{"meta":{"query_hash":"c37f3562306a","filters":{"venue":"GigaScience"},"cohort_total":134,"direct_labels_cover":1,"predictions_cover":134,"exported":134,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/c37f3562306a","api":"https://metacan.xera.ac/api/v1/cohort?venue=GigaScience"},"results":[{"id":"W1819131487","doi":"10.1186/s13742-015-0090-5","title":"A large and diverse collection of bovine genome sequences from the Canadian Cattle Genome Project","year":2015,"lang":"en","type":"article","venue":"GigaScience","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Agriculture Food and Rural Development; University of Guelph; University of Alberta","funders":"Agricultural Research Service; Genome Alberta; Scotland’s Rural College; Alberta Innovates; Alberta Innovates Bio Solutions; Alberta Livestock and Meat Agency; Western Canada Research Grid; Teagasc; Compute Canada; Genome Canada; AgResearch; U.S. Department of Agriculture","keywords":"Genome; Genomics; Biology; DNA sequencing; Computational biology; Bovine genome; Structural variation; Sustainability; Scale (ratio); Data science; Biotechnology; Genetics; Computer science; DNA; Geography; Gene; Ecology","score_opus":0.025545546968577297,"score_gpt":0.24607936388438545,"score_spread":0.22053381691580815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1819131487","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961977,0.0009378325,0.0007338439,0.00017360602,0.0001170167,0.00016366018,0.0001334142,0.0000031649759,0.0015397576],"genre_scores_gemma":[0.99665654,0.000024049448,0.0026583143,0.00018004731,0.000080472295,0.000007485185,0.000027954351,0.0000036928927,0.00036145057],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99937683,0.000036076734,0.000084270934,0.00020836054,0.00011812587,0.00017635776],"domain_scores_gemma":[0.9995948,0.000008063054,0.000041502673,0.00018038534,0.00006907486,0.000106173975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022156494,0.000067428926,0.000063769374,0.000023348968,0.00017123415,0.000020219162,0.0002243291,0.000050599032,0.000009863949],"category_scores_gemma":[0.00006877124,0.000049377923,0.000016658953,0.00014144086,0.00025991336,0.0000040673353,0.00007613272,0.000041174255,0.0000031231227],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033791095,0.0002593608,0.26731592,0.00005192436,0.00020556377,0.0000068238323,0.03851117,0.0019175296,0.6679314,0.008053255,0.012807807,0.002601346],"study_design_scores_gemma":[0.0005848552,0.00083459174,0.9419494,0.000007834823,0.000027050359,0.0000190926,0.0027308166,0.000048473543,0.0049732523,0.0016115383,0.046977673,0.00023536917],"about_ca_topic_score_codex":0.045493316,"about_ca_topic_score_gemma":0.13071166,"teacher_disagreement_score":0.67463356,"about_ca_system_score_codex":0.000020357846,"about_ca_system_score_gemma":0.00066320424,"threshold_uncertainty_score":0.9608628},"labels":[],"label_agreement":null},{"id":"W1999791778","doi":"10.1186/s13742-015-0056-7","title":"A genome draft of the legless anguid lizard, <i>Ophisaurus gracilis</i>","year":2015,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Ontario Museum","funders":"","keywords":"Lizard; Genome; Biology; Hull; Evolutionary biology; Zoology; Genetics; Oceanography; Geology; Gene","score_opus":0.02020388429449019,"score_gpt":0.2320215883515764,"score_spread":0.21181770405708622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999791778","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9930963,0.0023567122,0.00012910005,0.00021205611,0.00031088092,0.000114062386,0.000024845565,0.0000020887348,0.0037539715],"genre_scores_gemma":[0.99861753,0.00008380216,0.00034705558,0.00026965135,0.00009578226,0.000008393242,0.0000022307943,0.000006723355,0.000568816],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991859,0.000031450578,0.0001446103,0.0002505319,0.00018799228,0.00019948305],"domain_scores_gemma":[0.9992643,0.000005147855,0.00007465804,0.000443696,0.00013463238,0.000077571276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002436831,0.0000968898,0.00010372241,0.000015798629,0.00008785523,0.000013776275,0.00052067795,0.000046514426,0.0000022206934],"category_scores_gemma":[0.000102911246,0.00006814602,0.00007320704,0.00016212,0.0003357465,9.2778333e-7,0.00034913945,0.00003928525,0.0000051319657],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010020189,0.000021444988,0.005520095,0.000004278962,0.00000942639,5.58414e-7,0.00027883973,0.00020301697,0.9931351,0.00010023095,0.00037248505,0.00034450553],"study_design_scores_gemma":[0.0007462181,0.0004460462,0.12542969,0.000014550848,0.000030904725,0.00004475824,0.000663482,0.000049905735,0.6287314,0.0009537222,0.24248768,0.00040158018],"about_ca_topic_score_codex":0.000037110796,"about_ca_topic_score_gemma":0.000037634407,"teacher_disagreement_score":0.36440364,"about_ca_system_score_codex":0.000008507813,"about_ca_system_score_gemma":0.0001536611,"threshold_uncertainty_score":0.27789143},"labels":[],"label_agreement":null},{"id":"W2102532874","doi":"10.1186/2047-217x-2-10","title":"Assemblathon 2: evaluating <i>de novo</i> methods of genome assembly in three vertebrate species","year":2013,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":735,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; BC Cancer Agency","funders":"National Human Genome Research Institute; National Institute of General Medical Sciences; Wellcome Trust","keywords":"Vertebrate; Genome; Computational biology; Evolutionary biology; Sequence assembly; Biology; Computer science; Data science; Genetics; Gene","score_opus":0.039269528767931536,"score_gpt":0.32710037716515594,"score_spread":0.2878308483972244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102532874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9894943,0.0009065065,0.0069026332,0.00009672699,0.000104603736,0.00018469317,0.0000042558954,0.000002311555,0.0023039547],"genre_scores_gemma":[0.95571876,0.00012391365,0.043742266,0.00016448482,0.00005329173,0.000028714445,0.00000199403,0.000009339896,0.00015726352],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99888444,0.00008832967,0.0002432063,0.0003233068,0.00014153396,0.00031916605],"domain_scores_gemma":[0.999404,0.00003554025,0.00009641653,0.00029758803,0.000110622226,0.000055845543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009850644,0.000120617326,0.00016768683,0.000048133657,0.00006390265,0.000028009646,0.0003408384,0.000055955337,0.000018207606],"category_scores_gemma":[0.0002189002,0.00011067391,0.0000561354,0.00020295382,0.0001409756,0.0000028679774,0.00021389108,0.000060396935,0.000007696458],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041213657,0.00002060743,0.015459355,0.000007745793,0.000007654005,4.6968472e-7,0.00013264416,0.00056049746,0.979854,0.000088682726,0.000015622047,0.003848583],"study_design_scores_gemma":[0.00026664746,0.00027436536,0.42248353,0.000010941333,0.000007874716,0.000008050148,0.00016463631,0.0029135395,0.57205033,0.001089138,0.00054448313,0.00018648582],"about_ca_topic_score_codex":0.00007368735,"about_ca_topic_score_gemma":0.00008749748,"teacher_disagreement_score":0.4078037,"about_ca_system_score_codex":0.000017311993,"about_ca_system_score_gemma":0.000107685955,"threshold_uncertainty_score":0.4513151},"labels":[],"label_agreement":null},{"id":"W2115567294","doi":"10.1186/2047-217x-3-17","title":"Data access for the 1,000 Plants (1KP) project","year":2014,"lang":"en","type":"review","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":608,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Université du Québec à Montréal; Université de Montréal; University of Alberta","funders":"U.S. National Library of Medicine; Ministry of Innovation and Advanced Education; Alberta Innovates; Alberta Innovates - Technology Futures; National Institutes of Health; National Science Foundation","keywords":"Upload; Phylogenomics; Visualization; Scalability; Computer science; Clade; Data science; Data visualization; Data mining; Phylogenetic tree; Computational biology; World Wide Web; Biology; Database; Gene","score_opus":0.20788350667753658,"score_gpt":0.4250069855068654,"score_spread":0.2171234788293288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115567294","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002919933,0.9953356,0.001112209,0.000028642597,0.0005423572,0.0010234838,0.0015472596,0.0000029510454,0.0003783288],"genre_scores_gemma":[0.00009521085,0.99787974,0.00031594298,0.00013538064,0.000562856,0.00021549838,0.00033958055,0.000024363784,0.00043144615],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998473,0.000049536015,0.00026523467,0.00075249525,0.00013244335,0.0003272764],"domain_scores_gemma":[0.9980934,0.00011650981,0.00020321304,0.0015066654,0.000042032574,0.000038143447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000638019,0.0002543692,0.00046479277,0.00003289973,0.0002725359,0.00012303956,0.0035530636,0.0001349111,0.0000022238455],"category_scores_gemma":[0.00017974206,0.00014820928,0.00015066603,0.00011098506,0.00020076468,0.0000013533388,0.0016153683,0.00008383528,0.0000053377535],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047416206,0.000013793512,0.000009539053,0.0011364619,0.00011359376,3.870565e-7,0.00001168415,0.0000022220654,0.000109190725,0.00002410287,0.025394347,0.97317994],"study_design_scores_gemma":[0.000063144034,0.0000615174,0.000012682989,0.00021961606,0.0001301814,0.000015874142,0.000007000897,0.000045277517,0.000029067478,0.000016505484,0.9991924,0.00020671928],"about_ca_topic_score_codex":0.000022079934,"about_ca_topic_score_gemma":0.000046549074,"teacher_disagreement_score":0.9737981,"about_ca_system_score_codex":0.000007077862,"about_ca_system_score_gemma":0.00031016266,"threshold_uncertainty_score":0.6602535},"labels":[],"label_agreement":null},{"id":"W2129071773","doi":"10.1186/2047-217x-3-18","title":"GWATCH: a web platform for automated gene association discovery analysis","year":2014,"lang":"en","type":"article","venue":"GigaScience","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; AIDS Vancouver; University of British Columbia","funders":"National Institute of Child Health and Human Development; National Eye Institute; National Institutes of Health; Megagrants; Michael Smith Health Research BC","keywords":"Genome-wide association study; Health Insurance Portability and Accountability Act; Genome; Genetic association; Human genome; Genetics; Indel; Computational biology; Biology; Single-nucleotide polymorphism; Gene; Computer science; Confidentiality","score_opus":0.011277456615169027,"score_gpt":0.2676463480472772,"score_spread":0.25636889143210817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129071773","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89619386,0.000035137527,0.10247035,0.0004236478,0.00015864284,0.00012395435,0.000048112634,0.000037675578,0.00050863175],"genre_scores_gemma":[0.988811,0.000031883286,0.008065889,0.00050284615,0.00013558999,0.00004153971,0.00018675138,0.000007107059,0.0022173668],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99891293,0.00005171319,0.00021634692,0.00035059825,0.00013399056,0.00033440883],"domain_scores_gemma":[0.9992945,0.00008228585,0.00019146138,0.00025771113,0.0001142845,0.000059708636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011154767,0.00009876507,0.00018582516,0.00006974751,0.00016502613,0.000043610136,0.00021303057,0.00014834345,0.0000048961456],"category_scores_gemma":[0.001055917,0.000089397414,0.00016590391,0.0003537483,0.000041493062,0.00000882241,0.00006240265,0.000036510897,0.000008809168],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029790914,0.00008648478,0.41394413,0.00001001151,0.00050637324,2.0932e-7,0.000084654755,0.012240675,0.55388063,0.00066275155,0.015896898,0.0026574032],"study_design_scores_gemma":[0.0010643627,0.00050151563,0.576084,0.0000044557764,0.00045066053,0.0000031561729,0.00007273203,0.3356148,0.03556092,0.0009157788,0.049186446,0.0005411186],"about_ca_topic_score_codex":0.000023755858,"about_ca_topic_score_gemma":0.00012625266,"teacher_disagreement_score":0.5183197,"about_ca_system_score_codex":0.00004939754,"about_ca_system_score_gemma":0.00007595237,"threshold_uncertainty_score":0.36455208},"labels":[],"label_agreement":null},{"id":"W2134164698","doi":"10.1186/2047-217x-2-3","title":"AXIOME: automated exploration of microbial diversity","year":2013,"lang":"en","type":"article","venue":"GigaScience","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Workflow; Computer science; Graphical user interface; Microbial ecology; Bottleneck; Automation; Personalization; Metagenomics; Data science; Ecology; Computational biology; Software engineering; Biology; World Wide Web; Database; Programming language","score_opus":0.019421764679513797,"score_gpt":0.22097067202460385,"score_spread":0.20154890734509007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134164698","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99592805,0.0000020099715,0.0002738511,0.00024629768,0.000112985486,0.00012146932,0.0000024857952,0.00006004042,0.0032528217],"genre_scores_gemma":[0.9988003,0.000003337947,0.0007036102,0.00028796177,0.0000051969055,0.000003284283,0.0000052076757,0.0000017377355,0.00018939847],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9994317,0.000081511476,0.000104901505,0.00013742904,0.00008080246,0.00016364793],"domain_scores_gemma":[0.99965554,0.00003346649,0.00006438211,0.00019230704,0.000012905455,0.000041378997],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001680717,0.00005659536,0.000083640145,0.000024305018,0.00032824828,0.000007654191,0.00043971976,0.000048629285,0.0063328305],"category_scores_gemma":[0.000029094757,0.00005274958,0.000024242945,0.00027429013,0.0005755481,0.00062967004,0.00083268195,0.000074162024,0.0013710356],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051995216,0.00006837458,0.011110116,0.0000028776105,0.0000020514476,4.0962095e-7,0.0012045564,0.0004799748,0.9643466,0.00010511157,0.021868719,0.0008060007],"study_design_scores_gemma":[0.00046397187,0.0003138771,0.90759057,0.000010441118,0.000010893678,0.000009216048,0.00035569104,0.0058582737,0.07414751,0.007561668,0.0033414215,0.00033645227],"about_ca_topic_score_codex":0.0012881662,"about_ca_topic_score_gemma":0.0002627972,"teacher_disagreement_score":0.89648044,"about_ca_system_score_codex":0.00003217405,"about_ca_system_score_gemma":0.000007971379,"threshold_uncertainty_score":0.9994065},"labels":[],"label_agreement":null},{"id":"W2141983233","doi":"10.1186/s13742-015-0065-6","title":"An image database of <i>Drosophila melanogaster</i> wings for phenomic and biometric analysis","year":2015,"lang":"en","type":"article","venue":"GigaScience","topic":"Morphological variations and asymmetry","field":"Mathematics","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Science Foundation","keywords":"Computer science; Artificial intelligence; Landmark; Pattern recognition (psychology); Biometrics; Inference; Phenomics; Biological data; Machine learning; Genomics; Bioinformatics; Biology; Genome","score_opus":0.08143931078614505,"score_gpt":0.3393304544468875,"score_spread":0.2578911436607424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141983233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7523486,0.00004918145,0.24678291,0.000093549985,0.000035745234,0.00013576407,0.00013179299,0.00001980314,0.00040266005],"genre_scores_gemma":[0.79013884,0.000003908781,0.20972924,0.000053251926,0.00001915986,0.000006924581,0.000011877183,0.000003957346,0.000032874126],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9991535,0.000028304106,0.00020703857,0.00026315343,0.00018940892,0.00015858463],"domain_scores_gemma":[0.9990869,0.00020209953,0.00013080335,0.00032910326,0.000108052474,0.00014302706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096226885,0.00007750467,0.00020699241,0.00037643837,0.00006110434,0.000044631972,0.0002499949,0.00002815579,0.000015982008],"category_scores_gemma":[0.0006161003,0.000059979782,0.000049839527,0.001971864,0.0001462401,0.00027712143,0.00007545046,0.000033615845,0.0000024363928],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010399435,0.001613996,0.035618972,0.00030935823,0.00029988767,0.000016564612,0.0018074032,0.00008688734,0.7703173,0.17655249,0.0058960067,0.0073771044],"study_design_scores_gemma":[0.010658287,0.0051186266,0.115425244,0.0001714116,0.00518257,0.000099886274,0.0050685406,0.28635764,0.14164877,0.42283714,0.0044204374,0.0030114604],"about_ca_topic_score_codex":0.000026492513,"about_ca_topic_score_gemma":0.0000029611635,"teacher_disagreement_score":0.62866855,"about_ca_system_score_codex":0.000013484729,"about_ca_system_score_gemma":0.000026953865,"threshold_uncertainty_score":0.24459046},"labels":[],"label_agreement":null},{"id":"W2146906779","doi":"10.1186/s13742-015-0066-5","title":"The ocean sampling day consortium","year":2015,"lang":"en","type":"article","venue":"GigaScience","topic":"Atmospheric and Environmental Gas Dynamics","field":"Environmental Science","cited_by":224,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"National Oceanic and Atmospheric Administration; Natural Environment Research Council; European Commission; Sight Research UK","keywords":"Sampling (signal processing); Computer science; Data science; Oceanography; Environmental science; Geology; Telecommunications","score_opus":0.02054981495592627,"score_gpt":0.23014290806859075,"score_spread":0.2095930931126645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146906779","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9394987,0.00007992033,0.035953872,0.00067518884,0.0004394985,0.0001378592,7.17293e-7,0.00006332757,0.023150891],"genre_scores_gemma":[0.9876205,0.00002799098,0.008251097,0.00048187064,0.000028628097,0.000003571497,4.9206363e-7,0.000008986584,0.0035768773],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99871314,0.000034423432,0.00014288959,0.00027666803,0.00046196333,0.00037094494],"domain_scores_gemma":[0.9993374,0.00006122864,0.000056908764,0.00032077442,0.0000032094047,0.00022051085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007553124,0.000102717386,0.000067255445,0.0000019923516,0.00040107386,0.000067400215,0.00056698074,0.000029441799,0.0001006554],"category_scores_gemma":[0.00010360598,0.000067932015,0.00003045496,0.00022489838,0.0011178063,0.00022376538,0.0003596403,0.000096892865,0.0005554346],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023736504,0.00010782385,0.589071,0.0000018292881,0.000008787838,0.000017636521,0.0023750686,0.31119815,0.00325051,0.0023415147,0.012754718,0.07884925],"study_design_scores_gemma":[0.0006790469,0.00024776979,0.35177982,0.000011642884,0.000021536422,0.00008196009,0.0040695323,0.078203395,0.00069331226,0.010133849,0.5532415,0.000836628],"about_ca_topic_score_codex":0.000103994455,"about_ca_topic_score_gemma":0.000020126341,"teacher_disagreement_score":0.5404868,"about_ca_system_score_codex":0.00018650424,"about_ca_system_score_gemma":0.000016987458,"threshold_uncertainty_score":0.7139174},"labels":[],"label_agreement":null},{"id":"W2156498700","doi":"10.1186/2047-217x-1-14","title":"A locally funded Puerto Rican parrot (Amazona vittata) genome sequencing project increases avian data and advances young researcher education","year":2012,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Genome; Contig; Biology; DNA sequencing; Population; Endangered species; Genomics; Evolutionary biology; Annotation; Computational biology; Library science; Genetics; Ecology; Gene; Computer science; Medicine","score_opus":0.05322739355772505,"score_gpt":0.33005442702112364,"score_spread":0.2768270334633986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156498700","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985095,0.01286677,0.00041366255,0.000099491444,0.00011934549,0.00028711944,0.00009015623,0.000004931983,0.0010235219],"genre_scores_gemma":[0.99323344,0.001426913,0.0046241963,0.00016231666,0.00021009792,0.00004376594,0.000102405495,0.000011681958,0.00018517017],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99868995,0.000073440344,0.0001485354,0.000477945,0.00018954181,0.00042060285],"domain_scores_gemma":[0.99911064,0.000020772,0.00006842681,0.00056511373,0.00008608848,0.00014898657],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006440608,0.000134213,0.000112269336,0.000050669,0.00023561095,0.000057838966,0.0004973496,0.00004643187,0.0000031445288],"category_scores_gemma":[0.00025545876,0.000116830335,0.00001972545,0.00017797468,0.00032755313,0.000015773365,0.0006302853,0.000066954024,0.0000025068773],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003556178,0.000090957205,0.115191706,0.00003704528,0.000023889068,0.0000011880214,0.00042958037,0.000007867641,0.8724165,0.000092483126,0.00038542255,0.011287789],"study_design_scores_gemma":[0.0009442295,0.0009068074,0.7246581,0.00009117327,0.00009157251,0.00031287648,0.008227035,0.00047971893,0.052443948,0.0007231199,0.20968564,0.0014358079],"about_ca_topic_score_codex":0.00055002276,"about_ca_topic_score_gemma":0.00051369,"teacher_disagreement_score":0.8199726,"about_ca_system_score_codex":0.00003081877,"about_ca_system_score_gemma":0.00044723623,"threshold_uncertainty_score":0.47642028},"labels":[],"label_agreement":null},{"id":"W2163434905","doi":"10.1186/2047-217x-3-15","title":"Between Two Fern Genomes","year":2014,"lang":"en","type":"review","venue":"GigaScience","topic":"Fern and Epiphyte Biology","field":"Agricultural and Biological Sciences","cited_by":81,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Fern; Genome; Biology; Evolutionary biology; Lineage (genetic); Clade; Genome size; Phylogenetics; Ecology; Genetics; Gene","score_opus":0.09422901975019328,"score_gpt":0.3264193411632683,"score_spread":0.23219032141307505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163434905","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00048136504,0.9958681,0.0000041810345,0.00009346971,0.00035711366,0.00025004955,0.00006991002,0.00008996513,0.0027858738],"genre_scores_gemma":[0.00044811273,0.9969537,0.000049355785,0.00012597303,0.0013296271,0.000024639226,0.0001247991,0.0000015015898,0.0009422809],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99801457,0.00017700996,0.00038455817,0.00066233333,0.00022188341,0.00053966563],"domain_scores_gemma":[0.99906725,0.00036012905,0.00022329639,0.00013391594,0.000030398296,0.00018502373],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005177528,0.00031829785,0.0011037944,0.000021440814,0.00024050513,0.00008915283,0.001242792,0.00022727734,0.00026712738],"category_scores_gemma":[0.000055153385,0.00009425555,0.00037293448,0.00054127333,0.00023490346,0.000063926134,0.00024411683,0.000239522,0.0012377789],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.1494598e-7,0.000005697973,0.00011758471,0.00015974094,0.0000062554964,0.0000012974207,0.0000032918927,1.7788214e-8,0.000017651893,0.00008390255,0.00028293591,0.9993214],"study_design_scores_gemma":[0.000018724504,0.000093092895,0.00048497078,0.00042005946,0.00005115714,0.000010447945,0.0000030748042,0.0000010763666,0.0000014041542,0.00013501928,0.9984956,0.00028540313],"about_ca_topic_score_codex":0.00008685639,"about_ca_topic_score_gemma":0.000089605455,"teacher_disagreement_score":0.999036,"about_ca_system_score_codex":0.000041353487,"about_ca_system_score_gemma":0.000033785727,"threshold_uncertainty_score":0.99953985},"labels":[],"label_agreement":null},{"id":"W2163795639","doi":"10.1186/2047-217x-3-2","title":"The founding charter of the Genomic Observatories Network","year":2014,"lang":"en","type":"article","venue":"GigaScience","topic":"Environmental Monitoring and Data Management","field":"Earth and Planetary Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Biotechnology and Biological Sciences Research Council; European Commission; Smithsonian Institution; Sight Research UK; Natural Environment Research Council; Gordon and Betty Moore Foundation; National Science Foundation","keywords":"Charter; Observatory; Biodiversity; Work (physics); State (computer science); Subject (documents); Genomics","score_opus":0.009852126532821859,"score_gpt":0.16841824526587199,"score_spread":0.15856611873305013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163795639","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99185324,0.00019030336,0.00024103514,0.00040288895,0.0024658889,0.00008058138,0.000004290615,0.000010560442,0.004751237],"genre_scores_gemma":[0.99890774,0.000038050493,0.00028160962,0.00015149711,0.00021623229,7.00372e-7,0.0000013675157,9.92919e-7,0.00040182954],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992915,0.00004714469,0.00010042316,0.00012950606,0.0002217455,0.0002097185],"domain_scores_gemma":[0.9994575,0.00011933963,0.0000599057,0.00032786198,0.0000037874781,0.000031627846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006403696,0.000051971867,0.000047944137,0.0000038104276,0.00057970535,0.000072373514,0.0006140568,0.000010807971,0.000031901214],"category_scores_gemma":[0.000035489655,0.000025805159,0.000025607385,0.00014143936,0.00028986685,0.00013263004,0.00006328847,0.000049763377,0.000054595926],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017386762,0.0000013630313,0.9824021,0.0000023723874,0.000001872173,8.308525e-8,0.000055602177,0.002176694,0.00007503873,0.00091171346,0.00034279656,0.014028646],"study_design_scores_gemma":[0.000025652485,0.00002068368,0.95015234,0.000007844079,0.0000028112295,5.7966065e-7,0.000060267674,0.0016809027,0.00008043973,0.00085210195,0.047078647,0.000037754162],"about_ca_topic_score_codex":0.00019490682,"about_ca_topic_score_gemma":0.00018836652,"teacher_disagreement_score":0.04673585,"about_ca_system_score_codex":0.0000034751667,"about_ca_system_score_gemma":0.000006832062,"threshold_uncertainty_score":0.44586834},"labels":[],"label_agreement":null},{"id":"W2167107931","doi":"10.1186/2047-217x-3-6","title":"A dataset comprising four micro-computed tomography scans of freshly fixed and museum earthworm specimens","year":2014,"lang":"en","type":"article","venue":"GigaScience","topic":"Invertebrate Taxonomy and Ecology","field":"Agricultural and Biological Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Emergent BioSolutions (Canada)","funders":"","keywords":"Earthworm; Lumbricus terrestris; Computer science; Oligochaeta (plant); Computed tomography; Biology; Artificial intelligence; Ecology; Radiology; Medicine","score_opus":0.019281353092608568,"score_gpt":0.1874057975244702,"score_spread":0.16812444443186164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167107931","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9981851,0.000029158875,0.00009683767,0.00066584436,0.00011442253,0.00014760639,0.0002438837,0.000022028782,0.00049509393],"genre_scores_gemma":[0.9977889,0.000005919205,0.0014531311,0.0005641357,0.000072501905,0.0000041554504,0.00009480259,4.652054e-7,0.000015953758],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99899715,0.000062374515,0.00018839029,0.00031603192,0.00012479517,0.00031128345],"domain_scores_gemma":[0.9995352,0.00013541298,0.00009928786,0.000091003174,0.000037438986,0.00010163475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035294634,0.00010718143,0.0001832857,0.000026741274,0.00024966095,0.00005304471,0.0003444212,0.00005716319,0.00015295319],"category_scores_gemma":[0.000027001068,0.00004762893,0.000040257873,0.00041583608,0.0003484598,0.00016109608,0.00013915848,0.00008021666,0.000025098172],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020915508,0.00010497862,0.056710087,0.000015135638,0.000012311374,0.0000050560107,0.00015110626,0.000025817228,0.90689397,0.00066861906,0.007996286,0.02739571],"study_design_scores_gemma":[0.000377769,0.0006573921,0.82481927,0.000049644343,0.000014604162,0.000037094116,0.00019072543,0.0048468583,0.04385622,0.00066933106,0.12408848,0.00039259635],"about_ca_topic_score_codex":0.00016263871,"about_ca_topic_score_gemma":0.0014053232,"teacher_disagreement_score":0.86303777,"about_ca_system_score_codex":0.0000057121674,"about_ca_system_score_gemma":0.000007753349,"threshold_uncertainty_score":0.19422515},"labels":[],"label_agreement":null},{"id":"W2167757586","doi":"10.1186/s13742-015-0076-3","title":"LINKS: Scalable, alignment-free scaffolding of draft genomes with long reads","year":2015,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":279,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; BC Cancer Agency","funders":"National Human Genome Research Institute; National Institutes of Health; Genome British Columbia; Genome Canada","keywords":"Scaffold; Genome; Computer science; Computational biology; Scalability; Hull; Biology; Genetics; Engineering; Programming language; Gene; Database; Marine engineering","score_opus":0.016736622768235315,"score_gpt":0.2330619362130425,"score_spread":0.21632531344480718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167757586","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99203026,0.003109972,0.0010283137,0.00014738225,0.00010821667,0.00011065262,0.000011501658,0.0000036330343,0.00345008],"genre_scores_gemma":[0.99347097,0.00023432408,0.0055926084,0.00011698515,0.000079460886,0.000009166589,0.0000042152783,0.000010756743,0.00048149293],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990237,0.000019735853,0.00015430035,0.00032188796,0.00022383628,0.00025655743],"domain_scores_gemma":[0.99915534,0.000007829127,0.00008639347,0.0004974516,0.0001375623,0.00011544363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030504953,0.00012024092,0.00013709688,0.000034464054,0.00007303721,0.000021103255,0.0004626488,0.00007275657,0.000003115108],"category_scores_gemma":[0.000059191647,0.00009642191,0.00003555204,0.00015684134,0.00028472717,0.0000019655934,0.00032491848,0.00004078621,0.000003417384],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060831793,0.000060382306,0.1266923,0.000020414298,0.000061120765,0.0000053228887,0.00042241707,0.00097061746,0.8666273,0.00026012288,0.0015630717,0.0032561528],"study_design_scores_gemma":[0.0015993771,0.0015472339,0.04747481,0.000054097156,0.000054322227,0.000054941833,0.00085760956,0.0001720456,0.92774427,0.0008327599,0.019060938,0.00054757623],"about_ca_topic_score_codex":0.000030330448,"about_ca_topic_score_gemma":0.00004237121,"teacher_disagreement_score":0.079217486,"about_ca_system_score_codex":0.000012855071,"about_ca_system_score_gemma":0.00013610967,"threshold_uncertainty_score":0.39319712},"labels":[],"label_agreement":null},{"id":"W2170531036","doi":"10.1186/2047-217x-2-2","title":"Crowdsourcing genomic analyses of ash and ash dieback – power to the people","year":2013,"lang":"en","type":"editorial","venue":"GigaScience","topic":"Plant Pathogens and Fungal Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; Gatsby Charitable Foundation","keywords":"Crowdsourcing; Genomics; Data science; Population; World Wide Web; Computer science; Biology; Genome; Genetics; Gene; Environmental health; Medicine","score_opus":0.009411719794097495,"score_gpt":0.26471901054180225,"score_spread":0.25530729074770475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170531036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8591457,0.0041037053,0.00036118686,0.00008755448,0.13301972,0.00037160586,0.0021022016,0.000010145616,0.00079816696],"genre_scores_gemma":[0.79908293,0.0015335468,0.0008089268,0.00033737018,0.19446823,0.00006898053,0.0005603386,0.000059468082,0.0030801762],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99866,0.000048199923,0.00020002839,0.0004964071,0.00032008116,0.00027522657],"domain_scores_gemma":[0.99903995,0.00007338897,0.00013363287,0.00046296327,0.00015405029,0.00013604591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002468654,0.00019568802,0.00023533299,0.000051133924,0.00012997868,0.000081966886,0.0005579111,0.00020434527,0.0000233212],"category_scores_gemma":[0.00057306,0.00013563626,0.00009838668,0.00014907002,0.00013267696,0.000004613889,0.00041546754,0.000117835814,0.00002285503],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010714244,0.000010432638,0.000283692,0.00001535414,0.000016862774,8.372854e-7,0.00004504555,0.000044665918,0.5849529,0.0000011565909,0.41448024,0.00013810075],"study_design_scores_gemma":[0.00021650536,0.00041231347,0.031606305,0.00007999915,0.00012344013,0.0000072220055,0.0001704714,0.000037799113,0.026467953,0.000015194775,0.9403412,0.00052160496],"about_ca_topic_score_codex":0.00011683938,"about_ca_topic_score_gemma":0.000107571104,"teacher_disagreement_score":0.558485,"about_ca_system_score_codex":0.0000087246935,"about_ca_system_score_gemma":0.00019229382,"threshold_uncertainty_score":0.55310863},"labels":[],"label_agreement":null},{"id":"W2170999689","doi":"10.1186/2047-217x-1-8","title":"Tissue sampling methods and standards for vertebrate genomics","year":2012,"lang":"en","type":"article","venue":"GigaScience","topic":"Molecular Biology Techniques and Applications","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Zoo; Royal Ontario Museum; University of Toronto","funders":"Chinese Academy of Sciences; National Science Foundation","keywords":"Computational biology; Biology; DNA sequencing; Genome; Genomics; DNA; genomic DNA; RNA; Evolutionary biology; Genetics; Gene","score_opus":0.028127704343869235,"score_gpt":0.41507636471671655,"score_spread":0.3869486603728473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170999689","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13663717,0.001188419,0.8613282,0.00011465412,0.00006031555,0.00020207881,0.0000413869,0.000012773809,0.00041503826],"genre_scores_gemma":[0.48615327,0.00021598348,0.512863,0.00041856422,0.00010864205,0.000090657035,0.000023537928,0.000010272272,0.00011607593],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993927,0.000024020706,0.000087600136,0.00021115449,0.000058712903,0.00022580467],"domain_scores_gemma":[0.99959433,0.000011426415,0.000034350564,0.00019892555,0.0000792281,0.00008175139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094093295,0.00007282763,0.000067830086,0.00001618525,0.00013683774,0.000017033026,0.00013180905,0.000075134805,0.0000040652612],"category_scores_gemma":[0.00012340983,0.00006670358,0.00002398163,0.00005145269,0.00012551234,0.000003877885,0.00009511448,0.0000309217,7.7576374e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004612665,0.000008534194,0.00024086623,0.0000047041717,0.0000034443542,2.0320185e-8,0.000020397549,0.0000018302143,0.96072054,0.0023011197,0.0005004945,0.036193423],"study_design_scores_gemma":[0.000056638826,0.000063044055,0.0002757124,0.0000015106853,0.0000048226993,0.000008146817,0.000010406321,0.000057102618,0.60045797,0.0004138042,0.3985794,0.00007147332],"about_ca_topic_score_codex":0.0000024687924,"about_ca_topic_score_gemma":0.0000017854309,"teacher_disagreement_score":0.3980789,"about_ca_system_score_codex":0.0000140649645,"about_ca_system_score_gemma":0.00006286776,"threshold_uncertainty_score":0.2720093},"labels":[],"label_agreement":null},{"id":"W2178546947","doi":"10.1186/s13742-015-0098-x","title":"Exemplary multiplex bisulfite amplicon data used to demonstrate the utility of Methpat","year":2015,"lang":"en","type":"article","venue":"GigaScience","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Infection and Immunity; National Health and Medical Research Council; State Government of Victoria; University of Queensland; Queensland University of Technology; La Trobe University; Peter MacCallum Cancer Centre; Victorian Cancer Agency; National Breast Cancer Foundation; University of Melbourne; Cancer Research Institute","keywords":"DNA methylation; Bisulfite sequencing; Illumina Methylation Assay; Bisulfite; Amplicon; Massive parallel sequencing; Biology; Computational biology; Multiplex; Epigenetics; Methylated DNA immunoprecipitation; DNA sequencing; Methylation; Genetics; DNA; Gene; Polymerase chain reaction; Gene expression","score_opus":0.2228141854584456,"score_gpt":0.3689320310071647,"score_spread":0.1461178455487191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2178546947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9754369,0.0005663831,0.02271767,0.00025635798,0.00013129624,0.00019480553,0.00006478795,0.0000059868466,0.0006257677],"genre_scores_gemma":[0.99574393,0.000030750864,0.003921506,0.00012086805,0.000047058427,0.000006030922,0.000057635712,0.0000060694074,0.000066175075],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988884,0.00009241589,0.00019001115,0.00039680247,0.00024375539,0.00018863475],"domain_scores_gemma":[0.9985365,0.000031734227,0.00007782453,0.0010970794,0.0001208923,0.00013594437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013121604,0.00009033876,0.00009677414,0.000026957377,0.000069519956,0.000027579337,0.00082047813,0.00005786555,0.0000071768495],"category_scores_gemma":[0.00054881163,0.00006500992,0.000028424898,0.00022913102,0.00018922336,0.0000091840175,0.0004776234,0.000049132657,0.0000074913746],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002548016,0.00002602211,0.01788951,0.0000033703732,0.000005678012,4.3380493e-7,0.00011875338,0.00009291315,0.97059137,0.0000128277625,0.00068283366,0.010550805],"study_design_scores_gemma":[0.00023517487,0.00015972211,0.050290152,0.0000062992012,0.000009984478,0.0000019112083,0.00013398229,0.0029527738,0.9256773,0.00027185475,0.020131145,0.00012970762],"about_ca_topic_score_codex":0.00013051444,"about_ca_topic_score_gemma":0.00016378041,"teacher_disagreement_score":0.044914078,"about_ca_system_score_codex":0.00000399188,"about_ca_system_score_gemma":0.00013781083,"threshold_uncertainty_score":0.26510274},"labels":[],"label_agreement":null},{"id":"W2335271347","doi":"10.1186/s13742-016-0121-x","title":"Brainhack: a collaborative workshop for the open neuroscience community","year":2016,"lang":"en","type":"review","venue":"GigaScience","topic":"Biomedical and Engineering Education","field":"Engineering","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Baycrest Hospital; Ontario Institute for Cancer Research; McGill University; University of Toronto; University Health Network; Montreal Neurological Institute and Hospital; Université de Montréal; Polytechnique Montréal; Institut Universitaire de Gériatrie de Montréal","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute on Alcohol Abuse and Alcoholism; Centre d'Imagerie BioMédicale; Wellcome Trust; Agence Nationale de la Recherche; Child Mind Institute; Réseau en Bio-Imagerie du Quebec; Wellcome; Ontario Brain Institute; Microsoft Azure; National Institutes of Health; Amazon Web Services; Frontiers Clinical and Translational Science Institute, University of Kansas; Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital","keywords":"Open science; Computer science; Data science; Neuroscience; World Wide Web; Cognitive science; Psychology","score_opus":0.11557639374539015,"score_gpt":0.38047957248462133,"score_spread":0.2649031787392312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2335271347","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.944025e-7,0.96451455,0.030784387,0.00029891398,0.0022396487,0.001139197,0.00009037967,0.00013129812,0.0008006315],"genre_scores_gemma":[0.000056084038,0.99784094,0.00046261263,0.000106875705,0.00014061626,0.00064686517,0.000007539987,0.00002865159,0.0007097863],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989293,0.00007175546,0.000245163,0.00022553986,0.00018356969,0.00034464887],"domain_scores_gemma":[0.9980262,0.0011512724,0.00006118502,0.00059416256,0.000052116742,0.000115065974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010045985,0.00022791495,0.00041670862,0.00006656462,0.00043685193,0.0002709884,0.0028312067,0.00011826867,0.000013833902],"category_scores_gemma":[0.0005267207,0.00012013508,0.00009202597,0.001168181,0.0003556827,0.00023758438,0.00029955452,0.0003902842,0.000027199538],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.497864e-7,0.000010482462,2.6292959e-8,0.0018053647,0.0000067117285,2.038751e-7,0.00016827277,0.000033740565,0.000009451603,0.00040282353,0.012145858,0.9854167],"study_design_scores_gemma":[0.000042004267,0.000015578507,0.0000045905367,0.0026046194,0.000026598653,0.00000602516,0.000038875616,0.0007883036,0.000002234092,0.00008002344,0.9962127,0.00017844117],"about_ca_topic_score_codex":0.0000064530905,"about_ca_topic_score_gemma":0.000008219073,"teacher_disagreement_score":0.98523825,"about_ca_system_score_codex":0.0001033063,"about_ca_system_score_gemma":0.00030124566,"threshold_uncertainty_score":0.52611333},"labels":[],"label_agreement":null},{"id":"W2406165027","doi":"10.1186/s13742-016-0126-5","title":"Introducing BASE: the Biomes of Australian Soil Environments soil microbial diversity database","year":2016,"lang":"en","type":"article","venue":"GigaScience","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":246,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Directorate for Biological Sciences; Western Sydney University; Department of Economic Development, Jobs, Transport and Resources; Murdoch University; Hawkesbury Institute for the Environment, Western Sydney University; University of New South Wales; Monash University; La Trobe University; Cotton Research and Development Corporation; Commonwealth Scientific and Industrial Research Organisation; Australian Government; Science and Industry Endowment Fund; ACT Government; University of Queensland; Department of Economic Development, Jobs, Transport and Resources, State Government of Victoria; James Cook University; South Australian Grain Industry Trust Fund","keywords":"Biome; Diversity (politics); Soil microbiology; Environmental science; Base (topology); Database; Soil science; Ecology; Computer science; Soil water; Biology; Ecosystem; Mathematics","score_opus":0.01653282813234212,"score_gpt":0.21614878979457408,"score_spread":0.19961596166223197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406165027","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99636185,0.000005284603,0.0005079718,0.0023517876,0.00022008197,0.00009994515,0.00006300213,0.0000102741915,0.0003798057],"genre_scores_gemma":[0.9977578,0.000028855631,0.0003787156,0.0003505273,0.000027931415,0.0000020396715,0.0000065727313,0.0000038032456,0.0014437777],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988036,0.00020473471,0.00016112809,0.00032650793,0.0001652645,0.0003387643],"domain_scores_gemma":[0.9990184,0.00014556282,0.00011143666,0.0006502562,0.000003757963,0.00007063681],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006824071,0.000114295566,0.00012711094,0.000028017064,0.00072102196,0.0000078314315,0.0011471526,0.000056027264,0.0047517247],"category_scores_gemma":[0.00007947755,0.000068447785,0.000050200757,0.00020997596,0.0022515764,0.00028383295,0.0023281637,0.00012564052,0.00054898974],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001648793,0.000060522703,0.017873751,0.0000024343415,0.0000046940268,0.0000016152999,0.00038304,0.00019201079,0.97040313,0.00003728001,0.009552916,0.0014721031],"study_design_scores_gemma":[0.0008044411,0.00021483039,0.17754047,0.000037509337,0.000035566463,0.000025184936,0.0002534125,0.00007599101,0.78805697,0.0010669846,0.031486105,0.000402556],"about_ca_topic_score_codex":0.0010611363,"about_ca_topic_score_gemma":0.0010960373,"teacher_disagreement_score":0.1823462,"about_ca_system_score_codex":0.00008595007,"about_ca_system_score_gemma":0.000016519816,"threshold_uncertainty_score":0.99615806},"labels":[],"label_agreement":null},{"id":"W2415150137","doi":"10.1186/s13742-016-0128-3","title":"Transcriptome sequences spanning key developmental states as a resource for the study of the cestode <i>Schistocephalus solidus</i> , a threespine stickleback parasite","year":2016,"lang":"en","type":"article","venue":"GigaScience","topic":"Parasite Biology and Host Interactions","field":"Environmental Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Stickleback; Gasterosteus; Biology; Cestoda; Key (lock); Parasite hosting; Transcriptome; Zoology; Evolutionary biology; Ecology; Fish <Actinopterygii>; Fishery; Gene; Computer science; Helminths; Genetics; World Wide Web","score_opus":0.022304080336991897,"score_gpt":0.3063321583073012,"score_spread":0.2840280779703093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2415150137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9942355,0.000066333276,0.0016221629,0.0014856126,0.00021190665,0.0007147604,0.000026167734,0.000023378449,0.0016141454],"genre_scores_gemma":[0.9968987,0.000012672714,0.00044641463,0.00046902138,0.00002064469,0.00008252895,7.5442597e-7,0.000007131329,0.002062142],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9985416,0.00008875634,0.00027175763,0.00039116835,0.00035001052,0.0003567354],"domain_scores_gemma":[0.99909294,0.00037115172,0.00015434167,0.00029640744,0.000017058388,0.00006812928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052123953,0.00015440943,0.00014455746,0.000025274327,0.0008249994,0.00002795218,0.0009653311,0.00003976428,0.00023625224],"category_scores_gemma":[0.00013610657,0.00007024383,0.00007262983,0.00032441554,0.0011648453,0.00028144426,0.00015586868,0.00010396605,0.00009220707],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021613919,0.0004366439,0.41286254,0.0000056418085,0.00005433992,0.000004630733,0.024139935,0.0017906921,0.5477118,0.00031973148,0.0016679363,0.010789984],"study_design_scores_gemma":[0.0013799786,0.0010803347,0.88366425,0.000096652235,0.00009442938,0.00010862841,0.010226523,0.00042565257,0.031082874,0.0009939157,0.070410125,0.0004366434],"about_ca_topic_score_codex":0.0004729859,"about_ca_topic_score_gemma":0.0011171673,"teacher_disagreement_score":0.5166289,"about_ca_system_score_codex":0.000119590826,"about_ca_system_score_gemma":0.000056884102,"threshold_uncertainty_score":0.6345312},"labels":[],"label_agreement":null},{"id":"W2525962615","doi":"10.1186/s13742-016-0145-2","title":"A picture is worth a thousand data points: an imagery dataset of paired shrub-open microsites within the Carrizo Plain National Monument","year":2016,"lang":"en","type":"article","venue":"GigaScience","topic":"Amphibian and Reptile Biology","field":"Environmental Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"U.S. Bureau of Land Management; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Nature Conservancy","keywords":"Shrub; Endangered species; Habitat; Ecology; Vegetation (pathology); Geography; National park; Understory; Threatened species; Leopard; Lizard; Cloud forest; Biology; Canopy","score_opus":0.03505645089221978,"score_gpt":0.2836897823958264,"score_spread":0.24863333150360659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2525962615","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98056185,0.00008916172,0.001332915,0.004793184,0.0002337811,0.000696812,0.010929407,0.00003154662,0.0013313112],"genre_scores_gemma":[0.99267644,0.000016293057,0.0039493106,0.0025267971,0.00003876944,0.000012333529,0.00029246227,0.00000775128,0.00047985913],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99829245,0.00012107379,0.00026140347,0.00063743605,0.00043502197,0.00025260894],"domain_scores_gemma":[0.9986213,0.00008108664,0.00018680065,0.0009928716,0.00001395763,0.000103994615],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013756275,0.00013047057,0.0001365563,0.0000227601,0.00023647942,0.00007115657,0.0027144975,0.000052126983,0.0009331013],"category_scores_gemma":[0.00012082101,0.00006230119,0.000022186488,0.00022133124,0.0013440264,0.0008311259,0.0018997706,0.00006987739,0.000112314505],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012612663,0.00028850345,0.15501538,0.00000876659,0.000028356959,0.000014386007,0.0027463979,0.000054537053,0.62250143,0.00036421925,0.20833832,0.010513572],"study_design_scores_gemma":[0.0034255104,0.0010299815,0.6184388,0.00027923973,0.000085949585,0.0003155151,0.002784694,0.00597575,0.12743935,0.007702161,0.23069024,0.0018328371],"about_ca_topic_score_codex":0.00027291648,"about_ca_topic_score_gemma":0.00046830703,"teacher_disagreement_score":0.49506208,"about_ca_system_score_codex":0.00006272465,"about_ca_system_score_gemma":0.00008270235,"threshold_uncertainty_score":0.99998015},"labels":[],"label_agreement":null},{"id":"W2592740179","doi":"10.1093/gigascience/gix012","title":"RED-ML: a novel, effective RNA editing detection method based on machine learning","year":2017,"lang":"en","type":"article","venue":"GigaScience","topic":"RNA regulation and disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Shenzhen Peacock Plan","keywords":"Computer science; Artificial intelligence; Machine learning; Computational biology; Information retrieval; Biology","score_opus":0.00987373618343957,"score_gpt":0.2913332919219214,"score_spread":0.28145955573848186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592740179","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58527744,0.00003519934,0.4058648,0.0004572208,0.00041392475,0.000239036,0.000007878783,0.00003752362,0.0076669566],"genre_scores_gemma":[0.99571985,0.0000017455674,0.0034982616,0.0002468992,0.00019048364,0.000018359222,0.000008424721,0.0000085599,0.0003074309],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992049,0.000060454102,0.000080225735,0.00032985208,0.00016347232,0.00016112658],"domain_scores_gemma":[0.9993604,0.000022488359,0.00012722625,0.0003421001,0.00005509543,0.000092718685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004493408,0.00009028973,0.00006699255,0.00003719606,0.000528449,0.00009467887,0.00021253354,0.0000557176,0.000011486236],"category_scores_gemma":[0.0011806876,0.00008246028,0.00005935002,0.000050708615,0.00009068018,0.0000101305895,0.0000666147,0.0000837068,0.0000069381176],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062970415,0.000028080387,0.0028311044,0.0000051356233,0.0000031214163,0.0000015344066,0.000009904711,0.006397427,0.95243394,0.000022634236,0.000028225975,0.038175933],"study_design_scores_gemma":[0.0007849497,0.00033180555,0.071589366,0.00002182743,0.000009818856,0.0000049429354,0.000014873267,0.27581814,0.6457644,0.000031425916,0.0054644747,0.00016395758],"about_ca_topic_score_codex":0.000029015144,"about_ca_topic_score_gemma":0.000017555218,"teacher_disagreement_score":0.41044238,"about_ca_system_score_codex":0.000014618669,"about_ca_system_score_gemma":0.00003354191,"threshold_uncertainty_score":0.4064456},"labels":[],"label_agreement":null},{"id":"W2606235571","doi":"10.1186/s13742-016-0147-0-f","title":"Automatic extraction of academic collaborations in neuroimaging","year":2016,"lang":"en","type":"article","venue":"GigaScience","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Neuroimaging; Computer science; Extraction (chemistry); Data science; Artificial intelligence; Neuroscience; Chemistry; Psychology; Chromatography","score_opus":0.5944381460399508,"score_gpt":0.6029800787514076,"score_spread":0.008541932711456757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606235571","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98375344,0.000121073506,0.011040674,0.0026184965,0.0003377526,0.00013200061,0.000009262607,0.00001606324,0.0019712357],"genre_scores_gemma":[0.99812186,0.00009239544,0.0011011523,0.00005281965,0.000014874113,0.0000066354964,9.0871545e-8,0.0000029404011,0.00060723],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9935879,0.00015645393,0.0006396765,0.00046366127,0.0047818045,0.00037052075],"domain_scores_gemma":[0.9942276,0.003791206,0.00024873376,0.00046404044,0.0011081434,0.00016027219],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.0143781165,0.00006711669,0.00015533765,0.027151326,0.000102669655,0.00028676842,0.0016849615,0.00004895034,0.0003158183],"category_scores_gemma":[0.04826321,0.00003836458,0.000038944454,0.17092937,0.0003316453,0.0015562654,0.0002478787,0.00013443503,0.0001849842],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028601637,0.000045422825,0.2983263,0.0000021564888,5.856857e-7,0.000005105941,0.00013568423,0.000038103055,0.2883255,0.0018880909,0.0014084658,0.40982172],"study_design_scores_gemma":[0.0002965362,0.000059186314,0.94877636,0.000030903575,0.000001009468,0.000009228966,0.00025334323,0.021324234,0.015505826,0.01107083,0.0025704664,0.00010206703],"about_ca_topic_score_codex":0.000027774571,"about_ca_topic_score_gemma":0.000017008959,"teacher_disagreement_score":0.65045005,"about_ca_system_score_codex":0.00008683061,"about_ca_system_score_gemma":0.00033457816,"threshold_uncertainty_score":0.9838751},"labels":[],"label_agreement":null},{"id":"W2736993784","doi":"10.1093/gigascience/gix053","title":"An expanded mammal mitogenome dataset from Southeast Asia","year":2017,"lang":"en","type":"article","venue":"GigaScience","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Ontario Museum","funders":"Leibniz-Gemeinschaft; H. Lundbeck A/S; Deutsches Primatenzentrum; Lundbeckfonden; Bundesministerium für Bildung und Forschung","keywords":"Threatened species; Biodiversity; Mammal; Mitochondrial DNA; DNA barcoding; Taxon; Range (aeronautics); Evolutionary biology; Biology; Identification (biology); Barcode; Environmental DNA; DNA sequencing; Ecology; Geography; Habitat; Computer science; DNA; Genetics","score_opus":0.024321911275661773,"score_gpt":0.24674313759422833,"score_spread":0.22242122631856656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736993784","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920131,0.000022894761,0.00010017687,0.00021494913,0.0002978904,0.00012788622,0.0016630889,0.000032031076,0.005528007],"genre_scores_gemma":[0.99248487,0.000015726897,0.0069597885,0.00014358315,0.00006803973,0.0000060624775,0.00013104544,0.000006710869,0.00018416104],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9983412,0.000032722015,0.000119765704,0.00055854244,0.00050509226,0.00044265692],"domain_scores_gemma":[0.99839497,0.000019205645,0.000119641474,0.0012181611,0.0000017081791,0.0002463454],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00023621622,0.00016258979,0.00012926018,0.000015764235,0.0015421147,0.00018375592,0.0017806601,0.000047182977,0.0015012006],"category_scores_gemma":[0.00004945918,0.00015059182,0.000036029407,0.000048038164,0.0016310348,0.0013436264,0.001267257,0.000094954994,0.0038945014],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007854656,0.00008023299,0.95392686,6.1409946e-7,0.000004565259,0.000010918154,0.00039155097,0.00002174275,0.039829794,0.000012640126,0.0041357796,0.0015774519],"study_design_scores_gemma":[0.00018256712,0.000048348444,0.9858178,0.0000037114203,0.000010419333,0.0000034771192,0.00087677245,0.00006765129,0.0045587365,0.000097764685,0.008120001,0.00021276684],"about_ca_topic_score_codex":0.0015394818,"about_ca_topic_score_gemma":0.00012640648,"teacher_disagreement_score":0.03527106,"about_ca_system_score_codex":0.00010870722,"about_ca_system_score_gemma":0.0000028024551,"threshold_uncertainty_score":0.99975777},"labels":[],"label_agreement":null},{"id":"W2745619054","doi":"10.1093/gigascience/gix073","title":"Positive and relaxed selection associated with flight evolution and loss in insect transcriptomes","year":2017,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Ontario; Chinese Universities Scientific Fund; China Agricultural University; University of Guelph","keywords":"Biology; Nonsynonymous substitution; Gene; Evolutionary biology; Selection (genetic algorithm); Genetics; Insect flight; Negative selection; Insect; Transcriptome; Computational biology; Genome; Gene expression; Ecology","score_opus":0.008354393732964389,"score_gpt":0.21600738198682057,"score_spread":0.20765298825385617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2745619054","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99862057,0.00061442115,0.0001674403,0.00015038215,0.000034159144,0.0000817839,0.0000062155395,0.0000014596288,0.000323544],"genre_scores_gemma":[0.9995484,0.00019685636,0.00011038339,0.000030292551,0.000014716305,0.0000058309247,0.0000018662292,0.0000036395359,0.00008805255],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99951214,0.000019872969,0.000057767054,0.0002269745,0.000055585533,0.00012766472],"domain_scores_gemma":[0.9997881,0.000006280999,0.000047133522,0.00009093836,0.000038163074,0.000029358353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014024126,0.00006738249,0.000070409274,0.000023285898,0.00026830594,0.000038905844,0.000072859904,0.000045430683,3.3936794e-7],"category_scores_gemma":[0.00006382631,0.00005660599,0.000009036254,0.000042441614,0.0002565762,0.0000032329663,0.0000401234,0.00003631436,1.4298459e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027767088,0.00001252758,0.46712628,0.0000020418113,0.0000111053605,0.0000012579103,0.00019859773,0.000007160922,0.5319542,0.00008879532,0.000006866622,0.00056338176],"study_design_scores_gemma":[0.0003747843,0.00024595682,0.97632265,0.000014623407,0.000006396565,0.000014059428,0.000034372704,0.00009033097,0.022583926,0.00015171296,0.00007764123,0.00008353211],"about_ca_topic_score_codex":0.00012286977,"about_ca_topic_score_gemma":0.0010102877,"teacher_disagreement_score":0.50937027,"about_ca_system_score_codex":0.000012882058,"about_ca_system_score_gemma":0.00002943979,"threshold_uncertainty_score":0.23083253},"labels":[],"label_agreement":null},{"id":"W2747802896","doi":"10.1093/gigascience/gix085","title":"<i>De novo</i> PacBio long-read and phased avian genome assemblies correct and add to reference genes generated with intermediate and short reads","year":2017,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":266,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Howard Hughes Medical Institute","keywords":"Genome; Gene; Biology; Computational biology; Genetics; Computer science","score_opus":0.020812918337313406,"score_gpt":0.2666273901343261,"score_spread":0.2458144717970127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2747802896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9964213,0.002012653,0.0005887715,0.00013680605,0.00007007546,0.00016295849,0.000053626805,0.0000044868093,0.0005493558],"genre_scores_gemma":[0.9967314,0.0016356577,0.001034665,0.00028313353,0.000069447255,0.000021534208,0.000009852725,0.000012158326,0.00020217973],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989317,0.000021206382,0.00011770292,0.0005332255,0.00009451814,0.00030163818],"domain_scores_gemma":[0.99927425,0.000010817313,0.000059150625,0.00037976872,0.00008427099,0.00019173865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020146198,0.00018189821,0.0001698879,0.000036394442,0.0004219993,0.00024100552,0.00025197907,0.000066291905,0.0000022364597],"category_scores_gemma":[0.000058030677,0.00014645474,0.000012827447,0.000046332978,0.00052777724,0.000005447948,0.00027310452,0.000054961834,7.1782205e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052780084,0.000011644602,0.095692046,0.000009509619,0.000019080948,0.0000072530515,0.0001654482,0.0000058767205,0.89325386,0.000011717012,0.000024584591,0.0107461875],"study_design_scores_gemma":[0.00047107282,0.00091748114,0.79303837,0.00002891495,0.00003371826,0.00014467114,0.00014286122,0.000049923034,0.19849333,0.00002064923,0.0062615704,0.00039740582],"about_ca_topic_score_codex":0.0000581947,"about_ca_topic_score_gemma":0.0005144251,"teacher_disagreement_score":0.6973463,"about_ca_system_score_codex":0.000007170193,"about_ca_system_score_gemma":0.00006309436,"threshold_uncertainty_score":0.59722507},"labels":[],"label_agreement":null},{"id":"W2749046585","doi":"10.1093/gigascience/gix077","title":"The sponge microbiome project","year":2017,"lang":"en","type":"article","venue":"GigaScience","topic":"Marine Sponges and Natural Products","field":"Biochemistry, Genetics and Molecular Biology","cited_by":257,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"John Templeton Foundation; Gordon and Betty Moore Foundation; W. M. Keck Foundation; Howard Hughes Medical Institute","keywords":"Biology; Microbiome; Sponge; Phylum; 16S ribosomal RNA; Metagenomics; Clade; Taxon; Environmental DNA; Microbial ecology; Evolutionary biology; UniFrac; Phylogenetics; Ecology; Computational biology; Biodiversity; Gene; Genetics; Paleontology; Bacteria","score_opus":0.013937566657037588,"score_gpt":0.29454210247841,"score_spread":0.2806045358213724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2749046585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9877493,0.0006158984,0.000017504448,0.0020555134,0.00053366425,0.00015985091,0.00000433068,0.000007745992,0.008856227],"genre_scores_gemma":[0.9850095,0.00022768325,0.00022393272,0.00012608842,0.00021756486,0.000005295107,0.000003934069,0.0000046779865,0.014181304],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993561,0.000014521309,0.000066230175,0.00026172042,0.000085446474,0.00021599056],"domain_scores_gemma":[0.9990682,0.0000046040313,0.00006744936,0.00078164774,0.000048691716,0.000029405639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003505389,0.00006928301,0.000042864478,0.000010834568,0.00095017784,0.00017543873,0.0008435521,0.000035392604,0.0000036691226],"category_scores_gemma":[0.00029251826,0.000041586416,0.000035868423,0.00003922519,0.0003466684,0.000006026117,0.00036857204,0.000053946733,0.000015364123],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023596189,0.000009556517,0.0015033941,0.0000037262323,0.000005328034,0.0000022435142,0.000012721131,4.024107e-7,0.95607847,0.00038507482,0.009481613,0.032493856],"study_design_scores_gemma":[0.00013482584,0.00009492193,0.037158534,0.0000036692918,0.0000027246456,0.000027345726,0.000013445852,0.000016820006,0.22516663,0.000089788926,0.7371689,0.00012237263],"about_ca_topic_score_codex":0.00005425344,"about_ca_topic_score_gemma":0.0000742833,"teacher_disagreement_score":0.73091185,"about_ca_system_score_codex":0.0000038038079,"about_ca_system_score_gemma":0.00006152529,"threshold_uncertainty_score":0.73080957},"labels":[],"label_agreement":null},{"id":"W2766113466","doi":"10.1093/gigascience/gix101","title":"LAGOS-NE: a multi-scaled geospatial and temporal database of lake ecological context and water quality for thousands of US lakes","year":2017,"lang":"en","type":"article","venue":"GigaScience","topic":"Fish Ecology and Management Studies","field":"Environmental Science","cited_by":151,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Water quality; Geospatial analysis; Context (archaeology); Database; Environmental science; Lake ecosystem; Ecology; Hydrology (agriculture); Ecosystem; Geography; Remote sensing; Computer science; Geology; Biology","score_opus":0.03614684440999965,"score_gpt":0.2977309115800397,"score_spread":0.26158406717004007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766113466","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99777424,0.000010331422,0.000797469,0.0004453179,0.00007326422,0.00028375833,0.00007006529,0.000007781512,0.00053778465],"genre_scores_gemma":[0.99706846,0.000031554093,0.0023523874,0.00017413232,0.000006841862,0.000025528147,0.0000047629437,0.0000022643037,0.0003340506],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99916136,0.000034631597,0.00018953656,0.00029020666,0.00011855298,0.00020570486],"domain_scores_gemma":[0.9994847,0.00008198884,0.00013719969,0.00023731087,0.000012294844,0.00004650941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00080685795,0.00008595114,0.00020681939,0.000014351173,0.0004327466,0.00001940487,0.00026234146,0.000043068838,0.00013313125],"category_scores_gemma":[0.00025150125,0.000057128505,0.000024744091,0.000020564727,0.0020162384,0.00026216535,0.00072456844,0.000041467105,0.000003170027],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048326212,0.00010547017,0.99349886,0.000038664843,0.0000074983345,0.0000017841676,0.0003309384,0.0000032330088,0.0040551885,0.00012774226,0.00043022356,0.0013520834],"study_design_scores_gemma":[0.0008121953,0.00016480226,0.9945827,0.0000071942327,0.000013753447,9.557546e-7,0.00014563395,0.0004168084,0.0021759365,0.00014910373,0.001448107,0.000082788174],"about_ca_topic_score_codex":0.00027495212,"about_ca_topic_score_gemma":0.041470513,"teacher_disagreement_score":0.04119556,"about_ca_system_score_codex":0.000006046459,"about_ca_system_score_gemma":0.000004042728,"threshold_uncertainty_score":0.97602016},"labels":[],"label_agreement":null},{"id":"W2774363476","doi":"10.1093/gigascience/gix121","title":"The intriguing evolution of effect sizes in biomedical research over time: smaller but more often statistically significant","year":2017,"lang":"en","type":"article","venue":"GigaScience","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Centre Hospitalier Universitaire de Toulouse; Université de Toulouse; Agence Nationale de la Recherche","keywords":"Computer science; Data science; Computational biology; Biology","score_opus":0.58753692297953,"score_gpt":0.5720309981907186,"score_spread":0.01550592478881141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774363476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9760871,0.00038326802,0.015214737,0.00335192,0.00030106996,0.00095244305,0.00002303544,0.00000420176,0.0036822085],"genre_scores_gemma":[0.99449736,0.000013501481,0.0017590552,0.000024628409,0.000045504567,0.000033877954,6.90569e-7,0.000004971134,0.0036204387],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9754773,0.008144789,0.0041972734,0.0009941491,0.010590788,0.00059570157],"domain_scores_gemma":[0.9740327,0.018569645,0.0019619341,0.0041455165,0.0010846247,0.0002056072],"candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.25489786,0.00016579943,0.0013518856,0.00039159792,0.0008987576,0.0013730476,0.0053308927,0.00007980957,0.0010942076],"category_scores_gemma":[0.25809872,0.000065281034,0.0003652243,0.0013723463,0.00241874,0.00030942986,0.000610199,0.00029938002,0.00095382775],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021714886,0.00041296307,0.29783598,0.00024355167,0.00019833274,0.00014140124,0.0026650948,0.00017832378,0.10746187,0.047775976,0.15861502,0.38425434],"study_design_scores_gemma":[0.00049751747,0.00034437742,0.84729105,0.00019739552,0.000048768514,0.000007337554,0.0006201807,0.11364529,0.00060179667,0.02213624,0.014366309,0.00024376293],"about_ca_topic_score_codex":0.00025485276,"about_ca_topic_score_gemma":0.00005011749,"teacher_disagreement_score":0.54945505,"about_ca_system_score_codex":0.00009612659,"about_ca_system_score_gemma":0.00029144197,"threshold_uncertainty_score":0.99982405},"labels":[],"label_agreement":null},{"id":"W2791824528","doi":"10.1093/gigascience/giy016","title":"Boutiques: a flexible framework to integrate command-line applications in computing platforms","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Compute Canada; Institut Universitaire de Gériatrie de Montréal; McGill University; Montreal Neurological Institute and Hospital; Concordia University","funders":"CHIST-ERA; Compute Canada; McGill University","keywords":"Computer science; JSON; Neuroinformatics; Software engineering; Software; Domain (mathematical analysis); Redundancy (engineering); Set (abstract data type); World Wide Web; Data science; Operating system; Programming language","score_opus":0.16361345235278488,"score_gpt":0.460288796668139,"score_spread":0.29667534431535414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791824528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33823648,0.000015275797,0.6546104,0.0007277039,0.00059257186,0.00031386619,0.000008763977,0.00010418911,0.0053907507],"genre_scores_gemma":[0.9518326,0.0000012078599,0.045440882,0.0013404494,0.00016676717,0.000016267199,0.0000041902204,0.0000062549534,0.0011913681],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9962689,0.000050477374,0.00070073706,0.0011433796,0.0012749303,0.00056155905],"domain_scores_gemma":[0.9967735,0.00087672414,0.00017283637,0.0016204177,0.00031898392,0.00023757452],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008216657,0.00016009751,0.00024218962,0.0006713135,0.0006004337,0.000904944,0.0029056298,0.00005322122,0.00013138619],"category_scores_gemma":[0.002817924,0.000112778645,0.000056915942,0.0060292147,0.00044365707,0.0004062524,0.0012441485,0.00020994192,0.0014097082],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006126099,0.00045787077,0.07051269,0.0000145484,0.000010807526,0.000012230477,0.021626601,0.0073421155,0.00082725263,0.21380708,0.048707906,0.6366196],"study_design_scores_gemma":[0.00046948445,0.0004708736,0.07935062,0.00035019364,0.0000084177145,0.0000112520565,0.010095049,0.21406333,0.004091174,0.43576884,0.25444365,0.00087711285],"about_ca_topic_score_codex":0.00015718241,"about_ca_topic_score_gemma":0.00031663757,"teacher_disagreement_score":0.63574255,"about_ca_system_score_codex":0.00007275206,"about_ca_system_score_gemma":0.00008517942,"threshold_uncertainty_score":0.99936783},"labels":[],"label_agreement":null},{"id":"W2793054360","doi":"10.1093/gigascience/giy013","title":"10KP: A phylodiverse genome sequencing plan","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Plant Pathogens and Fungal Diseases","field":"Biochemistry, Genetics and Molecular Biology","cited_by":258,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of British Columbia; Dalhousie University","funders":"Government of Jiangxi Province; Natural Environment Research Council; Sight Research UK","keywords":"Genome; Context (archaeology); Biology; Protist; Data science; DNA sequencing; Computational biology; Whole genome sequencing; Evolutionary biology; Computer science; Genetics; Gene","score_opus":0.020087651818708096,"score_gpt":0.2270615127199526,"score_spread":0.2069738609012445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793054360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9909895,0.00015063798,0.0008993236,0.000019721103,0.00013113472,0.00006135014,0.00024043587,0.000015301648,0.007492593],"genre_scores_gemma":[0.99799675,0.000029899616,0.0006719912,0.000511148,0.00027159217,0.0000038175026,0.000043227494,0.0000048819406,0.000466709],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992662,0.000015315236,0.000073459,0.00029136523,0.000117859345,0.00023576533],"domain_scores_gemma":[0.9995876,0.0000030815927,0.00003010478,0.0002192567,0.000050697643,0.00010928268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010480327,0.00008130533,0.000056566576,0.000026124022,0.00015870335,0.000027702408,0.0002441617,0.00004054178,0.0000506234],"category_scores_gemma":[0.0000498904,0.000072603165,0.000039670107,0.00010292843,0.00021658844,0.0000049162472,0.000102638565,0.000027593569,0.00013401115],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013712725,0.000008672865,0.0020717045,0.0000023695968,0.0000034362547,0.000009858589,0.00004414101,0.0000066058915,0.99702895,0.000052951793,0.00045149348,0.00030609855],"study_design_scores_gemma":[0.00085677917,0.0015377044,0.16353281,0.00004178818,0.000047322636,0.00026472472,0.0006613627,0.00084927824,0.61380064,0.00025396422,0.21705675,0.0010968562],"about_ca_topic_score_codex":0.000010217529,"about_ca_topic_score_gemma":0.000014995,"teacher_disagreement_score":0.3832283,"about_ca_system_score_codex":0.000011264222,"about_ca_system_score_gemma":0.00009597065,"threshold_uncertainty_score":0.29606712},"labels":[],"label_agreement":null},{"id":"W2802042505","doi":"10.1093/gigascience/giy050","title":"The long noncoding RNA landscape of neuroendocrine prostate cancer and its clinical implications","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Cancer-related molecular mechanisms research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; Simon Fraser University; Genome British Columbia; University of British Columbia","funders":"Terry Fox Foundation; Prostate Cancer Canada","keywords":"Prostate cancer; RNA; Prostate; Non-coding RNA; Computational biology; Long non-coding RNA; Cancer; Biology; Bioinformatics; Medicine; Internal medicine; Genetics; Gene","score_opus":0.0267332003243016,"score_gpt":0.36597892798983184,"score_spread":0.33924572766553024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802042505","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.992377,0.002150665,0.0022216672,0.0020818254,0.00023486036,0.00027240074,0.000018020228,0.000007765362,0.0006358222],"genre_scores_gemma":[0.995722,0.003330402,0.00009468311,0.0001472132,0.00014063239,0.0000317053,0.0000027821475,0.000008800741,0.00052180036],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990514,0.00004472396,0.00018639813,0.00031306667,0.00014871919,0.00025570198],"domain_scores_gemma":[0.9993071,0.00002777601,0.000077116296,0.0002969176,0.00020187201,0.00008920787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033181967,0.000070365604,0.00007566255,0.000024110255,0.00023234134,0.000032494958,0.00030125258,0.000028604203,0.000006862565],"category_scores_gemma":[0.0002412278,0.00005216075,0.000036473484,0.0002039872,0.0003497267,0.0000053279678,0.0002557818,0.00009497818,0.0000036404174],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000450727,0.000015547856,0.0018458266,0.000007076703,0.00001174247,0.0000016669924,0.000019322433,0.00001463204,0.9700527,0.00050298055,0.000518499,0.026964892],"study_design_scores_gemma":[0.00040251072,0.00045820413,0.012872836,0.000018569008,0.000011273721,0.000035686146,0.00002179746,0.0012407401,0.973871,0.00013586364,0.010819931,0.000111616304],"about_ca_topic_score_codex":0.000012762564,"about_ca_topic_score_gemma":0.00011083939,"teacher_disagreement_score":0.026853276,"about_ca_system_score_codex":0.00000604129,"about_ca_system_score_gemma":0.00016427819,"threshold_uncertainty_score":0.21270536},"labels":[],"label_agreement":null},{"id":"W2803125402","doi":"10.1093/gigascience/giy060","title":"The research data management platform (RDMP): A novel, process driven, open-source tool for the management of longitudinal cohorts of clinical data","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Horizon 2020; Medical Research Council Canada; European Commission; NHS Health Scotland; University of Dundee; Wellcome Trust; Medical Research Council; Wellcome","keywords":"Data management; Computer science; Data science; Data quality; Health informatics; Automatic summarization; Informatics; Scalability; Process (computing); Data as a service; Service (business); Health care; Data mining; Database; Information retrieval; Engineering","score_opus":0.7342223660210825,"score_gpt":0.5977625398701323,"score_spread":0.1364598261509502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803125402","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18552342,0.0004622735,0.76710594,0.00576624,0.007088118,0.009776617,0.0012670415,0.00008957847,0.022920761],"genre_scores_gemma":[0.965811,0.0001659832,0.027729949,0.00012259281,0.00022412885,0.00008425674,0.00006413832,0.000016424128,0.005781509],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.989668,0.00018572247,0.0018487014,0.0024852105,0.005047779,0.0007645957],"domain_scores_gemma":[0.9769253,0.0057430975,0.0008952193,0.015016425,0.0012853073,0.00013463486],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":["sts","open_science"],"category_scores_codex":[0.106121734,0.00017901474,0.00040095078,0.00021574167,0.0018935376,0.0016924377,0.044017747,0.00004312556,0.000045331155],"category_scores_gemma":[0.0041785343,0.00009258573,0.00007148006,0.0033465358,0.0035420693,0.001389566,0.0390308,0.00021245475,0.00006382184],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003175865,0.0005100103,0.0079814065,0.00010509455,0.00023411193,0.0000066812217,0.0003444134,0.0003448574,0.000012169963,0.028922731,0.25382,0.7074009],"study_design_scores_gemma":[0.0012560745,0.00037190126,0.076047674,0.0002788006,0.00012977699,0.000007281029,0.0072083734,0.28543353,0.000087235065,0.007137917,0.621764,0.00027738558],"about_ca_topic_score_codex":0.00007674174,"about_ca_topic_score_gemma":0.00021325861,"teacher_disagreement_score":0.7802876,"about_ca_system_score_codex":0.000024141467,"about_ca_system_score_gemma":0.00020439428,"threshold_uncertainty_score":0.99940586},"labels":[],"label_agreement":null},{"id":"W2804785656","doi":"10.1093/gigascience/giy058","title":"Evidence of evolutionary history and selective sweeps in the genome of Meishan pig reveals its genetic and phenotypic characterization","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Hair Growth and Disorders","field":"Medicine","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Domestication; Biology; Introgression; Gene; Breed; Selective sweep; Genetics; Phenotype; Population; Phenotypic trait; Evolutionary biology; Haplotype; Genotype","score_opus":0.028201343066507317,"score_gpt":0.2518259293404265,"score_spread":0.2236245862739192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804785656","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99455094,0.004285401,0.00026926814,0.00023539012,0.000032408854,0.00023430875,0.0000022203935,0.0000041779517,0.00038590323],"genre_scores_gemma":[0.9990371,0.0003228082,0.0002681204,0.000278887,0.000026359847,0.000007163198,0.0000012221046,0.0000027577407,0.000055586595],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993258,0.000052975764,0.00015398295,0.00016900488,0.00018430727,0.000113931295],"domain_scores_gemma":[0.9995706,0.00006648011,0.00007908954,0.00011845958,0.00012333083,0.00004200841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002657756,0.000052278803,0.00011639619,0.000090007255,0.000036357313,0.0000024379983,0.00008684397,0.000027586842,0.000015871623],"category_scores_gemma":[0.00034788274,0.000041059844,0.000010671817,0.0002849189,0.00046216566,0.00013620194,0.000026396343,0.000046356286,0.0000016372561],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009545431,0.000055812947,0.119852416,0.00017199034,0.000003778609,0.0000019045233,0.008251558,9.403712e-7,0.8669372,0.00025796096,0.00003839884,0.0043325326],"study_design_scores_gemma":[0.00017638007,0.00043423427,0.99744695,0.00012894614,0.000011896294,0.000013509605,0.0001483261,0.00031456992,0.0010237008,0.00016856976,0.00009288402,0.00004000376],"about_ca_topic_score_codex":0.000028737546,"about_ca_topic_score_gemma":0.000012047414,"teacher_disagreement_score":0.87759453,"about_ca_system_score_codex":0.000039031253,"about_ca_system_score_gemma":0.00013377842,"threshold_uncertainty_score":0.17028686},"labels":[],"label_agreement":null},{"id":"W2808748058","doi":"10.1093/gigascience/giy068","title":"High-quality assembly of the reference genome for scarlet sage, <i>Salvia splendens</i>, an economically important ornamental plant","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Ornamental plant; SAGE; Salvia; Plant science; STELLA (programming language); Biology; Botany; Computer science; Artificial intelligence","score_opus":0.02460233219727057,"score_gpt":0.27428363461701427,"score_spread":0.2496813024197437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808748058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99811554,0.00021308595,0.00028060572,0.000092376795,0.00027488958,0.00023950328,0.00056949264,0.0000027847611,0.0002116943],"genre_scores_gemma":[0.99708784,0.000084211824,0.0022218293,0.00028925636,0.00017805822,0.00001930786,0.000029889019,0.000009911751,0.00007967298],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987881,0.00003978281,0.00033365982,0.00043643464,0.0001207977,0.00028122636],"domain_scores_gemma":[0.9990796,0.000016932181,0.00021260435,0.00051837304,0.00009627711,0.00007620831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048035083,0.00013481626,0.0001690532,0.00001579392,0.00019838147,0.000025478043,0.0006003946,0.00006762756,0.000008863416],"category_scores_gemma":[0.000053534397,0.00009924056,0.000078955454,0.000060507617,0.00045325857,0.0000025601078,0.00026461878,0.000042532873,0.0000019928784],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004410851,0.000035220877,0.0065014893,0.0000064710566,0.000018194285,1.4834472e-7,0.00006788949,0.000010269214,0.9923512,0.0005196478,0.00006249362,0.00038287867],"study_design_scores_gemma":[0.00037610845,0.00066395494,0.2630958,0.0000069605226,0.000016576363,0.000008840551,0.000106238236,0.000038990293,0.729665,0.00058868056,0.00522004,0.00021286853],"about_ca_topic_score_codex":0.000068479174,"about_ca_topic_score_gemma":0.0003371253,"teacher_disagreement_score":0.26268622,"about_ca_system_score_codex":0.000016847582,"about_ca_system_score_gemma":0.00013160065,"threshold_uncertainty_score":0.40469128},"labels":[],"label_agreement":null},{"id":"W2810419619","doi":"10.1093/gigascience/giy077","title":"Experimenting with reproducibility: a case study of robustness in bioinformatics","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"H2020 Societal Challenges; National Institute of Biomedical Imaging and Bioengineering; Horizon 2020 Framework Programme; National Institutes of Health; National Institute of Mental Health; Centre National de la Recherche Scientifique; Conny-Maeva Charitable Foundation; Université Paris Diderot; Agence Nationale de la Recherche; Fondation Cognacq-Jay","keywords":"Python (programming language); Computer science; Documentation; Reusability; MATLAB; MIT License; Robustness (evolution); Confusion; Software engineering; Programming language; Source code; Data mining; Software","score_opus":0.19997600909877267,"score_gpt":0.4185576707735836,"score_spread":0.2185816616748109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2810419619","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842541,0.000006501369,0.013384178,0.000057371723,0.00035101752,0.00032293497,0.0000011933683,0.000023807102,0.0015988677],"genre_scores_gemma":[0.9895789,8.1539596e-8,0.010176372,0.000024389545,0.000022234744,0.0000061031815,1.748056e-7,0.0000026073897,0.00018912027],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99613345,0.00012222612,0.00077262276,0.001235115,0.0014592067,0.00027736434],"domain_scores_gemma":[0.9956881,0.00025724096,0.0003000983,0.003341155,0.00034781877,0.00006557939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018595573,0.000094892246,0.00020025633,0.000436769,0.00024119287,0.00030670874,0.0011180862,0.00001406577,0.000041275707],"category_scores_gemma":[0.0031023554,0.00006140682,0.000019912144,0.0037006403,0.0004698765,0.00059231784,0.0007350975,0.00006005401,0.000021948754],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109741726,0.003065133,0.42082113,0.000033762706,0.00002142377,0.001424578,0.18242064,0.022528639,0.0006613702,0.00039660773,0.0025616365,0.36595532],"study_design_scores_gemma":[0.001386039,0.0015561073,0.027875734,0.00007978401,0.0000129669215,0.00059781777,0.45634225,0.50836563,0.002508561,0.00025595992,0.0006384585,0.00038067185],"about_ca_topic_score_codex":0.00055965135,"about_ca_topic_score_gemma":0.0010253837,"teacher_disagreement_score":0.485837,"about_ca_system_score_codex":0.000023378427,"about_ca_system_score_gemma":0.00006861285,"threshold_uncertainty_score":0.6444891},"labels":[],"label_agreement":null},{"id":"W2838664376","doi":"10.1093/gigascience/giy085","title":"A similarity-based approach to leverage multi-cohort medical data on the diagnosis and prognosis of Alzheimer's disease","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute on Aging; National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Sanofi Genzyme; Genentech; National Institutes of Health; IXICO; H. Lundbeck A/S; Servier; Eisai; F. Hoffmann-La Roche; National Institute of Environmental Health Sciences; Northern California Institute for Research and Education; Meso Scale Diagnostics; Teva Pharmaceutical Industries; University of Southern California; Pfizer; Biogen; GlaxoSmithKline; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Michael J. Fox Foundation for Parkinson's Research; Foundation for the National Institutes of Health; Alzheimer's Disease Neuroimaging Initiative; Sanofi; Alzheimer's Association; National Science Foundation","keywords":"Disease; Similarity (geometry); Cohort; Medicine; Leverage (statistics); Correlation; Receiver operating characteristic; Alzheimer's disease; Semantic similarity; Computer science; Artificial intelligence; Machine learning; Pathology; Mathematics","score_opus":0.1383658824148157,"score_gpt":0.3822898632272574,"score_spread":0.24392398081244168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2838664376","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9791939,0.00017481741,0.005029584,0.011778804,0.000051807372,0.001829433,0.00007031942,0.000029701736,0.0018415928],"genre_scores_gemma":[0.9932717,0.00002880453,0.0020117965,0.0043157917,0.000055795288,0.00025274983,0.000020001318,0.000008044932,0.000035304794],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99754786,0.00010411825,0.00017559991,0.00055099744,0.0013048998,0.00031652764],"domain_scores_gemma":[0.9984074,0.0001799511,0.00003735563,0.0006666971,0.00016683244,0.00054174144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001734553,0.00011336602,0.00016422155,0.000100588804,0.0001836166,0.00003993415,0.00056820613,0.00003482393,0.00017842554],"category_scores_gemma":[0.0017770841,0.00006874452,0.00003444689,0.0004700433,0.000929349,0.00009606706,0.00043060968,0.00014851465,0.00002218121],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014049995,0.001684345,0.98304427,0.00005709184,0.000057178142,0.000022958515,0.00013141478,7.078495e-7,0.00021968943,0.00016645786,0.0025543151,0.011921079],"study_design_scores_gemma":[0.00070973154,0.0005816134,0.9738494,0.0001969255,0.00014637297,0.0000029735018,0.00008060998,0.016795084,0.006464204,0.00001495643,0.0010603749,0.00009772302],"about_ca_topic_score_codex":0.000048905404,"about_ca_topic_score_gemma":0.000007399466,"teacher_disagreement_score":0.016794376,"about_ca_system_score_codex":0.0000116278225,"about_ca_system_score_gemma":0.00034657228,"threshold_uncertainty_score":0.34242252},"labels":[],"label_agreement":null},{"id":"W2883121292","doi":"10.1093/gigascience/giy082","title":"Nighres: processing tools for high-resolution neuroimaging","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; Douglas Mental Health University Institute","funders":"","keywords":"Toolbox; Computer science; Neuroimaging; Python (programming language); Leverage (statistics); Data science; Documentation; Image processing; Segmentation; High resolution; Artificial intelligence; Image (mathematics); Programming language; Remote sensing","score_opus":0.07902175696149145,"score_gpt":0.3032714258366896,"score_spread":0.22424966887519815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883121292","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83575046,0.000075406024,0.13897893,0.01567327,0.002391354,0.0008073872,0.000029796325,0.00049753074,0.0057958397],"genre_scores_gemma":[0.9906991,0.0000032055532,0.0030100674,0.005470956,0.00037847567,0.000062769155,5.055333e-7,0.000012806721,0.0003620788],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99825543,0.000046276225,0.00015455931,0.00072089094,0.0003869631,0.00043586048],"domain_scores_gemma":[0.9973264,0.0021378081,0.00008702301,0.00023022734,0.00015742975,0.00006110958],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004008054,0.00012704334,0.00011591717,0.00009667624,0.0012211484,0.0002932861,0.0003792705,0.000025061772,0.000013625416],"category_scores_gemma":[0.01821461,0.00011623875,0.000038932434,0.0006151757,0.00081353914,0.0013070666,0.0001446198,0.000081184204,0.000076064345],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058100104,0.00005861314,0.0002942635,0.000031022842,0.0000013711624,0.000003914803,0.00053822395,0.00009560774,0.924836,0.016362587,0.0056155995,0.052104685],"study_design_scores_gemma":[0.0008685877,0.00080224243,0.015526154,0.00009597722,0.000016453992,0.000067370405,0.00026172897,0.044115722,0.862218,0.020953042,0.05443198,0.0006427048],"about_ca_topic_score_codex":0.00001264785,"about_ca_topic_score_gemma":0.000014021237,"teacher_disagreement_score":0.15494865,"about_ca_system_score_codex":0.000058409132,"about_ca_system_score_gemma":0.000102614955,"threshold_uncertainty_score":0.9900554},"labels":[],"label_agreement":null},{"id":"W2885022976","doi":"10.1093/gigascience/giy094","title":"A near complete, chromosome-scale assembly of the black raspberry (<i>Rubus occidentalis</i>) genome","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Berry genetics and cultivation research","field":"Agricultural and Biological Sciences","cited_by":150,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"","keywords":"Biology; Genome; Sequence assembly; Synteny; Comparative genomics; Genetics; Genomics; Contig; Reference genome; Computational biology; Gene; Transcriptome","score_opus":0.031221027268664894,"score_gpt":0.24622504581234295,"score_spread":0.21500401854367807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885022976","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946453,0.000038065515,0.00000889761,0.001157085,0.00011426545,0.00019480173,0.000039243365,0.00001665926,0.0037856638],"genre_scores_gemma":[0.9985668,0.000011886136,0.00014307517,0.00042675575,0.00014422428,0.0000059583917,0.0000050959256,7.944648e-7,0.00069542613],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99855727,0.00006699323,0.00019897727,0.00029497538,0.0005568792,0.00032488754],"domain_scores_gemma":[0.99940145,0.000057247165,0.000098959244,0.00014267272,0.00019943652,0.000100232624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033300585,0.000096298536,0.00011657769,0.0000075261028,0.00048251954,0.000108830274,0.0009410757,0.000048465477,0.00077160826],"category_scores_gemma":[0.000046773308,0.00003269168,0.00008303601,0.00094609766,0.0012110055,0.0001016457,0.00029915955,0.000090954076,0.00014172115],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004803086,0.000041738418,0.008602832,0.0000023244083,0.0000024151684,3.546273e-7,0.00018405121,0.000009710233,0.9886678,0.00008953307,0.0005190619,0.0018753796],"study_design_scores_gemma":[0.00008398923,0.00020804418,0.9185949,0.000013303906,0.000003187003,0.0000052031337,0.00024984794,0.0007124567,0.05888645,0.00018341765,0.020944146,0.000115082985],"about_ca_topic_score_codex":0.00023094783,"about_ca_topic_score_gemma":0.000585578,"teacher_disagreement_score":0.9297813,"about_ca_system_score_codex":0.000018115054,"about_ca_system_score_gemma":0.000031761352,"threshold_uncertainty_score":0.8448569},"labels":[],"label_agreement":null},{"id":"W2887864821","doi":"10.1186/s13742-016-0147-0-k","title":"Nipype interfaces in CBRAIN","year":2016,"lang":"en","type":"article","venue":"GigaScience","topic":"Characterization and Applications of Magnetic Nanoparticles","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Computer science; Data science","score_opus":0.0045478876074085605,"score_gpt":0.17499535666468158,"score_spread":0.170447469057273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887864821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9916693,0.000028261404,0.0052094823,0.0008757092,0.000059224767,0.000041832194,0.0000016547759,0.000089592715,0.0020249689],"genre_scores_gemma":[0.9992723,0.000024139517,0.00040723526,0.00004212735,0.000008538917,0.000010869145,1.4685409e-7,0.000003176057,0.00023147339],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996896,0.000003649183,0.00007708848,0.000075916636,0.000053621345,0.00010013338],"domain_scores_gemma":[0.99984086,0.00002160739,0.0000059902577,0.000098433324,0.0000064567344,0.000026644337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006894901,0.00003406028,0.000032942982,0.00003860488,0.000012172354,0.000014682965,0.00012800955,0.000010536016,0.0001248294],"category_scores_gemma":[0.000023111648,0.000024092828,0.0000053536246,0.00018478636,0.000047125093,0.00011140045,0.000015234171,0.000014872645,0.00016955203],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.6723557e-7,0.000005828612,0.0014013562,0.0000017849305,2.25299e-7,3.1044243e-7,0.000065343585,0.00009102377,0.92977035,0.0010118338,0.00020674083,0.06744476],"study_design_scores_gemma":[0.00041230448,0.000025065734,0.10337594,0.000059819173,0.0000010585144,0.00000419881,0.00006224416,0.0070053767,0.8611529,0.0016515065,0.026031602,0.00021797833],"about_ca_topic_score_codex":0.0000012801619,"about_ca_topic_score_gemma":0.000007591082,"teacher_disagreement_score":0.101974584,"about_ca_system_score_codex":0.000013432871,"about_ca_system_score_gemma":0.0000047617277,"threshold_uncertainty_score":0.21793048},"labels":[],"label_agreement":null},{"id":"W2888278728","doi":"10.1186/s13742-016-0147-0-w","title":"DIPY: Brain tissue classification","year":2016,"lang":"en","type":"article","venue":"GigaScience","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Brain tissue; Computer science; Computational biology; Artificial intelligence; Neuroscience; Biology","score_opus":0.11838140739627466,"score_gpt":0.4176493103567173,"score_spread":0.29926790296044264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888278728","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09954938,0.00003392893,0.755183,0.13191551,0.00008797674,0.0004185106,0.0000068253153,0.00051240553,0.01229246],"genre_scores_gemma":[0.97453845,0.000025160405,0.019150885,0.0015087416,0.000054951048,0.00003942437,0.0000010314396,0.000006775412,0.0046745823],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99944216,0.0000060867605,0.00008253261,0.0002175413,0.00012653795,0.00012513161],"domain_scores_gemma":[0.9994872,0.00004803807,0.000032200576,0.00032453882,0.000037896098,0.00007008923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009242929,0.000046470166,0.00005602464,0.000035696947,0.000064927975,0.000007350168,0.00011116214,0.000016824957,0.000042313073],"category_scores_gemma":[0.00014191985,0.000028906665,0.000015424912,0.0002026995,0.00015643837,0.00009715597,0.000026530704,0.000035768462,0.00012159728],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025580919,0.000020820673,0.001959257,0.0000022013855,3.6249452e-7,0.0000018908725,0.000011269555,5.9016536e-8,0.86144173,0.016326262,0.005861917,0.11437169],"study_design_scores_gemma":[0.00030707673,0.00013248401,0.13246985,0.000068224086,0.00000716281,0.00008430981,0.000011785922,0.00016054773,0.19430685,0.0112696225,0.66105735,0.0001247335],"about_ca_topic_score_codex":0.0000015312162,"about_ca_topic_score_gemma":3.0992112e-7,"teacher_disagreement_score":0.8749891,"about_ca_system_score_codex":0.000027969143,"about_ca_system_score_gemma":0.000030217061,"threshold_uncertainty_score":0.15629275},"labels":[],"label_agreement":null},{"id":"W2889722799","doi":"10.1093/gigascience/giy108","title":"A draft genome assembly of the Chinese sillago (<i>Sillago sinica</i>), the first reference genome for Sillaginidae fishes","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Genome; Biology; Zoology; Fishery; Genetics; Gene","score_opus":0.01357673040026643,"score_gpt":0.25060409713924314,"score_spread":0.2370273667389767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889722799","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935686,0.0015431072,0.0002458293,0.0014138747,0.00033553163,0.00047931244,0.00009413908,0.0000050669787,0.002314537],"genre_scores_gemma":[0.99738157,0.00026925627,0.0005114694,0.0010420985,0.0003767437,0.000053461536,0.0000056460012,0.000018300001,0.00034147513],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9984668,0.000042334283,0.00031756941,0.00052588223,0.00022941646,0.0004179782],"domain_scores_gemma":[0.99841577,0.00007910551,0.00020756424,0.0009499205,0.00028193963,0.00006567245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048785677,0.0002238388,0.00021630856,0.000024255758,0.00063812814,0.000050080052,0.0013144558,0.00009874831,0.000008249273],"category_scores_gemma":[0.00029872207,0.00012482668,0.00016969602,0.0003189957,0.0010803454,0.0000026746936,0.0006019693,0.00007335603,0.000008454353],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037488568,0.00003434748,0.008367441,0.000020404987,0.00004190893,1.8924013e-7,0.00063625164,0.000093998606,0.98997927,0.0001703644,0.0002837419,0.0003346142],"study_design_scores_gemma":[0.0005648903,0.0008672028,0.69838303,0.000018068238,0.0000456988,0.000019330815,0.0003044847,0.00015928049,0.083745085,0.0005751157,0.21487583,0.00044197153],"about_ca_topic_score_codex":0.000038566624,"about_ca_topic_score_gemma":0.00039430463,"teacher_disagreement_score":0.90623415,"about_ca_system_score_codex":0.000013149254,"about_ca_system_score_gemma":0.00014026387,"threshold_uncertainty_score":0.50902843},"labels":[],"label_agreement":null},{"id":"W2889887734","doi":"10.1093/gigascience/giy111","title":"Metabolomics investigation of dietary effects on flesh quality in grass carp (<i>Ctenopharyngodon idellus</i>)","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Aquaculture Nutrition and Growth","field":"Agricultural and Biological Sciences","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Fundamental Research Funds for the Central Universities; Earmarked Fund for China Agriculture Research System; China Scholarship Council; National Natural Science Foundation of China; McGill University","keywords":"Grass carp; Flesh; Metabolomics; Food science; Biology; Quality (philosophy); Fish <Actinopterygii>; Fishery; Bioinformatics; Physics","score_opus":0.030974890572975596,"score_gpt":0.2599074644378891,"score_spread":0.2289325738649135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889887734","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99741375,0.000075475684,0.000009365152,0.0012205142,0.00012141035,0.00017966729,0.000019748473,0.00003353244,0.00092655467],"genre_scores_gemma":[0.998068,0.00002732155,0.00023482775,0.0014256453,0.00016960649,0.000008601401,0.00002021812,6.1496036e-7,0.000045189863],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99866754,0.0001808041,0.0002695829,0.00033272235,0.00031569984,0.00023365814],"domain_scores_gemma":[0.9993923,0.00020795432,0.00012449578,0.00007594088,0.000095762334,0.00010359007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006010652,0.00011983749,0.00020290342,0.000024914598,0.00012805691,0.000023303906,0.0003079947,0.00007876476,0.000024695464],"category_scores_gemma":[0.00015501278,0.000048744212,0.00006372228,0.0008287014,0.00034210223,0.00019925795,0.000051339754,0.000107026266,0.000032165462],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031352654,0.00004588311,0.027963348,0.000012659492,0.000001833615,0.0000012612554,0.0001818867,0.0000012612545,0.96198523,0.0011554615,0.0002907248,0.00832909],"study_design_scores_gemma":[0.00016002459,0.00031313612,0.7188435,0.000037649672,0.0000036578494,9.630553e-7,0.00007901591,0.000052068208,0.2763563,0.0033922475,0.00064463227,0.000116763666],"about_ca_topic_score_codex":0.00038103672,"about_ca_topic_score_gemma":0.00084955496,"teacher_disagreement_score":0.6908802,"about_ca_system_score_codex":0.000022985048,"about_ca_system_score_gemma":0.000010917637,"threshold_uncertainty_score":0.19877313},"labels":[],"label_agreement":null},{"id":"W2891086312","doi":"10.1093/gigascience/giy114","title":"Chromosome-level genome assembly of the spotted sea bass, <i>Lateolabrax maculatus</i>","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Population and Public Health; King Saud University","keywords":"Lateolabrax; Bass (fish); Genome; Biology; Chromosome; Sea bass; Fishery; Zoology; Genetics; Evolutionary biology; Computational biology; Gene; Fish <Actinopterygii>","score_opus":0.016001671138840264,"score_gpt":0.23112994976235385,"score_spread":0.21512827862351358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891086312","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9964082,0.00044496017,0.00032921572,0.00020403549,0.00033420397,0.00014543033,0.0000755151,0.000003082174,0.0020553372],"genre_scores_gemma":[0.99761033,0.000065202075,0.001115591,0.0005093988,0.00020630324,0.0000066422253,0.0000053874937,0.000011652185,0.00046947118],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989283,0.000035647714,0.00018600195,0.00035305467,0.00020123522,0.00029572455],"domain_scores_gemma":[0.9991088,0.000008287432,0.000107005704,0.0005476509,0.0001671856,0.00006106841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022617461,0.0001353077,0.0001288351,0.000022073149,0.00026443947,0.000024913064,0.00061451393,0.000073288684,0.00001508982],"category_scores_gemma":[0.00006305257,0.00009764107,0.0000927751,0.00026677526,0.0007327364,0.0000014179851,0.00041316927,0.00005362995,0.000011508857],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008323398,0.000019493225,0.010303711,0.0000052891587,0.000019114355,3.8807372e-7,0.00006882546,0.000025516696,0.9887856,0.0001118634,0.00032628138,0.00032559832],"study_design_scores_gemma":[0.00024076653,0.00019367477,0.3350557,0.000008776998,0.000015328096,0.0000140412785,0.00003293925,0.00010045807,0.64111066,0.00010694179,0.022943513,0.00017719166],"about_ca_topic_score_codex":0.000039318908,"about_ca_topic_score_gemma":0.00006759442,"teacher_disagreement_score":0.34767494,"about_ca_system_score_codex":0.00001044902,"about_ca_system_score_gemma":0.00015432261,"threshold_uncertainty_score":0.3981687},"labels":[],"label_agreement":null},{"id":"W2892435532","doi":"10.1093/gigascience/giy120","title":"Chromosomal-level assembly of yellow catfish genome using third-generation DNA sequencing and Hi-C analysis","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":182,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Fundamental Research Funds for the Central Universities; Earmarked Fund for China Agriculture Research System","keywords":"Catfish; Aquaculture; Biology; Germplasm; Genome; Fishery; Sexual dimorphism; Zoology; Genetics; Evolutionary biology; Fish <Actinopterygii>; Gene; Botany","score_opus":0.05134085903561971,"score_gpt":0.2668489330916167,"score_spread":0.215508074055997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892435532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99204016,0.00043265094,0.0069937273,0.00002171724,0.0000925744,0.00006977528,0.000021299531,0.0000019578072,0.00032611316],"genre_scores_gemma":[0.99240786,0.00009752391,0.007097347,0.000093644514,0.0001999691,0.000002515911,0.000009960269,0.0000064709266,0.00008473204],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991206,0.00002584691,0.00017761516,0.00035629055,0.00012532016,0.0001943327],"domain_scores_gemma":[0.9994218,0.000005510949,0.00010372885,0.00025437438,0.00015901735,0.00005559608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024097407,0.00010588309,0.000158449,0.00007046013,0.00018382902,0.000027431133,0.00016011127,0.000059555492,0.000003950381],"category_scores_gemma":[0.000041764164,0.00010083772,0.000059007678,0.0003170291,0.00031683114,0.0000026735008,0.00014274482,0.000025632124,0.0000010116622],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027366243,0.000006788925,0.0056922114,0.000004194511,0.00007353762,4.3926832e-7,0.00025063244,0.00034828915,0.99339736,0.000020523688,0.000012843501,0.00019046637],"study_design_scores_gemma":[0.000119704746,0.00018264455,0.0485581,0.0000037642653,0.00012488615,0.000009431349,0.00012805594,0.006907248,0.9434601,0.00002947473,0.00030767443,0.0001689329],"about_ca_topic_score_codex":0.0001090812,"about_ca_topic_score_gemma":0.000277928,"teacher_disagreement_score":0.049937256,"about_ca_system_score_codex":0.000018994819,"about_ca_system_score_gemma":0.00010395417,"threshold_uncertainty_score":0.4112043},"labels":[],"label_agreement":null},{"id":"W2904144759","doi":"10.1093/gigascience/giy145","title":"Erratum to: The sponge microbiome project","year":2018,"lang":"en","type":"erratum","venue":"GigaScience","topic":"Marine Sponges and Natural Products","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Sponge; Microbiome; Binomial (polynomial); Value (mathematics); Mathematics; Biology; Statistics; Bioinformatics; Paleontology","score_opus":0.01234545571110051,"score_gpt":0.26994094579441824,"score_spread":0.2575954900833177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904144759","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07764388,0.026691867,0.0002986024,0.030926649,0.31942672,0.007429967,0.0010265753,0.00027538973,0.5362804],"genre_scores_gemma":[0.0084630335,0.00060489913,0.00055149186,0.0027247157,0.009055467,0.000046791647,0.0005431663,0.000052191364,0.97795826],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99770945,0.00007148554,0.00022626494,0.0010690943,0.0003274585,0.00059625146],"domain_scores_gemma":[0.99825096,0.000005807899,0.00013602209,0.0012708681,0.00022905055,0.000107281536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006192719,0.00035043957,0.00022374322,0.00011098084,0.00029985182,0.00013080996,0.0016761799,0.00038696348,0.00004963241],"category_scores_gemma":[0.00034923,0.00022434602,0.00013884885,0.0006390371,0.00034412707,0.000005021754,0.0009846987,0.00046726465,0.00020617862],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019926896,0.000014399524,0.0000067337587,0.000024945743,0.000013865786,0.0000031273908,0.00003829735,4.368085e-7,0.04815026,0.00000919189,0.94998676,0.0017320744],"study_design_scores_gemma":[0.00006837462,0.00034944317,0.00040903775,0.000038471255,0.00001548653,0.000051537703,0.000015198778,0.00000697616,0.009780556,0.000018166887,0.98889774,0.00034898936],"about_ca_topic_score_codex":0.00009820077,"about_ca_topic_score_gemma":0.00031456808,"teacher_disagreement_score":0.44167787,"about_ca_system_score_codex":0.000024951465,"about_ca_system_score_gemma":0.0005746489,"threshold_uncertainty_score":0.91485655},"labels":[],"label_agreement":null},{"id":"W2913839917","doi":"10.1093/gigascience/giy164","title":"Genome sequence of <i>Malania oleifera</i>, a tree with great value for nervonic acid production","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Plant biochemistry and biosynthesis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fundamental Research Funds for the Central Universities; Chinese Academy of Sciences","keywords":"Whole genome sequencing; Genome; Value (mathematics); Production (economics); Tree (set theory); Sequence (biology); Biology; Computational biology; Genetics; Computer science; Gene; Mathematics; Machine learning; Combinatorics","score_opus":0.0100501738120856,"score_gpt":0.21269513088483347,"score_spread":0.20264495707274788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913839917","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99829835,0.00014049932,0.00025411785,0.00012684797,0.00009510367,0.00028730746,0.000114846844,0.000010474289,0.0006724319],"genre_scores_gemma":[0.99643,0.00003333354,0.0017103024,0.0000706199,0.00008899634,0.00002184671,0.00008931915,0.000008596947,0.0015470214],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989715,0.000015881154,0.00013401579,0.00047777235,0.00015674099,0.00024407204],"domain_scores_gemma":[0.9993682,0.0000082203,0.00009846156,0.00038113503,0.00008759256,0.000056406396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021518122,0.00013048382,0.00013318226,0.000022823062,0.000058678077,0.000014445963,0.0003125055,0.00008140711,0.000005193862],"category_scores_gemma":[0.000058266618,0.0001004129,0.000056742454,0.00014966799,0.00016022965,0.000009933368,0.000048591166,0.00004105645,0.0000049496007],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001350025,0.000026593048,0.0020015922,0.000055731885,0.000012616143,7.610324e-7,0.000014985306,0.000060363098,0.9972126,0.000027107963,0.00003861963,0.00041401744],"study_design_scores_gemma":[0.00019399005,0.0005026092,0.001858985,0.000031464795,0.000015449466,0.00007245791,0.000022161901,0.000048464837,0.99311453,0.0000145112635,0.0039676554,0.00015773877],"about_ca_topic_score_codex":0.0000052561813,"about_ca_topic_score_gemma":0.000009159873,"teacher_disagreement_score":0.0040980983,"about_ca_system_score_codex":0.000012342696,"about_ca_system_score_gemma":0.00012765893,"threshold_uncertainty_score":0.40947193},"labels":[],"label_agreement":null},{"id":"W2926155048","doi":"10.1093/gigascience/giz019","title":"<i>De novo</i> genome assembly of the white-spotted flower chafer (<i>Protaetia brevitarsis</i>)","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Genome; Biology; Sequence assembly; Metis; Gene; Computational biology; Genetics; World Wide Web; Gene expression; Computer science","score_opus":0.005996281471931252,"score_gpt":0.203950746702157,"score_spread":0.19795446523022572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2926155048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9949583,0.00069617946,0.00015036945,0.00031593832,0.00029442046,0.00026676402,0.000022563105,0.0000025107813,0.0032929562],"genre_scores_gemma":[0.9971442,0.00008077511,0.00048261773,0.0007429566,0.00006762606,0.000012337541,0.0000027141557,0.000011782938,0.0014549393],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989522,0.000037322814,0.00017303997,0.00033378025,0.00017228365,0.00033139158],"domain_scores_gemma":[0.99918926,0.0000078506055,0.00008671017,0.0005713589,0.000092784416,0.00005204403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000315937,0.00012917398,0.00014241562,0.000019847837,0.000097562115,0.000018737646,0.00058893603,0.000067986366,0.000028427661],"category_scores_gemma":[0.000041309017,0.000093996605,0.00011320843,0.00019359148,0.0001636283,0.0000013771158,0.00034664644,0.00006511555,0.000020590305],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010581593,0.000022465489,0.025660917,0.000010872157,0.000014326742,2.1542846e-7,0.00011739201,0.00031220794,0.97349554,0.000058549827,0.00014573707,0.00015119679],"study_design_scores_gemma":[0.0004589292,0.00020351888,0.39244884,0.000021030843,0.000024005389,0.000020268448,0.00012796659,0.00006384938,0.56117946,0.00006376098,0.045084156,0.0003042114],"about_ca_topic_score_codex":0.000007634287,"about_ca_topic_score_gemma":0.0000135213595,"teacher_disagreement_score":0.41231608,"about_ca_system_score_codex":0.000010831665,"about_ca_system_score_gemma":0.0001070406,"threshold_uncertainty_score":0.38330704},"labels":[],"label_agreement":null},{"id":"W2939535658","doi":"10.1093/gigascience/giz029","title":"An efficient and robust laboratory workflow and tetrapod database for larger scale environmental DNA studies","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Kunming Institute of Zoology, Chinese Academy of Sciences; Natural Environment Research Council; State Key Laboratory of Genetic Resources and Evolution; Leibniz-Gemeinschaft; Bureau of International Cooperation, Chinese Academy of Sciences; Chinese Academy of Sciences; Bundesministerium für Bildung und Forschung; Bundesministerium für Bildung und Frauen; National Natural Science Foundation of China; Rijksuniversiteit Groningen; Sight Research UK; Groninger Universiteitsfonds","keywords":"Amplicon; Environmental DNA; Database; Computational biology; Biology; Computer science; Pipeline (software); Workflow; Taxonomic rank; Annotation; DNA extraction; Polymerase chain reaction; Data mining; Genetics; Gene; Ecology","score_opus":0.012672834819084208,"score_gpt":0.22010850399172488,"score_spread":0.20743566917264067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2939535658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99794304,0.00072724523,0.00012260686,0.000137465,0.00016328295,0.00051536807,0.00024697627,0.000031003732,0.00011298383],"genre_scores_gemma":[0.976254,0.00038006337,0.022729946,0.00038896073,0.000018762737,0.00002415094,0.000011181383,0.000011702793,0.00018122341],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982078,0.000038762297,0.0001491554,0.0008005594,0.00039374584,0.00040999678],"domain_scores_gemma":[0.99929595,0.00010070213,0.00006385927,0.00035815925,0.0000032866117,0.00017803579],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045687458,0.00021062836,0.00019786862,0.00003715491,0.00050602114,0.000049942457,0.00027756713,0.0000469214,0.00016814507],"category_scores_gemma":[0.000026160886,0.00018790596,0.000027781833,0.00015200526,0.0015856675,0.00046959962,0.0006578498,0.00008798131,0.00016814019],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020060255,0.00017191179,0.86348116,0.000022481729,0.00001353895,0.0000031000302,0.001310675,0.0012106589,0.1316734,0.000013171581,0.00062556297,0.0014542743],"study_design_scores_gemma":[0.00095381634,0.00039603174,0.9720198,0.000034740915,0.000045503806,0.000008995752,0.005169579,0.0038625065,0.013917971,0.000047376892,0.0029793829,0.00056432653],"about_ca_topic_score_codex":0.000010139704,"about_ca_topic_score_gemma":0.000014520663,"teacher_disagreement_score":0.11775542,"about_ca_system_score_codex":0.00014782789,"about_ca_system_score_gemma":0.0000030189346,"threshold_uncertainty_score":0.76625824},"labels":[],"label_agreement":null},{"id":"W2942737328","doi":"10.1093/gigascience/giz035","title":"Datastorr: a workflow and package for delivering successive versions of 'evolving data' directly into R","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Australian Research Council; Natural Sciences and Engineering Research Council of Canada","keywords":"Workflow; Computer science; Software versioning; Data sharing; Process (computing); Software; Software engineering; Cornerstone; Data science; Data mining; Information retrieval; Database; Programming language","score_opus":0.11171467329020339,"score_gpt":0.38129092102490064,"score_spread":0.26957624773469724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942737328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.75096935,0.00036411497,0.24365489,0.00037218438,0.0019771992,0.00049976277,0.00040557285,0.000049504328,0.0017074227],"genre_scores_gemma":[0.96698815,0.000007641917,0.032332156,0.00006602386,0.000027132037,0.0000032695375,0.00004054086,0.0000046545606,0.00053044414],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971293,0.000056212677,0.0003855548,0.0011421915,0.0009991297,0.0002876045],"domain_scores_gemma":[0.99529475,0.0018051938,0.00023050248,0.0023385244,0.00021185695,0.00011914342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00524648,0.00010597482,0.00021348397,0.00026274731,0.0003187175,0.0004737937,0.0030749585,0.000024350753,0.00012876754],"category_scores_gemma":[0.005033305,0.00008256293,0.000037450605,0.0010980753,0.0002523259,0.0014087007,0.0031391256,0.0000608357,0.000085375716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067701316,0.00013716171,0.042346627,0.000105350904,0.000031824544,0.000009165353,0.003860614,0.00076419616,0.032548763,0.0024118968,0.095917456,0.8217992],"study_design_scores_gemma":[0.0009868358,0.00020469137,0.032869875,0.00028452292,0.000042418804,0.000005928319,0.0040634684,0.8678613,0.0029081644,0.0061089867,0.08412275,0.0005411026],"about_ca_topic_score_codex":0.0001704407,"about_ca_topic_score_gemma":0.00008749374,"teacher_disagreement_score":0.8670971,"about_ca_system_score_codex":0.000022177766,"about_ca_system_score_gemma":0.00007349656,"threshold_uncertainty_score":0.60257},"labels":[],"label_agreement":null},{"id":"W2944508336","doi":"10.1093/gigascience/giz055","title":"A highly predictive signature of cognition and brain atrophy for progression to Alzheimer's dementia","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Dementia and Cognitive Impairment Research","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; Institut Universitaire en Santé Mentale de Québec; Université de Montréal; Institut Universitaire de Gériatrie de Montréal; McGill University; Douglas Mental Health University Institute","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institutes of Health; Northern California Institute for Research and Education; Novartis Pharmaceuticals Corporation; Natural Sciences and Engineering Research Council of Canada; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; Canadian Institutes of Health Research; University of Southern California; National Institute on Aging; Eli Lilly and Company; Bristol-Myers Squibb","keywords":"Dementia; Neuroimaging; Cognition; Atrophy; Alzheimer's disease; Disease; Medicine; Intervention (counseling); Psychology; Clinical psychology; Cognitive psychology; Psychiatry; Internal medicine","score_opus":0.013716139057054532,"score_gpt":0.32150496714065896,"score_spread":0.3077888280836044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2944508336","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9898691,0.0005978541,0.004165328,0.0015160484,0.0000798033,0.0023118057,0.000030244348,0.000021555803,0.0014082292],"genre_scores_gemma":[0.9957365,0.00000863662,0.00347798,0.00050528,0.000030106155,0.000110983055,0.000017016351,0.000007062401,0.000106429885],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988844,0.000024897527,0.00012874368,0.0002984975,0.00042491104,0.0002385718],"domain_scores_gemma":[0.999344,0.000076458084,0.000050920087,0.00011002126,0.00027539747,0.00014324057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035297353,0.00008257226,0.00013872907,0.00012183155,0.00006121642,0.000019375155,0.000079010824,0.00004204129,0.00005527249],"category_scores_gemma":[0.00010720597,0.00006411557,0.00004079208,0.00027251896,0.0001167669,0.0001300325,0.00007524679,0.00007302198,0.000014124561],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012153919,0.0002775895,0.066476725,0.00017639493,0.000258656,0.000006099176,0.0005361594,0.0000025870597,0.88059455,0.00031997307,0.0015950768,0.04854079],"study_design_scores_gemma":[0.0042417645,0.012176175,0.4551239,0.0006305184,0.000562966,0.00001884191,0.00052706857,0.0013772508,0.5217492,0.0007786611,0.002599899,0.00021373529],"about_ca_topic_score_codex":0.0000027456858,"about_ca_topic_score_gemma":6.9159364e-7,"teacher_disagreement_score":0.38864717,"about_ca_system_score_codex":0.0000085608835,"about_ca_system_score_gemma":0.000084032465,"threshold_uncertainty_score":0.2614557},"labels":[],"label_agreement":null},{"id":"W2949355358","doi":"10.1093/gigascience/giz037","title":"GenPipes: an open-source framework for distributed and scalable genomic analyses","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":211,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; McGill University; National Research Council Canada; Compute Canada; McGill University and Génome Québec Innovation Centre; Université de Montréal; Ontario Genomics","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Compute Canada; Genome Canada; Canarie","keywords":"Computer science; Workflow; Scalability; Cloud computing; Genomics; MIT License; Metagenomics; Python (programming language); Software; Software deployment; Data science; Computational biology; Distributed computing; Software engineering; Database; Genome; Operating system; Biology","score_opus":0.0323129437284491,"score_gpt":0.3186136926475547,"score_spread":0.28630074891910556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949355358","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97279185,0.0009932636,0.025410658,0.00008421903,0.0001102325,0.00034685087,0.00007331633,0.000003738707,0.0001858824],"genre_scores_gemma":[0.9823857,0.00014260913,0.016670553,0.00032365567,0.00007366388,0.000028905919,0.000034255823,0.000012759736,0.00032788242],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903977,0.000019791012,0.00012416553,0.00048713817,0.000067961046,0.00026114748],"domain_scores_gemma":[0.9993816,0.000024459627,0.00005984709,0.0003796321,0.0000601268,0.00009433694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021185809,0.00011785806,0.00014586558,0.000019668836,0.00017632332,0.00012194791,0.0004944291,0.00007221862,0.000009636277],"category_scores_gemma":[0.000066914516,0.00010508807,0.00003206616,0.00009602901,0.0001222269,0.0000032354799,0.00039874294,0.000037427475,0.0000063327707],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000294451,0.000025785666,0.01224227,0.000008748171,0.00002128424,1.2951884e-7,0.00006577718,0.00043663525,0.9847586,0.0005146909,0.0001497311,0.0017469001],"study_design_scores_gemma":[0.002239375,0.003594715,0.26590392,0.000051760282,0.0001169644,0.000034907578,0.0016060543,0.0057938686,0.50989604,0.013503869,0.19579479,0.0014637467],"about_ca_topic_score_codex":0.000035842033,"about_ca_topic_score_gemma":0.00001537147,"teacher_disagreement_score":0.4748626,"about_ca_system_score_codex":0.0000078056755,"about_ca_system_score_gemma":0.00005504729,"threshold_uncertainty_score":0.42853668},"labels":[],"label_agreement":null},{"id":"W2950266744","doi":"10.1093/gigascience/gix010","title":"NanoSim: nanopore sequence read simulator based on statistical characterization","year":2017,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":279,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Human Genome Research Institute; National Institutes of Health; University of British Columbia; Genome British Columbia; Genome Canada","keywords":"Nanopore; Computer science; Sequence (biology); Characterization (materials science); Nanopore sequencing; Computational biology; Nanotechnology; Biology; DNA sequencing; Materials science; Genetics","score_opus":0.025035175912847464,"score_gpt":0.2890163993418289,"score_spread":0.2639812234289814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950266744","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9929371,0.000019255853,0.0050368933,0.00033668856,0.0002872771,0.00012156554,0.00012971763,0.000004150601,0.0011273632],"genre_scores_gemma":[0.99795103,0.00003392142,0.0009774612,0.00055895123,0.000094788404,0.000011411327,0.00004908729,0.000009050365,0.0003143017],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9991243,0.000019325555,0.000111314235,0.00037387578,0.00015741118,0.0002137594],"domain_scores_gemma":[0.999147,0.00001511696,0.00009930816,0.00059437245,0.000069392656,0.0000748062],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014770325,0.00010719962,0.000090113965,0.000017863653,0.00047318745,0.00008810231,0.0003971598,0.000058028,0.000014677555],"category_scores_gemma":[0.0003226128,0.00009943149,0.000028602357,0.000027820075,0.0002961153,0.0000019202087,0.00010924981,0.00003971876,0.00001554026],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021302203,0.000023354023,0.00628989,0.000004352225,0.0000034605177,0.0000033927142,0.000013709729,0.00021253644,0.9862547,0.00031528005,0.0000653416,0.006792692],"study_design_scores_gemma":[0.0006694432,0.00082708785,0.51871365,0.000037295988,0.000016271786,0.0000059240647,0.00001682641,0.015867125,0.41146344,0.00029781112,0.051568974,0.0005161218],"about_ca_topic_score_codex":0.000011123851,"about_ca_topic_score_gemma":0.0000065649324,"teacher_disagreement_score":0.57479125,"about_ca_system_score_codex":0.000009756354,"about_ca_system_score_gemma":0.00009295324,"threshold_uncertainty_score":0.40546983},"labels":[],"label_agreement":null},{"id":"W2950391801","doi":"10.1093/gigascience/gix015","title":"Enhancing knowledge discovery from cancer genomics data with Galaxy","year":2017,"lang":"en","type":"article","venue":"GigaScience","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre; Ontario Institute for Cancer Research; BC Cancer Agency; Simon Fraser University","funders":"Canadian Institutes of Health Research","keywords":"Genomics; Data science; Computational biology; Computer science; Genome; Biology; Genetics; Gene","score_opus":0.03709075180775934,"score_gpt":0.3193324964112867,"score_spread":0.28224174460352736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950391801","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97149044,0.0012298457,0.02406656,0.00032234113,0.00043243507,0.00009443566,0.00009618338,0.000008372282,0.0022593604],"genre_scores_gemma":[0.99598867,0.00038779978,0.0011330049,0.0001031923,0.00030533728,0.00001713696,0.00007297517,0.000009536795,0.0019823792],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9990949,0.000014631071,0.000089867746,0.0005289492,0.00010632767,0.0001653169],"domain_scores_gemma":[0.99810725,0.000004418135,0.000119689445,0.0016603225,0.00004341953,0.000064888336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012990365,0.000089346664,0.00007192583,0.0000142485715,0.00034351347,0.00020594725,0.001233848,0.000046538007,0.000015919592],"category_scores_gemma":[0.000054322252,0.00006997044,0.000015959133,0.000034309414,0.00018910698,0.00003711165,0.00050577975,0.000048977305,0.000010417383],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019953668,0.000012617192,0.005475153,0.0000029054067,0.0000067030533,4.6259228e-7,0.00005857013,0.000011310606,0.9856739,0.00002080302,0.0014999383,0.0072176955],"study_design_scores_gemma":[0.00028723537,0.000043277232,0.07324412,0.00004424215,0.000012517854,0.0000016390364,0.00011356734,0.0003433853,0.83516365,0.000046787118,0.09050555,0.00019403892],"about_ca_topic_score_codex":0.00018153388,"about_ca_topic_score_gemma":0.0011909857,"teacher_disagreement_score":0.15051024,"about_ca_system_score_codex":0.000018103688,"about_ca_system_score_gemma":0.00032346635,"threshold_uncertainty_score":0.28533116},"labels":[],"label_agreement":null},{"id":"W2950671516","doi":"10.1093/gigascience/giz043","title":"Ultra-deep, long-read nanopore sequencing of mock microbial community standards","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":341,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of British Columbia; Northeastern University; Medical Research Council; University of Birmingham; Ontario Institute for Cancer Research; National Institute for Health and Care Research; Oxford Nanopore Technologies; University of Nottingham; University of Queensland; Cornell University","keywords":"Metagenomics; Nanopore sequencing; Deep sequencing; Sequence assembly; Computational biology; Microbial population biology; Illumina dye sequencing; DNA sequencing; Biology; Nanopore; Computer science; Genome; Data mining; Genetics; Gene; Nanotechnology; Bacteria","score_opus":0.011691406482181806,"score_gpt":0.24367053065394553,"score_spread":0.23197912417176372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950671516","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99363464,0.00058131997,0.00031911506,0.000024522787,0.0002165379,0.00013718597,0.00007415041,0.0000028463116,0.0050096614],"genre_scores_gemma":[0.9987265,0.00010980196,0.00048786408,0.000098535005,0.000036297875,0.0000029026,0.000011739867,0.000008845207,0.0005175062],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99912006,0.00006130769,0.00017839558,0.00022222761,0.00018385261,0.0002341312],"domain_scores_gemma":[0.999196,0.000015353295,0.000093660296,0.00046288103,0.00018177192,0.00005032271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005083352,0.00011669435,0.00015405497,0.00002603821,0.00014057173,0.000015357879,0.0004095143,0.00006645955,0.000028628257],"category_scores_gemma":[0.00007153559,0.00010726346,0.0000692077,0.000107821834,0.00023847954,0.0000014114537,0.00015775146,0.00009546759,0.0000056792574],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016882477,0.000019595345,0.012147969,0.00002473327,0.000014743537,4.9325274e-7,0.00038548867,0.00022145305,0.98642004,0.00003164985,0.00012058592,0.00059635116],"study_design_scores_gemma":[0.00034909902,0.00039209574,0.015558918,0.000023603525,0.00000977043,0.000016844735,0.000604435,0.000027382257,0.9794315,0.00015531832,0.003240415,0.00019058007],"about_ca_topic_score_codex":0.00018853939,"about_ca_topic_score_gemma":0.00015148868,"teacher_disagreement_score":0.0069885165,"about_ca_system_score_codex":0.000027808319,"about_ca_system_score_gemma":0.00019560564,"threshold_uncertainty_score":0.4374077},"labels":[],"label_agreement":null},{"id":"W2951296328","doi":"10.1093/gigascience/giz024","title":"Combinatorial Detection of Conserved Alteration Patterns for Identifying Cancer Subnetworks","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Genome British Columbia; Simon Fraser University","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; International Business Machines Corporation; National Science Foundation","keywords":"Computational biology; Biology; Gene; Genome; Identification (biology); Conserved sequence; Genetics; Base sequence","score_opus":0.01443653803342532,"score_gpt":0.26429634220387827,"score_spread":0.24985980417045295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951296328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8870092,0.00013626833,0.11110439,0.00002119757,0.0013858898,0.00024919648,0.000014113629,0.0000037250602,0.00007602527],"genre_scores_gemma":[0.9993596,0.00004659106,0.00020565635,0.00008409754,0.00017592563,0.000024276203,0.000025468647,0.0000054450456,0.00007295624],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99944454,0.000011408292,0.00016728294,0.00015110293,0.00008037359,0.00014531305],"domain_scores_gemma":[0.9996073,0.000010224041,0.00011477139,0.0001569591,0.00008199427,0.000028701008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022375198,0.000062776264,0.00008043362,0.000018132245,0.000056606663,0.000026351081,0.00013035709,0.00007312748,0.000008174628],"category_scores_gemma":[0.000011719719,0.00006074349,0.00004876235,0.000056739966,0.000034783025,0.000008195942,0.000043305812,0.000036359244,0.0000017813929],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057752153,0.000013738866,0.004715028,0.000057190926,0.000012954196,5.737936e-8,0.00007452523,0.001250456,0.98692495,0.00043104452,0.00010703618,0.00635527],"study_design_scores_gemma":[0.0013511857,0.0004287064,0.0059260805,0.000065306966,0.000018176956,0.0000039983083,0.00010328259,0.051681288,0.9358513,0.0011182657,0.003207467,0.000244973],"about_ca_topic_score_codex":0.00003725687,"about_ca_topic_score_gemma":0.00006764723,"teacher_disagreement_score":0.11235039,"about_ca_system_score_codex":0.000009962773,"about_ca_system_score_gemma":0.000042488227,"threshold_uncertainty_score":0.24770476},"labels":[],"label_agreement":null},{"id":"W2951685627","doi":"10.1093/gigascience/gix042","title":"Kronos: a workflow assembler for genome analytics and informatics","year":2017,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; BC Cancer Agency; Simon Fraser University; University of British Columbia; Ontario Institute for Cancer Research; University of British Columbia Hospital","funders":"Terry Fox Research Institute; Genome British Columbia; Science and Engineering Research Council; Genome Canada","keywords":"Computer science; Workflow; Python (programming language); Modular design; Software engineering; Executable; Cloud computing; Programming language; Operating system; Database","score_opus":0.02344197264771384,"score_gpt":0.2723642364955647,"score_spread":0.24892226384785085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951685627","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98986953,0.00048516062,0.0075714625,0.00017242228,0.00012693637,0.00015525971,0.000019941524,0.0000017947231,0.0015974602],"genre_scores_gemma":[0.9864119,0.0003300645,0.01257003,0.00018326145,0.00009787687,0.000015472235,0.0000040760688,0.00000598221,0.00038133573],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99944854,0.000003821515,0.00012331313,0.00015748569,0.000065049404,0.00020177866],"domain_scores_gemma":[0.9993669,0.000008410269,0.00009993152,0.00039819788,0.00006346753,0.00006313825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002032102,0.00008715759,0.000091610724,0.000017367374,0.000458974,0.00013399268,0.00032255336,0.000046599947,0.0000010612137],"category_scores_gemma":[0.0001209642,0.00007754567,0.000036654597,0.000019741947,0.00020208723,0.000002586835,0.0002389983,0.000025158468,0.000001950411],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048903694,0.000046354875,0.053587563,0.00007061904,0.00010638123,0.0000010676047,0.00067805994,0.0005044399,0.9118868,0.0010554226,0.0010311707,0.030983182],"study_design_scores_gemma":[0.0016733557,0.0009141154,0.6506359,0.000029218407,0.00008736812,0.000027544489,0.0005422018,0.0058019846,0.050624162,0.0032685986,0.2854873,0.00090827927],"about_ca_topic_score_codex":0.0000044677176,"about_ca_topic_score_gemma":0.000018234396,"teacher_disagreement_score":0.8612627,"about_ca_system_score_codex":0.000004376438,"about_ca_system_score_gemma":0.000041048657,"threshold_uncertainty_score":0.35301036},"labels":[],"label_agreement":null},{"id":"W2952080813","doi":"10.1093/gigascience/giy009","title":"Single-molecule, full-length transcript sequencing provides insight into the extreme metabolism of the ruby-throated hummingbird <i>Archilochus colubris</i>","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Bird parasitology and diseases","field":"Immunology and Microbiology","cited_by":91,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hummingbird; Lipogenesis; Biology; Nectar; Foraging; Energy metabolism; Lipid metabolism; Biochemistry; Ecology; Endocrinology","score_opus":0.028037043233042944,"score_gpt":0.23996726436089794,"score_spread":0.21193022112785498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952080813","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98746383,0.005207987,0.00088997866,0.0011920398,0.0010577581,0.00033581982,0.000009330988,0.00008323708,0.003759988],"genre_scores_gemma":[0.9982617,0.000021871423,0.00019599275,0.0011814688,0.000046603658,0.000019930669,0.0000021478875,0.000010023076,0.0002602551],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99828565,0.00042566357,0.00032349594,0.00039737736,0.000105372856,0.0004624578],"domain_scores_gemma":[0.9989238,0.00015333912,0.00015984128,0.00056432455,0.00015811082,0.00004059398],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00042933787,0.00018554958,0.00022658127,0.000069421396,0.0009828893,0.000029198234,0.0009694152,0.0001338202,0.00010614418],"category_scores_gemma":[0.00026911483,0.00010899657,0.0001253524,0.0006541309,0.004826565,0.00021038095,0.00012708417,0.000247583,0.00007307009],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112699265,0.00008747905,0.002148787,0.000008205149,0.000041611383,0.0000022847255,0.0070154523,0.0000031481525,0.9828356,0.004846101,0.0003299033,0.0025687246],"study_design_scores_gemma":[0.0005944627,0.00023411507,0.023495385,0.000039610368,0.00009800506,0.00010394349,0.00077708764,0.000025171392,0.9609584,0.001305952,0.01217418,0.00019368771],"about_ca_topic_score_codex":0.00032082788,"about_ca_topic_score_gemma":0.00040701337,"teacher_disagreement_score":0.021877203,"about_ca_system_score_codex":0.000028173929,"about_ca_system_score_gemma":0.0002603843,"threshold_uncertainty_score":0.9978817},"labels":[],"label_agreement":null},{"id":"W2953131636","doi":"10.1093/gigascience/giy103","title":"Monitoring changes in the Gene Ontology and their impact on genomic data analysis","year":2018,"lang":"en","type":"article","venue":"GigaScience","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Institute of Mental Health; Canadian Institutes of Health Research; National Institutes of Health","keywords":"Gene ontology; Ontology; Data science; Computer science; Computational biology; Gene; Information retrieval; Bioinformatics; Biology; Genetics; Gene expression","score_opus":0.027373510855618184,"score_gpt":0.29222376374266573,"score_spread":0.26485025288704755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953131636","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9971368,0.00050350715,0.0015954735,0.00026455364,0.00008457613,0.00007012479,0.000023321401,0.0000023028156,0.00031936713],"genre_scores_gemma":[0.99860746,0.00025212427,0.0005040004,0.00033169976,0.00025754268,0.0000033320362,0.000023611894,0.0000030179963,0.00001718909],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9993503,0.00003143808,0.00009244349,0.0002576125,0.000056405937,0.00021178059],"domain_scores_gemma":[0.9992256,0.000017119968,0.000045581142,0.0006603993,0.000015737482,0.00003556132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054389006,0.000092871735,0.00009906299,0.0000561191,0.00009760022,0.00004252031,0.0006242876,0.000055194578,0.0000039912043],"category_scores_gemma":[0.000017153066,0.0000514092,0.00002547868,0.00022123236,0.00018791242,0.000004430098,0.00024862247,0.00005838492,0.000003251964],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014561054,0.0001018055,0.14841071,0.000010894288,0.00038252035,0.0000059434547,0.0044467133,0.0007443752,0.6969814,0.00019679674,0.0011016554,0.14747159],"study_design_scores_gemma":[0.0005727919,0.0014725552,0.87478715,0.000018570814,0.000104727296,0.00007002567,0.001280965,0.037054434,0.07659008,0.0006633982,0.0068560173,0.0005292675],"about_ca_topic_score_codex":0.000058814116,"about_ca_topic_score_gemma":0.000568986,"teacher_disagreement_score":0.7263765,"about_ca_system_score_codex":0.000008197248,"about_ca_system_score_gemma":0.00003280752,"threshold_uncertainty_score":0.20964062},"labels":[],"label_agreement":null},{"id":"W2954449684","doi":"10.1093/gigascience/giz069","title":"Box, stalked, and upside-down? Draft genomes from diverse jellyfish (Cnidaria, Acraspeda) lineages: <i>Alatina alata</i> (Cubozoa), <i>Calvadosia cruxmelitensis</i> (Staurozoa), and <i>Cassiopea xamachana</i> (Scyphozoa)","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Marine Invertebrate Physiology and Ecology","field":"Earth and Planetary Sciences","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Oak Ridge Institute for Science and Education; University of Maryland; University of Florida; National Sleep Foundation","keywords":"Scyphozoa; Jellyfish; Cnidaria; Hydrozoa; Clade; Biology; Anthozoa; Evolutionary biology; Zoology; Ecology; Phylogenetics; Genetics; Coral; Gene","score_opus":0.006957848359408341,"score_gpt":0.18413048208770436,"score_spread":0.177172633728296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954449684","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98756707,0.0018246147,0.00006911425,0.0008097149,0.0010685212,0.0005387115,0.00036754107,0.00013268593,0.007622055],"genre_scores_gemma":[0.991094,0.0012161834,0.0012514339,0.0050035384,0.00021754888,0.000005501311,0.00022739713,0.000017231878,0.00096718775],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99610895,0.00023541355,0.0005762786,0.0015212346,0.0004783988,0.0010797388],"domain_scores_gemma":[0.99772257,0.0006059399,0.0002807502,0.0007194163,0.00010513827,0.00056620425],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00065165974,0.0005348285,0.00072081236,0.00017042884,0.00067138235,0.0002924555,0.00072600984,0.00029696425,0.0037205874],"category_scores_gemma":[0.00011826948,0.0004575555,0.000109572284,0.0005096358,0.0010846333,0.0010588024,0.0004143047,0.0005343652,0.00084353867],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102865044,0.000047249323,0.96095186,0.00004372274,0.0000509259,0.000079072546,0.0006444597,0.00026073022,0.0054029413,0.000090833644,0.0030652764,0.02926006],"study_design_scores_gemma":[0.00150077,0.00070212234,0.94302684,0.000054235956,0.00009592649,0.00009871258,0.001087338,0.023893928,0.0008759102,0.0023145918,0.02534942,0.0010001999],"about_ca_topic_score_codex":0.0057853283,"about_ca_topic_score_gemma":0.004305607,"teacher_disagreement_score":0.02825986,"about_ca_system_score_codex":0.000013625676,"about_ca_system_score_gemma":0.00015506125,"threshold_uncertainty_score":0.99993443},"labels":[],"label_agreement":null},{"id":"W2955824638","doi":"10.1093/gigascience/giz073","title":"A large interactive visual database of copy number variants discovered in taurine cattle","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Alberta; Agriculture and Agri-Food Canada","funders":"Genome Alberta; Science Foundation Ireland; Department of Agriculture, Food and the Marine, Ireland; Compute Canada; Genome Canada; Western Canada Research Grid; University of California, Santa Cruz","keywords":"Copy-number variation; Bovine genome; Genome; Biology; Whole genome sequencing; Structural variation; Genetics; Genotype; Computational biology; Database; Gene; Computer science","score_opus":0.004909729039155327,"score_gpt":0.25838044132879484,"score_spread":0.2534707122896395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955824638","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9970091,0.000022350105,0.0006954905,0.00002524772,0.00013389732,0.00009940176,0.00018879405,0.0000016134366,0.0018241004],"genre_scores_gemma":[0.99853355,0.000015065696,0.00033059256,0.00006227198,0.000025212348,0.0000070123087,0.00011165656,0.0000048434886,0.0009097704],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993463,0.000026323312,0.00014149997,0.00022153399,0.000091573245,0.00017276443],"domain_scores_gemma":[0.9996537,0.000009413146,0.0000630481,0.00020634741,0.000036847236,0.000030648738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014579085,0.000069740505,0.00009192754,0.000024828747,0.000023159359,0.000012393578,0.00016833456,0.00003235671,0.00023653127],"category_scores_gemma":[0.000036052523,0.00006390012,0.000027513608,0.000112009526,0.00004605972,0.000017432343,0.00017616086,0.000043919732,0.000049747083],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008621073,0.00027420692,0.26026458,0.000030413596,0.0000138446685,0.0000026707326,0.00063602644,0.00010541513,0.73721516,0.0011261185,0.00018041774,0.00006497894],"study_design_scores_gemma":[0.0019040524,0.000368983,0.23204608,0.00008315329,0.000010137945,0.00003879166,0.0024723487,0.00067084,0.7591106,0.00018891037,0.0027535183,0.00035257448],"about_ca_topic_score_codex":0.00013277118,"about_ca_topic_score_gemma":0.00009279958,"teacher_disagreement_score":0.028218478,"about_ca_system_score_codex":0.000012742248,"about_ca_system_score_gemma":0.000092356284,"threshold_uncertainty_score":0.26057714},"labels":[],"label_agreement":null},{"id":"W2962240230","doi":"10.1093/gigascience/giz074","title":"Identifying, understanding, and correcting technical artifacts on the sex chromosomes in next-generation sequencing data","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Genetic and Clinical Aspects of Sex Determination and Chromosomal Abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; BC Children's Hospital; University of British Columbia","funders":"National Institutes of Health; National Institute of General Medical Sciences; Arizona State University","keywords":"Biology; Genetics; Genomics; Computational biology; Reference genome; DNA sequencing; Genome; Exome sequencing; Gene; Mutation","score_opus":0.1799402187632382,"score_gpt":0.3168781260450433,"score_spread":0.13693790728180508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962240230","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99628,0.0001203841,0.00050860073,0.0003674759,0.00015590682,0.00013857892,0.000004087973,0.000008920567,0.0024160116],"genre_scores_gemma":[0.9983785,0.00010885555,0.00014024117,0.0006123849,0.00007641413,0.0000047014432,0.000024722804,0.00000536355,0.00064881874],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99903125,0.000045871824,0.0001742186,0.00039591917,0.00017388657,0.00017888715],"domain_scores_gemma":[0.9994337,0.000060300263,0.000061496765,0.00038487927,0.000015700924,0.000043953238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005116225,0.000089433386,0.00008391457,0.000027654483,0.00012584293,0.000120658704,0.00033774247,0.00006421581,0.000054003256],"category_scores_gemma":[0.00019465153,0.000064981294,0.000017938337,0.000097636526,0.00012173398,0.000022243621,0.00023852572,0.00010639677,0.000019043793],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012842655,0.00004120022,0.014867306,0.000018965726,0.0000065524537,0.000005095949,0.0002974863,0.00009924345,0.97624147,0.0031868352,0.00061071967,0.0046123047],"study_design_scores_gemma":[0.0014508137,0.0018313708,0.028695727,0.00037664175,0.000030099614,0.00028955296,0.025754655,0.034052,0.895198,0.005934887,0.005110677,0.0012755645],"about_ca_topic_score_codex":0.000018066554,"about_ca_topic_score_gemma":0.00011689771,"teacher_disagreement_score":0.08104344,"about_ca_system_score_codex":0.000028434431,"about_ca_system_score_gemma":0.000061081446,"threshold_uncertainty_score":0.264986},"labels":[],"label_agreement":null},{"id":"W2969811969","doi":"10.1093/gigascience/giz089","title":"A chromosomal-level genome assembly for the insect vector for Chagas disease, <i>Triatoma rubrofasciata</i>","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Trypanosoma species research and implications","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Key Research and Development Program of China; Chinese Academy of Sciences","keywords":"Genome; Biology; Sequence assembly; Contig; Genomics; Reference genome; Genetics; Genome project; Gene; Chagas disease; DNA sequencing; Comparative genomics; Computational biology; Genome size; Evolutionary biology; Transcriptome; Virology","score_opus":0.07277992598226626,"score_gpt":0.3211912732258518,"score_spread":0.24841134724358552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969811969","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9412891,0.0013605956,0.024513347,0.020194193,0.0006857092,0.008639081,0.0016152029,0.00016736815,0.0015353698],"genre_scores_gemma":[0.99001247,0.000080178186,0.0017198015,0.0013440113,0.0004157335,0.0010795641,0.00006565955,0.000029146016,0.005253429],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99801683,0.000019380857,0.0002351249,0.00051257084,0.00052806013,0.0006880543],"domain_scores_gemma":[0.9977938,0.0005826772,0.00008496355,0.000857771,0.0002831747,0.000397596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015931277,0.00016251883,0.00023234184,0.0001009453,0.00043581094,0.00011267588,0.0006353441,0.000050043516,0.00010777053],"category_scores_gemma":[0.00090440654,0.000108014,0.00022112826,0.0005861433,0.0002072302,0.00022880554,0.00011672674,0.0001295933,0.00017379751],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067522755,0.0003007522,0.0041019623,0.00028229624,0.00007913674,0.000004228506,0.00023584013,0.000012514655,0.9631592,0.0138046965,0.011469362,0.0058747777],"study_design_scores_gemma":[0.001989841,0.0007052295,0.8074927,0.000039785584,0.00005633282,0.00002220841,0.000075436335,0.002735646,0.0057878466,0.00028855493,0.18061551,0.00019091903],"about_ca_topic_score_codex":0.000018926168,"about_ca_topic_score_gemma":0.00001649538,"teacher_disagreement_score":0.95737135,"about_ca_system_score_codex":0.00012103167,"about_ca_system_score_gemma":0.0007556484,"threshold_uncertainty_score":0.4404683},"labels":[],"label_agreement":null},{"id":"W2975619549","doi":"10.1093/gigascience/giz107","title":"A field guide for the compositional analysis of any-omics data","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":369,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Normalization (sociology); Compositional data; Computer science; Extant taxon; Data mining; Sample size determination; Computational biology; Data set; Field (mathematics); Bioinformatics; Statistics; Biology; Mathematics; Artificial intelligence; Machine learning; Evolutionary biology","score_opus":0.03295175102729838,"score_gpt":0.2817874691237989,"score_spread":0.24883571809650049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975619549","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020676622,0.000057898018,0.9656833,0.0078332415,0.00019165975,0.000144728,0.000034858676,0.000021100184,0.0053565837],"genre_scores_gemma":[0.9668074,0.0000041993753,0.031368803,0.00083329465,0.000017713617,0.0000050000667,0.000019005156,4.880532e-7,0.0009440963],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920493,0.000010902462,0.00014387113,0.00030846446,0.00018507153,0.00014674827],"domain_scores_gemma":[0.9980963,0.0005600291,0.0000821392,0.0011351574,0.0001010432,0.000025321542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006430928,0.000049237326,0.00010544326,0.000041929095,0.000098577904,0.000047921294,0.0027141927,0.00002312096,0.000034657634],"category_scores_gemma":[0.00018983976,0.00003405938,0.00005693161,0.0007217675,0.00006455126,0.00021228517,0.000596902,0.00004269243,0.000004852576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000634495,0.00030559718,0.074191175,0.0001658721,0.00097356655,0.000006582794,0.0020154186,0.08565492,0.27095413,0.47510925,0.05082994,0.039730117],"study_design_scores_gemma":[0.000080433136,0.000040061615,0.008585357,0.0000052682426,0.000044582408,0.0000031717937,0.00003594771,0.95590967,0.0074850977,0.0015247103,0.026216388,0.00006933065],"about_ca_topic_score_codex":0.000029618413,"about_ca_topic_score_gemma":0.000005712841,"teacher_disagreement_score":0.94613075,"about_ca_system_score_codex":0.0000054427496,"about_ca_system_score_gemma":0.00006495335,"threshold_uncertainty_score":0.5043691},"labels":[],"label_agreement":null},{"id":"W2979549191","doi":"10.1093/gigascience/giz119","title":"PIRATE: A fast and scalable pangenomics toolbox for clustering diverged orthologues in bacteria","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":272,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Medical Research Council; Medical Research Council Canada; Sight Research UK","keywords":"Genome; Cluster analysis; Biology; Scalability; Bacterial genome size; Toolbox; Computational biology; Gene; Computer science; Data mining; Genetics; Database; Artificial intelligence","score_opus":0.011593272892526369,"score_gpt":0.22363016255893559,"score_spread":0.2120368896664092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979549191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99819684,0.0004423963,0.0005372333,0.000048865244,0.00019022333,0.00023388077,0.000024176255,0.000002012271,0.00032439336],"genre_scores_gemma":[0.99604475,0.00017901609,0.0031925216,0.00014831185,0.000039620783,0.00002300939,0.000008576066,0.0000075616326,0.00035661046],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99928886,0.000012272892,0.000113907794,0.00031931186,0.000040324452,0.00022534195],"domain_scores_gemma":[0.9997289,0.000009724332,0.00003580029,0.00016086172,0.000028882638,0.000035806323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018588097,0.00009093047,0.00011035856,0.000026058056,0.000065217,0.00003196315,0.00013741218,0.00004997333,0.0000036158328],"category_scores_gemma":[0.000025640515,0.00008520734,0.000025208556,0.00005605402,0.00007681472,0.0000019377433,0.00017625793,0.000026535317,0.000004220256],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028429287,0.000009591643,0.07320098,0.000014485308,0.000005070556,3.494174e-7,0.0001354783,0.00017157615,0.9241385,0.000022431042,0.00003375803,0.0022393959],"study_design_scores_gemma":[0.0017932322,0.0009353283,0.82139975,0.000033184,0.000015281395,0.000021714695,0.0007270153,0.002827354,0.14740436,0.00021796704,0.023996036,0.0006287643],"about_ca_topic_score_codex":0.000018735032,"about_ca_topic_score_gemma":0.0001469911,"teacher_disagreement_score":0.7767341,"about_ca_system_score_codex":0.0000076349015,"about_ca_system_score_gemma":0.000028338205,"threshold_uncertainty_score":0.34746546},"labels":[],"label_agreement":null},{"id":"W2982160768","doi":"10.1093/gigascience/giz126","title":"Access to RNA-sequencing data from 1,173 plant species: The 1000 Plant transcriptomes initiative (1KP)","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":179,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Transcriptome; Biology; Gene; Computational biology; De novo transcriptome assembly; Plant species; Genome; Evolutionary biology; DNA sequencing; Genetics; Gene expression; Botany","score_opus":0.0913276990228843,"score_gpt":0.2848141458978796,"score_spread":0.19348644687499533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982160768","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907245,0.0007071045,0.0005848098,0.00078332116,0.00053416303,0.00030471568,0.0017446191,0.000004906771,0.004611846],"genre_scores_gemma":[0.99645025,0.00032263438,0.00033561257,0.0022245022,0.0001950878,0.000014210778,0.0001718503,0.000010674163,0.00027516164],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998617,0.000041034524,0.00018035965,0.00062089454,0.00022141909,0.000319307],"domain_scores_gemma":[0.9988274,0.00005398132,0.00006509793,0.00092401035,0.000046017787,0.000083502804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027311506,0.00016049274,0.00015601462,0.000030155597,0.00017815016,0.0001289639,0.0018864804,0.000050565908,0.000061009978],"category_scores_gemma":[0.00005265885,0.000110911205,0.00004096471,0.0001498084,0.00014523648,0.000007414485,0.0007817348,0.000080767706,0.000048987702],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034066565,0.000012036018,0.0077758096,0.0000045885195,0.000041672814,0.0000030251936,0.00096481066,0.00014729002,0.9859394,0.00007736712,0.004655546,0.00034442125],"study_design_scores_gemma":[0.00057399174,0.0003594027,0.13283072,0.00005945047,0.000042462205,0.000017034874,0.003063448,0.0007491761,0.64293987,0.00029228214,0.21843386,0.0006383335],"about_ca_topic_score_codex":0.00018127217,"about_ca_topic_score_gemma":0.00032367415,"teacher_disagreement_score":0.34299952,"about_ca_system_score_codex":0.000019841189,"about_ca_system_score_gemma":0.00016086455,"threshold_uncertainty_score":0.45228276},"labels":[],"label_agreement":null},{"id":"W2990971319","doi":"10.1093/gigascience/giz152","title":"A draft genome sequence of the elusive giant squid, <i>Architeuthis dux</i>","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Cephalopods and Marine Biology","field":"Agricultural and Biological Sciences","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Bioinformatics Solutions (Canada)","funders":"FP7 People: Marie-Curie Actions; European Regional Development Fund; Fundação para a Ciência e a Tecnologia; Biotechnology and Biological Sciences Research Council; Directorate for Biological Sciences; Rede Nacional de Espectrometria de Massa; Novo Nordisk Fonden; H. Lundbeck A/S; Vedecká Grantová Agentúra MŠVVaŠ SR a SAV; Danish e-Infrastructure Cooperation; Novo Nordisk; Danmarks Grundforskningsfond; David and Lucile Packard Foundation; Deutsche Forschungsgemeinschaft; National Research Foundation; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Wellcome Trust; European Molecular Biology Laboratory; National Science Foundation; Wellcome; Villum Fonden; Lundbeckfonden","keywords":"Squid; Computational biology; Genome; Evolutionary biology; Sequence (biology); Biology; Genetics; Gene; Ecology","score_opus":0.02936419815462609,"score_gpt":0.2076561284294966,"score_spread":0.1782919302748705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990971319","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9819146,0.00013236214,0.00001546816,0.014932136,0.00016120338,0.00018402805,0.00009196444,0.000030357895,0.0025379134],"genre_scores_gemma":[0.99649996,0.000039266746,0.00011550398,0.0029621786,0.00013178724,0.0000057756274,0.0000068444238,4.894286e-7,0.00023822162],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989796,0.00006393148,0.00017682744,0.00032076688,0.000189043,0.0002698201],"domain_scores_gemma":[0.9995575,0.0000834773,0.00010131855,0.00008113922,0.0000569051,0.00011966515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016780918,0.00010065268,0.00014146577,0.0000043523,0.00018824635,0.000020894475,0.00086288946,0.000043710217,0.00019150172],"category_scores_gemma":[0.00011797618,0.000030342264,0.00009975571,0.0006411858,0.000478832,0.00006907032,0.0004888389,0.00010814161,0.000031249318],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066289153,0.000016183823,0.0021006,0.0000044020007,0.0000017662153,0.0000019822326,0.00035229244,0.000004713565,0.983213,0.0007786503,0.00011269456,0.0134070655],"study_design_scores_gemma":[0.00026985025,0.0011182264,0.5469125,0.000036102367,0.000021339702,0.000060757982,0.0008262349,0.0005507528,0.03733991,0.0012524772,0.41108152,0.00053029344],"about_ca_topic_score_codex":0.00027670752,"about_ca_topic_score_gemma":0.00021938863,"teacher_disagreement_score":0.9458731,"about_ca_system_score_codex":0.000012016104,"about_ca_system_score_gemma":0.000034631426,"threshold_uncertainty_score":0.20968094},"labels":[],"label_agreement":null},{"id":"W2995906327","doi":"10.1093/gigascience/giz146","title":"Systematic processing of ribosomal RNA gene amplicon sequencing data","year":2019,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":77,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; National Research Council Canada","funders":"McGill University","keywords":"Amplicon; Computer science; Computational biology; Pipeline (software); Workflow; Ribosomal RNA; Amplicon sequencing; Scripting language; Data mining; Biology; Gene; Genetics; Database; 16S ribosomal RNA; Operating system; Polymerase chain reaction","score_opus":0.0278345674920407,"score_gpt":0.25740096879237834,"score_spread":0.22956640130033765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995906327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9954517,0.002254923,0.0011077663,0.000017027796,0.00011649269,0.0002167797,0.000022455091,0.0000024040635,0.00081049214],"genre_scores_gemma":[0.9971123,0.000058976122,0.0025648647,0.00006128737,0.000043417556,0.0000050218578,0.000014003125,0.0000074369805,0.00013274103],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99904066,0.000022630302,0.00023933673,0.00036940447,0.00014342114,0.00018456359],"domain_scores_gemma":[0.9990418,0.000009882976,0.00015222751,0.0006867619,0.00007231233,0.000037036378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003662501,0.00009179099,0.00016964704,0.000023016537,0.000059819617,0.000021444614,0.000617374,0.000039348244,0.0000028507804],"category_scores_gemma":[0.00008396948,0.00007734836,0.000028804636,0.00010170731,0.000093019495,0.0000024362587,0.00040914174,0.00002964775,0.000008037087],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030621245,0.0000066485177,0.0019575597,0.00061232364,0.00001172933,3.3916828e-7,0.00008444671,0.000105189916,0.9969809,0.000027012837,0.000012751757,0.00019800807],"study_design_scores_gemma":[0.00028529504,0.00020485565,0.0052991128,0.0005167759,0.0000363989,0.000034261706,0.00045393375,0.0032066943,0.9893837,0.00009942664,0.00020837037,0.00027115125],"about_ca_topic_score_codex":0.000018726281,"about_ca_topic_score_gemma":0.000005157309,"teacher_disagreement_score":0.0075972043,"about_ca_system_score_codex":0.000009285215,"about_ca_system_score_gemma":0.00013927129,"threshold_uncertainty_score":0.31541747},"labels":[],"label_agreement":null},{"id":"W3005225423","doi":"10.1093/gigascience/giz165","title":"The Data Tags Suite (DATS) model for discovering data access and use requirements","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; Biotechnology and Biological Sciences Research Council; Purdue University; Office of Integrative Activities; McGill University; University of California, San Diego; GlaxoSmithKline; National Institutes of Health; National Science Foundation","keywords":"Metadata; Computer science; Suite; Confidentiality; Data access; Data element; Schema (genetic algorithms); Data science; Reuse; Data dictionary; Information retrieval; World Wide Web; Database; Computer security; Engineering","score_opus":0.9523679111342898,"score_gpt":0.6863204922221864,"score_spread":0.2660474189121034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005225423","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36357418,0.0006956886,0.4416845,0.18599968,0.0005619151,0.0032745013,0.0028052775,0.00014758625,0.0012566815],"genre_scores_gemma":[0.9800122,0.0016235171,0.011325575,0.005249553,0.00016530784,0.000017023602,0.00016122717,0.000019837269,0.0014257719],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99759257,0.000026046826,0.00025913416,0.00083392276,0.00093365443,0.00035468087],"domain_scores_gemma":[0.99223435,0.0044577615,0.00007145938,0.00277107,0.00014892689,0.0003164385],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.004421572,0.00008163427,0.0001349551,0.00001636622,0.0003487979,0.00054741773,0.003992423,0.00005853325,0.000004599199],"category_scores_gemma":[0.049740326,0.000052488595,0.000014805894,0.00023578046,0.00067069853,0.0020384644,0.008620915,0.0004781648,0.000005129957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0045035924,0.00090438494,0.34486496,0.004954501,0.00049695355,0.00020311156,0.0074661295,0.0024712603,0.10399752,0.1306738,0.14936723,0.25009653],"study_design_scores_gemma":[0.00045866557,0.00008021411,0.0027563947,0.00008662662,0.000023127885,0.0000018954023,0.000059053666,0.9854293,0.00020050253,0.004309416,0.006515268,0.000079565616],"about_ca_topic_score_codex":0.00005286579,"about_ca_topic_score_gemma":0.00023488754,"teacher_disagreement_score":0.982958,"about_ca_system_score_codex":0.000017572642,"about_ca_system_score_gemma":0.00046062146,"threshold_uncertainty_score":0.99939716},"labels":[],"label_agreement":null},{"id":"W3006424385","doi":"10.1093/gigascience/giaa004","title":"Inferring putative ancient whole-genome duplications in the 1000 Plants (1KP) initiative: access to gene family phylogenies and age distributions","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Chromosomal and Genetic Variations","field":"Agricultural and Biological Sciences","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Key Research and Development Program of China; Alberta Innovates - Technology Futures; Ministry of Science and Technology of the People's Republic of China; National Science Foundation","keywords":"Biology; Genome; Synteny; Phylogenomics; Evolutionary biology; Phylogenetics; Computational biology; Gene; Genetics; Clade","score_opus":0.07155533801846872,"score_gpt":0.2764420204757829,"score_spread":0.2048866824573142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006424385","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.978689,0.00009739287,0.0003701345,0.01926248,0.00002581881,0.00032985938,0.0008423746,0.000022604689,0.0003603437],"genre_scores_gemma":[0.996069,0.00002360819,0.00015227825,0.003487923,0.00006422087,0.00008311558,0.000113361166,4.8625367e-7,0.000006002652],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989904,0.0000616203,0.00016261816,0.000335181,0.00020346069,0.00024669126],"domain_scores_gemma":[0.9995592,0.00015627149,0.000046629044,0.00005745534,0.000043745593,0.00013667686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016634552,0.00009950069,0.00010288266,0.000014389354,0.00043147002,0.00022294566,0.00053591613,0.000027122753,0.000017131182],"category_scores_gemma":[0.00009504958,0.000040545354,0.000026423777,0.0010280756,0.0001410351,0.00018802726,0.00022816473,0.000087665234,0.000024921175],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046554173,0.00005776369,0.010870105,0.0000020040368,0.0000033941724,0.000007895498,0.0067753773,0.00025580585,0.9778166,0.00044974612,0.00006672406,0.00368992],"study_design_scores_gemma":[0.00005976421,0.00010072956,0.99038404,0.0000048658317,0.0000035183723,0.0000043290106,0.0013746399,0.00019160676,0.002056122,0.00047156148,0.005239423,0.000109387016],"about_ca_topic_score_codex":0.0000936547,"about_ca_topic_score_gemma":0.00036349136,"teacher_disagreement_score":0.97951394,"about_ca_system_score_codex":0.000020916643,"about_ca_system_score_gemma":0.00002240949,"threshold_uncertainty_score":0.33185622},"labels":[],"label_agreement":null},{"id":"W3010319582","doi":"10.1093/gigascience/giaa018","title":"Light-responsive expression atlas reveals the effects of light quality and intensity in <i>Kalanchoë fedtschenkoi</i>, a plant with crassulacean acid metabolism","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Photosynthetic Processes and Mechanisms","field":"Biochemistry, Genetics and Molecular Biology","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Oak Ridge National Laboratory; Office of Science; U.S. Department of Energy","keywords":"Crassulacean acid metabolism; Light intensity; Photosynthesis; Dusk; photoperiodism; Biology; Context (archaeology); Botany; Gene; Biochemistry; Ecology; Physics; Optics","score_opus":0.008879164314264741,"score_gpt":0.23354776949467945,"score_spread":0.2246686051804147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010319582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962943,0.0007998742,0.000944745,0.001478104,0.00008192453,0.00027918225,0.000010117841,0.000007803292,0.00010393483],"genre_scores_gemma":[0.9982021,0.00015464156,0.00038207622,0.0011655589,0.000049349823,0.000020224525,0.000003109287,0.000007777639,0.0000151569875],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99884695,0.0000973475,0.00019483855,0.00042092978,0.00021390727,0.0002260471],"domain_scores_gemma":[0.9993308,0.000040296545,0.00014143487,0.00027995248,0.0000846181,0.00012289852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003719814,0.00014736212,0.00024678494,0.000022329657,0.000092178765,0.00002185186,0.00030592375,0.000074801355,0.0000013340965],"category_scores_gemma":[0.0005268662,0.000087331035,0.000036671183,0.0001907393,0.00010597553,0.000010735543,0.00023395225,0.00011327646,9.744538e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035553088,0.00002588134,0.00042368905,0.000076102166,0.000007072776,0.0000070839437,0.00083447737,0.0000010427758,0.9979928,0.00008387009,0.000101002,0.00009142001],"study_design_scores_gemma":[0.00044506686,0.0003007186,0.0031364977,0.000097213255,0.000013268248,0.000016999225,0.00024966183,0.000015958074,0.99320215,0.00011323625,0.0022799303,0.00012931458],"about_ca_topic_score_codex":0.000016640899,"about_ca_topic_score_gemma":0.000023368928,"teacher_disagreement_score":0.0047906926,"about_ca_system_score_codex":0.000004260209,"about_ca_system_score_gemma":0.00006899464,"threshold_uncertainty_score":0.35612562},"labels":[],"label_agreement":null},{"id":"W3011183076","doi":"10.1093/gigascience/giaa021","title":"<i>De novo</i> assembly of the cattle reference genome with single-molecule sequencing","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":908,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Human Genome Research Institute; Biotechnology and Biological Sciences Research Council; U.S. National Library of Medicine; National Institute of Food and Agriculture; National Institutes of Health; Ministry of Health, British Columbia; Korea Health Industry Development Institute; Eunice Kennedy Shriver National Institute of Child Health and Human Development; U.S. Department of Agriculture","keywords":"Sequence assembly; Computational biology; Genome; Biology; Reference genome; Genetics; Evolutionary biology; Gene","score_opus":0.026000724162414134,"score_gpt":0.22230037256301627,"score_spread":0.19629964840060213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011183076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97196174,0.00013421712,0.021296855,0.00034913985,0.000036463123,0.00010155698,0.000014446902,0.0000074882137,0.0060981056],"genre_scores_gemma":[0.9875004,0.0000034417174,0.01121535,0.00105495,0.000053016138,0.0000046100886,0.0000035186513,0.000008542419,0.0001561695],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991944,0.00003339226,0.000114260016,0.00027750613,0.00017051298,0.00020995796],"domain_scores_gemma":[0.99948126,0.000007536544,0.000075008735,0.00028735,0.00006124159,0.00008759878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008706726,0.000093862676,0.00008170412,0.0000072217745,0.00007856387,0.000017628636,0.00051593716,0.00004893146,0.000008466742],"category_scores_gemma":[0.00006574342,0.00006456157,0.000030988034,0.00018795887,0.000263351,0.0000034718166,0.00013032685,0.000077657765,0.0000028789766],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001468419,0.000013172534,0.0008224135,0.000011527763,0.000004975136,3.1299226e-7,0.0002726297,0.0023727424,0.9955743,0.0007059753,0.00004318734,0.00016410646],"study_design_scores_gemma":[0.00021802504,0.0007088729,0.0332353,0.000018261044,0.000014549518,0.000033399585,0.00019869153,0.00003547978,0.9624592,0.00010500546,0.0028027575,0.00017047297],"about_ca_topic_score_codex":0.000011661979,"about_ca_topic_score_gemma":0.000009509704,"teacher_disagreement_score":0.03311509,"about_ca_system_score_codex":0.000012260888,"about_ca_system_score_gemma":0.00027140093,"threshold_uncertainty_score":0.26327446},"labels":[],"label_agreement":null},{"id":"W3033216646","doi":"10.1093/gigascience/giaa061","title":"Trans-NanoSim characterizes and simulates nanopore RNA-sequencing data","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"National Human Genome Research Institute; Natural Sciences and Engineering Research Council of Canada; National Institutes of Health; Genome Alberta; University of British Columbia; Genome British Columbia; Genome Canada","keywords":"Nanopore; Computational biology; RNA; Computer science; Data science; Biology; Nanotechnology; Genetics; Gene; Materials science","score_opus":0.04942781226728855,"score_gpt":0.2538366595288191,"score_spread":0.20440884726153058,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033216646","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962188,0.0015902325,0.00042777008,0.0012940858,0.00007307821,0.00008728078,0.00006720651,0.000004923011,0.00023661234],"genre_scores_gemma":[0.99704975,0.00070884125,0.0008880403,0.0011537236,0.000120356526,0.000002764734,0.000027725924,0.0000082851475,0.000040498606],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99911857,0.000014270711,0.00011796748,0.00047120845,0.00008704799,0.00019093112],"domain_scores_gemma":[0.9995168,0.000009018132,0.000038480848,0.00030668167,0.000028096601,0.00010091286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010628724,0.00010703336,0.00010523572,0.000009755974,0.00012217206,0.000038759084,0.00041950584,0.00004252644,0.00000531318],"category_scores_gemma":[0.000077782846,0.00009494596,0.000020124076,0.000074147334,0.00017060412,0.0000028799402,0.0003366641,0.000039738003,0.0000020179302],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008915861,0.0000036975573,0.00194044,0.000009661385,0.000009764954,0.000001916568,0.0002534458,0.000031910506,0.9946439,0.000013842632,0.00012121144,0.0029612563],"study_design_scores_gemma":[0.0006668489,0.0005767178,0.026631253,0.000021992859,0.000039816176,0.000021136233,0.0005493107,0.0053063263,0.8685288,0.00015033943,0.0969033,0.00060416025],"about_ca_topic_score_codex":0.000010587489,"about_ca_topic_score_gemma":0.000007616665,"teacher_disagreement_score":0.12611514,"about_ca_system_score_codex":0.0000027915685,"about_ca_system_score_gemma":0.00006015834,"threshold_uncertainty_score":0.38717836},"labels":[],"label_agreement":null},{"id":"W3033544833","doi":"10.1093/gigascience/giaa053","title":"Metagenomic analysis of planktonic riverine microbial consortia using nanopore sequencing reveals insight into river microbe taxonomy and function","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre; McGill Genome Centre; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Division of Environmental Biology; National Institute of General Medical Sciences; Rijkswaterstaat; Medical Research Council; National Institutes of Health; Canada Research Chairs; Biotechnology and Biological Sciences Research Council; Rosetrees Trust; Canada Foundation for Innovation; National Science Foundation; Canadian Institutes of Health Research; Compute Canada; Oxford Nanopore Technologies; Genome Canada","keywords":"Metagenomics; Computational biology; Function (biology); Taxonomy (biology); Biological classification; Nanopore; Plankton; Biology; Nanopore sequencing; Computer science; Ecology; Evolutionary biology; DNA sequencing; Nanotechnology; Genetics; Gene; Materials science","score_opus":0.03684712461829864,"score_gpt":0.22435940711501184,"score_spread":0.1875122824967132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033544833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9973963,0.000084084975,0.0018829087,0.00007599515,0.00006481797,0.00017643895,0.000020591362,0.000015218055,0.00028363717],"genre_scores_gemma":[0.9939171,0.000022768547,0.0050829607,0.0009145775,0.000011853745,0.000002924638,0.000019901197,0.000005237807,0.00002265266],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99882144,0.00017595856,0.00029217362,0.00039236204,0.00007956162,0.00023852932],"domain_scores_gemma":[0.99936336,0.000066694105,0.00021522163,0.00023446704,0.000015172899,0.00010508737],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029240022,0.0001435551,0.00035239971,0.000095195326,0.0003081161,0.000014884989,0.00034713492,0.000082972336,0.0014867063],"category_scores_gemma":[0.000041654646,0.0001407598,0.000083285966,0.0008927239,0.0012199937,0.000241553,0.0005140597,0.0001687826,0.000037084777],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003663581,0.000013054565,0.025550809,0.000010372455,0.000088959554,0.0000027756155,0.0020759914,0.00499639,0.966804,0.000033537082,0.00011668394,0.00027078053],"study_design_scores_gemma":[0.0020718265,0.0012025121,0.5837929,0.000058022328,0.003625601,0.00008362715,0.0011566126,0.0430607,0.32111874,0.0010260823,0.041017376,0.0017859754],"about_ca_topic_score_codex":0.0011967211,"about_ca_topic_score_gemma":0.0007520414,"teacher_disagreement_score":0.64568526,"about_ca_system_score_codex":0.00012813164,"about_ca_system_score_gemma":0.00004963662,"threshold_uncertainty_score":0.99942607},"labels":[],"label_agreement":null},{"id":"W3033579812","doi":"10.1093/gigascience/giaa106","title":"File-based localization of numerical perturbations in data analysis pipelines","year":2020,"lang":"en","type":"preprint","venue":"GigaScience","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital; Concordia University","funders":"Taylor Family Institute for Innovative Psychiatric Research, Washington University School of Medicine in St. Louis","keywords":"Pipeline transport; Pipeline (software); Computer science; Process (computing); Numerical analysis; Engineering; Mathematics; Mechanical engineering","score_opus":0.34348498514809667,"score_gpt":0.4379596613734127,"score_spread":0.09447467622531602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033579812","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013530537,0.000056829445,0.99181956,0.003000666,0.00067782385,0.00021521971,0.0022052876,0.000044803804,0.0006267624],"genre_scores_gemma":[0.9687724,0.0000043086848,0.027333952,0.00048127,0.00006380944,0.000012634199,0.0029041986,0.0000068895642,0.00042053434],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934693,0.0002936281,0.001194909,0.0022305336,0.002556076,0.00025556545],"domain_scores_gemma":[0.9928064,0.0014177449,0.00067438534,0.004566527,0.0004000228,0.00013496917],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005449075,0.0001860317,0.00054579927,0.0013287032,0.00012656047,0.0005873694,0.0067489427,0.00008544395,0.001082081],"category_scores_gemma":[0.017583793,0.00014964031,0.00016323228,0.010588389,0.00029232935,0.00028813208,0.0054302486,0.00018082667,0.00008755433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058577452,0.000113632996,0.013693748,0.000019977922,0.000024046152,0.000004518647,0.00030288583,0.864175,0.000012044215,0.0002032156,0.10867122,0.012773843],"study_design_scores_gemma":[0.00007341586,0.000009028451,0.020098712,0.000036750404,0.00007112441,1.2696684e-7,0.00015417178,0.9649713,0.000014110433,0.0030568214,0.011367392,0.00014702891],"about_ca_topic_score_codex":0.00042315116,"about_ca_topic_score_gemma":0.00026323396,"teacher_disagreement_score":0.9674193,"about_ca_system_score_codex":0.000043332668,"about_ca_system_score_gemma":0.00045777764,"threshold_uncertainty_score":0.9998311},"labels":[],"label_agreement":null},{"id":"W3036259867","doi":"10.1093/gigascience/giaa066","title":"CandiMeth: Powerful yet simple visualization and quantification of DNA methylation at candidate genes","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Epigenetics and DNA Methylation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Economic and Social Research Council; Biotechnology and Biological Sciences Research Council; Medical Research Council Canada; Public Health Agency; Medical Research Council; Cereal Partners Worldwide","keywords":"DNA methylation; Computational biology; Genome browser; Biology; Methylation; Workflow; Visualization; Genome; Epigenomics; Candidate gene; Epigenetics; Genomics; Computer science; Gene; Genetics; Data mining; Database; Gene expression","score_opus":0.022366074360956174,"score_gpt":0.2937630208027434,"score_spread":0.27139694644178725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036259867","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9563856,0.00133981,0.041787744,0.00013936278,0.00005796468,0.00011988288,0.00002134755,0.00000708568,0.00014116034],"genre_scores_gemma":[0.99875003,0.0004893411,0.00041786997,0.000080752376,0.000036627185,0.0000029314326,0.00016236227,0.000008106565,0.00005199966],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991843,0.000056363686,0.00019251482,0.00029867853,0.00015296137,0.00011517304],"domain_scores_gemma":[0.99950933,0.000015671203,0.00014286065,0.00015180792,0.00009909353,0.00008124087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025005467,0.00008084979,0.00009152415,0.00003233637,0.00008177116,0.00001820486,0.00009604965,0.00006324358,0.0000134752845],"category_scores_gemma":[0.00019444768,0.000079131954,0.000024224108,0.00019757627,0.000098485965,0.000009121384,0.000078689125,0.000020475043,0.000003398826],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020185229,0.000007305683,0.007980694,0.000013477301,0.0000042701135,1.213029e-7,0.00019021533,0.0002831835,0.98865414,0.0002284203,0.000060033664,0.0025579664],"study_design_scores_gemma":[0.00014617671,0.00015589614,0.011107063,0.0000027802048,0.000009599823,5.310494e-7,0.000044926892,0.0037792502,0.9787745,0.00013261299,0.0057531125,0.000093585666],"about_ca_topic_score_codex":0.000051105897,"about_ca_topic_score_gemma":0.000059113423,"teacher_disagreement_score":0.042364366,"about_ca_system_score_codex":0.000008847208,"about_ca_system_score_gemma":0.00004460389,"threshold_uncertainty_score":0.32269076},"labels":[],"label_agreement":null},{"id":"W3072271736","doi":"10.1093/gigascience/giaa080","title":"Initial data release and announcement of the 10,000 Fish Genomes Project (Fish10K)","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":100,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Vertebrate; Fish <Actinopterygii>; Workflow; Genome; Genomics; Biology; Evolutionary biology; Procurement; Data science; Computer science; Computational biology; Fishery; Business; Database; Genetics","score_opus":0.054097061056457715,"score_gpt":0.279385028098642,"score_spread":0.2252879670421843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3072271736","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99591583,0.0010991134,0.000054303182,0.0011819379,0.00008046904,0.00017926742,0.00034303323,0.0000016637786,0.0011443566],"genre_scores_gemma":[0.99794185,0.0004399111,0.00032489674,0.001073188,0.00009999023,0.0000054222455,0.00002136463,0.000004323455,0.000089045214],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992821,0.00002453516,0.00011821426,0.000324146,0.00011852671,0.00013245214],"domain_scores_gemma":[0.9994402,0.000006509316,0.00005870845,0.00040052267,0.000052702548,0.000041345415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012259596,0.00007584376,0.00008018813,0.000007399464,0.00009695214,0.000017617294,0.00053515186,0.000026343916,0.0000073106157],"category_scores_gemma":[0.00012779722,0.000054378444,0.000019254896,0.00012721906,0.00025541734,0.0000015281217,0.0009056659,0.000032020525,7.561774e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007134089,0.000045319837,0.012789185,0.000048834492,0.000046421577,0.0000019062783,0.00089846784,0.000046200727,0.9541286,0.0000635579,0.020638028,0.011222091],"study_design_scores_gemma":[0.0010028401,0.00092762726,0.07530652,0.000023443019,0.00006627959,0.000017398906,0.0009657512,0.0012106198,0.2147507,0.00009400519,0.70516354,0.00047125993],"about_ca_topic_score_codex":0.000024299403,"about_ca_topic_score_gemma":0.000020592423,"teacher_disagreement_score":0.7393779,"about_ca_system_score_codex":0.0000023395473,"about_ca_system_score_gemma":0.00011398064,"threshold_uncertainty_score":0.22174886},"labels":[],"label_agreement":null},{"id":"W3090042218","doi":"10.1093/gigascience/giaa095","title":"An extensible big data software architecture managing a research resource of real-world clinical radiology data linked to other health data from the whole Scottish population","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Economic and Social Research Council; Engineering and Physical Sciences Research Council; Chief Scientist Office, Scottish Government Health and Social Care Directorate; Medical Research Council Canada; Medical Research Council; Public Health Agency; Department of Health and Social Care; British Heart Foundation; Scottish Government; Health and Social Care Research and Development Division; National Institute for Health and Care Research; NHS Health Scotland; Wellcome Trust; University of Dundee","keywords":"Computer science; Data science; Resource (disambiguation); Software; Population; Big data; Open data; Architecture; Data management; Modalities; World Wide Web; Data mining; Medicine; Geography","score_opus":0.734126092735917,"score_gpt":0.5776870521595462,"score_spread":0.1564390405763708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090042218","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5692049,0.0012309289,0.0634786,0.36016193,0.0011322821,0.0021934216,0.002277704,0.00017065488,0.00014951381],"genre_scores_gemma":[0.9455948,0.00020659732,0.024291022,0.020684317,0.003214955,0.000007830728,0.0058742943,0.000033100463,0.000093108996],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99566185,0.00093320094,0.0008124486,0.0014279374,0.0006676968,0.0004968375],"domain_scores_gemma":[0.9913264,0.0014290332,0.00020971913,0.006346861,0.00018407966,0.00050392706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077952635,0.00011858802,0.00036134667,0.00013355067,0.00038738656,0.000067977766,0.0039620283,0.000083200815,0.00003195855],"category_scores_gemma":[0.007566427,0.00008928967,0.00001977409,0.0014253106,0.00043438945,0.00032403762,0.0018113112,0.000708475,0.000050526924],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027964113,0.00012440432,0.18013918,0.000074566684,0.000015246381,0.000006832763,0.004023891,0.00027678796,0.0005138812,0.000042903997,0.08274309,0.73175955],"study_design_scores_gemma":[0.000260678,0.0018486546,0.67132527,0.0010913763,0.00007705017,0.000020996655,0.009234415,0.09325275,0.000116859475,0.0038329123,0.21852627,0.00041275655],"about_ca_topic_score_codex":0.053427562,"about_ca_topic_score_gemma":0.022933444,"teacher_disagreement_score":0.7313468,"about_ca_system_score_codex":0.000050901406,"about_ca_system_score_gemma":0.0009282235,"threshold_uncertainty_score":0.99489546},"labels":[],"label_agreement":null},{"id":"W3092870154","doi":"10.1093/gigascience/giaa104","title":"The genetics-BIDS extension: Easing the search for genetic data associated with human brain imaging","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine","funders":"Wellcome Trust","keywords":"Imaging genetics; Human genetics; Neuroscience; Genetic data; Neuroimaging; Computational biology; Computer science; Data science; Genetics; Psychology; Biology; Medicine; Gene","score_opus":0.07224503405580496,"score_gpt":0.3304395405562857,"score_spread":0.25819450650048076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092870154","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90031385,0.0024934306,0.066066906,0.029901847,0.00018946455,0.000640617,0.000036429552,0.00003025574,0.00032719164],"genre_scores_gemma":[0.9963347,0.000056724282,0.0006514198,0.0024427762,0.00017751587,0.00002393362,0.00005671513,0.000014145192,0.00024212651],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99877626,0.00008768367,0.00013130638,0.0004947352,0.00025119536,0.00025884056],"domain_scores_gemma":[0.9988824,0.000050387214,0.000070484195,0.0007850572,0.00012840165,0.00008325506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005289416,0.00009359276,0.00006030328,0.000009947137,0.0008006049,0.00014767343,0.0010431075,0.000030968138,0.0000031820277],"category_scores_gemma":[0.00023439858,0.000052960415,0.000026845873,0.00020128985,0.0003165757,0.000006331278,0.00030336113,0.00007622039,0.0000020098119],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024505698,0.000010328789,0.002176333,0.0000032125047,0.0000090508,7.5925936e-7,0.00012406326,0.00017274577,0.9712514,0.000072397,0.01305558,0.013099607],"study_design_scores_gemma":[0.001822935,0.0008001097,0.19690685,0.00008313763,0.00007156925,0.00003361174,0.0023812896,0.08282833,0.34711796,0.00032811478,0.36687133,0.0007547768],"about_ca_topic_score_codex":0.0000038543426,"about_ca_topic_score_gemma":0.000017304175,"teacher_disagreement_score":0.62413347,"about_ca_system_score_codex":0.000009656894,"about_ca_system_score_gemma":0.00014206214,"threshold_uncertainty_score":0.6157686},"labels":[],"label_agreement":null},{"id":"W3095596037","doi":"10.1093/gigascience/giab025","title":"An analysis of security vulnerabilities in container images for scientific data analysis","year":2021,"lang":"en","type":"preprint","venue":"GigaScience","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Container (type theory); Vulnerability (computing); Computer science; Software deployment; Software; Secure coding; Computer security; Vulnerability management; Vulnerability assessment; Software security assurance; Security analysis; Attack surface; Security bug; Information security; Software engineering; Engineering; Operating system; Security service","score_opus":0.2169682895091375,"score_gpt":0.45563119819616094,"score_spread":0.23866290868702345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095596037","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81947714,0.00029846764,0.17240219,0.00028719986,0.0017087902,0.00047451857,0.0050729294,0.00004187296,0.00023686867],"genre_scores_gemma":[0.9840774,0.0000070668484,0.011779136,0.000047959347,0.000039320388,0.000031581607,0.0034150435,0.0000077272125,0.0005947723],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9876366,0.00078577467,0.0019127758,0.005440077,0.003585038,0.0006396965],"domain_scores_gemma":[0.9805954,0.0022956755,0.0010140585,0.014224005,0.0016485672,0.00022229226],"candidate_categories":["metaresearch","metaepi_narrow","bibliometrics","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.048143283,0.0003408676,0.0015616121,0.006477854,0.00042627292,0.005280026,0.012348314,0.00014383759,0.000341108],"category_scores_gemma":[0.011535269,0.00028335874,0.0007022448,0.022887282,0.0014150252,0.0013167667,0.008475308,0.0003249436,0.0000046834116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036934365,0.00082999497,0.20037904,0.000101106634,0.001587924,0.00001541996,0.008319709,0.76674396,0.0006552944,0.0012073019,0.0065179165,0.013605396],"study_design_scores_gemma":[0.00013186627,0.000025941323,0.0888861,0.000026505793,0.0017563814,2.2656627e-7,0.008139844,0.8942288,0.00019869984,0.0054058256,0.00088007085,0.0003197288],"about_ca_topic_score_codex":0.002248661,"about_ca_topic_score_gemma":0.01024414,"teacher_disagreement_score":0.16460022,"about_ca_system_score_codex":0.00011439717,"about_ca_system_score_gemma":0.0006608214,"threshold_uncertainty_score":0.99996185},"labels":[],"label_agreement":null},{"id":"W3116451876","doi":"10.1093/gigascience/giaa149","title":"GALLO: An R package for genomic annotation and integration of multiple data sources in livestock for positional candidate loci","year":2020,"lang":"en","type":"article","venue":"GigaScience","topic":"Genetic Mapping and Diversity in Plants and Animals","field":"Biochemistry, Genetics and Molecular Biology","cited_by":327,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Agriculture and Agri-Food Canada; Beef Cattle Research Council; Beef Farmers of Ontario; Alberta Beef Producers","keywords":"Annotation; Computational biology; Livestock; R package; Genome; Computer science; Biology; Genomic selection; Data science; Genetics; Bioinformatics; Information retrieval; Gene; Genotype; Single-nucleotide polymorphism","score_opus":0.045845087855967345,"score_gpt":0.27261234929252914,"score_spread":0.22676726143656178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116451876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96582186,0.00006242506,0.033093106,0.00021657105,0.000014304543,0.00020162492,0.000572322,0.0000020222992,0.000015758802],"genre_scores_gemma":[0.99262214,0.000025618989,0.0062743477,0.00017463739,0.000037613256,0.000007048858,0.000840113,0.0000020043806,0.000016460408],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99958396,0.000009714016,0.00007871471,0.00021058435,0.00004105981,0.00007596209],"domain_scores_gemma":[0.9997868,0.00001375307,0.000041238512,0.00008503145,0.000034463472,0.00003870391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011435704,0.000042820255,0.000053451506,0.000014734137,0.00005474208,0.00001801266,0.00014656923,0.00002299175,0.0000014848321],"category_scores_gemma":[0.00009127439,0.000040417624,0.000010079247,0.000028660708,0.000049584298,0.00000953376,0.000054767068,0.00001336229,2.210818e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009159152,0.00001787218,0.00624789,0.000018513858,0.0000024792682,9.480031e-8,0.0002668178,0.00009670348,0.9921208,0.000053798984,0.00028862376,0.00079482613],"study_design_scores_gemma":[0.003830851,0.0056242235,0.37324014,0.00006308433,0.000047652185,0.000010153059,0.0032760752,0.12370332,0.47928694,0.000775349,0.009578674,0.0005635309],"about_ca_topic_score_codex":0.000041258794,"about_ca_topic_score_gemma":0.00009826538,"teacher_disagreement_score":0.51283383,"about_ca_system_score_codex":0.0000017410543,"about_ca_system_score_gemma":0.00003073196,"threshold_uncertainty_score":0.16481829},"labels":[],"label_agreement":null},{"id":"W3122054437","doi":"10.1093/gigascience/giaa155","title":"Understanding the impact of preprocessing pipelines on neuroimaging cortical surface analyses","year":2021,"lang":"en","type":"article","venue":"GigaScience","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health; Université de Montréal; Douglas Mental Health University Institute; McGill University; Montreal Neurological Institute and Hospital","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; National Institutes of Health","keywords":"Computer science; Neuroimaging; Preprocessor; Pipeline (software); Artificial intelligence; Human Connectome Project; Software; Machine learning; Replicate; Functional magnetic resonance imaging; Univariate; Task (project management); Data mining; Pattern recognition (psychology); Multivariate statistics; Psychology; Statistics; Functional connectivity","score_opus":0.3705436409879074,"score_gpt":0.4177528521224563,"score_spread":0.0472092111345489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122054437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9798477,0.000070705195,0.013632354,0.002896795,0.00020635525,0.00007224265,0.0000060425596,0.000047674494,0.0032201235],"genre_scores_gemma":[0.9988843,0.000013019962,0.00011420361,0.0008477212,0.000031820837,0.0000013955672,1.5525012e-7,0.0000074054637,0.000099969584],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99827296,0.00020148196,0.00018353804,0.00054478727,0.0005236777,0.00027353814],"domain_scores_gemma":[0.9931168,0.0062920866,0.00010142413,0.00034187984,0.000097883065,0.000049916205],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00041979455,0.00012180403,0.00015794496,0.000048653088,0.00061820186,0.000115932795,0.00028556475,0.000016455415,0.000024943492],"category_scores_gemma":[0.020228632,0.00007704332,0.00011521492,0.0012450304,0.00065609306,0.00026348443,0.00017029527,0.0001820328,0.00000878664],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018531935,0.0000617923,0.008305383,0.000008214835,0.0000053015006,0.000019689358,0.0003451411,0.04689669,0.94262975,0.0012773317,0.0003145285,0.000117638396],"study_design_scores_gemma":[0.00024384442,0.00018201023,0.06283859,0.00009068746,0.000022714585,0.00011627056,0.0013862586,0.08961654,0.8396254,0.005614898,0.00002642328,0.00023634364],"about_ca_topic_score_codex":0.000025181089,"about_ca_topic_score_gemma":0.000006208705,"teacher_disagreement_score":0.10300434,"about_ca_system_score_codex":0.00010237122,"about_ca_system_score_gemma":0.00021891379,"threshold_uncertainty_score":0.9880244},"labels":[],"label_agreement":null},{"id":"W3127731354","doi":"10.1093/gigascience/giab006","title":"AXIOME3: Automation, eXtension, and Integration Of Microbial Ecology","year":2021,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Nuclear Waste Management Organization; Natural Sciences and Engineering Research Council of Canada; McKnight Foundation","keywords":"Computer science; Visualization; Pipeline (software); Data mining; Graphical user interface; Usability; Data visualization; Programming language; Human–computer interaction","score_opus":0.009364098253512788,"score_gpt":0.23302492872562133,"score_spread":0.22366083047210855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127731354","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99775106,0.00058271753,0.0011018572,0.00018961159,0.00013425088,0.000038466413,0.0000054341176,0.000001287854,0.00019533573],"genre_scores_gemma":[0.9960051,0.00023660512,0.0034215092,0.00016238989,0.00002795182,0.0000026521204,0.000007685918,0.000002592066,0.00013347389],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999552,0.000020819076,0.00010485475,0.00019636417,0.000041869953,0.00008406402],"domain_scores_gemma":[0.99965376,0.0000075749217,0.000029801582,0.00013503451,0.00015095375,0.000022894648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010773803,0.000048040823,0.00006795388,0.000017812648,0.000058026824,0.000008335999,0.000058645568,0.00003085452,0.000005322719],"category_scores_gemma":[0.0001137645,0.000044476397,0.000016583388,0.00008108299,0.00013885305,7.058288e-7,0.000095792275,0.000017325756,0.0000011538094],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004050647,0.000015356527,0.0021509926,0.0000033411002,0.0000043907685,5.7910574e-7,0.00006139468,0.0000143586185,0.99577135,0.0002389786,0.00021871591,0.0015164737],"study_design_scores_gemma":[0.00013290247,0.00013277629,0.23235367,0.0000038338903,0.0000047725134,0.000028558692,0.00008292034,0.00008834781,0.76544607,0.00024799677,0.0014227048,0.000055463326],"about_ca_topic_score_codex":0.0000063882944,"about_ca_topic_score_gemma":0.00006503607,"teacher_disagreement_score":0.23032533,"about_ca_system_score_codex":0.000002754066,"about_ca_system_score_gemma":0.00006561847,"threshold_uncertainty_score":0.18136948},"labels":[],"label_agreement":null},{"id":"W3136433340","doi":"10.1093/gigascience/giab021","title":"Torix <i>Rickettsia</i> are widespread in arthropods and reflect a neglected symbiosis","year":2021,"lang":"en","type":"article","venue":"GigaScience","topic":"Insect symbiosis and bacterial influences","field":"Agricultural and Biological Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Biotechnology and Biological Sciences Research Council; Natural Environment Research Council; Sight Research UK; Institute for the Promotion of Teaching Science and Technology","keywords":"Biology; Rickettsia; Wolbachia; Arthropod; Host (biology); Zoology; Ecology; Virology","score_opus":0.011885331804250526,"score_gpt":0.20502760721544347,"score_spread":0.19314227541119294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136433340","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960214,0.0004864912,6.831333e-7,0.0021413355,0.00028213122,0.00008884195,0.000014366559,0.000046489487,0.0009182516],"genre_scores_gemma":[0.99833524,0.00020873055,0.00015145537,0.0010528339,0.00011319664,0.000011978154,0.0000070727697,7.4167247e-7,0.00011873156],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99856603,0.000108398955,0.00022711465,0.0004925998,0.0002213282,0.00038450438],"domain_scores_gemma":[0.99948883,0.00014869729,0.00008408684,0.000078359204,0.000095587755,0.00010446213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018564222,0.00014272015,0.00020837474,0.000017323007,0.000253576,0.00021458721,0.00022099522,0.00008585302,0.00021002199],"category_scores_gemma":[0.00022289937,0.00006114304,0.000048622598,0.00118701,0.00019301772,0.00028854568,0.00011879396,0.00011144563,0.00001534128],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008510978,0.00005266105,0.039284293,0.0000037786808,0.0000018267061,0.000025446328,0.00009939364,2.7645189e-7,0.9482731,0.00012741656,0.00016181807,0.011961488],"study_design_scores_gemma":[0.0001284311,0.00016270431,0.82392967,0.00010981672,0.0000047920357,0.000041710904,0.0004455662,0.000019127228,0.1698968,0.00057142397,0.004438023,0.00025194045],"about_ca_topic_score_codex":0.0004690497,"about_ca_topic_score_gemma":0.0033591986,"teacher_disagreement_score":0.7846454,"about_ca_system_score_codex":0.000028815257,"about_ca_system_score_gemma":0.000025932051,"threshold_uncertainty_score":0.24933408},"labels":[],"label_agreement":null},{"id":"W3159102117","doi":"10.1093/gigascience/giab029","title":"The germline mutational process in rhesus macaque and its implications for phylogenetic dating","year":2021,"lang":"en","type":"article","venue":"GigaScience","topic":"Cancer Genomics and Diagnostics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trinity College","funders":"European Research Council; Novo Nordisk Fonden; Carlsbergfondet; Aarhus Universitet; Chinese Academy of Sciences; Villum Fonden","keywords":"Macaque; Phylogenetic tree; Germline; Rhesus macaque; Process (computing); Biology; Evolutionary biology; Phylogenetics; Genetics; Computational biology; Computer science; Paleontology; Gene","score_opus":0.015313918316185613,"score_gpt":0.306229397649273,"score_spread":0.29091547933308737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159102117","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99478424,0.0018487958,0.0017443334,0.0012377575,0.000050472572,0.00013492047,0.000054209773,0.0000016451688,0.00014364958],"genre_scores_gemma":[0.9983586,0.00036579862,0.0007714557,0.00024989035,0.000061522005,0.00008487494,0.000039798088,0.0000041886015,0.00006388541],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995243,0.000007770466,0.00009674456,0.0002055189,0.000038551396,0.00012712565],"domain_scores_gemma":[0.999647,0.000068489826,0.000032556527,0.000107433196,0.00011370806,0.00003079179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010120937,0.00004389103,0.000036758454,0.000009211251,0.00015001821,0.000038461374,0.00010707436,0.000024200312,0.0000011247766],"category_scores_gemma":[0.0004292773,0.000038244616,0.000013387366,0.00009709133,0.000052432017,0.000002075954,0.000053415122,0.000023343777,3.5958013e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012866683,0.000031150626,0.0076741157,0.000021288399,0.0000055317682,0.0000011346945,0.00009046963,0.0017160231,0.9721466,0.006126338,0.00015353886,0.012020967],"study_design_scores_gemma":[0.0012035344,0.0001890201,0.24836054,0.00003098148,0.000017894406,0.000115794646,0.00042300107,0.009995056,0.7099417,0.0137977395,0.015524943,0.0003997821],"about_ca_topic_score_codex":0.0000018656623,"about_ca_topic_score_gemma":0.00010092218,"teacher_disagreement_score":0.26220486,"about_ca_system_score_codex":0.000006657598,"about_ca_system_score_gemma":0.00021086645,"threshold_uncertainty_score":0.15595701},"labels":[],"label_agreement":null},{"id":"W3183267169","doi":"10.1093/gigascience/giab055","title":"Preventing dataset shift from breaking machine-learning biomarkers","year":2021,"lang":"en","type":"review","venue":"GigaScience","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":92,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; National Institutes of Health; Agence Nationale de la Recherche","keywords":"Biomarker; Machine learning; Artificial intelligence; Computer science; Biomarker discovery; Population; Medicine; Biology; Proteomics","score_opus":0.2725123400981636,"score_gpt":0.4901105873463265,"score_spread":0.2175982472481629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183267169","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015721022,0.9974869,0.0002750795,0.0001802307,0.00086115114,0.0004330798,0.00030073727,0.00005359635,0.00025201062],"genre_scores_gemma":[0.00035737822,0.99034923,0.0013442944,0.00021985045,0.00046790647,0.000041491352,0.0070560365,0.000031682932,0.00013213772],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99744534,0.0002356268,0.00072921853,0.00074756285,0.00040960457,0.00043262224],"domain_scores_gemma":[0.9983498,0.00040201886,0.00039315867,0.0005670427,0.0000677442,0.00022026002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087161,0.00027037467,0.0009072427,0.00017884254,0.00032503103,0.00012397206,0.0003425509,0.00020923547,0.00046761485],"category_scores_gemma":[0.0010007372,0.00022971506,0.00024117013,0.00084314967,0.00012597837,0.00016661944,0.00017196799,0.0006533268,0.0002432127],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014593654,0.000029818333,0.00036502883,0.0020098598,0.00003911011,0.00003898804,0.00024607722,5.272836e-7,0.000002590205,0.000011878606,0.0007443375,0.9965103],"study_design_scores_gemma":[0.000010223566,0.00003148293,0.000026731122,0.017005485,0.00036649388,0.000066933804,0.00019986965,0.0001298156,0.000021479987,0.000037915634,0.98189497,0.00020857797],"about_ca_topic_score_codex":0.0029799375,"about_ca_topic_score_gemma":0.000118313306,"teacher_disagreement_score":0.9963018,"about_ca_system_score_codex":0.00016645456,"about_ca_system_score_gemma":0.0011826189,"threshold_uncertainty_score":0.9367508},"labels":[],"label_agreement":null},{"id":"W3195098488","doi":"10.1093/gigascience/giab051","title":"Centering inclusivity in the design of online conferences—An OHBM–Open Science perspective","year":2021,"lang":"en","type":"article","venue":"GigaScience","topic":"Conferences and Exhibitions Management","field":"Social Sciences","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hospital for Sick Children; Montreal Heart Institute; Université de Montréal; Centre for Addiction and Mental Health; University of Toronto; Montreal Neurological Institute and Hospital; Université de Sherbrooke; Centre Hospitalier Universitaire Sainte-Justine; Polytechnique Montréal; Concordia University; McGill University","funders":"National Institute on Drug Abuse; National Institute of Mental Health; University of Sydney; Biotechnology and Biological Sciences Research Council; Alan Turing Institute; Fonds Wetenschappelijk Onderzoek; Weizmann Institute of Science; Motor Neurone Disease Australia; National Center for Advancing Translational Sciences; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Wellcome Trust; Vlaamse regering; National Institutes of Health; National Science Foundation","keywords":"Perspective (graphical); Open science; Data science; Computer science; Citizen science; Engineering ethics; World Wide Web; Engineering; Artificial intelligence; Mathematics; Biology","score_opus":0.12125578782261576,"score_gpt":0.4088888678745069,"score_spread":0.28763308005189114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3195098488","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7506347,0.00014741682,0.018610341,0.02168455,0.00055699464,0.0012563544,0.000024961433,0.000046132976,0.20703855],"genre_scores_gemma":[0.9968041,0.00010088873,0.0025184052,0.00039826002,0.000035719608,0.000014821653,0.0000011427807,0.0000020707419,0.00012457765],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9974822,0.00042985808,0.00019404602,0.00045486892,0.0010546619,0.00038439594],"domain_scores_gemma":[0.99861634,0.000145013,0.000095485455,0.00039119882,0.00066286576,0.000089116926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055527124,0.00008218046,0.00014035238,0.00012483362,0.0011071045,0.00053839287,0.0031202005,0.000024596715,0.00015194497],"category_scores_gemma":[0.001006596,0.00006444538,0.000027141125,0.002221989,0.0017574104,0.0009935399,0.0010008935,0.000118820244,0.000004188291],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011037158,0.0006105425,0.002962503,0.000006487231,0.0000032513487,0.000025946018,0.07418969,0.0004649775,0.003941477,0.9027377,0.00006586608,0.01498054],"study_design_scores_gemma":[0.0006613799,0.00034380134,0.13170502,0.00021049642,0.000021936074,0.000009113703,0.7609185,0.008654686,0.0020576129,0.08459371,0.01031641,0.00050732633],"about_ca_topic_score_codex":0.015658865,"about_ca_topic_score_gemma":0.037639327,"teacher_disagreement_score":0.81814396,"about_ca_system_score_codex":0.00024342437,"about_ca_system_score_gemma":0.0032895207,"threshold_uncertainty_score":0.9908959},"labels":[],"label_agreement":null},{"id":"W3207397300","doi":"10.1093/gigascience/giab071","title":"Population modeling with machine learning can enhance measures of mental health","year":2021,"lang":"en","type":"article","venue":"GigaScience","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"Medical Research Council; Canadian Institutes of Health Research; Canada First Research Excellence Fund","keywords":"Biobank; Machine learning; Artificial intelligence; Population; Mental health; Computer science; Psychology; Clinical psychology; Cognitive psychology; Medicine; Psychiatry; Bioinformatics; Environmental health","score_opus":0.059099745124013385,"score_gpt":0.28788506039609474,"score_spread":0.22878531527208135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3207397300","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97001916,0.00032097497,0.02073065,0.008116919,0.0001933208,0.00012896265,0.000015436895,0.00006376388,0.00041079056],"genre_scores_gemma":[0.99740475,0.000058165853,0.0012715624,0.0010559887,0.000016246691,0.0000052528385,0.0000029809705,0.0000073447427,0.0001777152],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99845326,0.0001348602,0.00015929293,0.00044654176,0.0005815809,0.0002244733],"domain_scores_gemma":[0.99933803,0.00027289407,0.00010558293,0.00014868728,0.00008015716,0.000054669854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034653558,0.00009194316,0.0001557494,0.000054524102,0.00048537174,0.000026056008,0.00012693858,0.000013362585,0.00000867728],"category_scores_gemma":[0.0023323367,0.00007990179,0.000026665366,0.0005681956,0.00011366203,0.00018867492,0.000081793136,0.00012542047,0.0000020589134],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079021826,0.00014801483,0.02949564,0.00006372912,0.000009525912,0.000012189755,0.0032884723,0.15819238,0.7892427,0.0053423876,0.000083186176,0.014042735],"study_design_scores_gemma":[0.0005761571,0.0005720496,0.010278946,0.00023307269,0.0000073343535,0.00013474716,0.00085465424,0.34637967,0.6386621,0.0011964123,0.0006765077,0.0004283412],"about_ca_topic_score_codex":0.0005698916,"about_ca_topic_score_gemma":0.0012224257,"teacher_disagreement_score":0.18818727,"about_ca_system_score_codex":0.00008494887,"about_ca_system_score_gemma":0.00016107662,"threshold_uncertainty_score":0.3733136},"labels":[],"label_agreement":null},{"id":"W4200033631","doi":"10.1093/gigascience/giab086","title":"On the relationship between research parasites and fairness in machine learning: challenges and opportunities","year":2021,"lang":"en","type":"article","venue":"GigaScience","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Universidad Nacional del Litoral; International Development Research Centre; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Computer science; Diversity (politics); Unintended consequences; Artificial intelligence; Field (mathematics); Machine learning; Work (physics); Data science; Training set; Knowledge management; Management science; Sociology; Political science; Economics; Engineering; Law","score_opus":0.6342861627828406,"score_gpt":0.48627200238538637,"score_spread":0.1480141603974542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200033631","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8494382,0.002494381,0.0000026066646,0.11360549,0.000025402138,0.000070216825,0.0000014589681,0.0000125905535,0.03434969],"genre_scores_gemma":[0.9919343,0.0063711912,0.000016648495,0.00019058242,0.00004491157,0.0000048825245,7.5985565e-7,0.0000032246828,0.0014335162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9978968,0.001022113,0.00008876649,0.0001957713,0.00052401854,0.00027252926],"domain_scores_gemma":[0.9936594,0.0059511964,0.000028364651,0.000094960225,0.00015519117,0.00011092588],"candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.006973981,0.000050930274,0.00008444049,0.00007441899,0.0015186279,0.0002661209,0.00016824075,0.000081163475,0.000013922239],"category_scores_gemma":[0.012830126,0.00003932679,0.000010950343,0.00028113998,0.0015531237,0.00027509697,0.000093156836,0.00055116066,0.0000028629158],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.543579e-7,0.000007766489,0.10512221,0.000005210314,9.641154e-7,0.0000065601917,0.03711614,7.609501e-7,0.000008746219,0.8529368,0.000018452303,0.0047755134],"study_design_scores_gemma":[0.000053117885,0.000041245494,0.6122316,0.000048420905,0.0000014209677,5.02256e-7,0.041826334,0.000014221683,0.0000167822,0.34321645,0.0024850431,0.00006484115],"about_ca_topic_score_codex":0.00074358174,"about_ca_topic_score_gemma":0.004141732,"teacher_disagreement_score":0.5097204,"about_ca_system_score_codex":0.000027043066,"about_ca_system_score_gemma":0.00025447493,"threshold_uncertainty_score":0.99978125},"labels":[],"label_agreement":null},{"id":"W4200087885","doi":"10.1093/gigascience/giab087","title":"Multi-dimensional leaf phenotypes reflect root system genotype in grafted grapevine over the growing season","year":2021,"lang":"en","type":"article","venue":"GigaScience","topic":"Horticultural and Viticultural Research","field":"Agricultural and Biological Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Agricultural Research Service; Saint Louis University; University of Missouri; U.S. Department of Agriculture; National Science Foundation","keywords":"Rootstock; Biology; Phenotype; Shoot; Vine; Growing season; Metabolomics; Modalities; Botany; Genetics; Bioinformatics; Gene","score_opus":0.03864156922018465,"score_gpt":0.28274587277751684,"score_spread":0.2441043035573322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200087885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9939167,0.00074024557,0.0000019623196,0.004660621,0.00016643961,0.00020002206,0.000011760067,0.000067215646,0.00023503497],"genre_scores_gemma":[0.9981263,0.000018797535,0.00016628363,0.0004675502,0.00016431304,0.00002320327,0.000027676746,0.0000011649823,0.0010047045],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9976963,0.00022579837,0.0002594526,0.00053467473,0.00067819067,0.000605611],"domain_scores_gemma":[0.9992535,0.0001999436,0.000056232704,0.00011064006,0.00021926273,0.00016042782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005429558,0.00017902357,0.00020018512,0.000014217581,0.0005520722,0.00018062604,0.00048649378,0.0000774649,0.0002074758],"category_scores_gemma":[0.00029101557,0.000052074756,0.00011379643,0.0016113296,0.00016575771,0.0004759861,0.00023334967,0.00026453467,0.00009743612],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001774215,0.00006121485,0.006316962,0.000010947284,0.000006094284,0.00006121988,0.0000904377,0.000065471366,0.9821914,0.0005562542,0.0001968027,0.010425476],"study_design_scores_gemma":[0.00021541963,0.00010428239,0.96019316,0.00011191672,0.000009585018,0.000055081848,0.0008104642,0.0019039231,0.030126078,0.000042385127,0.0061710267,0.00025669826],"about_ca_topic_score_codex":0.00062304776,"about_ca_topic_score_gemma":0.0046968916,"teacher_disagreement_score":0.9538762,"about_ca_system_score_codex":0.00009870779,"about_ca_system_score_gemma":0.00004122061,"threshold_uncertainty_score":0.42461488},"labels":[],"label_agreement":null},{"id":"W4205642924","doi":"10.1093/gigascience/giaa074","title":"Corrigendum to: Metagenomic analysis of planktonic riverine microbial consortia using nanopore sequencing reveals insight into river microbe taxonomy and function","year":2020,"lang":"en","type":"erratum","venue":"GigaScience","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University and Génome Québec Innovation Centre; Canada's Michael Smith Genome Sciences Centre; University of British Columbia","funders":"Biotechnology and Biological Sciences Research Council","keywords":"Metagenomics; Computational biology; Taxonomy (biology); Function (biology); Biology; Nanopore sequencing; Evolutionary biology; Ecology; DNA sequencing; Genetics; Gene","score_opus":0.03866700205081907,"score_gpt":0.23517019834271335,"score_spread":0.19650319629189428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205642924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.985731,0.00045517273,0.0018537454,0.00010598173,0.007836846,0.00085059856,0.00024964768,0.000043419925,0.0028735604],"genre_scores_gemma":[0.96524835,0.00035971293,0.013765673,0.0037316214,0.00028029134,0.000039963277,0.0010344718,0.00006777857,0.015472155],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974557,0.00033462865,0.0006068809,0.0009240649,0.00019003372,0.0004886835],"domain_scores_gemma":[0.99847597,0.00006247224,0.00059208926,0.00060883857,0.00003856676,0.00022206226],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047236338,0.0004077378,0.0009961412,0.00035601627,0.0005268632,0.000037721242,0.00090156606,0.00042172527,0.0023827085],"category_scores_gemma":[0.00008434943,0.00041648478,0.00020914566,0.0016413729,0.0015742915,0.00022648838,0.0014233763,0.000776494,0.00011016878],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066632565,0.000029198254,0.0029576423,0.000055050637,0.00035230423,0.000013418215,0.0023041852,0.0016180705,0.8925707,0.000018489814,0.0996997,0.00031465117],"study_design_scores_gemma":[0.0005719501,0.0007252662,0.051354073,0.00015185883,0.0038582108,0.000059836446,0.00032026807,0.004371101,0.010022901,0.00027837008,0.9266668,0.0016193977],"about_ca_topic_score_codex":0.0036504765,"about_ca_topic_score_gemma":0.005004723,"teacher_disagreement_score":0.88254774,"about_ca_system_score_codex":0.00053141336,"about_ca_system_score_gemma":0.0002645727,"threshold_uncertainty_score":0.9998287},"labels":[],"label_agreement":null},{"id":"W4213288981","doi":"10.1093/gigascience/giac003","title":"Future-proofing and maximizing the utility of metadata: The PHA4GE SARS-CoV-2 contextual data specification package","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Dalhousie University; McMaster University; BC Centre for Disease Control; Simon Fraser University","funders":"Biotechnology and Biological Sciences Research Council; National Institutes of Health; U.S. National Library of Medicine; Wellcome Trust; Bill and Melinda Gates Foundation","keywords":"Interoperability; Computer science; Metadata; Harmonization; Standardization; Consistency (knowledge bases); Data science; Open science; Data sharing; Openness to experience; Best practice; Data integration; World Wide Web; Data mining; Medicine","score_opus":0.10222059033546696,"score_gpt":0.32143076272178844,"score_spread":0.21921017238632148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213288981","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9778286,0.006418903,0.009854907,0.0043890304,0.0004409376,0.00022561036,0.0002338732,0.000014866039,0.0005932454],"genre_scores_gemma":[0.9984371,0.00013049922,0.00074801984,0.0004493224,0.0001051429,0.000011008155,0.00005689081,0.0000035287521,0.000058466983],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99897474,0.00014378311,0.00015172968,0.00035065695,0.00022423825,0.00015483094],"domain_scores_gemma":[0.9988957,0.000056602596,0.00009927894,0.00090635376,0.000024604476,0.0000174613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00142754,0.00007258877,0.000088197936,0.000012536019,0.00041913387,0.000042486816,0.0011291221,0.000029632829,0.000007698054],"category_scores_gemma":[0.00026041918,0.000041302446,0.00002425591,0.00016103743,0.0007598143,0.000011564187,0.0011044106,0.00012798377,4.969393e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043883163,0.000043177828,0.00082813925,0.000009805319,0.000023679217,0.0000016436776,0.00045310645,7.177833e-7,0.85446745,0.0006959457,0.013839396,0.12959307],"study_design_scores_gemma":[0.00038029,0.00021686462,0.020756302,0.000006271174,0.00003765093,0.000069333844,0.007382172,0.0015229392,0.2917612,0.00039173363,0.677278,0.0001972853],"about_ca_topic_score_codex":0.000034679524,"about_ca_topic_score_gemma":0.000033987617,"teacher_disagreement_score":0.66343856,"about_ca_system_score_codex":0.0000037602772,"about_ca_system_score_gemma":0.000054800228,"threshold_uncertainty_score":0.32236812},"labels":[],"label_agreement":null},{"id":"W4221113494","doi":"10.1093/gigascience/giac005","title":"Democratizing data-independent acquisition proteomics analysis on public cloud infrastructures via the Galaxy framework","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Agence Nationale de la Recherche; Deutsche Forschungsgemeinschaft","keywords":"Cloud computing; Data science; Proteomics; Computer science; Galaxy; Astrophysics; Chemistry; Physics","score_opus":0.02169270853131717,"score_gpt":0.28820264880154306,"score_spread":0.2665099402702259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221113494","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21941315,0.00004083504,0.77624756,0.0022251531,0.000067497844,0.00033633137,0.00022017844,0.00018137737,0.0012679199],"genre_scores_gemma":[0.91835195,0.000011261458,0.08027693,0.00060071074,0.00012351676,0.00039899896,0.00015199835,0.000013599977,0.00007104088],"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99817324,0.000040228188,0.00025286575,0.0006212789,0.00059039594,0.00032197175],"domain_scores_gemma":[0.99782884,0.0001056632,0.0002333411,0.0017050969,0.000047943202,0.000079104364],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005349514,0.00015077156,0.00014727312,0.00009680343,0.0015086049,0.0001685088,0.0020289128,0.000062128536,0.00092910655],"category_scores_gemma":[0.000091439644,0.00012140448,0.00007858933,0.0012749102,0.00015533829,0.0002119105,0.0010221011,0.00066223444,0.000007167329],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000104242434,0.0003715379,0.016865656,0.000052798656,0.0003806982,0.000020792462,0.0015793561,0.064541094,0.6986272,0.1823816,0.0033411963,0.03173386],"study_design_scores_gemma":[0.00036763347,0.00014161601,0.0049195737,0.000033248103,0.00036390565,0.000098965895,0.001478958,0.13197568,0.2785096,0.5615755,0.019335551,0.0011998229],"about_ca_topic_score_codex":0.000024263578,"about_ca_topic_score_gemma":0.0000074327863,"teacher_disagreement_score":0.6989388,"about_ca_system_score_codex":0.0001723926,"about_ca_system_score_gemma":0.00008032249,"threshold_uncertainty_score":0.9999842},"labels":[],"label_agreement":null},{"id":"W4223923854","doi":"10.1093/gigascience/giac013","title":"Benchmarking missing-values approaches for predictive models on health databases","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; Museo delle Scienze; National Institutes of Health; Agence Nationale de la Recherche","keywords":"Missing data; Imputation (statistics); Benchmarking; Computer science; Predictive modelling; Machine learning; Discriminative model; Data mining; Benchmark (surveying); Artificial intelligence","score_opus":0.1635602176719167,"score_gpt":0.34281773681462735,"score_spread":0.17925751914271065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4223923854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002637379,0.00036952202,0.98412144,0.010072862,0.00071967306,0.0006650956,0.00007455598,0.0002687824,0.0010706615],"genre_scores_gemma":[0.7876184,0.000011795923,0.20825396,0.003465862,0.00014245436,0.00033767073,0.000033603716,0.00001762258,0.000118658],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968442,0.00035643898,0.00029373544,0.0009916947,0.00087611825,0.0006378343],"domain_scores_gemma":[0.99817187,0.0004776642,0.0002344819,0.00085452606,0.000052676744,0.00020876834],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0022663956,0.00017251569,0.0002096022,0.00019276411,0.0021004651,0.00013905148,0.0017777035,0.000016961769,0.000011353319],"category_scores_gemma":[0.00020217097,0.00016964217,0.0000684424,0.0007323604,0.00011774814,0.0006638202,0.0008649858,0.00036499609,0.0000022814033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026213029,0.00013353297,0.0005915409,0.00009262821,0.000005875535,0.000004294985,0.0053954413,0.5723672,0.000013262513,0.17331423,0.0033120702,0.2447437],"study_design_scores_gemma":[0.00014482741,0.0008219712,0.0006210472,0.00003508687,0.000001415566,0.000017679793,0.00020761302,0.9760832,0.000034344226,0.017615251,0.004253093,0.00016446858],"about_ca_topic_score_codex":0.00021862425,"about_ca_topic_score_gemma":0.000008517003,"teacher_disagreement_score":0.784981,"about_ca_system_score_codex":0.00027746195,"about_ca_system_score_gemma":0.00062546204,"threshold_uncertainty_score":0.9991987},"labels":[],"label_agreement":null},{"id":"W4225308572","doi":"10.1093/gigascience/giac040","title":"Message in a Bottle—Metabarcoding enables biodiversity comparisons across ecoregions","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"Ontario Ministry of Research, Innovation and Science; Canada Foundation for Innovation; Canada First Research Excellence Fund; University of Guelph","keywords":"Species richness; Biodiversity; Ecology; Beta diversity; Gamma diversity; Nestedness; Habitat; Arthropod; Metacommunity; Ecosystem; Geography; Ecoregion; Biomass (ecology); Biomonitoring; Species diversity; Biology; Biological dispersal","score_opus":0.027805440073020594,"score_gpt":0.23430820306909206,"score_spread":0.20650276299607145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225308572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99456894,0.000068194175,0.00006905879,0.0006444012,0.00017317732,0.00019188551,0.00018728864,0.000047569985,0.004049468],"genre_scores_gemma":[0.9969695,0.000030955245,0.0016674289,0.00041468925,0.0000047214457,0.00002258049,0.0000077838995,0.0000035383364,0.000878773],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979388,0.000097386575,0.00016126751,0.0005725457,0.0006347538,0.00059521035],"domain_scores_gemma":[0.99946207,0.000059803402,0.000081434046,0.00028699954,0.0000019153624,0.000107756205],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000598887,0.00015147279,0.00017296468,0.000052168296,0.0020017836,0.0000394219,0.00089241366,0.000023856022,0.0023130837],"category_scores_gemma":[0.000030744526,0.000165745,0.0000704306,0.00072292006,0.0010335684,0.0002981365,0.0037752755,0.0002572238,0.0008684137],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065063527,0.00013228282,0.972603,0.0000016726884,0.0000030974475,0.00003624931,0.001988163,0.0029391856,0.002974311,0.000011911004,0.018995274,0.00030833928],"study_design_scores_gemma":[0.0003473301,0.00006063589,0.94674027,0.0000030410451,0.0000073242577,0.000012491768,0.0104983775,0.00030600766,0.00059997296,0.000038925333,0.041121192,0.0002644328],"about_ca_topic_score_codex":0.0015392834,"about_ca_topic_score_gemma":0.0005361144,"teacher_disagreement_score":0.025862738,"about_ca_system_score_codex":0.0006681447,"about_ca_system_score_gemma":0.0000051479815,"threshold_uncertainty_score":0.9999095},"labels":[],"label_agreement":null},{"id":"W4226138424","doi":"10.1093/gigascience/giac026","title":"A high-quality, long-read genome assembly of the endangered ring-tailed lemur (<i>Lemur catta</i>)","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Human Genome Research Institute; Agencia Estatal de Investigación; European Research Council; National Institutes of Health; Generalitat de Catalunya; European Commission; Horizon 2020 Framework Programme; Centres de Recerca de Catalunya","keywords":"Lemur catta; Lemur; Endangered species; Biology; Geography; Ecology; Evolutionary biology; Primate","score_opus":0.01827073132917295,"score_gpt":0.2574377732867426,"score_spread":0.23916704195756966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226138424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9967184,0.0010470634,0.00016204618,0.0004096668,0.00042873132,0.00022933757,0.00012760605,0.0000041551784,0.00087297347],"genre_scores_gemma":[0.9980201,0.00006161409,0.00029267243,0.00041594022,0.00008876608,0.00005880665,0.000012158288,0.000014116452,0.0010357879],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9984306,0.00013813238,0.00028924388,0.00044749767,0.00035852476,0.00033600366],"domain_scores_gemma":[0.9989742,0.000022776198,0.00020570747,0.00065016386,0.00008512025,0.00006204559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057831494,0.00015482798,0.00019357422,0.000034662447,0.00044245247,0.000021040318,0.00092839357,0.000040837047,0.00003958167],"category_scores_gemma":[0.00008099732,0.00012574438,0.00013821614,0.00028156987,0.00025846416,0.000001347052,0.0012915286,0.00011069388,0.000003621517],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020364096,0.00006002452,0.012149517,0.00001127085,0.00003141696,0.0000013466304,0.00024453003,0.0010708286,0.9853529,0.00038255274,0.00015167834,0.0005235923],"study_design_scores_gemma":[0.00074569887,0.00044864282,0.61165935,0.0000063770904,0.000035998044,0.000032624088,0.00041602802,0.00002929463,0.3684764,0.00035416282,0.01738696,0.00040844682],"about_ca_topic_score_codex":0.00019953641,"about_ca_topic_score_gemma":0.00017163732,"teacher_disagreement_score":0.6168765,"about_ca_system_score_codex":0.00003143611,"about_ca_system_score_gemma":0.00015907893,"threshold_uncertainty_score":0.5127707},"labels":[],"label_agreement":null},{"id":"W4226283917","doi":"10.1093/gigascience/giab095","title":"Citation needed? Wikipedia bibliometrics during the first wave of the COVID-19 pandemic","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Wikis in Education and Collaboration","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Azrieli Foundation","keywords":"Bibliometrics; Coronavirus disease 2019 (COVID-19); Citation; Pandemic; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Data science; Information retrieval; Computer science; Library science; Biology; Medicine; Virology; Pathology","score_opus":0.086409079141209,"score_gpt":0.35195995743805114,"score_spread":0.26555087829684215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226283917","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9713045,0.00010249999,0.00017869046,0.021959212,0.001464597,0.00028553873,0.000010111127,0.000035536552,0.004659355],"genre_scores_gemma":[0.99591583,0.00006842409,0.00005124234,0.0025257324,0.00010207219,0.00004415837,7.98228e-7,0.0000028894394,0.0012888262],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982653,0.0002409347,0.0001573314,0.00015543507,0.0010036418,0.00017735962],"domain_scores_gemma":[0.9990388,0.0003462232,0.00017947091,0.0002272829,0.00013752407,0.00007067314],"candidate_categories":["bibliometrics","sts"],"consensus_categories":[],"category_scores_codex":[0.002258248,0.000047510406,0.000051333085,0.0006203291,0.0034928801,0.00010418847,0.0006733666,0.000022845583,0.00026359595],"category_scores_gemma":[0.002431077,0.00003311403,0.000035932248,0.02466674,0.000520016,0.0002238921,0.00013644672,0.00012548281,0.0000037876825],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028157345,0.00019629419,0.5098718,0.000041354615,0.000010406853,0.0000015155717,0.37017754,0.007731778,0.0035545398,0.06938702,0.03469179,0.0043078368],"study_design_scores_gemma":[0.00026412844,0.00004123404,0.24357918,0.000004587554,0.0000135376795,0.000012415959,0.19151856,0.00042974585,0.0002302882,0.0048212833,0.55889904,0.00018601425],"about_ca_topic_score_codex":0.0012370443,"about_ca_topic_score_gemma":0.0016228599,"teacher_disagreement_score":0.52420723,"about_ca_system_score_codex":0.0003753262,"about_ca_system_score_gemma":0.0010378021,"threshold_uncertainty_score":0.99780446},"labels":[],"label_agreement":null},{"id":"W4282925344","doi":"10.1093/gigascience/giac045","title":"Analysis of SARS-CoV-2 known and novel subgenomic mRNAs in cell culture, animal model, and clinical samples using LeTRS, a bioinformatic tool to identify unique sequence identifiers","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Viral gastroenteritis research and epidemiology","field":"Medicine","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Biotechnology and Biological Sciences Research Council; Medical Research Council; Food and Drug Administration; UK Research and Innovation; U.S. Food and Drug Administration; National Institute for Health and Care Research; Medical Research Council Canada; Wellcome Trust","keywords":"Biology; Computational biology; Coronavirus; Coronaviridae; Subgenomic mRNA; Gene; Genetics; DNA sequencing; Coronavirus disease 2019 (COVID-19); Infectious disease (medical specialty); Genome; Disease; Medicine","score_opus":0.17478377341440895,"score_gpt":0.4405248091052409,"score_spread":0.26574103569083196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282925344","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9874303,0.00011502173,0.011808039,0.00017979315,0.000033545173,0.00029089165,0.000101377154,0.000009154561,0.000031909498],"genre_scores_gemma":[0.9844712,0.00015263108,0.014622496,0.0006925003,0.000008142697,0.000012176734,0.000014505584,0.000005898624,0.000020451636],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980347,0.0001322871,0.0006821508,0.00040823093,0.00031612656,0.00042647307],"domain_scores_gemma":[0.9993446,0.000043848664,0.00015008185,0.00024106252,0.00006408863,0.00015630794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020389808,0.00012224588,0.0005225986,0.00056533155,0.00013619348,0.000039645434,0.00024534942,0.000046655132,0.00000835035],"category_scores_gemma":[0.0005202874,0.0001129128,0.00010096757,0.0011301985,0.00045332767,0.000248045,0.00047089093,0.00028917054,9.1649014e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001824432,0.0000797947,0.18900149,0.00006113176,0.000049354538,0.000017266644,0.0005242974,0.0023662122,0.8069629,0.000086597436,0.00009186532,0.00057662],"study_design_scores_gemma":[0.0011277932,0.0011099464,0.32411817,0.00006925039,0.0002033546,0.00013202158,0.00086116436,0.669147,0.0027932688,0.00014206827,0.00009962278,0.0001963295],"about_ca_topic_score_codex":0.00095168385,"about_ca_topic_score_gemma":0.00033674782,"teacher_disagreement_score":0.80416965,"about_ca_system_score_codex":0.00013079253,"about_ca_system_score_gemma":0.00017810878,"threshold_uncertainty_score":0.46044502},"labels":[],"label_agreement":null},{"id":"W4285817857","doi":"10.1093/gigascience/giac065","title":"Toward global integration of biodiversity big data: a harmonized metabarcode data generation module for terrestrial arthropods","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Environmental DNA in Biodiversity Studies","field":"Environmental Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Horizon 2020 Framework Programme; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Fundación Bancaria Caixa d'Estalvis i Pensions de Barcelona; European Commission","keywords":"Big data; Biodiversity; Computer science; Data science; Data integration; Ecology; Data mining; Biology","score_opus":0.2371889043425931,"score_gpt":0.2950674986009877,"score_spread":0.05787859425839459,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285817857","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9516013,0.00009506088,0.036272217,0.00095814915,0.0013996841,0.00071544567,0.008741363,0.000038542225,0.00017818913],"genre_scores_gemma":[0.96037483,0.00005621096,0.037898038,0.00018018026,0.000075512384,0.000017350621,0.0013409847,0.0000031680884,0.00005369698],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979577,0.00009254009,0.00021035424,0.00080967444,0.00068223185,0.00024748873],"domain_scores_gemma":[0.9987468,0.00003073548,0.00016123476,0.0009917674,0.000005288983,0.00006418262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000800956,0.00013260217,0.00017110814,0.000027559994,0.00078382745,0.0000354662,0.0020634902,0.000026209202,0.0002226403],"category_scores_gemma":[0.00014436699,0.00013217353,0.000044000535,0.00038290466,0.0006857951,0.0007808236,0.00640043,0.0000809977,0.00004043357],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045662175,0.0010913998,0.44374293,0.000021314774,0.00012632656,0.00001596265,0.0017940791,0.006856032,0.26028538,0.00011481517,0.16086999,0.12462515],"study_design_scores_gemma":[0.008144665,0.0017603299,0.5367352,0.000016903932,0.00063627155,0.000043889002,0.006481769,0.27369884,0.051183682,0.0011461248,0.11827138,0.001880991],"about_ca_topic_score_codex":0.0011789355,"about_ca_topic_score_gemma":0.00032320162,"teacher_disagreement_score":0.2668428,"about_ca_system_score_codex":0.00031597898,"about_ca_system_score_gemma":0.000018146062,"threshold_uncertainty_score":0.7977678},"labels":[],"label_agreement":null},{"id":"W4291283000","doi":"10.1093/gigascience/giac068","title":"Benchmarking ultra-high molecular weight DNA preservation methods for long-read and long-range sequencing","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"U.S. Fish and Wildlife Service; Wellcome Trust","keywords":"Benchmarking; DNA sequencing; Range (aeronautics); Computational biology; DNA; Computer science; Biology; Genetics; Engineering; Business","score_opus":0.02097132317033206,"score_gpt":0.290464002811846,"score_spread":0.2694926796415139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291283000","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8951295,0.002718181,0.10104337,0.00020900996,0.0002832548,0.00033228096,0.000026883234,0.0000048599304,0.00025265213],"genre_scores_gemma":[0.9698626,0.00016216657,0.029069284,0.00038790802,0.00010253738,0.00016957475,0.000035579567,0.000015559757,0.0001947977],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99880046,0.000095962285,0.00016822759,0.00049633346,0.00014387089,0.00029514445],"domain_scores_gemma":[0.99946123,0.000044183576,0.00008855421,0.00026944414,0.00007244319,0.00006415133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007378391,0.00013689321,0.00013087227,0.000043348708,0.00045940647,0.000037791015,0.0002838241,0.000042644868,0.000014871705],"category_scores_gemma":[0.00010068416,0.0001396595,0.00006011177,0.00015377256,0.00011756254,0.0000037056461,0.0002586513,0.000065225584,2.6190415e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020128526,0.000013593208,0.008684946,0.000020470492,0.000025616215,0.000002350932,0.00017720569,0.00066851516,0.97940445,0.00038477717,0.00006677592,0.010531144],"study_design_scores_gemma":[0.0011777689,0.0012430735,0.07558853,0.000019997593,0.00009566091,0.00009611793,0.00031659318,0.0031640865,0.8829925,0.004055504,0.030423753,0.00082639325],"about_ca_topic_score_codex":0.000037098078,"about_ca_topic_score_gemma":0.000020567546,"teacher_disagreement_score":0.09641195,"about_ca_system_score_codex":0.000032070937,"about_ca_system_score_gemma":0.00008160618,"threshold_uncertainty_score":0.56951493},"labels":[],"label_agreement":null},{"id":"W4306912551","doi":"10.1093/gigascience/giac092","title":"A virtual library for behavioral performance in standard conditions—rodent spontaneous activity in an open field during repeated testing and after treatment with drugs or brain lesions","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Obsessive-Compulsive Spectrum Disorders","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Max-Planck-Gesellschaft; Canadian Institutes of Health Research; Ontario Mental Health Foundation; McMaster University","keywords":"Computer science; Schema (genetic algorithms); Raw data; Field (mathematics); Information retrieval; Reuse; Resource (disambiguation); Machine learning; Artificial intelligence","score_opus":0.02511134909956551,"score_gpt":0.32165731020302374,"score_spread":0.2965459611034582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306912551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979112,0.000013541381,0.000015968864,0.0005156352,0.00007140329,0.0010566621,0.00014389222,0.000040278344,0.00023142257],"genre_scores_gemma":[0.9976118,0.0000020181258,0.0005778968,0.00015253076,0.000009008389,0.0010498319,0.000010762812,0.000019107176,0.0005669982],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985914,0.00014360777,0.00017338946,0.0005650899,0.00016475254,0.00036170843],"domain_scores_gemma":[0.99928546,0.00027449476,0.000081563725,0.00026570426,0.000013640366,0.000079140555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017176996,0.00014883275,0.0001990698,0.00018528638,0.00035345927,0.00010337566,0.00029851025,0.000030418623,0.00043761314],"category_scores_gemma":[0.000027576663,0.00012730624,0.000014918258,0.0005580113,0.0001171851,0.00066498946,0.0002453772,0.00017022718,0.0000011426802],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01025957,0.0013765171,0.9353924,0.00001617724,0.000010819771,0.0025932512,0.015422415,0.00080903096,0.0035713299,0.000092487215,0.000029421306,0.030426627],"study_design_scores_gemma":[0.0039937394,0.010519508,0.9762369,0.00006488893,0.0000114847335,0.0004214628,0.006349242,0.0007967534,0.0011952657,0.000047177564,0.00006564097,0.00029795177],"about_ca_topic_score_codex":0.00056156365,"about_ca_topic_score_gemma":0.0031546685,"teacher_disagreement_score":0.04084453,"about_ca_system_score_codex":0.0001942389,"about_ca_system_score_gemma":0.00019579813,"threshold_uncertainty_score":0.51913977},"labels":[],"label_agreement":null},{"id":"W4309360833","doi":"10.1093/gigascience/giac108","title":"An <i>in vitro</i> whole-cell electrophysiology dataset of human cortical neurons","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University Health Network; Ontario Brain Institute; Centre for Addiction and Mental Health","funders":"","keywords":"Electrophysiology; Neuroscience; Set (abstract data type); Cortical neurons; Neurophysiology; Metadata; Computer science; Multielectrode array; Patch clamp; Current clamp; Biology; Chemistry; Microelectrode; World Wide Web","score_opus":0.021052139756430454,"score_gpt":0.26742362361989946,"score_spread":0.24637148386346902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309360833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9988641,0.0000027656981,0.00007212341,0.00016791005,0.00020968357,0.0001182324,0.0004079088,0.00002174269,0.00013551803],"genre_scores_gemma":[0.99816704,0.0000018587411,0.000045840014,0.0015736489,0.0000144077485,0.000018112942,0.00011774325,0.000007708245,0.000053640604],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99828994,0.0002945499,0.00022720624,0.00053670444,0.0002773834,0.00037422823],"domain_scores_gemma":[0.99932307,0.000101532736,0.00009277459,0.00039431642,0.000009387806,0.00007891534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026735288,0.000091090784,0.0001338852,0.00010657014,0.0003636117,0.000020611415,0.00066994986,0.000017072323,0.000061487095],"category_scores_gemma":[0.000074400334,0.000088709814,0.000029606697,0.0006492799,0.00028087222,0.00019404823,0.0002205677,0.00031457038,0.000009943118],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003688339,0.0002338196,0.00006145664,0.0000028027418,1.0865077e-7,0.000024372399,0.000030843275,0.0005308203,0.997636,0.0010202564,0.00020102055,0.00022160752],"study_design_scores_gemma":[0.00029883388,0.0014240256,0.002608261,9.100182e-7,0.000003060038,0.000033143544,0.00003964563,0.023108093,0.96943074,0.0008703613,0.0020350476,0.00014788091],"about_ca_topic_score_codex":0.00004948822,"about_ca_topic_score_gemma":0.000008337764,"teacher_disagreement_score":0.028205272,"about_ca_system_score_codex":0.000033472574,"about_ca_system_score_gemma":0.000045486027,"threshold_uncertainty_score":0.36174813},"labels":[],"label_agreement":null},{"id":"W4309659057","doi":"10.1093/gigascience/giac103","title":"Defining the characteristics of interferon-alpha–stimulated human genes: insight from expression data and machine learning","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"interferon and immune responses","field":"Immunology and Microbiology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Medical Research Council; Medical Research Council Canada; China Scholarship Council","keywords":"Gene; Biology; Computational biology; Interferon; Genetics","score_opus":0.02760187418918106,"score_gpt":0.2665313053611547,"score_spread":0.23892943117197366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309659057","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902528,0.00856249,0.0002626621,0.00008751752,0.00036836005,0.00008291138,0.00019491269,0.000028673721,0.00015965103],"genre_scores_gemma":[0.99880886,0.000086264365,0.00004046459,0.00009823138,0.000006627675,0.0000060818793,0.0003995497,0.000008618803,0.00054527237],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987459,0.0004245262,0.00026500042,0.0003110606,0.000059925747,0.0001935745],"domain_scores_gemma":[0.99904835,0.00025845013,0.00017235188,0.00048170294,0.000026810154,0.00001234752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048102764,0.00011020995,0.00018402482,0.000068782014,0.0008402008,0.000023395822,0.0008819766,0.00004343457,0.0007063239],"category_scores_gemma":[0.00016391296,0.00007837992,0.000022975131,0.00012603353,0.0003784442,0.00011293687,0.0017955542,0.00041086925,0.0000192945],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017896868,0.00003580547,0.0042102546,0.0000033189094,0.000018541048,0.0000024249678,0.0016590753,0.000011461511,0.9873935,0.00017789213,0.00012263174,0.006186155],"study_design_scores_gemma":[0.0016075528,0.0015021987,0.05492277,0.00014184578,0.00006866288,0.00012913572,0.0032353727,0.003265634,0.8232199,0.00006404301,0.111410916,0.00043200134],"about_ca_topic_score_codex":0.00022845682,"about_ca_topic_score_gemma":0.000006432183,"teacher_disagreement_score":0.1641736,"about_ca_system_score_codex":0.000016004462,"about_ca_system_score_gemma":0.0000391192,"threshold_uncertainty_score":0.7733751},"labels":[],"label_agreement":null},{"id":"W4311585301","doi":"10.1093/gigascience/giac099","title":"annotate_my_genomes: an easy-to-use pipeline to improve genome annotation and uncover neglected genes by hybrid RNA sequencing","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; Research Institute in Oncology and Hematology; CancerCare Manitoba","funders":"Fondo Nacional de Desarrollo Científico y Tecnológico; Canadian Institutes of Health Research","keywords":"Genome; Annotation; Gene Annotation; Computational biology; Gene; Gene prediction; Genome project; Pipeline (software); Biology; Transcriptome; DNA sequencing; Identification (biology); Exon; Reference genome; Computer science; Genetics; Gene expression","score_opus":0.012198686535176521,"score_gpt":0.22979259089344578,"score_spread":0.21759390435826925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311585301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99460113,0.0010153663,0.003098864,0.00023330995,0.00020903639,0.00036156803,0.000406869,0.000009622347,0.0000642577],"genre_scores_gemma":[0.99339235,0.00014737468,0.0027399748,0.00273706,0.00009372218,0.000083470935,0.00010301065,0.00002344839,0.00067959254],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99837613,0.0000669287,0.00021509903,0.0007285363,0.00022092898,0.0003923751],"domain_scores_gemma":[0.9991974,0.000012698665,0.00007027763,0.00036349616,0.00012571947,0.00023040111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021538048,0.00018843853,0.00015039118,0.00008242571,0.00045627696,0.000092555085,0.0003283505,0.000025849347,0.000010440929],"category_scores_gemma":[0.00007378511,0.00019740901,0.000033763023,0.00031283963,0.00007279021,0.000006582298,0.0005141862,0.000071041984,0.000004689954],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004122581,0.000020528465,0.0004809579,0.00000384077,0.000010255859,0.0000032299884,0.00038271555,0.0038993156,0.98954064,0.0000053140866,0.0005557073,0.005056243],"study_design_scores_gemma":[0.00066301075,0.0027845223,0.018113801,0.000004341847,0.000032864144,0.000066826055,0.0009962843,0.0015641599,0.74219537,0.00015716125,0.23244502,0.0009766399],"about_ca_topic_score_codex":0.00016855643,"about_ca_topic_score_gemma":0.000034863253,"teacher_disagreement_score":0.2473453,"about_ca_system_score_codex":0.0000652632,"about_ca_system_score_gemma":0.00012357115,"threshold_uncertainty_score":0.80501056},"labels":[],"label_agreement":null},{"id":"W4327896682","doi":"10.1093/gigascience/giad013","title":"Characterization and simulation of metagenomic nanopore sequencing data with Meta-NanoSim","year":2023,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre; Genome British Columbia; University of British Columbia","funders":"National Human Genome Research Institute; National Institutes of Health; Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Genome British Columbia; Genome Canada","keywords":"Metagenomics; Computational biology; Nanopore; Computer science; Characterization (materials science); Nanopore sequencing; Data science; Biology; DNA sequencing; Nanotechnology; Genetics; Materials science; Gene","score_opus":0.0653916397109796,"score_gpt":0.2779367005378232,"score_spread":0.2125450608268436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327896682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9963848,0.0002629263,0.0030584617,0.000048942766,0.000033803128,0.000095417236,0.00007230443,0.0000035034502,0.000039831604],"genre_scores_gemma":[0.99872094,0.00021171762,0.0007332675,0.000043407857,0.000021833692,0.000005309843,0.00012650494,0.0000063737684,0.00013061597],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993949,0.000016217797,0.000107137435,0.00028466457,0.000086426146,0.00011066515],"domain_scores_gemma":[0.9995146,0.000011119404,0.000075275086,0.00032671628,0.000047339458,0.000024968887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023182303,0.000072403935,0.00011137964,0.000032883374,0.000072107614,0.000013457877,0.00018445995,0.000025404264,0.000002179723],"category_scores_gemma":[0.00003720386,0.000054721204,0.000016334328,0.00015860907,0.00010635149,0.0000031473594,0.000221824,0.000015640964,0.000001169381],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000590873,0.000002541275,0.0014072348,0.000007873242,0.000070590846,4.5036091e-7,0.00008212675,0.004680098,0.99284166,0.000013835328,0.0000061924093,0.00088148005],"study_design_scores_gemma":[0.0003954909,0.0003730599,0.089094564,0.000012452417,0.00043548027,0.000010541752,0.00028521952,0.042652104,0.85665387,0.00008818979,0.009646322,0.00035270237],"about_ca_topic_score_codex":0.000009316105,"about_ca_topic_score_gemma":0.000014460034,"teacher_disagreement_score":0.13618779,"about_ca_system_score_codex":0.0000030924857,"about_ca_system_score_gemma":0.000049370756,"threshold_uncertainty_score":0.22314659},"labels":[],"label_agreement":null},{"id":"W4375840921","doi":"10.1093/gigascience/giad031","title":"A workflow reproducibility scale for automatic validation of biological interpretation results","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Core Research for Evolutional Science and Technology; Institute of Genetics; Japan Science and Technology Agency; National Bioscience Database Center; Japan Society for the Promotion of Science","keywords":"Workflow; Reproducibility; Computer science; Scale (ratio); Interpretation (philosophy); Data science; Data mining; Chemistry; Chromatography; Database; Programming language; Cartography","score_opus":0.18596343308780897,"score_gpt":0.40229847680741077,"score_spread":0.2163350437196018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375840921","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8891981,0.0000114303775,0.10751981,0.00084788434,0.0011334354,0.00039687956,0.0000942539,0.000052287254,0.0007459096],"genre_scores_gemma":[0.98316604,2.64359e-7,0.016165694,0.000074028234,0.000018808843,0.000043776763,0.000024409403,0.000001850349,0.0005051175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99587137,0.00034278494,0.00077711215,0.0015469627,0.0012677528,0.00019404266],"domain_scores_gemma":[0.9958998,0.0012968887,0.00041157985,0.002118135,0.00022558233,0.000048030775],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.037792344,0.00006731792,0.00016361206,0.00021758779,0.0004229488,0.0001624158,0.0013899433,0.000014045493,0.0001109389],"category_scores_gemma":[0.021571275,0.000050333747,0.00008781422,0.0018503963,0.00021088912,0.00023499735,0.00080617133,0.000058271016,0.000018104747],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002860654,0.0004120404,0.010575376,0.000016646847,0.0000061004844,0.0000011854429,0.0056618447,0.037515204,0.0057648723,0.0008516593,0.032421377,0.90648764],"study_design_scores_gemma":[0.00065751106,0.00059580256,0.06492393,0.000023556384,0.000010928581,0.00000622098,0.0028156335,0.8347022,0.008477094,0.075993896,0.011558992,0.00023422787],"about_ca_topic_score_codex":0.000014401083,"about_ca_topic_score_gemma":0.0000031241784,"teacher_disagreement_score":0.9062534,"about_ca_system_score_codex":0.00005163431,"about_ca_system_score_gemma":0.00006229746,"threshold_uncertainty_score":0.99079525},"labels":[],"label_agreement":null},{"id":"W4380870059","doi":"10.1093/gigascience/giad043","title":"EraSOR: a software tool to eliminate inflation caused by sample overlap in polygenic score analyses","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Mental Health; Medical Research Council; National Institutes of Health; King's College London; National Institute for Health and Care Research; Medical Research Council Canada; South London and Maudsley NHS Foundation Trust","keywords":"Sample size determination; Sample (material); Genome-wide association study; Computer science; Statistics; Large sample; Polygenic risk score; Software; Inflation (cosmology); Scale (ratio); Computational biology; Biology; Mathematics; Genetics; Single-nucleotide polymorphism; Cartography; Physics; Genotype","score_opus":0.027529593328148694,"score_gpt":0.30796448493867257,"score_spread":0.2804348916105239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380870059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99176306,0.00021980147,0.00721267,0.0003847214,0.000100282974,0.00016374506,0.00010892763,0.0000093992685,0.00003736978],"genre_scores_gemma":[0.9948352,0.000022442387,0.0034065882,0.0011930553,0.000027727363,0.000083807936,0.00015523737,0.00000812179,0.00026782573],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.998776,0.000115576026,0.0002266965,0.00039046374,0.00017791588,0.0003133152],"domain_scores_gemma":[0.99950105,0.000046849193,0.0000833583,0.00026655447,0.00004005933,0.000062146326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004900342,0.00009901568,0.00012911516,0.0000858924,0.00021272167,0.000016474292,0.00027324478,0.000051491574,0.00006144045],"category_scores_gemma":[0.00083630055,0.000104790204,0.00005265739,0.00045461926,0.000041365354,0.000005116015,0.0002526361,0.00008457701,0.000007051316],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023622655,0.000058019163,0.47518137,0.0000034151692,0.000013311239,0.0000014833224,0.00019676148,0.014187805,0.5003058,0.000027059128,0.0054148054,0.004586566],"study_design_scores_gemma":[0.00042876438,0.0004502435,0.9649103,0.0000041769576,0.000012463925,0.000004918302,0.000315659,0.0012317047,0.010667537,0.0003249845,0.021322703,0.0003265325],"about_ca_topic_score_codex":0.00030646328,"about_ca_topic_score_gemma":0.00021288668,"teacher_disagreement_score":0.48972896,"about_ca_system_score_codex":0.000068330875,"about_ca_system_score_gemma":0.00011779351,"threshold_uncertainty_score":0.42732206},"labels":[],"label_agreement":null},{"id":"W4385154653","doi":"10.1093/gigascience/giad051","title":"A new haplotype-resolved turkey genome to enable turkey genetics and genomics research","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomic variations and chromosomal abnormalities","field":"Biochemistry, Genetics and Molecular Biology","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Grand River Hospital","funders":"Southwest University; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Haplotype; Genomics; Genome; Human genetics; Genetics; Biology; Computational biology; Gene; Allele","score_opus":0.027053633512949173,"score_gpt":0.2758492135263816,"score_spread":0.2487955800134324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385154653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99400127,0.0012797373,0.001973322,0.00057546777,0.00017352875,0.0002815697,0.000054837496,0.00001293075,0.0016473214],"genre_scores_gemma":[0.98434496,0.000117273405,0.007161313,0.0003931433,0.00021609564,0.000054385957,0.000029977731,0.000019498475,0.0076633315],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99843764,0.00009463988,0.00017548613,0.0004964763,0.00031941218,0.00047632123],"domain_scores_gemma":[0.9991934,0.000014975863,0.000036699174,0.00042262336,0.00009077505,0.00024157674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006709398,0.00011894723,0.00010592981,0.00010383417,0.0007075997,0.00010374357,0.00054424553,0.000046841895,0.00014343699],"category_scores_gemma":[0.00005323664,0.00012632218,0.000035907615,0.00033666356,0.00010615171,0.000006121678,0.0011700174,0.00015531808,0.0000263191],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045955043,0.000032797958,0.0008276662,0.000007848173,0.000013659636,0.000005389113,0.0012574829,0.008615312,0.983416,0.0008188603,0.0037621253,0.0011968997],"study_design_scores_gemma":[0.0005034406,0.0010977277,0.004776665,0.000003754306,0.000011653354,0.000103661114,0.0020385082,0.0006389922,0.08822603,0.0013732769,0.90079015,0.00043616127],"about_ca_topic_score_codex":0.00038461902,"about_ca_topic_score_gemma":0.000041578503,"teacher_disagreement_score":0.897028,"about_ca_system_score_codex":0.000072021576,"about_ca_system_score_gemma":0.00044900057,"threshold_uncertainty_score":0.54423565},"labels":[],"label_agreement":null},{"id":"W4386201130","doi":"10.1093/gigascience/giad068","title":"The founding charter of the Omic Biodiversity Observation Network (Omic BON)","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Horizon 2020 Framework Programme; Natural Environment Research Council; European Commission; Battelle; National Science Foundation","keywords":"Omics; Charter; Biodiversity; Thematic map; Data science; Geography; Biology; Computer science; Ecology; Bioinformatics; Cartography","score_opus":0.14989449729646365,"score_gpt":0.3205717572693741,"score_spread":0.17067725997291044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386201130","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9789038,0.00005047284,0.0023387037,0.008306468,0.009417055,0.00020188889,0.00001886282,0.000022243295,0.0007405539],"genre_scores_gemma":[0.9952637,0.0000025604515,0.00030034798,0.000909805,0.00006179803,0.0000051769384,0.0000016614952,0.0000015051055,0.0034534442],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9967903,0.0002716327,0.00032724478,0.00047577202,0.001844047,0.00029100783],"domain_scores_gemma":[0.9976325,0.00069083134,0.00031501043,0.0012350811,0.00008905818,0.0000375215],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.011834016,0.00006601702,0.00009191059,0.00006694898,0.0034233783,0.00041459972,0.0035802603,0.000009404811,0.00011621132],"category_scores_gemma":[0.0008481377,0.000036066493,0.00008955329,0.0022886398,0.0003612228,0.00025764573,0.002360988,0.00011625323,0.00007494311],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018813276,0.000035810455,0.22707443,0.0000018082836,0.0000073702463,0.0000013344728,0.001303982,0.015823638,0.00052133994,0.007457401,0.7131753,0.034578793],"study_design_scores_gemma":[0.00016484992,0.000037845388,0.42131716,0.000006933372,0.000009200985,0.000003916532,0.0022735968,0.0528987,0.00010242197,0.013440642,0.5096241,0.00012060778],"about_ca_topic_score_codex":0.00006263289,"about_ca_topic_score_gemma":0.00004002084,"teacher_disagreement_score":0.20355117,"about_ca_system_score_codex":0.00007171586,"about_ca_system_score_gemma":0.00007409478,"threshold_uncertainty_score":0.997874},"labels":[],"label_agreement":null},{"id":"W4389932371","doi":"10.1093/gigascience/giad105","title":"Chromosome-level genome assembly of the Pacific geoduck <i>Panopea generosa</i> reveals major inter- and intrachromosomal rearrangements and substantial expansion of the copine gene family","year":2022,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Chinese Academy of Sciences","keywords":"Genome; Gene; Biology; Chromosome; Gene family; Genetics; Evolutionary biology","score_opus":0.016196384552166102,"score_gpt":0.21678733745159634,"score_spread":0.20059095289943024,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389932371","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959537,0.0028735949,0.000056634046,0.00015463943,0.0002851501,0.00028714773,0.0002562583,0.0000013126078,0.00013158814],"genre_scores_gemma":[0.99867356,0.0005026727,0.00039208567,0.00014279886,0.000051724375,0.000021123331,0.0000068480986,0.000010876971,0.00019832744],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987908,0.00010771066,0.00026764473,0.0003733674,0.00024953578,0.00021093812],"domain_scores_gemma":[0.9992235,0.000010869565,0.00019648626,0.00045947317,0.00006874137,0.000040960207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033660606,0.00013583922,0.00017579587,0.000023078297,0.00033602986,0.000015118941,0.0004758787,0.000036993646,0.0000047724443],"category_scores_gemma":[0.000029638819,0.00009306769,0.000060864622,0.00019034318,0.0004616971,0.000002484368,0.0012042419,0.000078786084,1.9994386e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022513572,0.000027795444,0.007199309,0.000018743247,0.000024069266,4.5936315e-7,0.0002583399,0.000032385728,0.99165046,0.00002061747,0.000113325026,0.00063200365],"study_design_scores_gemma":[0.0004239695,0.00026832332,0.29879642,0.000012804359,0.000026753834,0.000024957626,0.00034425347,0.000023449214,0.6983451,0.00003822278,0.0015648102,0.00013089011],"about_ca_topic_score_codex":0.000035468325,"about_ca_topic_score_gemma":0.000013617035,"teacher_disagreement_score":0.2933053,"about_ca_system_score_codex":0.000012863107,"about_ca_system_score_gemma":0.00008063486,"threshold_uncertainty_score":0.37951905},"labels":[],"label_agreement":null},{"id":"W4390508023","doi":"10.1093/gigascience/giad103","title":"Evolutionary genomics of three agricultural pest moths reveals rapid evolution of host adaptation and immune-related genes","year":2024,"lang":"en","type":"article","venue":"GigaScience","topic":"Invertebrate Immune Response Mechanisms","field":"Immunology and Microbiology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada","funders":"Animal and Plant Health Inspection Service; Indian Agricultural Research Institute; University of Florida; U.S. Department of Agriculture","keywords":"Biology; Gene family; PEST analysis; Genome; Host (biology); Host adaptation; Gene; Adaptation (eye); Phylogenetics; Genetics; Evolutionary biology; Botany","score_opus":0.012152198130516425,"score_gpt":0.20392414901400793,"score_spread":0.1917719508834915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390508023","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9338421,0.06238101,0.0023292473,0.00011551985,0.0007883087,0.00023871512,0.000041989857,0.000051160147,0.00021191014],"genre_scores_gemma":[0.99846613,0.00038027432,0.0006337328,0.000005653014,0.000008272387,0.000009401786,0.000027353217,0.000008450167,0.0004607455],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988197,0.00014179316,0.00044471727,0.00028850092,0.00007009212,0.0002351583],"domain_scores_gemma":[0.99936515,0.00011841207,0.0001671733,0.00019794503,0.0001361244,0.000015179152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005180844,0.00013740546,0.00022847754,0.00018080465,0.0001475369,0.000012764385,0.00022926024,0.00017150663,0.00008372003],"category_scores_gemma":[0.00008051464,0.00011110663,0.000082450366,0.00046140107,0.0005557394,0.00025819452,0.000106613246,0.00014699528,0.00006776627],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039027607,0.000024832636,0.00016608785,0.00004370711,0.000045968936,0.0000012880487,0.00066642236,0.000069867456,0.9786492,0.01576275,0.00005354203,0.0044772835],"study_design_scores_gemma":[0.000579017,0.00050824037,0.19601768,0.0002714541,0.0000901738,0.00037788978,0.00184854,0.0046854066,0.790306,0.004628986,0.00039196925,0.00029465076],"about_ca_topic_score_codex":0.00016141875,"about_ca_topic_score_gemma":0.000011370733,"teacher_disagreement_score":0.1958516,"about_ca_system_score_codex":0.000105830855,"about_ca_system_score_gemma":0.00019933938,"threshold_uncertainty_score":0.45307967},"labels":[],"label_agreement":null},{"id":"W4390842479","doi":"10.1093/gigascience/giad114","title":"Open Data Governance at the Canadian Open Neuroscience Platform (CONP): From the Walled Garden to the Arboretum","year":2024,"lang":"en","type":"article","venue":"GigaScience","topic":"Research Data Management Practices","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University and Génome Québec Innovation Centre; McGill University Health Centre; Terry Fox Research Institute; University of Toronto; Montreal Neurological Institute and Hospital; McGill University","funders":"Fondation Brain Canada","keywords":"Open science; Open data; Citizen science; Data science; World Wide Web; Computer science; Neuroscience; Biology; Botany; Physics","score_opus":0.2758934476905706,"score_gpt":0.4059608317831537,"score_spread":0.13006738409258306,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390842479","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040463884,0.001211692,0.018829426,0.8711597,0.003030565,0.004972358,0.0012036709,0.00013650054,0.09540972],"genre_scores_gemma":[0.87571234,0.0008637267,0.00486337,0.06277444,0.00032108344,0.0004286651,0.000060838964,0.000040355055,0.05493518],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99497384,0.00026439992,0.00028505217,0.0019411108,0.0015630644,0.0009725178],"domain_scores_gemma":[0.98998135,0.0010682158,0.00012399879,0.008368916,0.000074833086,0.00038268362],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.008468287,0.00021934345,0.00016421649,0.000052831354,0.0031167287,0.06111741,0.14124198,0.000032745633,0.00012861643],"category_scores_gemma":[0.002536186,0.000102260616,0.000032513228,0.0025177274,0.0006635047,0.041486796,0.09295143,0.0005089907,0.0008167952],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014720804,0.000024621431,0.00035325467,0.0000067383653,0.000027524758,0.00016908131,0.0019292682,0.00033259336,0.00034193028,0.25115937,0.7153663,0.030274585],"study_design_scores_gemma":[0.00007678283,0.000038114937,0.019667637,0.000026900812,0.000011645646,0.000013642121,0.00011630071,0.04833529,0.00006620401,0.0008141437,0.9306569,0.00017641272],"about_ca_topic_score_codex":0.3141188,"about_ca_topic_score_gemma":0.7715022,"teacher_disagreement_score":0.87166595,"about_ca_system_score_codex":0.00033308277,"about_ca_system_score_gemma":0.0020412463,"threshold_uncertainty_score":0.9999612},"labels":[{"model":"gemma","categories":["open_science","scholarly_communication"],"domain":null,"study_design":"not_applicable","genre":"empirical","about_ca_system":true,"about_ca_topic":true,"confidence":"medium"},{"model":"gpt","categories":["open_science"],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W4394583773","doi":"10.1093/gigascience/giae009","title":"On the variability of dynamic functional connectivity assessment methods","year":2024,"lang":"en","type":"article","venue":"GigaScience","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"National Institute of Biomedical Imaging and Bioengineering; National Institute of Mental Health; Fonds de recherche du Québec – Nature et technologies; McGill University; McDonnell Center for Systems Neuroscience; National Institutes of Health; Health Canada; Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Fondation Brain Canada","keywords":"Python (programming language); Computer science; Toolbox; Human Connectome Project; Functional magnetic resonance imaging; Dynamic functional connectivity; Similarity (geometry); Machine learning; Artificial intelligence; Functional connectivity; Data mining; Psychology; Neuroscience","score_opus":0.060986309093657445,"score_gpt":0.3736143941800098,"score_spread":0.31262808508635237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394583773","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6417033,0.00004655547,0.3131978,0.020184776,0.0032227016,0.00045100006,0.00004637128,0.00021874938,0.020928739],"genre_scores_gemma":[0.9960546,0.000005340815,0.001974103,0.0015703732,0.000030236135,0.000060604114,2.9741727e-7,0.00000821321,0.00029623698],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9973077,0.0008395572,0.00019492669,0.0007695931,0.0006473289,0.00024085637],"domain_scores_gemma":[0.95109355,0.048302345,0.00005671455,0.00044086302,0.00006434039,0.000042186988],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004381181,0.00014245285,0.00016006359,0.00009593249,0.0003943978,0.000081362225,0.0003458441,0.00003564444,0.00025431032],"category_scores_gemma":[0.024077982,0.00009092591,0.0001114834,0.0010172455,0.00082810916,0.00024113563,0.00019385827,0.00030689134,0.000042909254],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015726147,0.00011175184,0.00024693742,0.000028099646,0.000009714117,0.0000033656916,0.00011155663,0.0003789154,0.37830067,0.60993445,0.0012135329,0.009645298],"study_design_scores_gemma":[0.0002178498,0.00051932136,0.14504346,0.000103792634,0.000033304463,0.00005650866,0.00016557593,0.19280109,0.15857786,0.49618652,0.005870903,0.00042381865],"about_ca_topic_score_codex":0.000011777176,"about_ca_topic_score_gemma":0.0000059231884,"teacher_disagreement_score":0.35435125,"about_ca_system_score_codex":0.00018888187,"about_ca_system_score_gemma":0.0002583437,"threshold_uncertainty_score":0.9841426},"labels":[],"label_agreement":null},{"id":"W4401835181","doi":"10.1093/gigascience/giae056","title":"TooManyCellsInteractive: A visualization tool for dynamic exploration of single-cell data","year":2024,"lang":"en","type":"article","venue":"GigaScience","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"University of Toronto; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Workflow; Computer science; Visualization; Data science; Data exploration; Data visualization; Data mining; Database","score_opus":0.04687440646950489,"score_gpt":0.31662520260739146,"score_spread":0.26975079613788655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401835181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.383131,0.00043847333,0.61534977,0.00006357033,0.000455283,0.00020042736,0.00009050014,0.000017492062,0.0002534591],"genre_scores_gemma":[0.99579763,0.00007068843,0.0030023602,0.00005434509,0.00006558552,0.000011521316,0.00044759177,0.000014234303,0.00053605495],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99918306,0.0000182855,0.00017060689,0.00038820636,0.000110750545,0.0001290874],"domain_scores_gemma":[0.9995185,0.000022939272,0.000044047487,0.00031972787,0.00007110173,0.00002366303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019793725,0.00008463742,0.00007456702,0.00004503354,0.00004811299,0.00006508025,0.00030905823,0.000054240503,0.000005247304],"category_scores_gemma":[0.000067214154,0.000080619386,0.000041629897,0.00014680633,0.000073476804,0.000054418535,0.00007066226,0.000027664966,0.0000035281548],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003289253,0.00007650175,0.000037463757,0.00007616457,0.000005735006,4.451684e-7,0.00011675349,0.000079914695,0.9936216,0.000245931,0.00037670918,0.0053299116],"study_design_scores_gemma":[0.00022503799,0.0003934618,0.00005462953,0.000051050327,0.000021231932,0.0000032525875,0.00007281484,0.06582592,0.9140214,0.00021094346,0.018966693,0.00015356527],"about_ca_topic_score_codex":0.00000648085,"about_ca_topic_score_gemma":0.000019011039,"teacher_disagreement_score":0.6126666,"about_ca_system_score_codex":0.000013269388,"about_ca_system_score_gemma":0.000085939675,"threshold_uncertainty_score":0.3287563},"labels":[],"label_agreement":null},{"id":"W4402927730","doi":"10.1093/gigascience/giae068","title":"Harnessing population diversity: in search of tools of the trade","year":2024,"lang":"en","type":"article","venue":"GigaScience","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute; Montreal Neurological Institute and Hospital","funders":"","keywords":"Diversity (politics); Data science; Population; Computer science; Big data; Sample (material); Cohort; Data mining; Political science; Sociology; Statistics; Demography","score_opus":0.12619699903071688,"score_gpt":0.30729370933229366,"score_spread":0.18109671030157679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402927730","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99571115,0.000046147325,0.00011905633,0.0029945688,0.00033240416,0.00009082668,0.0000074313975,0.000014424568,0.0006839988],"genre_scores_gemma":[0.9997168,0.0000042633965,0.000035367302,0.00016840691,0.000010076365,0.0000012953708,7.3365854e-8,0.0000021146786,0.00006157651],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990587,0.00007546966,0.00010397791,0.0002237403,0.000426235,0.00011182527],"domain_scores_gemma":[0.9984864,0.0013401932,0.000025833382,0.00012593453,0.000010047288,0.000011582822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003916408,0.00004196579,0.00007389066,0.00009314769,0.00016300054,0.000026039705,0.00026200622,0.000015401945,0.000005782119],"category_scores_gemma":[0.0022159454,0.000030328343,0.000037788395,0.0010882606,0.00028698953,0.00034985246,0.0003363157,0.0000883193,0.0000017533098],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011795636,0.000050842034,0.13785607,0.00011300858,0.0000020402624,0.0000061926175,0.0035906897,0.001966487,0.8164564,0.020954916,0.00013504394,0.01885655],"study_design_scores_gemma":[0.000058391808,0.000023651353,0.7664546,0.000114595954,0.0000025968804,0.0000044347066,0.00015455883,0.0045100898,0.22665825,0.0018769726,0.00009417497,0.000047675792],"about_ca_topic_score_codex":0.0001326306,"about_ca_topic_score_gemma":0.00003639294,"teacher_disagreement_score":0.6285985,"about_ca_system_score_codex":0.000042406533,"about_ca_system_score_gemma":0.000045387747,"threshold_uncertainty_score":0.26528537},"labels":[],"label_agreement":null},{"id":"W4404168806","doi":"10.1093/gigascience/giae083","title":"CAT Bridge: an efficient toolkit for gene–metabolite association mining from multiomics data","year":2024,"lang":"en","type":"article","venue":"GigaScience","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Metabolomics Innovation Centre; University of Alberta","funders":"Peking University","keywords":"Bridge (graph theory); Metabolite; Computational biology; Computer science; Data science; Biology; Medicine; Internal medicine","score_opus":0.028955679167377894,"score_gpt":0.2891565746364574,"score_spread":0.2602008954690795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404168806","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90536696,0.0012824987,0.090762064,0.00015201133,0.0010377384,0.00019885953,0.0010459928,0.000024646291,0.00012926139],"genre_scores_gemma":[0.9527027,0.00014492072,0.042608917,0.00046479926,0.000845725,0.00001843534,0.0026242088,0.000019225086,0.0005710498],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99891204,0.000016700134,0.00019913806,0.00044877655,0.00014562863,0.00027771093],"domain_scores_gemma":[0.9991973,0.000035365945,0.00006832381,0.00056271243,0.00005497835,0.00008133967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064883,0.000106006315,0.00009427596,0.000027465192,0.0001230201,0.00021889507,0.00054521824,0.00011095458,0.0000039633],"category_scores_gemma":[0.000105061146,0.000100429956,0.000044326236,0.0001009795,0.000041042655,0.00001501923,0.00024062594,0.000046413606,0.000011625955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007970032,0.00015132602,0.0034876803,0.000076992226,0.00020227491,0.0000046067976,0.0023873076,0.014155202,0.7599086,0.00086163444,0.032541737,0.18614294],"study_design_scores_gemma":[0.0002488092,0.0000667881,0.0025440187,0.000014646462,0.000039885526,0.0000036788233,0.00007781679,0.8622356,0.0137947565,0.00011925255,0.12061755,0.00023720477],"about_ca_topic_score_codex":0.000048881848,"about_ca_topic_score_gemma":0.000045243545,"teacher_disagreement_score":0.8480804,"about_ca_system_score_codex":0.00003592496,"about_ca_system_score_gemma":0.00014270579,"threshold_uncertainty_score":0.40954146},"labels":[],"label_agreement":null},{"id":"W4404716635","doi":"10.1093/gigascience/giae084","title":"Construction and analysis of telomere-to-telomere genomes for 2 sweet oranges: Longhuihong and Newhall (<i>Citrus sinensis</i>)","year":2024,"lang":"en","type":"article","venue":"GigaScience","topic":"Telomeres, Telomerase, and Senescence","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministry of Agriculture - Saskatchewan","keywords":"Genome; Orange (colour); Citrus × sinensis; Biology; Germplasm; Genomics; Reference genome; Telomere; Genetics; Biotechnology; Gene; Botany; Horticulture","score_opus":0.017002267250382477,"score_gpt":0.2847449564585429,"score_spread":0.26774268920816047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404716635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98729354,0.0066220798,0.0034840412,0.0012826902,0.000289798,0.0005230301,0.00010535723,0.00010225433,0.0002971877],"genre_scores_gemma":[0.9837476,0.000923619,0.014502473,0.00039611245,0.00009427061,0.000024067675,0.000018296603,0.000021657905,0.00027192317],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99802524,0.00002626763,0.00040604957,0.00075369247,0.0003849161,0.0004038083],"domain_scores_gemma":[0.99879444,0.00024709688,0.00008389364,0.000339159,0.00019256107,0.00034285444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039890557,0.00023837069,0.0006234307,0.0009833291,0.00014891443,0.00011232149,0.00013717338,0.000095819174,0.000042354393],"category_scores_gemma":[0.00019473482,0.00020051589,0.00014044016,0.002619773,0.00062670204,0.00024166987,0.00008125404,0.00012614432,0.000005429058],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033792458,0.00012414863,0.179689,0.0016400339,0.0010973823,0.00011546707,0.005556889,0.00009108146,0.22146031,0.005697697,0.00068046903,0.58350956],"study_design_scores_gemma":[0.00282403,0.00205048,0.85642296,0.0013253444,0.007075999,0.0009191737,0.0062020617,0.028740393,0.05613823,0.0017309019,0.03486053,0.0017099103],"about_ca_topic_score_codex":0.00010657546,"about_ca_topic_score_gemma":0.00009117896,"teacher_disagreement_score":0.676734,"about_ca_system_score_codex":0.000045239176,"about_ca_system_score_gemma":0.00016325411,"threshold_uncertainty_score":0.81768006},"labels":[],"label_agreement":null},{"id":"W4405222102","doi":"10.1093/gigascience/giae088","title":"GPU-accelerated Kendall distance computation for large or sparse data","year":2024,"lang":"en","type":"article","venue":"GigaScience","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Russian Science Foundation","keywords":"Computation; Computer science; Computational science; Parallel computing; Algorithm","score_opus":0.0900370016506466,"score_gpt":0.33166469457484954,"score_spread":0.24162769292420294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405222102","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2977956,0.0008113342,0.69903916,0.00023315944,0.0009099987,0.00027077628,0.00057739054,0.00005445384,0.00030817022],"genre_scores_gemma":[0.993927,0.00008251829,0.0039049268,0.00025638868,0.00017063072,0.000011934493,0.00069315074,0.000014396601,0.00093905366],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99901503,0.000014219466,0.00013614807,0.0004935243,0.000104965155,0.00023611968],"domain_scores_gemma":[0.9995517,0.000018101366,0.000022908664,0.00029903365,0.000052272808,0.000055940993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024162201,0.000097579665,0.00007815248,0.000022560138,0.00011517616,0.00012628979,0.00040333293,0.000056531608,0.000012536808],"category_scores_gemma":[0.0000632541,0.00007909976,0.000031025636,0.0001791927,0.00006531236,0.000016872298,0.00008660593,0.000047625468,0.000009381429],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001577791,0.00010907217,0.00034077483,0.00013857616,0.000021677733,0.000011287177,0.00012076061,0.00021390156,0.974155,0.00083082187,0.011401372,0.012498965],"study_design_scores_gemma":[0.0009275119,0.00044384794,0.00070191704,0.00011423445,0.00003080718,0.00002454826,0.00008449228,0.29514986,0.16625234,0.00027020136,0.535513,0.0004872766],"about_ca_topic_score_codex":0.000009375021,"about_ca_topic_score_gemma":0.00012534414,"teacher_disagreement_score":0.8079027,"about_ca_system_score_codex":0.000009460751,"about_ca_system_score_gemma":0.0001579342,"threshold_uncertainty_score":0.32255948},"labels":[],"label_agreement":null},{"id":"W4407117635","doi":"10.1093/gigascience/giae120","title":"Micromix: web infrastructure for visualizing and remixing microbial ‘omics data","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Microbial Community Ecology and Physiology","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Julius-Maximilians-Universität Würzburg","keywords":"World Wide Web; Computer science; Data science","score_opus":0.016389330742154175,"score_gpt":0.28865713777320645,"score_spread":0.2722678070310523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407117635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99441594,0.00006551319,0.0020236776,0.00058149686,0.00037168234,0.0002425171,0.00008110552,0.00002926212,0.0021888022],"genre_scores_gemma":[0.9844824,0.000057970934,0.01247536,0.0024518555,0.000031199022,0.0000055824944,0.00007703126,0.000006525364,0.00041205029],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990088,0.00006897026,0.00015793822,0.00042584975,0.00004308376,0.0002953654],"domain_scores_gemma":[0.99916285,0.00017643672,0.000057953428,0.00055022235,0.000007814241,0.000044712386],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005383135,0.00010967962,0.0001438577,0.000038998365,0.0005640984,0.000044859797,0.0010623172,0.00010112083,0.00018029727],"category_scores_gemma":[0.00016233286,0.00010731608,0.00002048303,0.000243776,0.0006475048,0.00025626723,0.0017761445,0.00017880763,0.000015936617],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022949505,0.000014983291,0.0053331745,0.000013549848,0.0000046673163,4.3475734e-7,0.00017927986,0.00005994409,0.96167,0.000591537,0.028147526,0.003962002],"study_design_scores_gemma":[0.0020220422,0.00021225668,0.09966762,0.000092425835,0.00008104577,0.00007173948,0.0004861601,0.019807674,0.0612963,0.022058157,0.79332316,0.0008814406],"about_ca_topic_score_codex":0.00007712292,"about_ca_topic_score_gemma":0.00048489473,"teacher_disagreement_score":0.90037364,"about_ca_system_score_codex":0.000054136086,"about_ca_system_score_gemma":0.00005790477,"threshold_uncertainty_score":0.43762228},"labels":[],"label_agreement":null},{"id":"W4407560614","doi":"10.1093/gigascience/giae122","title":"Guidance framework to apply best practices in ecological data analysis: lessons learned from building Galaxy-Ecology","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Research Data Management Practices","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"Erasmus+; Horizon 2020 Framework Programme; Muséum National d'Histoire Naturelle; HORIZON EUROPE Framework Programme; Ministère de l'Education Nationale, de l'Enseignement Superieur et de la Recherche; Agence Nationale de la Recherche; European Commission","keywords":"Workflow; Ecology; Computer science; Data science; Best practice; Transparency (behavior); Management science; Engineering; Biology","score_opus":0.3335599778707115,"score_gpt":0.4947599725959817,"score_spread":0.1611999947252702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407560614","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049272824,0.00022633423,0.8740081,0.07223394,0.00037907093,0.00043009582,0.000035521753,0.000109065324,0.003305025],"genre_scores_gemma":[0.56036514,0.00042124785,0.43600336,0.002323977,0.00004220857,0.00009370765,0.000017310387,0.0000046411665,0.00072840275],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99464387,0.00068178825,0.0004981017,0.0024742794,0.0008407401,0.00086125074],"domain_scores_gemma":[0.991007,0.0036449158,0.0004591673,0.004566296,0.00011475963,0.00020788203],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.0062164934,0.00020962904,0.00039152364,0.0010039415,0.0003506672,0.0033276437,0.016876522,0.00012999255,0.00004277098],"category_scores_gemma":[0.024502123,0.0001946919,0.00005206305,0.009723747,0.00023556859,0.019526377,0.011624878,0.00065207586,0.00013872805],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006571928,0.0009204172,0.169691,0.00003872572,0.0003827807,0.0003640068,0.0004687528,0.0095281,0.0040079607,0.7155062,0.0038138714,0.09521248],"study_design_scores_gemma":[0.00040495256,0.00023061497,0.655959,0.00015752272,0.00019616922,0.0000025205695,0.00059612555,0.16508386,0.00046379154,0.049334344,0.12691319,0.00065788516],"about_ca_topic_score_codex":0.00162991,"about_ca_topic_score_gemma":0.0035975121,"teacher_disagreement_score":0.66617185,"about_ca_system_score_codex":0.00015014104,"about_ca_system_score_gemma":0.00038983574,"threshold_uncertainty_score":0.997707},"labels":[],"label_agreement":null},{"id":"W4408363127","doi":"10.1093/gigascience/giae098","title":"An analysis of performance bottlenecks in MRI preprocessing","year":2024,"lang":"en","type":"article","venue":"GigaScience","topic":"Advanced MRI Techniques and Applications","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Addiction and Mental Health; Concordia University","funders":"Concordia University; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation","keywords":"Bottleneck; Computer science; Preprocessor; Pipeline (software); Pipeline transport; Segmentation; Data pre-processing; Artificial intelligence; Deep learning; Software; Data mining; Machine learning; Embedded system; Engineering","score_opus":0.015176497222274578,"score_gpt":0.37073633195020284,"score_spread":0.35555983472792824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408363127","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7741072,0.00022186145,0.22364104,0.00015748505,0.000010555294,0.000084793035,0.0000023673051,0.00007337609,0.0017013169],"genre_scores_gemma":[0.97225904,0.000087565175,0.027473584,0.00004505782,0.0000089702935,0.000018291272,0.0000036971019,0.00000340311,0.000100363744],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994288,0.0000031268262,0.00012818315,0.00021712965,0.00012343112,0.0000993453],"domain_scores_gemma":[0.99966574,0.000012254511,0.000020668409,0.00023354356,0.000029070754,0.000038698097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017862052,0.000040952425,0.00011120172,0.00024395413,0.000029162806,0.000011951747,0.000094225914,0.000020365713,0.00002138239],"category_scores_gemma":[0.000009869084,0.00003364769,0.000031553736,0.0019338118,0.00009589013,0.00018605903,0.000014645802,0.00006354067,0.0000020673258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032484375,0.00039641463,0.20693646,0.00039528334,0.000038556227,0.00002300716,0.003116402,0.05128809,0.3674696,0.0103443535,0.000052851912,0.35990646],"study_design_scores_gemma":[0.000056166755,0.00010724823,0.12323644,0.00019829407,0.00012570931,0.00000707074,0.00014089252,0.8216546,0.052528568,0.0003259539,0.0015415164,0.000077510515],"about_ca_topic_score_codex":0.000011706804,"about_ca_topic_score_gemma":0.000007787575,"teacher_disagreement_score":0.77036655,"about_ca_system_score_codex":0.000027265167,"about_ca_system_score_gemma":0.000059312944,"threshold_uncertainty_score":0.13721131},"labels":[],"label_agreement":null},{"id":"W4409765253","doi":"10.1093/gigascience/giaf038","title":"Overture: an open-source genomics data platform","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; University of Toronto; Ontario Institute for Cancer Research","funders":"National Cancer Institute; Canadian Institutes of Health Research; Canada Foundation for Innovation","keywords":"Computer science; Interoperability; Data science; Genomics; Data management; Reuse; Big data; Data sharing; World Wide Web; Database; Data mining; Genome; Engineering","score_opus":0.3207349943837839,"score_gpt":0.4543667571292983,"score_spread":0.13363176274551442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409765253","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24265799,0.00021471246,0.6189994,0.004682853,0.006702335,0.0007887742,0.00020603169,0.00026350384,0.12548439],"genre_scores_gemma":[0.9012659,0.000013180111,0.028247295,0.00685579,0.00014139462,0.000008494639,0.00011306973,0.000013122296,0.06334172],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99573237,0.00007939146,0.00052313076,0.0018968331,0.0013541694,0.00041410985],"domain_scores_gemma":[0.9923074,0.00054467027,0.00016352483,0.006670339,0.0001456771,0.00016834178],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.012685928,0.00013559932,0.00020459713,0.0003232393,0.0007305985,0.0046183597,0.021323208,0.00004016386,0.00018640094],"category_scores_gemma":[0.0035485746,0.0001014287,0.000026280199,0.0027301828,0.00029680578,0.0028609482,0.01423519,0.00012662512,0.00040928842],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015146604,0.000108584034,0.0012628015,0.0000023145676,0.0000059323756,0.000005087657,0.00032750986,0.000977206,0.0005649537,0.02016192,0.3633561,0.6132124],"study_design_scores_gemma":[0.00018070424,0.000028229048,0.0063638273,0.000011209256,0.0000056511553,0.0000030726278,0.00068178424,0.16425167,0.00011879774,0.018411318,0.8098051,0.00013866909],"about_ca_topic_score_codex":0.00019886767,"about_ca_topic_score_gemma":0.00021585106,"teacher_disagreement_score":0.65860796,"about_ca_system_score_codex":0.000057797213,"about_ca_system_score_gemma":0.00031046127,"threshold_uncertainty_score":0.99641496},"labels":[],"label_agreement":null},{"id":"W4410344814","doi":"10.1093/gigascience/giae101","title":"New implementation of data standards for AI in oncology: Experience from the EuCanImage project","year":2024,"lang":"en","type":"article","venue":"GigaScience","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Agencia Estatal de Investigación; Euskal Herriko Unibertsitatea; Horizon 2020 Framework Programme; Eusko Jaurlaritza; European Commission; Ministerio de Ciencia e Innovación; Centres de Recerca de Catalunya","keywords":"Workflow; Standardization; Interoperability; Electronic data capture; Computer science; Data science; Data quality; Data sharing; Automatic identification and data capture; Data dictionary; Health care; Precision medicine; Metadata; Medicine; Database; World Wide Web; Clinical trial; Engineering","score_opus":0.41253011965183084,"score_gpt":0.6273102827878646,"score_spread":0.21478016313603376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410344814","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92947584,0.0010688386,0.043686952,0.02296191,0.0009539382,0.0012913442,0.00029417194,0.000032022315,0.00023500064],"genre_scores_gemma":[0.9932387,0.00008559699,0.0055790334,0.0007484022,0.00018580527,0.000047858506,0.000051429786,0.0000045519223,0.00005864976],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990413,0.000024938736,0.00026165738,0.00026978468,0.00024905178,0.000153233],"domain_scores_gemma":[0.9992665,0.0002482039,0.000037969636,0.0003064666,0.00010201474,0.00003885417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008815045,0.000048250484,0.0000926158,0.00005307082,0.000056000456,0.00003263605,0.0002676779,0.000028105731,0.00009134051],"category_scores_gemma":[0.00029209643,0.00003265944,0.000017367442,0.00043852945,0.000100118894,0.00034502658,0.00005301814,0.00008707764,0.0000031553193],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005520923,0.000023373717,0.009734365,0.000047601297,0.0000041391154,0.0000029081104,0.038070325,9.129623e-7,0.013485768,0.0005536925,0.029181484,0.90884024],"study_design_scores_gemma":[0.00028992933,0.0017641883,0.053820554,0.0007737337,0.00008742506,0.000021309435,0.1811441,0.013694905,0.18204093,0.00828047,0.55780834,0.00027414912],"about_ca_topic_score_codex":0.019216346,"about_ca_topic_score_gemma":0.0049290997,"teacher_disagreement_score":0.90856606,"about_ca_system_score_codex":0.00016069881,"about_ca_system_score_gemma":0.0045677307,"threshold_uncertainty_score":0.98731476},"labels":[],"label_agreement":null},{"id":"W4410975639","doi":"10.1093/gigascience/giaf049","title":"Analysis-ready VCF at Biobank scale using Zarr","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Ontario Genomics","funders":"National Human Genome Research Institute; Knut och Alice Wallenbergs Stiftelse; Wellcome Trust; Bill and Melinda Gates Foundation","keywords":"Computer science; Biobank; Scalability; Terabyte; Data mining; Big data; Encoding (memory); Field (mathematics); Database; Bioinformatics; Artificial intelligence","score_opus":0.013477400476573925,"score_gpt":0.2740052126660191,"score_spread":0.2605278121894452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410975639","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99260765,0.0017554609,0.002000731,0.000088652334,0.00019974104,0.0000650932,0.00001643047,0.000003221608,0.0032629902],"genre_scores_gemma":[0.9961755,0.00011075251,0.0012488482,0.00029948898,0.000045028344,0.0000027848212,0.0000094848865,0.0000038163766,0.0021042854],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991546,0.000018931769,0.00012963382,0.0003736698,0.00009233963,0.00023081787],"domain_scores_gemma":[0.99950737,0.000006567221,0.000042620726,0.0003347733,0.00006215655,0.000046502493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014659177,0.00010080581,0.00012614454,0.00008199767,0.00023596898,0.000025036017,0.0002523772,0.00005402908,0.000010245701],"category_scores_gemma":[0.000024016275,0.00009258035,0.00012026175,0.0005082614,0.00018953912,6.4907766e-7,0.0003002511,0.000027370996,0.0000076457345],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007727995,0.000011257764,0.12989509,0.0000033394622,0.00011273453,5.3731657e-7,0.00003073552,0.0013388431,0.86753374,0.00006293138,0.00023267079,0.0007703939],"study_design_scores_gemma":[0.000494056,0.00014018253,0.38190463,0.000013821087,0.00056440267,0.000008893362,0.00018307983,0.004785123,0.55108356,0.00028381325,0.060017206,0.00052122114],"about_ca_topic_score_codex":0.000058859663,"about_ca_topic_score_gemma":0.00017844804,"teacher_disagreement_score":0.31645018,"about_ca_system_score_codex":0.00002156666,"about_ca_system_score_gemma":0.00006482885,"threshold_uncertainty_score":0.3775317},"labels":[],"label_agreement":null},{"id":"W4410975994","doi":"10.1093/gigascience/giaf050","title":"Health Data Nexus: an open data platform for AI research and education in medicine","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; Centre for Addiction and Mental Health; Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"","keywords":"Nexus (standard); Cloud computing; Computer science; Open data; Data science; Data management; Data sharing; Health data; Data security; Key (lock); Data curation; Knowledge management; World Wide Web; Health care; Computer security; Database; Medicine; Encryption","score_opus":0.8085438965902508,"score_gpt":0.6976983991760571,"score_spread":0.1108454974141937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410975994","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41933423,0.004810173,0.008132153,0.5507816,0.0024365978,0.0068221902,0.00011774778,0.000054758686,0.0075105573],"genre_scores_gemma":[0.97802097,0.0006067666,0.005671914,0.011603928,0.00040691957,0.00009890754,0.0013280561,0.000009784073,0.0022527368],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983107,0.00005046677,0.00037080506,0.00067843223,0.00025518617,0.00033440767],"domain_scores_gemma":[0.9975247,0.0002612287,0.000051996947,0.0016890389,0.00027921706,0.00019386629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063820924,0.00006450997,0.00019326806,0.00030046236,0.00033280323,0.00008983458,0.0015923769,0.0000470625,0.000016328639],"category_scores_gemma":[0.001996383,0.000053768475,0.0000025899708,0.0009002722,0.0003386409,0.0012989406,0.00087630947,0.00021630435,0.0000042421625],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009459201,0.00027920332,0.010068885,0.0001994128,0.0000019493411,4.4402825e-7,0.0020608648,7.1586544e-7,0.00017105839,0.009041247,0.083286695,0.89479494],"study_design_scores_gemma":[0.0008021236,0.005819847,0.106581606,0.004898531,0.000035907193,0.0000694704,0.09017565,0.087270014,0.0011054911,0.3384184,0.3643905,0.00043247198],"about_ca_topic_score_codex":0.020106936,"about_ca_topic_score_gemma":0.008801582,"teacher_disagreement_score":0.89436245,"about_ca_system_score_codex":0.0001404296,"about_ca_system_score_gemma":0.006399442,"threshold_uncertainty_score":0.99923337},"labels":[],"label_agreement":null},{"id":"W4411078464","doi":"10.1093/gigascience/giaf030","title":"Chromosome-level reference genome for the medically important Arabian horned viper ( <i>Cerastes gasperettii</i> )","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Venomous Animal Envenomation and Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Regional Development Fund; National Science Foundation; Generalitat de Catalunya; Ministerio de Ciencia e Innovación; York University; Agencia Estatal de Investigación; Ministerio de Ciencia, Innovación y Universidades; New York University Abu Dhabi","keywords":"Biology; Venom; Genome; Evolutionary biology; Genetics; Computational biology; Gene; Ecology","score_opus":0.026111067423953024,"score_gpt":0.27684550486728005,"score_spread":0.250734437443327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411078464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8945943,0.010380024,0.046255764,0.015909053,0.0009412448,0.002260062,0.00021343959,0.00008407011,0.02936203],"genre_scores_gemma":[0.99174577,0.0005359084,0.0008657961,0.0029348282,0.000102568374,0.0001537854,0.00001935125,0.000007952256,0.0036340202],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.99887955,0.000020301362,0.00024880853,0.00038986263,0.00017138933,0.00029006053],"domain_scores_gemma":[0.9993473,0.000041446754,0.00007733925,0.0003485918,0.00012320404,0.00006208471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039982802,0.0001345738,0.0001339755,0.000028274673,0.00041845877,0.00005448215,0.00049899967,0.00007260559,0.000026365364],"category_scores_gemma":[0.0002570339,0.0000903197,0.00007518095,0.00016867575,0.00032762633,0.0000057155944,0.00015971976,0.00007529344,0.000007903472],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008545195,0.00017275671,0.0009910983,0.000055089633,0.0001273324,0.0000032964713,0.00026512868,0.000043541226,0.97342193,0.011323178,0.00652109,0.006221037],"study_design_scores_gemma":[0.00958231,0.0023295158,0.0789488,0.00008000455,0.00011734429,0.000034774774,0.0012889565,0.001394477,0.056135748,0.0022637865,0.84692866,0.0008956425],"about_ca_topic_score_codex":0.0000135861055,"about_ca_topic_score_gemma":0.000098751414,"teacher_disagreement_score":0.91728616,"about_ca_system_score_codex":0.000017482194,"about_ca_system_score_gemma":0.00020169868,"threshold_uncertainty_score":0.36831307},"labels":[],"label_agreement":null},{"id":"W4411622822","doi":"10.1093/gigascience/giaf070","title":"Extraction of biological terms using large language models enhances the usability of metadata in the BioSample database","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute of Genetics; National Bioscience Database Center; Japan Society for the Promotion of Science; Japan Science and Technology Corporation","keywords":"Metadata; Computer science; Data curation; Information retrieval; World Wide Web; Usability; Data science; Database","score_opus":0.0670437112549849,"score_gpt":0.3748008608905625,"score_spread":0.30775714963557765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411622822","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9632863,0.0006989368,0.035506334,0.00017668423,0.000058579062,0.00008187763,0.00006415181,0.0000025085283,0.00012462068],"genre_scores_gemma":[0.99730664,0.00006961569,0.0024473462,0.0001258667,0.000012018825,0.000004720274,0.000017360153,8.754824e-7,0.000015545393],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99925596,0.00013100471,0.00017104184,0.00019987952,0.000110541776,0.00013159125],"domain_scores_gemma":[0.99939305,0.00011065019,0.000069714595,0.00039559873,0.000020421081,0.000010543915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012394639,0.000055269204,0.00009485755,0.000023537646,0.000058378824,0.000010569002,0.0005059103,0.00005669285,0.0000034996378],"category_scores_gemma":[0.0005410722,0.00002673485,0.000036249363,0.0002531036,0.0005781371,0.000010389013,0.00016401403,0.00006637669,9.788256e-8],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001526401,0.00007604763,0.0018549901,0.000012169435,0.000004604813,4.7862403e-7,0.00017704754,0.00002117528,0.9947298,0.0005415593,0.000040593895,0.0025262262],"study_design_scores_gemma":[0.0002479203,0.00013990757,0.017220503,0.000044435088,0.000016536444,0.00000695208,0.003977141,0.0045521585,0.97025484,0.0012551442,0.0021849787,0.00009950782],"about_ca_topic_score_codex":0.00019227444,"about_ca_topic_score_gemma":0.000109840345,"teacher_disagreement_score":0.034020346,"about_ca_system_score_codex":0.0000037903028,"about_ca_system_score_gemma":0.000049979823,"threshold_uncertainty_score":0.21301702},"labels":[],"label_agreement":null},{"id":"W4411691518","doi":"10.1093/gigascience/giaf072","title":"Integrating comparative genomics and risk classification by assessing virulence, antimicrobial resistance, and plasmid spread in microbial communities with gSpreadComp","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Gut microbiota and health","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"German Network for Bioinformatics Infrastructure; Fundação de Amparo à Pesquisa do Estado de São Paulo; Deutsche Forschungsgemeinschaft; International Development Research Centre; Alexander von Humboldt-Stiftung","keywords":"Metagenomics; Biology; Virulence; Genomics; Comparative genomics; Genetics; Antibiotic resistance; Workflow; Genome; Horizontal gene transfer; Computational biology; Gene; Computer science; Database","score_opus":0.0150347525249797,"score_gpt":0.27980903004685426,"score_spread":0.26477427752187455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411691518","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99550986,0.0005435802,0.002432358,0.00014517787,0.0000485207,0.00018128197,0.00005681923,0.000007854361,0.0010745737],"genre_scores_gemma":[0.99279606,0.00083551585,0.0059035793,0.00024446653,0.00001236529,0.000006553394,0.000053725213,0.0000056556933,0.00014207445],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99908376,0.000120957746,0.0002025944,0.000312681,0.0000536829,0.00022634228],"domain_scores_gemma":[0.9995477,0.00004120986,0.00012015411,0.00018763616,0.00006116462,0.000042107484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003082392,0.00014197134,0.00017337824,0.00008342516,0.000355877,0.00014816098,0.00017661364,0.00009136674,7.9093667e-7],"category_scores_gemma":[0.000016792943,0.00012850286,0.000012739857,0.00019159653,0.0006198995,0.00002387208,0.0001132645,0.00020868554,4.41829e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006517621,0.000032362866,0.05062982,0.00004050169,0.000007801012,3.497959e-7,0.00074800086,0.000010479149,0.9468353,0.00015592569,0.0011570427,0.00031723775],"study_design_scores_gemma":[0.0030670906,0.0003505285,0.42940214,0.001260836,0.000061348306,0.000043785967,0.014030134,0.0022289676,0.52674353,0.00015028026,0.021735067,0.0009262804],"about_ca_topic_score_codex":0.00037177774,"about_ca_topic_score_gemma":0.0047009806,"teacher_disagreement_score":0.42009175,"about_ca_system_score_codex":0.000034662113,"about_ca_system_score_gemma":0.00019201783,"threshold_uncertainty_score":0.5240195},"labels":[],"label_agreement":null},{"id":"W4413775747","doi":"10.1093/gigascience/giaf083","title":"DeepAnnotation: A novel interpretable deep learning–based genomic selection model that integrates comprehensive functional annotations","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Genetic and phenotypic traits in livestock","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Agriculture","funders":"Ministry of Science and Technology of the People's Republic of China","keywords":"Computer science; Selection (genetic algorithm); Artificial intelligence; Deep learning; Natural language processing; Computational biology; Machine learning; Biology","score_opus":0.01819563265140076,"score_gpt":0.24955002796224932,"score_spread":0.23135439531084856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413775747","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32146284,0.00021887274,0.6769131,0.000122536,0.00017448574,0.00011185873,0.0000058711626,0.000021274067,0.0009691766],"genre_scores_gemma":[0.92645144,0.00000855548,0.07069611,0.0007761674,0.000034843713,0.000046328576,0.000069263006,0.000008429278,0.0019088739],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990473,0.000033552216,0.00016613856,0.00040333677,0.00013142024,0.00021828608],"domain_scores_gemma":[0.9994728,0.000031320622,0.00007294205,0.00015597444,0.00021457489,0.00005241352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000091957896,0.00014192749,0.000101902166,0.00007187011,0.00030221595,0.000054554675,0.00020139488,0.00008681413,0.000022436458],"category_scores_gemma":[0.0000711162,0.00014099148,0.00006257425,0.00027328453,0.00018485443,0.000010981567,0.00006357109,0.00013608836,0.000009733864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047458132,0.000050504932,0.0025576204,0.000008856277,0.000015168618,3.9886473e-8,0.000095696654,0.6394771,0.35289872,0.0028573684,0.00034369063,0.0016478134],"study_design_scores_gemma":[0.0010428741,0.00038683705,0.22701822,0.000046456033,0.0000536897,0.000012594434,0.0005920227,0.68390644,0.07545597,0.0035013098,0.0075525586,0.00043102395],"about_ca_topic_score_codex":0.0000117240625,"about_ca_topic_score_gemma":0.000034688914,"teacher_disagreement_score":0.60621697,"about_ca_system_score_codex":0.000030771924,"about_ca_system_score_gemma":0.00028513724,"threshold_uncertainty_score":0.5749466},"labels":[],"label_agreement":null},{"id":"W4413812274","doi":"10.1093/gigascience/giaf089","title":"WaveSeekerNet: accurate prediction of influenza A virus subtypes and host source using attention-based deep learning","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Influenza Virus Research Studies","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada; University of Guelph; Canadian Science Centre for Human and Animal Health; Vector Institute; University of Manitoba; Canadian Food Inspection Agency","funders":"Canadian Bee Research Fund; University of Manitoba; Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Host (biology); Computer science; Artificial intelligence; Generalization; Transmission (telecommunications); Adaptation (eye); Influenza A virus; Machine learning; Deep learning; Computational biology; Biology; Virus; Virology; Genetics","score_opus":0.059380658045332116,"score_gpt":0.36065684576515145,"score_spread":0.30127618771981934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413812274","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98841,0.0011939723,0.00927373,0.000107147294,0.00006183747,0.0002726289,0.000009838628,0.00005247631,0.00061838113],"genre_scores_gemma":[0.9982104,0.00006699852,0.0009966812,0.00035281156,0.00002291873,0.000010646944,0.0000017285028,0.000007935569,0.00032991744],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9986464,0.000066381646,0.00026934803,0.0003026932,0.00041522266,0.00029997397],"domain_scores_gemma":[0.9991976,0.00015183286,0.000105966574,0.00018977777,0.0002739114,0.00008092171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005654279,0.00011725756,0.0002182831,0.00029137792,0.00031432917,0.00003879468,0.000108377964,0.000056231394,0.000016057975],"category_scores_gemma":[0.0011863952,0.000102309896,0.000049186743,0.00073542434,0.00058298575,0.00017337811,0.00012582907,0.00022021009,0.000005547394],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018160643,0.000053971395,0.48398003,0.0002312813,0.00004394489,0.0000050898643,0.00048162625,0.0023945414,0.5085938,0.00007449924,0.000018805646,0.003940822],"study_design_scores_gemma":[0.001460082,0.0002787887,0.750385,0.00050789316,0.00008572727,0.0000069740104,0.0005809556,0.21073262,0.032722548,0.000031011277,0.0030884526,0.00011995204],"about_ca_topic_score_codex":0.00021572638,"about_ca_topic_score_gemma":0.00002347537,"teacher_disagreement_score":0.47587124,"about_ca_system_score_codex":0.00008108024,"about_ca_system_score_gemma":0.00020829939,"threshold_uncertainty_score":0.41720766},"labels":[],"label_agreement":null},{"id":"W4413826251","doi":"10.1093/gigascience/giaf094","title":"Comparing linear and nonlinear finite element models of vertebral strength across the thoracolumbar spine: a benchmark from density-calibrated computed tomography","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Bone health and osteoporosis research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Alberta Bone and Joint Health Institute; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Calibration; Quantitative computed tomography; Computer science; Nonlinear system; Benchmark (surveying); Finite element method; Tomography; Jackknife resampling; Radiology; Mathematics; Statistics; Bone density; Medicine; Structural engineering; Physics; Osteoporosis; Estimator; Geology; Engineering","score_opus":0.028277091000321945,"score_gpt":0.32963224759904913,"score_spread":0.3013551565987272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413826251","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99275005,0.00065315876,0.004468571,0.0011177916,0.00011634755,0.0005494743,0.0000376208,0.00003962213,0.00026734904],"genre_scores_gemma":[0.98985124,0.00009295944,0.0088886535,0.0009861604,0.00004386498,0.000013335384,0.00004633292,0.0000073950678,0.000070070666],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980462,0.000094015384,0.00042766632,0.0004142346,0.0005168691,0.00050099957],"domain_scores_gemma":[0.99884194,0.00017179512,0.00009646566,0.00042346236,0.00023414151,0.00023221427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006570061,0.00014869115,0.00038400138,0.000116382,0.00035700997,0.00006371269,0.00029390134,0.00007848584,0.00001566208],"category_scores_gemma":[0.00011802399,0.0001097208,0.000072545416,0.0012819029,0.000531827,0.00015058773,0.00034147536,0.00036096998,0.000002264789],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063009304,0.0008313,0.9502303,0.00056538807,0.00017495405,0.00003945479,0.002542631,0.002655865,0.017674875,0.00091707933,0.001400055,0.022338012],"study_design_scores_gemma":[0.0010837652,0.00017559042,0.35315984,0.0002304995,0.000022386936,0.0000022222364,0.000324586,0.63913816,0.005367677,0.000173542,0.00023983269,0.000081900565],"about_ca_topic_score_codex":0.0013665926,"about_ca_topic_score_gemma":0.0005464565,"teacher_disagreement_score":0.6364823,"about_ca_system_score_codex":0.000027663034,"about_ca_system_score_gemma":0.00032226645,"threshold_uncertainty_score":0.44742844},"labels":[],"label_agreement":null},{"id":"W4413942662","doi":"10.1093/gigascience/giaf091","title":"High-precision machine learning identifies a reproducible functional connectivity signature of autism spectrum diagnosis in a subset of individuals","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Neurological Institute and Hospital; Université de Montréal; Centre Hospitalier Universitaire Sainte-Justine; Institut Universitaire de Gériatrie de Montréal","funders":"Australian Research Council; Consortium canadien en neurodégénérescence associée au vieillissement; Fondation Brain Canada; Institut de Valorisation des Données; Azrieli Foundation; Compute Canada","keywords":"Autism spectrum disorder; Neurotypical; Artificial intelligence; Computer science; Resting state fMRI; Machine learning; Autism; Default mode network; Population; Functional connectivity; Neuroscience; Psychology; Medicine; Developmental psychology","score_opus":0.02697713125968108,"score_gpt":0.26655886778034915,"score_spread":0.23958173652066808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413942662","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9893678,0.00043299148,0.00079397496,0.007533168,0.00091821124,0.0003308892,0.0000676819,0.000056756715,0.00049852114],"genre_scores_gemma":[0.9986827,0.00010421872,0.0001996234,0.00030267247,0.000019835627,0.000063002306,0.000002977834,0.000008208644,0.0006167646],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99695814,0.0003557261,0.0004679308,0.0011068141,0.00078112277,0.0003302541],"domain_scores_gemma":[0.9915521,0.0075523304,0.0002966656,0.0004922008,0.00006772835,0.00003893771],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0019942708,0.0001929263,0.00042829596,0.00067314494,0.0002796753,0.00004009655,0.00044520723,0.00009184379,0.00009853837],"category_scores_gemma":[0.031154413,0.00018249454,0.000101494144,0.002828717,0.0005996721,0.00048304748,0.0004899763,0.00042878173,0.0000075002035],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016764567,0.0005879283,0.4451746,0.000136367,0.000025069583,0.000013853059,0.0008664111,0.011864252,0.49224904,0.04501196,0.0019852573,0.001917625],"study_design_scores_gemma":[0.00040672784,0.00013154936,0.44954845,0.0001451222,0.000010269047,0.0000044839758,0.00007144756,0.00055207615,0.52320075,0.025394315,0.00040814717,0.00012666003],"about_ca_topic_score_codex":0.0005457261,"about_ca_topic_score_gemma":0.00034255913,"teacher_disagreement_score":0.030951722,"about_ca_system_score_codex":0.00009240512,"about_ca_system_score_gemma":0.0001675429,"threshold_uncertainty_score":0.9770066},"labels":[],"label_agreement":null},{"id":"W4414035551","doi":"10.1093/gigascience/giaf101","title":"A framework to mine laser microdissection-based omics data and uncover regulators of pancreatic cancer heterogeneity","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ontario Institute for Cancer Research","keywords":"Laser capture microdissection; Pancreatic cancer; Omics; Computational biology; Microdissection; Bioinformatics; Computer science; Data science; Biology; Cancer; Medicine; Internal medicine; Genetics; Gene; Gene expression","score_opus":0.018781259059910425,"score_gpt":0.29108046535933113,"score_spread":0.2722992062994207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414035551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9799995,0.0004987599,0.018746438,0.00024137464,0.00023742106,0.00012037967,0.000108459084,0.000005614361,0.00004204209],"genre_scores_gemma":[0.99438334,0.00006940038,0.0045227665,0.0008103115,0.000036852838,0.000007681896,0.000029517745,0.000006145599,0.00013397142],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992033,0.000020160283,0.00014404661,0.00039697514,0.00008548856,0.00015000289],"domain_scores_gemma":[0.999275,0.00002167227,0.000038744878,0.00054660457,0.00005533906,0.00006263756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014771799,0.00009635399,0.000121787336,0.0000429197,0.00006777621,0.000021469816,0.00033050377,0.00008107908,0.0000041888297],"category_scores_gemma":[0.00012913873,0.00008973465,0.000027379247,0.00024264911,0.00013915091,0.0000050188037,0.00012072966,0.000046812474,4.967601e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007949235,0.000043179545,0.13493747,0.000039872528,0.000018402925,3.4519644e-7,0.000025891874,0.0006816905,0.8625197,0.000022969705,0.0003742684,0.0012567369],"study_design_scores_gemma":[0.00024599038,0.00008661658,0.025848381,0.0000795236,0.000030569216,9.452338e-7,0.00001918916,0.0014018661,0.9687408,0.000067416084,0.0033502008,0.00012846683],"about_ca_topic_score_codex":0.00023813269,"about_ca_topic_score_gemma":0.00045363628,"teacher_disagreement_score":0.10908908,"about_ca_system_score_codex":0.000012469518,"about_ca_system_score_gemma":0.00015536555,"threshold_uncertainty_score":0.36592728},"labels":[],"label_agreement":null},{"id":"W4416143626","doi":"10.1093/gigascience/giaf133","title":"RNA-SeqEZPZ: a point-and-click pipeline for comprehensive transcriptomics analysis with interactive visualizations","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Research Institute, Nationwide Children's Hospital; Nationwide Children's Hospital; CancerFree KIDS; National Cancer Institute; National Institutes of Health; Alberta Water Research Institute; Alex's Lemonade Stand Foundation for Childhood Cancer","keywords":"Pipeline (software); Focus (optics); Scalability; Visualization; Data visualization","score_opus":0.013786332692127673,"score_gpt":0.29452397554180565,"score_spread":0.28073764284967795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416143626","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7051153,0.0006890587,0.29270765,0.0004584152,0.00007684429,0.00024879255,0.000060347178,0.0000051197326,0.000638457],"genre_scores_gemma":[0.9947839,0.00021534288,0.0037255804,0.00076778507,0.00002306756,0.000042413187,0.000027368607,0.0000056580425,0.00040889642],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992854,0.000017266193,0.00013511005,0.00034482675,0.000055938515,0.00016147584],"domain_scores_gemma":[0.9994905,0.00003237908,0.000049217873,0.00017990608,0.00020728781,0.000040688516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007338341,0.00011018155,0.00015904731,0.00009427922,0.0001676705,0.000033531174,0.00013925943,0.000037694597,0.0000016128093],"category_scores_gemma":[0.000038529994,0.00009268657,0.00007378422,0.00038803564,0.00018491084,0.0000017674266,0.000062299674,0.00003156364,3.5332994e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002051183,0.00007823935,0.006002455,0.000028468277,0.000682637,6.1452397e-7,0.00066341937,0.0018610049,0.9845437,0.0019254612,0.0010553775,0.002953511],"study_design_scores_gemma":[0.005547135,0.0018071336,0.10402211,0.00010344368,0.0030041698,0.000022644554,0.006403521,0.080816895,0.6563297,0.0025518066,0.13782735,0.0015640873],"about_ca_topic_score_codex":0.0000252854,"about_ca_topic_score_gemma":0.00014701439,"teacher_disagreement_score":0.328214,"about_ca_system_score_codex":0.000008490414,"about_ca_system_score_gemma":0.00006413578,"threshold_uncertainty_score":0.37796485},"labels":[],"label_agreement":null},{"id":"W4417277054","doi":"10.1093/gigascience/giaf152","title":"LinkML: an open data modeling framework","year":2025,"lang":"en","type":"article","venue":"GigaScience","topic":"Research Data Management Practices","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Simon Fraser University","funders":"National Cancer Institute; National Institutes of Health; National Human Genome Research Institute; National Institute of Mental Health; U.S. Department of Energy","keywords":"Documentation; Software; Code (set theory); Data modeling; Open data; Source code; Data model (GIS)","score_opus":0.3731083560290721,"score_gpt":0.49799181452110713,"score_spread":0.12488345849203503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417277054","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015095692,0.00010869437,0.96935225,0.008423939,0.0003593907,0.00028704552,0.0000071859463,0.00013172263,0.019820228],"genre_scores_gemma":[0.35174394,0.00036234554,0.64191765,0.0037560642,0.000051844087,0.000027510612,0.00002289499,0.0000068050736,0.0021109541],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972618,0.00016427402,0.0002095902,0.0012957584,0.0006221217,0.00044640538],"domain_scores_gemma":[0.9930701,0.00021145679,0.00006412176,0.006425512,0.000089552464,0.00013921548],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.00428142,0.00010503315,0.000116451054,0.00019180813,0.00042848467,0.012687808,0.049292207,0.000042048105,0.000011562274],"category_scores_gemma":[0.0017230667,0.000096023046,0.000010357209,0.0015821321,0.00010273535,0.106466755,0.03570374,0.00028669773,0.000057613768],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000334878,0.00007014509,0.00010729609,0.000009444658,0.000006564255,0.000012365563,0.00009594034,0.0017367352,0.00014267904,0.94423264,0.0011498325,0.052432988],"study_design_scores_gemma":[0.00007203202,0.000035856192,0.0001698162,0.000046048426,0.000003036794,0.0000012514595,0.000052182626,0.9230215,0.000057273523,0.03632089,0.040105417,0.00011471252],"about_ca_topic_score_codex":0.00026403737,"about_ca_topic_score_gemma":0.000039448252,"teacher_disagreement_score":0.92128474,"about_ca_system_score_codex":0.00003116892,"about_ca_system_score_gemma":0.000369022,"threshold_uncertainty_score":0.9883371},"labels":[],"label_agreement":null}]}