0.00006760939,0.00009753585],"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":[0.0009963552,0.0001169388,0.0003814145,0.001033435,0.00008958263,0.00001135766,0.00240273,0.00002012149,0.900762,0.0003051105,0.08024623,0.0136347],"study_design_scores_gemma":[0.001459354,0.000150256,0.0001590762,0.00005588966,0.00004735677,0.00002587373,0.001475327,0.007932519,0.3643343,0.000009547494,0.624121,0.0002294907],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9797413,0.0003222365,0.009137497,0.001166631,0.000754466,0.002168715,0.005588101,0.0002460784,0.0008750007],"genre_scores_gemma":[0.9886385,0.00008929573,0.004814393,0.0001775743,0.0005190728,0.0001407674,0.005094041,0.00004711,0.0004792447],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5438748,"threshold_uncertainty_score":0.4006854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2509885322","doi":"10.1093/database/baw121","title":"BioCreative V BioC track overview: collaborative biocurator assistant task for BioGRID","year":2016,"lang":"en","type":"article","venue":"Database","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Mount Sinai Hospital; Lunenfeld-Tanenbaum Research Institute; Université de Montréal; Institute for Research in Immunology and Cancer","funders":"National Institute of General Medical Sciences; Biotechnology and Biological Sciences Research Council; National Institutes of Health","keywords":"Computer science; Usability; Annotation; Task (project management); Interoperability; Classifier (UML); World Wide Web; Information retrieval; Data curation; Crowdsourcing; Natural language processing; Artificial intelligence; Human–computer interaction","retraction":null,"screen_n_in":null,"score":{"opus":0.02559781275306474,"gpt":0.3119697022994703,"spread":0.2863718895464056,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002507749,0.0002144818,0.0002125653,0.00005768818,0.0001086464,0.00002326857,0.000241381,0.0001671251,0.00004899327],"category_scores_gemma":[0.0006980587,0.0001318114,0.00009907167,0.0002019706,0.0003583073,0.000008020858,0.0001222045,0.00005026371,0.00004167664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001998335,"about_ca_system_score_gemma":0.0001679634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001939305,"about_ca_topic_score_gemma":0.00005130734,"domain_scores_codex":[0.9986824,0.00007859593,0.0002371724,0.0005319221,0.0001325207,0.0003374305],"domain_scores_gemma":[0.9989692,0.0001030898,0.0001183155,0.0004827341,0.0001713923,0.0001552958],"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":[0.0003383729,0.0001120545,0.0003541307,0.00003135649,0.0001061756,0.000006595483,0.00003256036,3.428907e-8,0.7945455,0.0003925014,0.165621,0.0384597],"study_design_scores_gemma":[0.000988979,0.0004370785,0.0003984066,0.00005445965,0.0000243887,0.000003404518,0.0001347722,0.000003158843,0.352395,0.00004194397,0.6453107,0.0002076619],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7156446,0.03957897,0.09639426,0.01097311,0.001871158,0.002406108,0.1318078,0.0003018649,0.001022082],"genre_scores_gemma":[0.9203973,0.009502882,0.05124261,0.002601742,0.001793551,0.0007765729,0.009681187,0.0001407253,0.003863402],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4796897,"threshold_uncertainty_score":0.5375115,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964307465","doi":"10.1093/database/baz077","title":"Tripal v3: an ontology-based toolkit for construction of FAIR biological community databases","year":2019,"lang":"en","type":"article","venue":"Database","topic":"Research Data Management Practices","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"National Institute of Food and Agriculture; Agricultural Research Service; Genome Canada; Saskatchewan Pulse Growers; Cotton Incorporated; Washington Tree Fruit Research Commission; U.S. Department of Agriculture; National Science Foundation","keywords":"Computer science; Ontology; World Wide Web; Database; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.2573459647153449,"gpt":0.4068510443479609,"spread":0.149505079632616,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002334212,0.0001410639,0.0002398794,0.0001878573,0.0001677983,0.0002317357,0.002430386,0.00004387873,0.00004828605],"category_scores_gemma":[0.001269381,0.0001208545,0.00004578967,0.0002994893,0.0002098947,0.01428025,0.001061203,0.0002864701,0.00003584963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002687931,"about_ca_system_score_gemma":0.0001193534,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006288003,"about_ca_topic_score_gemma":0.0002278261,"domain_scores_codex":[0.9978438,0.0007880088,0.0002998977,0.000458341,0.0002851426,0.0003248344],"domain_scores_gemma":[0.9954599,0.001343859,0.0002207143,0.002734707,0.0001280422,0.0001127522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005541833,0.001237308,0.0188171,0.0003304447,0.00006997211,0.00001636951,0.00008019328,0.00004279919,0.02459059,0.9330704,0.003355758,0.01783487],"study_design_scores_gemma":[0.01276594,0.00741509,0.03556867,0.0002633657,0.0001245567,0.00007182182,0.002639099,0.1043983,0.095181,0.00338087,0.7363141,0.001877201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3643375,0.00002561012,0.6310281,0.0004467532,0.0002536219,0.0006926011,0.002777765,0.0001517672,0.0002862902],"genre_scores_gemma":[0.5587494,0.00005775876,0.4320486,0.0005083528,0.00004777616,0.00008146271,0.008439631,0.00001413725,0.00005279102],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9296895,"threshold_uncertainty_score":0.9995065,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389579251","doi":"10.1093/database/baad088","title":"Genotype and phenotype data standardization, utilization and integration in the big data era for agricultural sciences","year":2023,"lang":"en","type":"review","venue":"Database","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; Saskatchewan Research Council (Canada)","funders":"Réseau de cancérologie Rossy; U.S. Department of Agriculture; National Institute of Food and Agriculture; National Science Foundation","keywords":"Data science; Raw data; Context (archaeology); Standardization; Computer science; Metadata; Annotation; Data collection; Biology; World Wide Web; Bioinformatics","retraction":null,"screen_n_in":null,"score":{"opus":0.298928971651219,"gpt":0.3947060009767093,"spread":0.09577702932549031,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007679857,0.0001663566,0.0002496687,0.00004476187,0.0001731495,0.00009254667,0.0006258388,0.00006475145,4.681732e-7],"category_scores_gemma":[0.0003768627,0.00009853124,0.0000146483,0.0002026895,0.0001078319,0.000005377403,0.0009297686,0.00006143079,7.773967e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004545956,"about_ca_system_score_gemma":0.0001262021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003654126,"about_ca_topic_score_gemma":0.000817704,"domain_scores_codex":[0.998868,0.00008548394,0.0002298977,0.0005965108,0.0000922543,0.0001278195],"domain_scores_gemma":[0.9989625,0.00007776346,0.0001103231,0.0007807007,0.00004815573,0.00002057312],"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":[0.00001294961,0.00002607585,0.00001868315,0.001510176,0.00007286683,6.70105e-7,0.00006341832,0.000001794952,0.0002350598,0.0005953567,0.009048839,0.9884141],"study_design_scores_gemma":[0.0001414052,0.00009591212,0.0001169478,0.0003585669,0.0001870144,0.000005267623,0.0001238941,0.0001166797,0.000005708103,0.00004807277,0.9986356,0.0001648777],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002046834,0.9794171,0.002499537,0.00005593085,0.0001580213,0.000698688,0.0169405,0.000002556195,0.00002293904],"genre_scores_gemma":[0.0002913861,0.9294894,0.000776704,0.00003207946,0.0002813865,0.00003561918,0.06906658,0.00001249162,0.00001438313],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9895868,"threshold_uncertainty_score":0.4017988,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2795044975","doi":"10.1093/database/bay032","title":"Biopanning data bank 2018: hugging next generation phage display","year":2018,"lang":"en","type":"article","venue":"Database","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":30,"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":"National Natural Science Foundation of China","keywords":"Biopanning; Computer science; Data bank; Library science; Telecommunications; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.1018156776606257,"gpt":0.3119855143685021,"spread":0.2101698367078764,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001692232,0.0001027565,0.00007092394,0.00003128413,0.0002875937,0.0001173956,0.0003779106,0.00002596684,0.008838445],"category_scores_gemma":[0.0000347725,0.0000950575,0.00001757675,0.0001571041,0.0001226497,0.001808621,0.0007715775,0.00009283441,0.004491608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004944629,"about_ca_system_score_gemma":0.000006300429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009850716,"about_ca_topic_score_gemma":0.0007189686,"domain_scores_codex":[0.9991313,0.00002750556,0.0001441485,0.0003896748,0.00009338291,0.0002140382],"domain_scores_gemma":[0.9989962,0.00001475224,0.00005652645,0.0008498225,0.000005296822,0.00007740375],"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":[0.000004128932,0.00003176617,0.0002108354,0.000001761679,0.000004062492,0.000006950175,0.00007338703,0.00000273316,0.8771195,0.0000152898,0.1159212,0.006608318],"study_design_scores_gemma":[0.0002542082,0.00004476936,0.006110254,0.00003235748,0.00003534878,0.00004773089,0.00006605806,0.02766637,0.07251802,0.000003005886,0.8929295,0.0002923584],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9797122,0.00005658464,0.01153426,0.0003450808,0.00122672,0.0001735714,0.002049031,0.00008646879,0.004816122],"genre_scores_gemma":[0.9844035,0.00002985279,0.007577867,0.0007204052,0.0007612873,0.000005566013,0.005010979,0.00001863896,0.001471906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8046016,"threshold_uncertainty_score":0.9962835,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}